WorldWideScience

Sample records for evolving classifiers methods

  1. Methods Evolved by Observation

    Science.gov (United States)

    Montessori, Maria

    2016-01-01

    Montessori's idea of the child's nature and the teacher's perceptiveness begins with amazing simplicity, and when she speaks of "methods evolved," she is unveiling a methodological system for observation. She begins with the early childhood explosion into writing, which is a familiar child phenomenon that Montessori has written about…

  2. Hybrid classifiers methods of data, knowledge, and classifier combination

    CERN Document Server

    Wozniak, Michal

    2014-01-01

    This book delivers a definite and compact knowledge on how hybridization can help improving the quality of computer classification systems. In order to make readers clearly realize the knowledge of hybridization, this book primarily focuses on introducing the different levels of hybridization and illuminating what problems we will face with as dealing with such projects. In the first instance the data and knowledge incorporated in hybridization were the action points, and then a still growing up area of classifier systems known as combined classifiers was considered. This book comprises the aforementioned state-of-the-art topics and the latest research results of the author and his team from Department of Systems and Computer Networks, Wroclaw University of Technology, including as classifier based on feature space splitting, one-class classification, imbalance data, and data stream classification.

  3. EVOLVE

    CERN Document Server

    Deutz, André; Schütze, Oliver; Legrand, Pierrick; Tantar, Emilia; Tantar, Alexandru-Adrian

    2017-01-01

    This book comprises nine selected works on numerical and computational methods for solving multiobjective optimization, game theory, and machine learning problems. It provides extended versions of selected papers from various fields of science such as computer science, mathematics and engineering that were presented at EVOLVE 2013 held in July 2013 at Leiden University in the Netherlands. The internationally peer-reviewed papers include original work on important topics in both theory and applications, such as the role of diversity in optimization, statistical approaches to combinatorial optimization, computational game theory, and cell mapping techniques for numerical landscape exploration. Applications focus on aspects including robustness, handling multiple objectives, and complex search spaces in engineering design and computational biology.

  4. A novel statistical method for classifying habitat generalists and specialists

    DEFF Research Database (Denmark)

    Chazdon, Robin L; Chao, Anne; Colwell, Robert K

    2011-01-01

    in second-growth (SG) and old-growth (OG) rain forests in the Caribbean lowlands of northeastern Costa Rica. We evaluate the multinomial model in detail for the tree data set. Our results for birds were highly concordant with a previous nonstatistical classification, but our method classified a higher......: (1) generalist; (2) habitat A specialist; (3) habitat B specialist; and (4) too rare to classify with confidence. We illustrate our multinomial classification method using two contrasting data sets: (1) bird abundance in woodland and heath habitats in southeastern Australia and (2) tree abundance...... fraction (57.7%) of bird species with statistical confidence. Based on a conservative specialization threshold and adjustment for multiple comparisons, 64.4% of tree species in the full sample were too rare to classify with confidence. Among the species classified, OG specialists constituted the largest...

  5. DFRFT: A Classified Review of Recent Methods with Its Application

    Directory of Open Access Journals (Sweden)

    Ashutosh Kumar Singh

    2013-01-01

    Full Text Available In the literature, there are various algorithms available for computing the discrete fractional Fourier transform (DFRFT. In this paper, all the existing methods are reviewed, classified into four categories, and subsequently compared to find out the best alternative from the view point of minimal computational error, computational complexity, transform features, and additional features like security. Subsequently, the correlation theorem of FRFT has been utilized to remove significantly the Doppler shift caused due to motion of receiver in the DSB-SC AM signal. Finally, the role of DFRFT has been investigated in the area of steganography.

  6. Using Statistical Process Control Methods to Classify Pilot Mental Workloads

    National Research Council Canada - National Science Library

    Kudo, Terence

    2001-01-01

    .... These include cardiac, ocular, respiratory, and brain activity measures. The focus of this effort is to apply statistical process control methodology on different psychophysiological features in an attempt to classify pilot mental workload...

  7. A deep learning method for classifying mammographic breast density categories.

    Science.gov (United States)

    Mohamed, Aly A; Berg, Wendie A; Peng, Hong; Luo, Yahong; Jankowitz, Rachel C; Wu, Shandong

    2018-01-01

    Mammographic breast density is an established risk marker for breast cancer and is visually assessed by radiologists in routine mammogram image reading, using four qualitative Breast Imaging and Reporting Data System (BI-RADS) breast density categories. It is particularly difficult for radiologists to consistently distinguish the two most common and most variably assigned BI-RADS categories, i.e., "scattered density" and "heterogeneously dense". The aim of this work was to investigate a deep learning-based breast density classifier to consistently distinguish these two categories, aiming at providing a potential computerized tool to assist radiologists in assigning a BI-RADS category in current clinical workflow. In this study, we constructed a convolutional neural network (CNN)-based model coupled with a large (i.e., 22,000 images) digital mammogram imaging dataset to evaluate the classification performance between the two aforementioned breast density categories. All images were collected from a cohort of 1,427 women who underwent standard digital mammography screening from 2005 to 2016 at our institution. The truths of the density categories were based on standard clinical assessment made by board-certified breast imaging radiologists. Effects of direct training from scratch solely using digital mammogram images and transfer learning of a pretrained model on a large nonmedical imaging dataset were evaluated for the specific task of breast density classification. In order to measure the classification performance, the CNN classifier was also tested on a refined version of the mammogram image dataset by removing some potentially inaccurately labeled images. Receiver operating characteristic (ROC) curves and the area under the curve (AUC) were used to measure the accuracy of the classifier. The AUC was 0.9421 when the CNN-model was trained from scratch on our own mammogram images, and the accuracy increased gradually along with an increased size of training samples

  8. Maternal hemodynamics: a method to classify hypertensive disorders of pregnancy.

    Science.gov (United States)

    Ferrazzi, Enrico; Stampalija, Tamara; Monasta, Lorenzo; Di Martino, Daniela; Vonck, Sharona; Gyselaers, Wilfried

    2018-01-01

    The classification of hypertensive disorders of pregnancy is based on the time at the onset of hypertension, proteinuria, and other associated complications. Maternal hemodynamic interrogation in hypertensive disorders of pregnancy considers not only the peripheral blood pressure but also the entire cardiovascular system, and it might help to classify the different clinical phenotypes of this syndrome. This study aimed to examine cardiovascular parameters in a cohort of patients affected by hypertensive disorders of pregnancy according to the clinical phenotypes that prioritize fetoplacental characteristics and not the time at onset of hypertensive disorders of pregnancy. At the fetal-maternal medicine unit of Ziekenhuis Oost-Limburg (Genk, Belgium), maternal cardiovascular parameters were obtained through impedance cardiography using a noninvasive continuous cardiac output monitor with the patients placed in a standing position. The patients were classified as pregnant women with hypertensive disorders of pregnancy who delivered appropriate- and small-for-gestational-age fetuses. Normotensive pregnant women with an appropriate-for-gestational-age fetus at delivery were enrolled as the control group. The possible impact of obesity (body mass index ≥30 kg/m 2 ) on maternal hemodynamics was reassessed in the same groups. Maternal age, parity, body mass index, and blood pressure were not significantly different between the hypertensive disorders of pregnancy/appropriate-for-gestational-age and hypertensive disorders of pregnancy/small-for-gestational-age groups. The mean uterine artery pulsatility index was significantly higher in the hypertensive disorders of pregnancy/small-for-gestational-age group. The cardiac output and cardiac index were significantly lower in the hypertensive disorders of pregnancy/small-for-gestational-age group (cardiac output 6.5 L/min, cardiac index 3.6) than in the hypertensive disorders of pregnancy/appropriate-for-gestational-age group

  9. Classifying and Designing the Educational Methods with Information Communications Technoligies

    Directory of Open Access Journals (Sweden)

    I. N. Semenova

    2013-01-01

    Full Text Available The article describes the conceptual apparatus for implementing the Information Communications Technologies (ICT in education. The authors suggest the classification variants of the related teaching methods according to the following component combinations: types of students work with information, goals of ICT incorporation into the training process, individualization degrees, contingent involvement, activity levels and pedagogical field targets, ideology of informational didactics, etc. Each classification can solve the educational tasks in the context of the partial paradigm of modern didactics; any kind of methods implies the particular combination of activities in educational environment.The whole spectrum of classifications provides the informational functional basis for the adequate selection of necessary teaching methods in accordance with the specified goals and planned results. The potential variants of ICT implementation methods are given for different teaching models. 

  10. Methods to classify bacterial pathogens in cystic fibrosis

    DEFF Research Database (Denmark)

    Bjarnsholt, Thomas; Nielsen, Xiaohui Chen; Johansen, Ulla

    2011-01-01

    for identification of isolates from the Burkholderia complex to the species level. DNA typing by PFGE, which can be used for any bacterial pathogen, is described as it is employed for Pseudomonas aeruginosa. A commercially available ELISA method is described for measuring IgG antibodies against P. aeruginosa in CF......Many bacteria can be detected in CF sputum, pathogenic and commensal. Modified Koch's criteria for identification of established and emerging CF pathogens are therefore described. Methods are described to isolate bacteria and to detect bacterial biofilms in sputum or lung tissue from CF patients...

  11. Variants of the Borda count method for combining ranked classifier hypotheses

    NARCIS (Netherlands)

    van Erp, Merijn; Schomaker, Lambert; Schomaker, Lambert; Vuurpijl, Louis

    2000-01-01

    The Borda count is a simple yet effective method of combining rankings. In pattern recognition, classifiers are often able to return a ranked set of results. Several experiments have been conducted to test the ability of the Borda count and two variant methods to combine these ranked classifier

  12. A method of evolving novel feature extraction algorithms for detecting buried objects in FLIR imagery using genetic programming

    Science.gov (United States)

    Paino, A.; Keller, J.; Popescu, M.; Stone, K.

    2014-06-01

    In this paper we present an approach that uses Genetic Programming (GP) to evolve novel feature extraction algorithms for greyscale images. Our motivation is to create an automated method of building new feature extraction algorithms for images that are competitive with commonly used human-engineered features, such as Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG). The evolved feature extraction algorithms are functions defined over the image space, and each produces a real-valued feature vector of variable length. Each evolved feature extractor breaks up the given image into a set of cells centered on every pixel, performs evolved operations on each cell, and then combines the results of those operations for every cell using an evolved operator. Using this method, the algorithm is flexible enough to reproduce both LBP and HOG features. The dataset we use to train and test our approach consists of a large number of pre-segmented image "chips" taken from a Forward Looking Infrared Imagery (FLIR) camera mounted on the hood of a moving vehicle. The goal is to classify each image chip as either containing or not containing a buried object. To this end, we define the fitness of a candidate solution as the cross-fold validation accuracy of the features generated by said candidate solution when used in conjunction with a Support Vector Machine (SVM) classifier. In order to validate our approach, we compare the classification accuracy of an SVM trained using our evolved features with the accuracy of an SVM trained using mainstream feature extraction algorithms, including LBP and HOG.

  13. Accuracy Evaluation of C4.5 and Naive Bayes Classifiers Using Attribute Ranking Method

    Directory of Open Access Journals (Sweden)

    S. Sivakumari

    2009-03-01

    Full Text Available This paper intends to classify the Ljubljana Breast Cancer dataset using C4.5 Decision Tree and Nai?ve Bayes classifiers. In this work, classification is carriedout using two methods. In the first method, dataset is analysed using all the attributes in the dataset. In the second method, attributes are ranked using information gain ranking technique and only the high ranked attributes are used to build the classification model. We are evaluating the results of C4.5 Decision Tree and Nai?ve Bayes classifiers in terms of classifier accuracy for various folds of cross validation. Our results show that both the classifiers achieve good accuracy on the dataset.

  14. A Bayesian method for comparing and combining binary classifiers in the absence of a gold standard

    Directory of Open Access Journals (Sweden)

    Keith Jonathan M

    2012-07-01

    Full Text Available Abstract Background Many problems in bioinformatics involve classification based on features such as sequence, structure or morphology. Given multiple classifiers, two crucial questions arise: how does their performance compare, and how can they best be combined to produce a better classifier? A classifier can be evaluated in terms of sensitivity and specificity using benchmark, or gold standard, data, that is, data for which the true classification is known. However, a gold standard is not always available. Here we demonstrate that a Bayesian model for comparing medical diagnostics without a gold standard can be successfully applied in the bioinformatics domain, to genomic scale data sets. We present a new implementation, which unlike previous implementations is applicable to any number of classifiers. We apply this model, for the first time, to the problem of finding the globally optimal logical combination of classifiers. Results We compared three classifiers of protein subcellular localisation, and evaluated our estimates of sensitivity and specificity against estimates obtained using a gold standard. The method overestimated sensitivity and specificity with only a small discrepancy, and correctly ranked the classifiers. Diagnostic tests for swine flu were then compared on a small data set. Lastly, classifiers for a genome-wide association study of macular degeneration with 541094 SNPs were analysed. In all cases, run times were feasible, and results precise. The optimal logical combination of classifiers was also determined for all three data sets. Code and data are available from http://bioinformatics.monash.edu.au/downloads/. Conclusions The examples demonstrate the methods are suitable for both small and large data sets, applicable to the wide range of bioinformatics classification problems, and robust to dependence between classifiers. In all three test cases, the globally optimal logical combination of the classifiers was found to be

  15. Using multivariate machine learning methods and structural MRI to classify childhood onset schizophrenia and healthy controls

    Directory of Open Access Journals (Sweden)

    Deanna eGreenstein

    2012-06-01

    Full Text Available Introduction: Multivariate machine learning methods can be used to classify groups of schizophrenia patients and controls using structural magnetic resonance imaging (MRI. However, machine learning methods to date have not been extended beyond classification and contemporaneously applied in a meaningful way to clinical measures. We hypothesized that brain measures would classify groups, and that increased likelihood of being classified as a patient using regional brain measures would be positively related to illness severity, developmental delays and genetic risk. Methods: Using 74 anatomic brain MRI sub regions and Random Forest, we classified 98 COS patients and 99 age, sex, and ethnicity-matched healthy controls. We also used Random Forest to determine the likelihood of being classified as a schizophrenia patient based on MRI measures. We then explored relationships between brain-based probability of illness and symptoms, premorbid development, and presence of copy number variation associated with schizophrenia. Results: Brain regions jointly classified COS and control groups with 73.7% accuracy. Greater brain-based probability of illness was associated with worse functioning (p= 0.0004 and fewer developmental delays (p=0.02. Presence of copy number variation (CNV was associated with lower probability of being classified as schizophrenia (p=0.001. The regions that were most important in classifying groups included left temporal lobes, bilateral dorsolateral prefrontal regions, and left medial parietal lobes. Conclusions: Schizophrenia and control groups can be well classified using Random Forest and anatomic brain measures, and brain-based probability of illness has a positive relationship with illness severity and a negative relationship with developmental delays/problems and CNV-based risk.

  16. An improved early detection method of type-2 diabetes mellitus using multiple classifier system

    KAUST Repository

    Zhu, Jia

    2015-01-01

    The specific causes of complex diseases such as Type-2 Diabetes Mellitus (T2DM) have not yet been identified. Nevertheless, many medical science researchers believe that complex diseases are caused by a combination of genetic, environmental, and lifestyle factors. Detection of such diseases becomes an issue because it is not free from false presumptions and is accompanied by unpredictable effects. Given the greatly increased amount of data gathered in medical databases, data mining has been used widely in recent years to detect and improve the diagnosis of complex diseases. However, past research showed that no single classifier can be considered optimal for all problems. Therefore, in this paper, we focus on employing multiple classifier systems to improve the accuracy of detection for complex diseases, such as T2DM. We proposed a dynamic weighted voting scheme called multiple factors weighted combination for classifiers\\' decision combination. This method considers not only the local and global accuracy but also the diversity among classifiers and localized generalization error of each classifier. We evaluated our method on two real T2DM data sets and other medical data sets. The favorable results indicated that our proposed method significantly outperforms individual classifiers and other fusion methods.

  17. High-resolution method for evolving complex interface networks

    Science.gov (United States)

    Pan, Shucheng; Hu, Xiangyu Y.; Adams, Nikolaus A.

    2018-04-01

    In this paper we describe a high-resolution transport formulation of the regional level-set approach for an improved prediction of the evolution of complex interface networks. The novelty of this method is twofold: (i) construction of local level sets and reconstruction of a global level set, (ii) local transport of the interface network by employing high-order spatial discretization schemes for improved representation of complex topologies. Various numerical test cases of multi-region flow problems, including triple-point advection, single vortex flow, mean curvature flow, normal driven flow, dry foam dynamics and shock-bubble interaction show that the method is accurate and suitable for a wide range of complex interface-network evolutions. Its overall computational cost is comparable to the Semi-Lagrangian regional level-set method while the prediction accuracy is significantly improved. The approach thus offers a viable alternative to previous interface-network level-set method.

  18. Sentiment analysis system for movie review in Bahasa Indonesia using naive bayes classifier method

    Science.gov (United States)

    Nurdiansyah, Yanuar; Bukhori, Saiful; Hidayat, Rahmad

    2018-04-01

    There are many ways of implementing the use of sentiments often found in documents; one of which is the sentiments found on the product or service reviews. It is so important to be able to process and extract textual data from the documents. Therefore, we propose a system that is able to classify sentiments from review documents into two classes: positive sentiment and negative sentiment. We use Naive Bayes Classifier method in this document classification system that we build. We choose Movienthusiast, a movie reviews in Bahasa Indonesia website as the source of our review documents. From there, we were able to collect 1201 movie reviews: 783 positive reviews and 418 negative reviews that we use as the dataset for this machine learning classifier. The classifying accuracy yields an average of 88.37% from five times of accuracy measuring attempts using aforementioned dataset.

  19. NATO Advanced Study Institute on Evolving Methods for Macromolecular Gystallography

    CERN Document Server

    Read, Randy J

    2007-01-01

    X-ray crystallography is the pre-eminent technique for visualizing the structures of macromolecules at atomic resolution. These structures are central to understanding the detailed mechanisms of biological processes, and to discovering novel therapeutics using a structure-based approach. As yet, structures are known for only a small fraction of the proteins encoded by human and pathogenic genomes. To counter the myriad modern threats of disease, there is an urgent need to determine the structures of the thousands of proteins whose structure and function remain unknown. This volume draws on the expertise of leaders in the field of macromolecular crystallography to illuminate the dramatic developments that are accelerating progress in structural biology. Their contributions span the range of techniques from crystallization through data collection, structure solution and analysis, and show how modern high-throughput methods are contributing to a deeper understanding of medical problems.

  20. The evolving role of new imaging methods in breast screening.

    Science.gov (United States)

    Houssami, Nehmat; Ciatto, Stefano

    2011-09-01

    The potential to avert breast cancer deaths through screening means that efforts continue to identify methods which may enhance early detection. While the role of most new imaging technologies remains in adjunct screening or in the work-up of mammography-detected abnormalities, some of the new breast imaging tests (such as MRI) have roles in screening groups of women defined by increased cancer risk. This paper highlights the evidence and the current role of new breast imaging technologies in screening, focusing on those that have broader application in population screening, including digital mammography, breast ultrasound in women with dense breasts, and computer-aided detection. It highlights that evidence on new imaging in screening comes mostly from non-randomised studies that have quantified test detection capability as adjunct to mammography, or have compared measures of screening performance for new technologies with that of conventional mammography. Two RCTs have provided high-quality evidence on the equivalence of digital and conventional mammography and on outcomes of screen-reading complemented by CAD. Many of these imaging technologies enhance cancer detection but also increase recall and false positives in screening. Copyright © 2011 Elsevier Inc. All rights reserved.

  1. A Cross-Classified CFA-MTMM Model for Structurally Different and Nonindependent Interchangeable Methods.

    Science.gov (United States)

    Koch, Tobias; Schultze, Martin; Jeon, Minjeong; Nussbeck, Fridtjof W; Praetorius, Anna-Katharina; Eid, Michael

    2016-01-01

    Multirater (multimethod, multisource) studies are increasingly applied in psychology. Eid and colleagues (2008) proposed a multilevel confirmatory factor model for multitrait-multimethod (MTMM) data combining structurally different and multiple independent interchangeable methods (raters). In many studies, however, different interchangeable raters (e.g., peers, subordinates) are asked to rate different targets (students, supervisors), leading to violations of the independence assumption and to cross-classified data structures. In the present work, we extend the ML-CFA-MTMM model by Eid and colleagues (2008) to cross-classified multirater designs. The new C4 model (Cross-Classified CTC[M-1] Combination of Methods) accounts for nonindependent interchangeable raters and enables researchers to explicitly model the interaction between targets and raters as a latent variable. Using a real data application, it is shown how credibility intervals of model parameters and different variance components can be obtained using Bayesian estimation techniques.

  2. Users in the Driver's Seat: A New Approach to Classifying Teaching Methods in a University Repository

    NARCIS (Netherlands)

    Neumann, Susanne; Oberhuemer, Petra; Koper, Rob

    2009-01-01

    Neumann, S., Oberhuemer, P., & Koper, R. (2009). Users in the Driver's Seat: A New Approach to Classifying Teaching Methods in a University Repository. In U. Cress, V. Dimitrova & M. Specht (Eds.), Learning in the Synergy of Multiple Disciplines. Proceedings of the Fourth European Conference on

  3. The Capacity Profile: a method to classify additional care needs in children with neurodevelopmental disabilities

    NARCIS (Netherlands)

    Meester-Delver, Anke; Beelen, Anita; Hennekam, Raoul; Nollet, Frans; Hadders-Algra, Mijna

    2007-01-01

    The aim of this study was to determine the interrater reliability and stability over time of the Capacity Profile (CAP). The CAP is a standardized method for classifying additional care needs indicated by current impairments in five domains of body functions: physical health, neuromusculoskeletal

  4. Automatically classifying sentences in full-text biomedical articles into Introduction, Methods, Results and Discussion.

    Science.gov (United States)

    Agarwal, Shashank; Yu, Hong

    2009-12-01

    Biomedical texts can be typically represented by four rhetorical categories: Introduction, Methods, Results and Discussion (IMRAD). Classifying sentences into these categories can benefit many other text-mining tasks. Although many studies have applied different approaches for automatically classifying sentences in MEDLINE abstracts into the IMRAD categories, few have explored the classification of sentences that appear in full-text biomedical articles. We first evaluated whether sentences in full-text biomedical articles could be reliably annotated into the IMRAD format and then explored different approaches for automatically classifying these sentences into the IMRAD categories. Our results show an overall annotation agreement of 82.14% with a Kappa score of 0.756. The best classification system is a multinomial naïve Bayes classifier trained on manually annotated data that achieved 91.95% accuracy and an average F-score of 91.55%, which is significantly higher than baseline systems. A web version of this system is available online at-http://wood.ims.uwm.edu/full_text_classifier/.

  5. Using hierarchical clustering methods to classify motor activities of COPD patients from wearable sensor data

    Directory of Open Access Journals (Sweden)

    Reilly John J

    2005-06-01

    Full Text Available Abstract Background Advances in miniature sensor technology have led to the development of wearable systems that allow one to monitor motor activities in the field. A variety of classifiers have been proposed in the past, but little has been done toward developing systematic approaches to assess the feasibility of discriminating the motor tasks of interest and to guide the choice of the classifier architecture. Methods A technique is introduced to address this problem according to a hierarchical framework and its use is demonstrated for the application of detecting motor activities in patients with chronic obstructive pulmonary disease (COPD undergoing pulmonary rehabilitation. Accelerometers were used to collect data for 10 different classes of activity. Features were extracted to capture essential properties of the data set and reduce the dimensionality of the problem at hand. Cluster measures were utilized to find natural groupings in the data set and then construct a hierarchy of the relationships between clusters to guide the process of merging clusters that are too similar to distinguish reliably. It provides a means to assess whether the benefits of merging for performance of a classifier outweigh the loss of resolution incurred through merging. Results Analysis of the COPD data set demonstrated that motor tasks related to ambulation can be reliably discriminated from tasks performed in a seated position with the legs in motion or stationary using two features derived from one accelerometer. Classifying motor tasks within the category of activities related to ambulation requires more advanced techniques. While in certain cases all the tasks could be accurately classified, in others merging clusters associated with different motor tasks was necessary. When merging clusters, it was found that the proposed method could lead to more than 12% improvement in classifier accuracy while retaining resolution of 4 tasks. Conclusion Hierarchical

  6. An Improved Ensemble Learning Method for Classifying High-Dimensional and Imbalanced Biomedicine Data.

    Science.gov (United States)

    Yu, Hualong; Ni, Jun

    2014-01-01

    Training classifiers on skewed data can be technically challenging tasks, especially if the data is high-dimensional simultaneously, the tasks can become more difficult. In biomedicine field, skewed data type often appears. In this study, we try to deal with this problem by combining asymmetric bagging ensemble classifier (asBagging) that has been presented in previous work and an improved random subspace (RS) generation strategy that is called feature subspace (FSS). Specifically, FSS is a novel method to promote the balance level between accuracy and diversity of base classifiers in asBagging. In view of the strong generalization capability of support vector machine (SVM), we adopt it to be base classifier. Extensive experiments on four benchmark biomedicine data sets indicate that the proposed ensemble learning method outperforms many baseline approaches in terms of Accuracy, F-measure, G-mean and AUC evaluation criterions, thus it can be regarded as an effective and efficient tool to deal with high-dimensional and imbalanced biomedical data.

  7. FEATURE SELECTION METHODS BASED ON MUTUAL INFORMATION FOR CLASSIFYING HETEROGENEOUS FEATURES

    Directory of Open Access Journals (Sweden)

    Ratri Enggar Pawening

    2016-06-01

    Full Text Available Datasets with heterogeneous features can affect feature selection results that are not appropriate because it is difficult to evaluate heterogeneous features concurrently. Feature transformation (FT is another way to handle heterogeneous features subset selection. The results of transformation from non-numerical into numerical features may produce redundancy to the original numerical features. In this paper, we propose a method to select feature subset based on mutual information (MI for classifying heterogeneous features. We use unsupervised feature transformation (UFT methods and joint mutual information maximation (JMIM methods. UFT methods is used to transform non-numerical features into numerical features. JMIM methods is used to select feature subset with a consideration of the class label. The transformed and the original features are combined entirely, then determine features subset by using JMIM methods, and classify them using support vector machine (SVM algorithm. The classification accuracy are measured for any number of selected feature subset and compared between UFT-JMIM methods and Dummy-JMIM methods. The average classification accuracy for all experiments in this study that can be achieved by UFT-JMIM methods is about 84.47% and Dummy-JMIM methods is about 84.24%. This result shows that UFT-JMIM methods can minimize information loss between transformed and original features, and select feature subset to avoid redundant and irrelevant features.

  8. A method of distributed avionics data processing based on SVM classifier

    Science.gov (United States)

    Guo, Hangyu; Wang, Jinyan; Kang, Minyang; Xu, Guojing

    2018-03-01

    Under the environment of system combat, in order to solve the problem on management and analysis of the massive heterogeneous data on multi-platform avionics system, this paper proposes a management solution which called avionics "resource cloud" based on big data technology, and designs an aided decision classifier based on SVM algorithm. We design an experiment with STK simulation, the result shows that this method has a high accuracy and a broad application prospect.

  9. On Reducing the Effect of Covariate Factors in Gait Recognition: A Classifier Ensemble Method.

    Science.gov (United States)

    Guan, Yu; Li, Chang-Tsun; Roli, Fabio

    2015-07-01

    Robust human gait recognition is challenging because of the presence of covariate factors such as carrying condition, clothing, walking surface, etc. In this paper, we model the effect of covariates as an unknown partial feature corruption problem. Since the locations of corruptions may differ for different query gaits, relevant features may become irrelevant when walking condition changes. In this case, it is difficult to train one fixed classifier that is robust to a large number of different covariates. To tackle this problem, we propose a classifier ensemble method based on the random subspace Method (RSM) and majority voting (MV). Its theoretical basis suggests it is insensitive to locations of corrupted features, and thus can generalize well to a large number of covariates. We also extend this method by proposing two strategies, i.e, local enhancing (LE) and hybrid decision-level fusion (HDF) to suppress the ratio of false votes to true votes (before MV). The performance of our approach is competitive against the most challenging covariates like clothing, walking surface, and elapsed time. We evaluate our method on the USF dataset and OU-ISIR-B dataset, and it has much higher performance than other state-of-the-art algorithms.

  10. Measurement properties of clinical assessment methods for classifying generalized joint hypermobility

    DEFF Research Database (Denmark)

    Juul-Kristensen, Birgit; Schmedling, Karoline; Rombaut, Lies

    2017-01-01

    methods. For BS-self, the validity showed unknown evidence compared with test assessment methods. In conclusion, following recommended uniformity of testing procedures, the recommendation for clinical use in adults is BS with cut-point of 5 of 9 including historical information, while in children it is BS...... with cut-point of at least 6 of 9. However, more studies are needed to conclude on the validity properties of these assessment methods, and before evidence-based recommendations can be made for clinical use on the "best" assessment method for classifying GJH. © 2017 Wiley Periodicals, Inc....... for evaluating the methodological quality of the identified studies, all included studies were rated "fair" or "poor." Most studies were using BS, and for BS the reliability most of the studies showed limited positive to conflicting evidence, with some shortcomings on studies for the validity. The three other...

  11. Methods to classify maize cultivars in use efficiency and response to nitrogen

    Directory of Open Access Journals (Sweden)

    Cleiton Lacerda Godoy

    2013-10-01

    Full Text Available n plant breeding programs that aim to obtain cultivars with nitrogen (N use efficiency, the focus is on methods of selection and experimental procedures that present low cost, fast response, high repeatability, and can be applied to a large number of cultivars. Thus, the objectives of this study were to classify maize cultivars regarding their use efficiency and response to N in a breeding program, and to validate the methodology with contrasting doses of the nutrient. The experimental design was a randomized block with the treatments arranged in a split-plot scheme with three replicates and five N doses (0, 30, 60, 120 and 200 kg ha-1 in the plots, and six cultivars in subplots. We compared a method examining the efficiency and response (ER with two contrasting doses of N. After that, the analysis of variance, mean comparison and regression analysis were performed. In conclusion, the method of the use efficiency and response based on two N levels classifies the cultivars in the same way as the regression analysis, and it is appropriate in plant breeding routine. Thus, it is necessary to identify the levels of N required to discriminate maize cultivars in conditions of low and high N availability in plant breeding programs that aim to obtain efficient and responsive cultivars. Moreover, the analysis of the interaction genotype x environment at experiments with contrasting doses is always required, even when the interaction is not significant.

  12. ADVANTAGES AND DISADVANTAGES OF APPLYING EVOLVED METHODS IN MANAGEMENT ACCOUNTING PRACTICE

    Directory of Open Access Journals (Sweden)

    SABOU FELICIA

    2014-05-01

    Full Text Available The evolved methods of management accounting have been developed with the purpose of removing the disadvantages of the classical methods, they are methods adapted to the new market conditions, which provide much more useful cost-related information so that the management of the company is able to take certain strategic decisions. Out of the category of evolved methods, the most used is the one of standard-costs due to the advantages that it presents, being used widely in calculating the production costs in some developed countries. The main advantages of the standard-cost method are: in-advance knowledge of the production costs and the measures that ensure compliance to these; with the help of the deviations calculated from the standard costs, one manages a systematic control over the costs, thus allowing the making of decision in due time, in as far as the elimination of the deviations and the improvement of the activity are concerned and it is a method of analysis, control and cost forecast; Although the advantages of using standards are significant, there are a few disadvantages to the employment of the standard-cost method: sometimes there can appear difficulties in establishing the deviations from the standard costs, the method does not allow an accurate calculation of the fixed costs. As a result of the study, we can observe the fact that the evolved methods of management accounting, as compared to the classical ones, present a series of advantages linked to a better analysis, control, and foreseeing of costs, whereas the main disadvantage is related to the large amount of work necessary for these methods to be applied.

  13. ADVANTAGES AND DISADVANTAGES OF APPLYING EVOLVED METHODS IN MANAGEMENT ACCOUNTING PRACTICE

    Directory of Open Access Journals (Sweden)

    SABOU FELICIA

    2014-05-01

    Full Text Available The evolved methods of management accounting have been developed with the purpose of removing the disadvantages of the classical methods, they are methods adapted to the new market conditions, which provide much more useful cost-related information so that the management of the company is able to take certain strategic decisions. Out of the category of evolved methods, the most used is the one of standard-costs due to the advantages that it presents, being used widely in calculating the production costs in some developed countries. The main advantages of the standard-cost method are: in-advance knowledge of the production costs and the measures that ensure compliance to these; with the help of the deviations calculated from the standard costs, one manages a systematic control over the costs, thus allowing the making of decision in due time, in as far as the elimination of the deviations and the improvement of the activity are concerned and it is a method of analysis, control and cost forecast; Although the advantages of using standards are significant, there are a few disadvantages to the employment of the standard-cost method: sometimes there can appear difficulties in establishing the deviations from the standard costs, the method does not allow an accurate calculation of the fixed costs. As a result of the study, we can observe the fact that the evolved methods of management accounting, as compared to the classical ones, present a series of advantages linked to a better analysis, control, and foreseeing of costs, whereas the main disadvantage is related to the large amount of work necessary for these methods to be applied

  14. An Ensemble Method with Integration of Feature Selection and Classifier Selection to Detect the Landslides

    Science.gov (United States)

    Zhongqin, G.; Chen, Y.

    2017-12-01

    Abstract Quickly identify the spatial distribution of landslides automatically is essential for the prevention, mitigation and assessment of the landslide hazard. It's still a challenging job owing to the complicated characteristics and vague boundary of the landslide areas on the image. The high resolution remote sensing image has multi-scales, complex spatial distribution and abundant features, the object-oriented image classification methods can make full use of the above information and thus effectively detect the landslides after the hazard happened. In this research we present a new semi-supervised workflow, taking advantages of recent object-oriented image analysis and machine learning algorithms to quick locate the different origins of landslides of some areas on the southwest part of China. Besides a sequence of image segmentation, feature selection, object classification and error test, this workflow ensemble the feature selection and classifier selection. The feature this study utilized were normalized difference vegetation index (NDVI) change, textural feature derived from the gray level co-occurrence matrices (GLCM), spectral feature and etc. The improvement of this study shows this algorithm significantly removes some redundant feature and the classifiers get fully used. All these improvements lead to a higher accuracy on the determination of the shape of landslides on the high resolution remote sensing image, in particular the flexibility aimed at different kinds of landslides.

  15. An advanced method for classifying atmospheric circulation types based on prototypes connectivity graph

    Science.gov (United States)

    Zagouras, Athanassios; Argiriou, Athanassios A.; Flocas, Helena A.; Economou, George; Fotopoulos, Spiros

    2012-11-01

    Classification of weather maps at various isobaric levels as a methodological tool is used in several problems related to meteorology, climatology, atmospheric pollution and to other fields for many years. Initially the classification was performed manually. The criteria used by the person performing the classification are features of isobars or isopleths of geopotential height, depending on the type of maps to be classified. Although manual classifications integrate the perceptual experience and other unquantifiable qualities of the meteorology specialists involved, these are typically subjective and time consuming. Furthermore, during the last years different approaches of automated methods for atmospheric circulation classification have been proposed, which present automated and so-called objective classifications. In this paper a new method of atmospheric circulation classification of isobaric maps is presented. The method is based on graph theory. It starts with an intelligent prototype selection using an over-partitioning mode of fuzzy c-means (FCM) algorithm, proceeds to a graph formulation for the entire dataset and produces the clusters based on the contemporary dominant sets clustering method. Graph theory is a novel mathematical approach, allowing a more efficient representation of spatially correlated data, compared to the classical Euclidian space representation approaches, used in conventional classification methods. The method has been applied to the classification of 850 hPa atmospheric circulation over the Eastern Mediterranean. The evaluation of the automated methods is performed by statistical indexes; results indicate that the classification is adequately comparable with other state-of-the-art automated map classification methods, for a variable number of clusters.

  16. Basic Emotions in the Nencki Affective Word List (NAWL BE): New Method of Classifying Emotional Stimuli.

    Science.gov (United States)

    Wierzba, Małgorzata; Riegel, Monika; Wypych, Marek; Jednoróg, Katarzyna; Turnau, Paweł; Grabowska, Anna; Marchewka, Artur

    2015-01-01

    The Nencki Affective Word List (NAWL) has recently been introduced as a standardized database of Polish words suitable for studying various aspects of language and emotions. Though the NAWL was originally based on the most commonly used dimensional approach, it is not the only way of studying emotions. Another framework is based on discrete emotional categories. Since the two perspectives are recognized as complementary, the aim of the present study was to supplement the NAWL database by the addition of categories corresponding to basic emotions. Thus, 2902 Polish words from the NAWL were presented to 265 subjects, who were instructed to rate them according to the intensity of each of the five basic emotions: happiness, anger, sadness, fear and disgust. The general characteristics of the present word database, as well as the relationships between the studied variables are shown to be consistent with typical patterns found in previous studies using similar databases for different languages. Here we present the Basic Emotions in the Nencki Affective Word List (NAWL BE) as a database of verbal material suitable for highly controlled experimental research. To make the NAWL more convenient to use, we introduce a comprehensive method of classifying stimuli to basic emotion categories. We discuss the advantages of our method in comparison to other methods of classification. Additionally, we provide an interactive online tool (http://exp.lobi.nencki.gov.pl/nawl-analysis) to help researchers browse and interactively generate classes of stimuli to meet their specific requirements.

  17. Basic Emotions in the Nencki Affective Word List (NAWL BE: New Method of Classifying Emotional Stimuli.

    Directory of Open Access Journals (Sweden)

    Małgorzata Wierzba

    Full Text Available The Nencki Affective Word List (NAWL has recently been introduced as a standardized database of Polish words suitable for studying various aspects of language and emotions. Though the NAWL was originally based on the most commonly used dimensional approach, it is not the only way of studying emotions. Another framework is based on discrete emotional categories. Since the two perspectives are recognized as complementary, the aim of the present study was to supplement the NAWL database by the addition of categories corresponding to basic emotions. Thus, 2902 Polish words from the NAWL were presented to 265 subjects, who were instructed to rate them according to the intensity of each of the five basic emotions: happiness, anger, sadness, fear and disgust. The general characteristics of the present word database, as well as the relationships between the studied variables are shown to be consistent with typical patterns found in previous studies using similar databases for different languages. Here we present the Basic Emotions in the Nencki Affective Word List (NAWL BE as a database of verbal material suitable for highly controlled experimental research. To make the NAWL more convenient to use, we introduce a comprehensive method of classifying stimuli to basic emotion categories. We discuss the advantages of our method in comparison to other methods of classification. Additionally, we provide an interactive online tool (http://exp.lobi.nencki.gov.pl/nawl-analysis to help researchers browse and interactively generate classes of stimuli to meet their specific requirements.

  18. Development of new estimation method for CO2 evolved from oil shale

    International Nuclear Information System (INIS)

    Sato, S.; Enomoto, M.

    1997-01-01

    The quality of fossil fuels tends to be evaluated by amounts of CO 2 emissions. For the evaluation of an oil shale from this point, an on-line thermogravimetric-gas chromatographic system was used to measure CO 2 evolution profiles on temperature with a small oil shale sample. This method makes it possible to estimate the amounts of CO 2 evolved from kerogen and carbonates in retorting and those from carbonates in combustion, respectively. These results will be basic data for a novel oil shale retorting process for the control of CO 2 emissions. The profiles for Thai and Colorado oil shales have shown CO 2 mainly evolved by the pyrolysis of kerogen below 550 degree C, and that evolved by the decomposition of carbonates above that temperature. On the other hand, the profile for Condor oil shale showed that most carbonates decomposed below 550 degree C, while only small amounts of carbonates decomposed above this temperature. 14 refs., 2 figs., 3 tabs

  19. Electronic nose with a new feature reduction method and a multi-linear classifier for Chinese liquor classification

    Energy Technology Data Exchange (ETDEWEB)

    Jing, Yaqi; Meng, Qinghao, E-mail: qh-meng@tju.edu.cn; Qi, Peifeng; Zeng, Ming; Li, Wei; Ma, Shugen [Tianjin Key Laboratory of Process Measurement and Control, Institute of Robotics and Autonomous Systems, School of Electrical Engineering and Automation, Tianjin University, Tianjin 300072 (China)

    2014-05-15

    An electronic nose (e-nose) was designed to classify Chinese liquors of the same aroma style. A new method of feature reduction which combined feature selection with feature extraction was proposed. Feature selection method used 8 feature-selection algorithms based on information theory and reduced the dimension of the feature space to 41. Kernel entropy component analysis was introduced into the e-nose system as a feature extraction method and the dimension of feature space was reduced to 12. Classification of Chinese liquors was performed by using back propagation artificial neural network (BP-ANN), linear discrimination analysis (LDA), and a multi-linear classifier. The classification rate of the multi-linear classifier was 97.22%, which was higher than LDA and BP-ANN. Finally the classification of Chinese liquors according to their raw materials and geographical origins was performed using the proposed multi-linear classifier and classification rate was 98.75% and 100%, respectively.

  20. Electronic nose with a new feature reduction method and a multi-linear classifier for Chinese liquor classification

    International Nuclear Information System (INIS)

    Jing, Yaqi; Meng, Qinghao; Qi, Peifeng; Zeng, Ming; Li, Wei; Ma, Shugen

    2014-01-01

    An electronic nose (e-nose) was designed to classify Chinese liquors of the same aroma style. A new method of feature reduction which combined feature selection with feature extraction was proposed. Feature selection method used 8 feature-selection algorithms based on information theory and reduced the dimension of the feature space to 41. Kernel entropy component analysis was introduced into the e-nose system as a feature extraction method and the dimension of feature space was reduced to 12. Classification of Chinese liquors was performed by using back propagation artificial neural network (BP-ANN), linear discrimination analysis (LDA), and a multi-linear classifier. The classification rate of the multi-linear classifier was 97.22%, which was higher than LDA and BP-ANN. Finally the classification of Chinese liquors according to their raw materials and geographical origins was performed using the proposed multi-linear classifier and classification rate was 98.75% and 100%, respectively

  1. EnsembleGASVR: A novel ensemble method for classifying missense single nucleotide polymorphisms

    KAUST Repository

    Rapakoulia, Trisevgeni

    2014-04-26

    Motivation: Single nucleotide polymorphisms (SNPs) are considered the most frequently occurring DNA sequence variations. Several computational methods have been proposed for the classification of missense SNPs to neutral and disease associated. However, existing computational approaches fail to select relevant features by choosing them arbitrarily without sufficient documentation. Moreover, they are limited to the problem ofmissing values, imbalance between the learning datasets and most of them do not support their predictions with confidence scores. Results: To overcome these limitations, a novel ensemble computational methodology is proposed. EnsembleGASVR facilitates a twostep algorithm, which in its first step applies a novel evolutionary embedded algorithm to locate close to optimal Support Vector Regression models. In its second step, these models are combined to extract a universal predictor, which is less prone to overfitting issues, systematizes the rebalancing of the learning sets and uses an internal approach for solving the missing values problem without loss of information. Confidence scores support all the predictions and the model becomes tunable by modifying the classification thresholds. An extensive study was performed for collecting the most relevant features for the problem of classifying SNPs, and a superset of 88 features was constructed. Experimental results show that the proposed framework outperforms well-known algorithms in terms of classification performance in the examined datasets. Finally, the proposed algorithmic framework was able to uncover the significant role of certain features such as the solvent accessibility feature, and the top-scored predictions were further validated by linking them with disease phenotypes. © The Author 2014.

  2. Application of hierarchical clustering method to classify of space-time rainfall patterns

    Science.gov (United States)

    Yu, Hwa-Lung; Chang, Tu-Je

    2010-05-01

    Understanding the local precipitation patterns is essential to the water resources management and flooding mitigation. The precipitation patterns can vary in space and time depending upon the factors from different spatial scales such as local topological changes and macroscopic atmospheric circulation. The spatiotemporal variation of precipitation in Taiwan is significant due to its complex terrain and its location at west pacific and subtropical area, where is the boundary between the pacific ocean and Asia continent with the complex interactions among the climatic processes. This study characterizes local-scale precipitation patterns by classifying the historical space-time precipitation records. We applied the hierarchical ascending clustering method to analyze the precipitation records from 1960 to 2008 at the six rainfall stations located in Lan-yang catchment at the northeast of the island. Our results identify the four primary space-time precipitation types which may result from distinct driving forces from the changes of atmospheric variables and topology at different space-time scales. This study also presents an important application of the statistical downscaling to combine large-scale upper-air circulation with local space-time precipitation patterns.

  3. Comparison of Shallow and Deep Learning Methods on Classifying the Regional Pattern of Diffuse Lung Disease.

    Science.gov (United States)

    Kim, Guk Bae; Jung, Kyu-Hwan; Lee, Yeha; Kim, Hyun-Jun; Kim, Namkug; Jun, Sanghoon; Seo, Joon Beom; Lynch, David A

    2017-10-17

    This study aimed to compare shallow and deep learning of classifying the patterns of interstitial lung diseases (ILDs). Using high-resolution computed tomography images, two experienced radiologists marked 1200 regions of interest (ROIs), in which 600 ROIs were each acquired using a GE or Siemens scanner and each group of 600 ROIs consisted of 100 ROIs for subregions that included normal and five regional pulmonary disease patterns (ground-glass opacity, consolidation, reticular opacity, emphysema, and honeycombing). We employed the convolution neural network (CNN) with six learnable layers that consisted of four convolution layers and two fully connected layers. The classification results were compared with the results classified by a shallow learning of a support vector machine (SVM). The CNN classifier showed significantly better performance for accuracy compared with that of the SVM classifier by 6-9%. As the convolution layer increases, the classification accuracy of the CNN showed better performance from 81.27 to 95.12%. Especially in the cases showing pathological ambiguity such as between normal and emphysema cases or between honeycombing and reticular opacity cases, the increment of the convolution layer greatly drops the misclassification rate between each case. Conclusively, the CNN classifier showed significantly greater accuracy than the SVM classifier, and the results implied structural characteristics that are inherent to the specific ILD patterns.

  4. Machine Learning Methods for Classifying Human Physical Activity from On-Body Accelerometers

    Science.gov (United States)

    Mannini, Andrea; Sabatini, Angelo Maria

    2010-01-01

    The use of on-body wearable sensors is widespread in several academic and industrial domains. Of great interest are their applications in ambulatory monitoring and pervasive computing systems; here, some quantitative analysis of human motion and its automatic classification are the main computational tasks to be pursued. In this paper, we discuss how human physical activity can be classified using on-body accelerometers, with a major emphasis devoted to the computational algorithms employed for this purpose. In particular, we motivate our current interest for classifiers based on Hidden Markov Models (HMMs). An example is illustrated and discussed by analysing a dataset of accelerometer time series. PMID:22205862

  5. Comparison of the Effects of Cross-validation Methods on Determining Performances of Classifiers Used in Diagnosing Congestive Heart Failure

    Directory of Open Access Journals (Sweden)

    Isler Yalcin

    2015-08-01

    Full Text Available Congestive heart failure (CHF occurs when the heart is unable to provide sufficient pump action to maintain blood flow to meet the needs of the body. Early diagnosis is important since the mortality rate of the patients with CHF is very high. There are different validation methods to measure performances of classifier algorithms designed for this purpose. In this study, k-fold and leave-one-out cross-validation methods were tested for performance measures of five distinct classifiers in the diagnosis of the patients with CHF. Each algorithm was run 100 times and the average and the standard deviation of classifier performances were recorded. As a result, it was observed that average performance was enhanced and the variability of performances was decreased when the number of data sections used in the cross-validation method was increased.

  6. Detecting and classifying method based on similarity matching of Android malware behavior with profile.

    Science.gov (United States)

    Jang, Jae-Wook; Yun, Jaesung; Mohaisen, Aziz; Woo, Jiyoung; Kim, Huy Kang

    2016-01-01

    Mass-market mobile security threats have increased recently due to the growth of mobile technologies and the popularity of mobile devices. Accordingly, techniques have been introduced for identifying, classifying, and defending against mobile threats utilizing static, dynamic, on-device, and off-device techniques. Static techniques are easy to evade, while dynamic techniques are expensive. On-device techniques are evasion, while off-device techniques need being always online. To address some of those shortcomings, we introduce Andro-profiler, a hybrid behavior based analysis and classification system for mobile malware. Andro-profiler main goals are efficiency, scalability, and accuracy. For that, Andro-profiler classifies malware by exploiting the behavior profiling extracted from the integrated system logs including system calls. Andro-profiler executes a malicious application on an emulator in order to generate the integrated system logs, and creates human-readable behavior profiles by analyzing the integrated system logs. By comparing the behavior profile of malicious application with representative behavior profile for each malware family using a weighted similarity matching technique, Andro-profiler detects and classifies it into malware families. The experiment results demonstrate that Andro-profiler is scalable, performs well in detecting and classifying malware with accuracy greater than 98 %, outperforms the existing state-of-the-art work, and is capable of identifying 0-day mobile malware samples.

  7. Applying a new unequally weighted feature fusion method to improve CAD performance of classifying breast lesions

    Science.gov (United States)

    Zargari Khuzani, Abolfazl; Danala, Gopichandh; Heidari, Morteza; Du, Yue; Mashhadi, Najmeh; Qiu, Yuchen; Zheng, Bin

    2018-02-01

    Higher recall rates are a major challenge in mammography screening. Thus, developing computer-aided diagnosis (CAD) scheme to classify between malignant and benign breast lesions can play an important role to improve efficacy of mammography screening. Objective of this study is to develop and test a unique image feature fusion framework to improve performance in classifying suspicious mass-like breast lesions depicting on mammograms. The image dataset consists of 302 suspicious masses detected on both craniocaudal and mediolateral-oblique view images. Amongst them, 151 were malignant and 151 were benign. The study consists of following 3 image processing and feature analysis steps. First, an adaptive region growing segmentation algorithm was used to automatically segment mass regions. Second, a set of 70 image features related to spatial and frequency characteristics of mass regions were initially computed. Third, a generalized linear regression model (GLM) based machine learning classifier combined with a bat optimization algorithm was used to optimally fuse the selected image features based on predefined assessment performance index. An area under ROC curve (AUC) with was used as a performance assessment index. Applying CAD scheme to the testing dataset, AUC was 0.75+/-0.04, which was significantly higher than using a single best feature (AUC=0.69+/-0.05) or the classifier with equally weighted features (AUC=0.73+/-0.05). This study demonstrated that comparing to the conventional equal-weighted approach, using an unequal-weighted feature fusion approach had potential to significantly improve accuracy in classifying between malignant and benign breast masses.

  8. Feature genes in metastatic breast cancer identified by MetaDE and SVM classifier methods.

    Science.gov (United States)

    Tuo, Youlin; An, Ning; Zhang, Ming

    2018-03-01

    The aim of the present study was to investigate the feature genes in metastatic breast cancer samples. A total of 5 expression profiles of metastatic breast cancer samples were downloaded from the Gene Expression Omnibus database, which were then analyzed using the MetaQC and MetaDE packages in R language. The feature genes between metastasis and non‑metastasis samples were screened under the threshold of PSVM) classifier training and verification. The accuracy of the SVM classifier was then evaluated using another independent dataset from The Cancer Genome Atlas database. Finally, function and pathway enrichment analyses for genes in the SVM classifier were performed. A total of 541 feature genes were identified between metastatic and non‑metastatic samples. The top 10 genes with the highest betweenness centrality values in the PPI network of feature genes were Nuclear RNA Export Factor 1, cyclin‑dependent kinase 2 (CDK2), myelocytomatosis proto‑oncogene protein (MYC), Cullin 5, SHC Adaptor Protein 1, Clathrin heavy chain, Nucleolin, WD repeat domain 1, proteasome 26S subunit non‑ATPase 2 and telomeric repeat binding factor 2. The cyclin‑dependent kinase inhibitor 1A (CDKN1A), E2F transcription factor 1 (E2F1), and MYC interacted with CDK2. The SVM classifier constructed by the top 30 feature genes was able to distinguish metastatic samples from non‑metastatic samples [correct rate, specificity, positive predictive value and negative predictive value >0.89; sensitivity >0.84; area under the receiver operating characteristic curve (AUROC) >0.96]. The verification of the SVM classifier in an independent dataset (35 metastatic samples and 143 non‑metastatic samples) revealed an accuracy of 94.38% and AUROC of 0.958. Cell cycle associated functions and pathways were the most significant terms of the 30 feature genes. A SVM classifier was constructed to assess the possibility of breast cancer metastasis, which presented high accuracy in several

  9. Spatio-Spectral Method for Estimating Classified Regions with High Confidence using MODIS Data

    International Nuclear Information System (INIS)

    Katiyal, Anuj; Rajan, Dr K S

    2014-01-01

    In studies like change analysis, the availability of very high resolution (VHR)/high resolution (HR) imagery for a particular period and region is a challenge due to the sensor revisit times and high cost of acquisition. Therefore, most studies prefer lower resolution (LR) sensor imagery with frequent revisit times, in addition to their cost and computational advantages. Further, the classification techniques provide us a global estimate of the class accuracy, which limits its utility if the accuracy is low. In this work, we focus on the sub-classification problem of LR images and estimate regions of higher confidence than the global classification accuracy within its classified region. The spectrally classified data was mined into spatially clustered regions and further refined and processed using statistical measures to arrive at local high confidence regions (LHCRs), for every class. Rabi season MODIS data of January 2006 and 2007 was used for this study and the evaluation of LHCR was done using the APLULC 2005 classified data. For Jan-2007, the global class accuracies for water bodies (WB), forested regions (FR) and Kharif crops and barren lands (KB) were 89%, 71.7% and 71.23% respectively, while the respective LHCRs had accuracies of 96.67%, 89.4% and 80.9% covering an area of 46%, 29% and 14.5% of the initially classified areas. Though areas are reduced, LHCRs with higher accuracies help in extracting more representative class regions. Identification of such regions can facilitate in improving the classification time and processing for HR images when combined with the more frequently acquired LR imagery, isolate pure vs. mixed/impure pixels and as training samples locations for HR imagery

  10. Estimation of coefficient of rolling friction by the evolvent pendulum method

    Science.gov (United States)

    Alaci, S.; Ciornei, F. C.; Ciogole, A.; Ciornei, M. C.

    2017-05-01

    The paper presents a method for finding the coefficient of rolling friction using an evolvent pendulum. The pendulum consists in a fixed cylindrical body and a mobile body presenting a plane surface in contact with a cylindrical surface. The mobile body is placed over the fixed one in an equilibrium state; after applying a small impulse, the mobile body oscillates. The motion of the body is video recorded and afterwards the movie is analyzed by frames and the decrease with time of angular amplitude of the pendulum is found. The equation of motion is established for oscillations of the mobile body. The equation of motion, differential nonlinear, is integrated by Runge-Kutta method. Imposing the same damping both to model’s solution and to theoretical model, the value of coefficient of rolling friction is obtained. The last part of the paper presents results for actual pairs of materials. The main advantage of the method is the fact that the dimensions of contact regions are small, of order a few millimeters, and thus is substantially reduced the possibility of variation of mechanical characteristic for the two surfaces.

  11. Methods of generalizing and classifying layer structures of a special form

    Energy Technology Data Exchange (ETDEWEB)

    Viktorova, N P

    1981-09-01

    An examination is made of the problem of classifying structures represented by weighted multilayer graphs of special form with connections between the vertices of each layer. The classification of structures of such a form is based on the construction of resolving sets of graphs as a result of generalization of the elements of the training sample of each class and the testing of whether an input object is isomorphic (with allowance for the weights) to the structures of the resolving set or not. 4 references.

  12. A Fuzzy Logic-Based Personalized Method to Classify Perceived Exertion in Workplaces Using a Wearable Heart Rate Sensor

    Directory of Open Access Journals (Sweden)

    Pablo Pancardo

    2018-01-01

    Full Text Available Knowing the perceived exertion of workers during their physical activities facilitates the decision-making of supervisors regarding the worker allocation in the appropriate job, actions to prevent accidents, and reassignment of tasks, among others. However, although wearable heart rate sensors represent an effective way to capture perceived exertion, ergonomic methods are generic and they do not consider the diffuse nature of the ranges that classify the efforts. Personalized monitoring is needed to enable a real and efficient classification of perceived individual efforts. In this paper, we propose a heart rate-based personalized method to assess perceived exertion; our method uses fuzzy logic as an option to manage imprecision and uncertainty in involved variables. We applied some experiments to cleaning staff and obtained results that highlight the importance of a custom method to classify perceived exertion of people doing physical work.

  13. Evolving a Method to Capture Science Stakeholder Inputs to Optimize Instrument, Payload, and Program Design

    Science.gov (United States)

    Clark, P. E.; Rilee, M. L.; Curtis, S. A.; Bailin, S.

    2012-03-01

    We are developing Frontier, a highly adaptable, stably reconfigurable, web-accessible intelligent decision engine capable of optimizing design as well as the simulating operation of complex systems in response to evolving needs and environment.

  14. Use of the parameterised finite element method to robustly and efficiently evolve the edge of a moving cell.

    Science.gov (United States)

    Neilson, Matthew P; Mackenzie, John A; Webb, Steven D; Insall, Robert H

    2010-11-01

    In this paper we present a computational tool that enables the simulation of mathematical models of cell migration and chemotaxis on an evolving cell membrane. Recent models require the numerical solution of systems of reaction-diffusion equations on the evolving cell membrane and then the solution state is used to drive the evolution of the cell edge. Previous work involved moving the cell edge using a level set method (LSM). However, the LSM is computationally very expensive, which severely limits the practical usefulness of the algorithm. To address this issue, we have employed the parameterised finite element method (PFEM) as an alternative method for evolving a cell boundary. We show that the PFEM is far more efficient and robust than the LSM. We therefore suggest that the PFEM potentially has an essential role to play in computational modelling efforts towards the understanding of many of the complex issues related to chemotaxis.

  15. A Fuzzy Logic-Based Personalized Method to Classify Perceived Exertion in Workplaces Using a Wearable Heart Rate Sensor

    OpenAIRE

    Pancardo, Pablo; Hernández-Nolasco, J. A.; Acosta-Escalante, Francisco

    2018-01-01

    Knowing the perceived exertion of workers during their physical activities facilitates the decision-making of supervisors regarding the worker allocation in the appropriate job, actions to prevent accidents, and reassignment of tasks, among others. However, although wearable heart rate sensors represent an effective way to capture perceived exertion, ergonomic methods are generic and they do not consider the diffuse nature of the ranges that classify the efforts. Personalized monitoring is ne...

  16. A Hierarchical Method for Transient Stability Prediction of Power Systems Using the Confidence of a SVM-Based Ensemble Classifier

    Directory of Open Access Journals (Sweden)

    Yanzhen Zhou

    2016-09-01

    Full Text Available Machine learning techniques have been widely used in transient stability prediction of power systems. When using the post-fault dynamic responses, it is difficult to draw a definite conclusion about how long the duration of response data used should be in order to balance the accuracy and speed. Besides, previous studies have the problem of lacking consideration for the confidence level. To solve these problems, a hierarchical method for transient stability prediction based on the confidence of ensemble classifier using multiple support vector machines (SVMs is proposed. Firstly, multiple datasets are generated by bootstrap sampling, then features are randomly picked up to compress the datasets. Secondly, the confidence indices are defined and multiple SVMs are built based on these generated datasets. By synthesizing the probabilistic outputs of multiple SVMs, the prediction results and confidence of the ensemble classifier will be obtained. Finally, different ensemble classifiers with different response times are built to construct different layers of the proposed hierarchical scheme. The simulation results show that the proposed hierarchical method can balance the accuracy and rapidity of the transient stability prediction. Moreover, the hierarchical method can reduce the misjudgments of unstable instances and cooperate with the time domain simulation to insure the security and stability of power systems.

  17. Classifying Microorganisms

    DEFF Research Database (Denmark)

    Sommerlund, Julie

    2006-01-01

    This paper describes the coexistence of two systems for classifying organisms and species: a dominant genetic system and an older naturalist system. The former classifies species and traces their evolution on the basis of genetic characteristics, while the latter employs physiological characteris......This paper describes the coexistence of two systems for classifying organisms and species: a dominant genetic system and an older naturalist system. The former classifies species and traces their evolution on the basis of genetic characteristics, while the latter employs physiological...... characteristics. The coexistence of the classification systems does not lead to a conflict between them. Rather, the systems seem to co-exist in different configurations, through which they are complementary, contradictory and inclusive in different situations-sometimes simultaneously. The systems come...

  18. Hyperspectral microscope imaging methods to classify gram-positive and gram-negative foodborne pathogenic bacteria

    Science.gov (United States)

    An acousto-optic tunable filter-based hyperspectral microscope imaging method has potential for identification of foodborne pathogenic bacteria from microcolony rapidly with a single cell level. We have successfully developed the method to acquire quality hyperspectral microscopic images from variou...

  19. Classifying Secondary Task Driving Safety Using Method of F-ANP

    Directory of Open Access Journals (Sweden)

    Lisheng Jin

    2015-02-01

    Full Text Available This study was designed to build an evaluation system for secondary task driving safety by using method of Fuzzy Analytic Network Process (F-ANP. Forty drivers completed driving on driving simulator while interacting with or without a secondary task. Measures of fixations, saccades, and vehicle running status were analyzed. According to five experts' opinions, a hierarchical model for secondary task driving safety evaluation was built. The hierarchical model was divided into three levels: goal, assessment dimension, and criteria. Seven indexes make up the level of criteria, and the assessment dimension includes two clusters: vehicle control risk and driver eye movement risk. By method of F-ANP, the priorities of the criteria and the subcriteria were determined. Furthermore, to rank the driving safety, an approach based on the principle of maximum membership degree was adopted. At last, a case study of secondary task driving safety evaluation by forty drivers using the proposed method was done. The results indicated that the application of the proposed method is practically feasible and adoptable for secondary task driving safety evaluation.

  20. Comparing methods of classifying life courses: Sequence analysis and latent class analysis

    NARCIS (Netherlands)

    Elzinga, C.H.; Liefbroer, Aart C.; Han, Sapphire

    2017-01-01

    We compare life course typology solutions generated by sequence analysis (SA) and latent class analysis (LCA). First, we construct an analytic protocol to arrive at typology solutions for both methodologies and present methods to compare the empirical quality of alternative typologies. We apply this

  1. Comparing methods of classifying life courses: sequence analysis and latent class analysis

    NARCIS (Netherlands)

    Han, Y.; Liefbroer, A.C.; Elzinga, C.

    2017-01-01

    We compare life course typology solutions generated by sequence analysis (SA) and latent class analysis (LCA). First, we construct an analytic protocol to arrive at typology solutions for both methodologies and present methods to compare the empirical quality of alternative typologies. We apply this

  2. Evaluating unsupervised methods to size and classify suspended particles using digital in-line holography

    Science.gov (United States)

    Davies, Emlyn J.; Buscombe, Daniel D.; Graham, George W.; Nimmo-Smith, W. Alex M.

    2015-01-01

    Substantial information can be gained from digital in-line holography of marine particles, eliminating depth-of-field and focusing errors associated with standard lens-based imaging methods. However, for the technique to reach its full potential in oceanographic research, fully unsupervised (automated) methods are required for focusing, segmentation, sizing and classification of particles. These computational challenges are the subject of this paper, in which we draw upon data collected using a variety of holographic systems developed at Plymouth University, UK, from a significant range of particle types, sizes and shapes. A new method for noise reduction in reconstructed planes is found to be successful in aiding particle segmentation and sizing. The performance of an automated routine for deriving particle characteristics (and subsequent size distributions) is evaluated against equivalent size metrics obtained by a trained operative measuring grain axes on screen. The unsupervised method is found to be reliable, despite some errors resulting from over-segmentation of particles. A simple unsupervised particle classification system is developed, and is capable of successfully differentiating sand grains, bubbles and diatoms from within the surf-zone. Avoiding miscounting bubbles and biological particles as sand grains enables more accurate estimates of sand concentrations, and is especially important in deployments of particle monitoring instrumentation in aerated water. Perhaps the greatest potential for further development in the computational aspects of particle holography is in the area of unsupervised particle classification. The simple method proposed here provides a foundation upon which further development could lead to reliable identification of more complex particle populations, such as those containing phytoplankton, zooplankton, flocculated cohesive sediments and oil droplets.

  3. Use of machine learning methods to classify Universities based on the income structure

    Science.gov (United States)

    Terlyga, Alexandra; Balk, Igor

    2017-10-01

    In this paper we discuss use of machine learning methods such as self organizing maps, k-means and Ward’s clustering to perform classification of universities based on their income. This classification will allow us to quantitate classification of universities as teaching, research, entrepreneur, etc. which is important tool for government, corporations and general public alike in setting expectation and selecting universities to achieve different goals.

  4. Comparison of several chemometric methods of libraries and classifiers for the analysis of expired drugs based on Raman spectra.

    Science.gov (United States)

    Gao, Qun; Liu, Yan; Li, Hao; Chen, Hui; Chai, Yifeng; Lu, Feng

    2014-06-01

    Some expired drugs are difficult to detect by conventional means. If they are repackaged and sold back into market, they will constitute a new public health challenge. For the detection of repackaged expired drugs within specification, paracetamol tablet from a manufacturer was used as a model drug in this study for comparison of Raman spectra-based library verification and classification methods. Raman spectra of different batches of paracetamol tablets were collected and a library including standard spectra of unexpired batches of tablets was established. The Raman spectrum of each sample was identified by cosine and correlation with the standard spectrum. The average HQI of the suspicious samples and the standard spectrum were calculated. The optimum threshold values were 0.997 and 0.998 respectively as a result of ROC and four evaluations, for which the accuracy was up to 97%. Three supervised classifiers, PLS-DA, SVM and k-NN, were chosen to establish two-class classification models and compared subsequently. They were used to establish a classification of expired batches and an unexpired batch, and predict the suspect samples. The average accuracy was 90.12%, 96.80% and 89.37% respectively. Different pre-processing techniques were tried to find that first derivative was optimal for methods of libraries and max-min normalization was optimal for that of classifiers. The results obtained from these studies indicated both libraries and classifier methods could detect the expired drugs effectively, and they should be used complementarily in the fast-screening. Copyright © 2014 Elsevier B.V. All rights reserved.

  5. Classifying human operator functional state based on electrophysiological and performance measures and fuzzy clustering method.

    Science.gov (United States)

    Zhang, Jian-Hua; Peng, Xiao-Di; Liu, Hua; Raisch, Jörg; Wang, Ru-Bin

    2013-12-01

    The human operator's ability to perform their tasks can fluctuate over time. Because the cognitive demands of the task can also vary it is possible that the capabilities of the operator are not sufficient to satisfy the job demands. This can lead to serious errors when the operator is overwhelmed by the task demands. Psychophysiological measures, such as heart rate and brain activity, can be used to monitor operator cognitive workload. In this paper, the most influential psychophysiological measures are extracted to characterize Operator Functional State (OFS) in automated tasks under a complex form of human-automation interaction. The fuzzy c-mean (FCM) algorithm is used and tested for its OFS classification performance. The results obtained have shown the feasibility and effectiveness of the FCM algorithm as well as the utility of the selected input features for OFS classification. Besides being able to cope with nonlinearity and fuzzy uncertainty in the psychophysiological data it can provide information about the relative importance of the input features as well as the confidence estimate of the classification results. The OFS pattern classification method developed can be incorporated into an adaptive aiding system in order to enhance the overall performance of a large class of safety-critical human-machine cooperative systems.

  6. Carbon classified?

    DEFF Research Database (Denmark)

    Lippert, Ingmar

    2012-01-01

    . Using an actor- network theory (ANT) framework, the aim is to investigate the actors who bring together the elements needed to classify their carbon emission sources and unpack the heterogeneous relations drawn on. Based on an ethnographic study of corporate agents of ecological modernisation over...... a period of 13 months, this paper provides an exploration of three cases of enacting classification. Drawing on ANT, we problematise the silencing of a range of possible modalities of consumption facts and point to the ontological ethics involved in such performances. In a context of global warming...

  7. Maintaining evolvability.

    Science.gov (United States)

    Crow, James F

    2008-12-01

    Although molecular methods, such as QTL mapping, have revealed a number of loci with large effects, it is still likely that the bulk of quantitative variability is due to multiple factors, each with small effect. Typically, these have a large additive component. Conventional wisdom argues that selection, natural or artificial, uses up additive variance and thus depletes its supply. Over time, the variance should be reduced, and at equilibrium be near zero. This is especially expected for fitness and traits highly correlated with it. Yet, populations typically have a great deal of additive variance, and do not seem to run out of genetic variability even after many generations of directional selection. Long-term selection experiments show that populations continue to retain seemingly undiminished additive variance despite large changes in the mean value. I propose that there are several reasons for this. (i) The environment is continually changing so that what was formerly most fit no longer is. (ii) There is an input of genetic variance from mutation, and sometimes from migration. (iii) As intermediate-frequency alleles increase in frequency towards one, producing less variance (as p --> 1, p(1 - p) --> 0), others that were originally near zero become more common and increase the variance. Thus, a roughly constant variance is maintained. (iv) There is always selection for fitness and for characters closely related to it. To the extent that the trait is heritable, later generations inherit a disproportionate number of genes acting additively on the trait, thus increasing genetic variance. For these reasons a selected population retains its ability to evolve. Of course, genes with large effect are also important. Conspicuous examples are the small number of loci that changed teosinte to maize, and major phylogenetic changes in the animal kingdom. The relative importance of these along with duplications, chromosome rearrangements, horizontal transmission and polyploidy

  8. A degenerate primer MOB typing (DPMT method to classify gamma-proteobacterial plasmids in clinical and environmental settings.

    Directory of Open Access Journals (Sweden)

    Andrés Alvarado

    Full Text Available Transmissible plasmids are responsible for the spread of genetic determinants, such as antibiotic resistance or virulence traits, causing a large ecological and epidemiological impact. Transmissible plasmids, either conjugative or mobilizable, have in common the presence of a relaxase gene. Relaxases were previously classified in six protein families according to their phylogeny. Degenerate primers hybridizing to coding sequences of conserved amino acid motifs were designed to amplify related relaxase genes from γ-Proteobacterial plasmids. Specificity and sensitivity of a selected set of 19 primer pairs were first tested using a collection of 33 reference relaxases, representing the diversity of γ-Proteobacterial plasmids. The validated set was then applied to the analysis of two plasmid collections obtained from clinical isolates. The relaxase screening method, which we call "Degenerate Primer MOB Typing" or DPMT, detected not only most known Inc/Rep groups, but also a plethora of plasmids not previously assigned to any Inc group or Rep-type.

  9. Minimal methylation classifier (MIMIC): A novel method for derivation and rapid diagnostic detection of disease-associated DNA methylation signatures.

    Science.gov (United States)

    Schwalbe, E C; Hicks, D; Rafiee, G; Bashton, M; Gohlke, H; Enshaei, A; Potluri, S; Matthiesen, J; Mather, M; Taleongpong, P; Chaston, R; Silmon, A; Curtis, A; Lindsey, J C; Crosier, S; Smith, A J; Goschzik, T; Doz, F; Rutkowski, S; Lannering, B; Pietsch, T; Bailey, S; Williamson, D; Clifford, S C

    2017-10-18

    Rapid and reliable detection of disease-associated DNA methylation patterns has major potential to advance molecular diagnostics and underpin research investigations. We describe the development and validation of minimal methylation classifier (MIMIC), combining CpG signature design from genome-wide datasets, multiplex-PCR and detection by single-base extension and MALDI-TOF mass spectrometry, in a novel method to assess multi-locus DNA methylation profiles within routine clinically-applicable assays. We illustrate the application of MIMIC to successfully identify the methylation-dependent diagnostic molecular subgroups of medulloblastoma (the most common malignant childhood brain tumour), using scant/low-quality samples remaining from the most recently completed pan-European medulloblastoma clinical trial, refractory to analysis by conventional genome-wide DNA methylation analysis. Using this approach, we identify critical DNA methylation patterns from previously inaccessible cohorts, and reveal novel survival differences between the medulloblastoma disease subgroups with significant potential for clinical exploitation.

  10. Clustering based gene expression feature selection method: A computational approach to enrich the classifier efficiency of differentially expressed genes

    KAUST Repository

    Abusamra, Heba

    2016-07-20

    The native nature of high dimension low sample size of gene expression data make the classification task more challenging. Therefore, feature (gene) selection become an apparent need. Selecting a meaningful and relevant genes for classifier not only decrease the computational time and cost, but also improve the classification performance. Among different approaches of feature selection methods, however most of them suffer from several problems such as lack of robustness, validation issues etc. Here, we present a new feature selection technique that takes advantage of clustering both samples and genes. Materials and methods We used leukemia gene expression dataset [1]. The effectiveness of the selected features were evaluated by four different classification methods; support vector machines, k-nearest neighbor, random forest, and linear discriminate analysis. The method evaluate the importance and relevance of each gene cluster by summing the expression level for each gene belongs to this cluster. The gene cluster consider important, if it satisfies conditions depend on thresholds and percentage otherwise eliminated. Results Initial analysis identified 7120 differentially expressed genes of leukemia (Fig. 15a), after applying our feature selection methodology we end up with specific 1117 genes discriminating two classes of leukemia (Fig. 15b). Further applying the same method with more stringent higher positive and lower negative threshold condition, number reduced to 58 genes have be tested to evaluate the effectiveness of the method (Fig. 15c). The results of the four classification methods are summarized in Table 11. Conclusions The feature selection method gave good results with minimum classification error. Our heat-map result shows distinct pattern of refines genes discriminating between two classes of leukemia.

  11. Rapid resolution of chronic shoulder pain classified as derangement using the McKenzie method: a case series

    Science.gov (United States)

    Aytona, Maria Corazon; Dudley, Karlene

    2013-01-01

    The McKenzie method, also known as Mechanical Diagnosis and Therapy (MDT), is primarily recognized as an evaluation and treatment method for the spine. However, McKenzie suggested that this method could also be applied to the extremities. Derangement is an MDT classification defined as an anatomical disturbance in the normal resting position of the joint, and McKenzie proposed that repeated movements could be applied to reduce internal joint displacement and rapidly reduce derangement symptoms. However, the current literature on MDT application to shoulder disorders is limited. Here, we present a case series involving four patients with chronic shoulder pain from a duration of 2–18 months classified as derangement and treated using MDT principles. Each patient underwent mechanical assessment and was treated with repeated movements based on their directional preference. All patients demonstrated rapid and clinically significant improvement in baseline measures and the disabilities of the arm, shoulder, and hand (QuickDASH) scores from an average of 38% at initial evaluation to 5% at discharge within 3–5 visits. Our findings suggest that MDT may be an effective treatment approach for shoulder pain. PMID:24421633

  12. A scalable and accurate method for classifying protein-ligand binding geometries using a MapReduce approach.

    Science.gov (United States)

    Estrada, T; Zhang, B; Cicotti, P; Armen, R S; Taufer, M

    2012-07-01

    We present a scalable and accurate method for classifying protein-ligand binding geometries in molecular docking. Our method is a three-step process: the first step encodes the geometry of a three-dimensional (3D) ligand conformation into a single 3D point in the space; the second step builds an octree by assigning an octant identifier to every single point in the space under consideration; and the third step performs an octree-based clustering on the reduced conformation space and identifies the most dense octant. We adapt our method for MapReduce and implement it in Hadoop. The load-balancing, fault-tolerance, and scalability in MapReduce allow screening of very large conformation spaces not approachable with traditional clustering methods. We analyze results for docking trials for 23 protein-ligand complexes for HIV protease, 21 protein-ligand complexes for Trypsin, and 12 protein-ligand complexes for P38alpha kinase. We also analyze cross docking trials for 24 ligands, each docking into 24 protein conformations of the HIV protease, and receptor ensemble docking trials for 24 ligands, each docking in a pool of HIV protease receptors. Our method demonstrates significant improvement over energy-only scoring for the accurate identification of native ligand geometries in all these docking assessments. The advantages of our clustering approach make it attractive for complex applications in real-world drug design efforts. We demonstrate that our method is particularly useful for clustering docking results using a minimal ensemble of representative protein conformational states (receptor ensemble docking), which is now a common strategy to address protein flexibility in molecular docking. Copyright © 2012 Elsevier Ltd. All rights reserved.

  13. Evaluation of a chemical risk assessment method of South Korea for chemicals classified as carcinogenic, mutagenic or reprotoxic (CMR).

    Science.gov (United States)

    Kim, Min-Uk; Byeon, Sang-Hoon

    2017-12-12

    Chemicals were used in various fields by the development of industry and science and technology. The Chemical Hazard Risk Management (CHARM) was developed to assess the risk of chemicals in South Korea. In this study, we were to evaluate the CHARM model developed for the effective management of workplace chemicals. We used 59 carcinogenic, mutagenic or reprotoxic (CMR) materials, which are both the work environment measurement result and the usage information among the manufacturer data. The CHARM model determines the risk to human health using the exposure level (based on working environment measurements or a combination of the quantity used and chemical physical properties (e.g., fugacity and volatility)), hazard (using occupational exposure limit (OEL) or Risk phrases (R-phrases)/Hazard statements (H-statements) from the Material Safety Data Sheet (MSDS)). The risk level was lower when using the results of the work environment measurement than when applying the chemical quantity and physical properties in the exposure level evaluation method. It was evaluated as grade 4 for the CMR material in the hazard class determination. The risk assessment method by R-phrases was evaluated more conservatively than the risk assessment method by OEL. And the risk assessment method by H-statements was evaluated more conservatively than the risk assessment method by R-phrases. The CHARM model was gradually conservatively assessed as it proceeded in the next step without quantitative information for individual workplaces. The CHARM is expected to help identify the risk if the hazards and exposure levels of chemicals were identified in individual workplaces. For CMR substances, although CHARM is highly evaluated for hazards, the risk is assessed to be low if exposure levels are assessed low. When evaluating the risk of highly hazardous chemicals such as CMR substances, we believe the model should be adapted to be more conservative and classify these as higher risk. This work is

  14. A geometric method for computing ocular kinematics and classifying gaze events using monocular remote eye tracking in a robotic environment.

    Science.gov (United States)

    Singh, Tarkeshwar; Perry, Christopher M; Herter, Troy M

    2016-01-26

    Robotic and virtual-reality systems offer tremendous potential for improving assessment and rehabilitation of neurological disorders affecting the upper extremity. A key feature of these systems is that visual stimuli are often presented within the same workspace as the hands (i.e., peripersonal space). Integrating video-based remote eye tracking with robotic and virtual-reality systems can provide an additional tool for investigating how cognitive processes influence visuomotor learning and rehabilitation of the upper extremity. However, remote eye tracking systems typically compute ocular kinematics by assuming eye movements are made in a plane with constant depth (e.g. frontal plane). When visual stimuli are presented at variable depths (e.g. transverse plane), eye movements have a vergence component that may influence reliable detection of gaze events (fixations, smooth pursuits and saccades). To our knowledge, there are no available methods to classify gaze events in the transverse plane for monocular remote eye tracking systems. Here we present a geometrical method to compute ocular kinematics from a monocular remote eye tracking system when visual stimuli are presented in the transverse plane. We then use the obtained kinematics to compute velocity-based thresholds that allow us to accurately identify onsets and offsets of fixations, saccades and smooth pursuits. Finally, we validate our algorithm by comparing the gaze events computed by the algorithm with those obtained from the eye-tracking software and manual digitization. Within the transverse plane, our algorithm reliably differentiates saccades from fixations (static visual stimuli) and smooth pursuits from saccades and fixations when visual stimuli are dynamic. The proposed methods provide advancements for examining eye movements in robotic and virtual-reality systems. Our methods can also be used with other video-based or tablet-based systems in which eye movements are performed in a peripersonal

  15. Enhanced least squares Monte Carlo method for real-time decision optimizations for evolving natural hazards

    DEFF Research Database (Denmark)

    Anders, Annett; Nishijima, Kazuyoshi

    The present paper aims at enhancing a solution approach proposed by Anders & Nishijima (2011) to real-time decision problems in civil engineering. The approach takes basis in the Least Squares Monte Carlo method (LSM) originally proposed by Longstaff & Schwartz (2001) for computing American option...... prices. In Anders & Nishijima (2011) the LSM is adapted for a real-time operational decision problem; however it is found that further improvement is required in regard to the computational efficiency, in order to facilitate it for practice. This is the focus in the present paper. The idea behind...... the improvement of the computational efficiency is to “best utilize” the least squares method; i.e. least squares method is applied for estimating the expected utility for terminal decisions, conditional on realizations of underlying random phenomena at respective times in a parametric way. The implementation...

  16. Translating Basic Behavioral and Social Science Research to Clinical Application: The EVOLVE Mixed Methods Approach

    Science.gov (United States)

    Peterson, Janey C.; Czajkowski, Susan; Charlson, Mary E.; Link, Alissa R.; Wells, Martin T.; Isen, Alice M.; Mancuso, Carol A.; Allegrante, John P.; Boutin-Foster, Carla; Ogedegbe, Gbenga; Jobe, Jared B.

    2013-01-01

    Objective: To describe a mixed-methods approach to develop and test a basic behavioral science-informed intervention to motivate behavior change in 3 high-risk clinical populations. Our theoretically derived intervention comprised a combination of positive affect and self-affirmation (PA/SA), which we applied to 3 clinical chronic disease…

  17. Order Patterns Networks (orpan – a method toestimate time-evolving functional connectivity frommultivariate time series

    Directory of Open Access Journals (Sweden)

    Stefan eSchinkel

    2012-11-01

    Full Text Available Complex networks provide an excellent framework for studying the functionof the human brain activity. Yet estimating functional networks from mea-sured signals is not trivial, especially if the data is non-stationary and noisyas it is often the case with physiological recordings. In this article we proposea method that uses the local rank structure of the data to define functionallinks in terms of identical rank structures. The method yields temporal se-quences of networks which permits to trace the evolution of the functionalconnectivity during the time course of the observation. We demonstrate thepotentials of this approach with model data as well as with experimentaldata from an electrophysiological study on language processing.

  18. Systems, methods and apparatus for developing and maintaining evolving systems with software product lines

    Science.gov (United States)

    Hinchey, Michael G. (Inventor); Rash, James L. (Inventor); Pena, Joaquin (Inventor)

    2011-01-01

    Systems, methods and apparatus are provided through which an evolutionary system is managed and viewed as a software product line. In some embodiments, the core architecture is a relatively unchanging part of the system, and each version of the system is viewed as a product from the product line. Each software product is generated from the core architecture with some agent-based additions. The result may be a multi-agent system software product line.

  19. Single classifier, OvO, OvA and RCC multiclass classification method in handheld based smartphone gait identification

    Science.gov (United States)

    Raziff, Abdul Rafiez Abdul; Sulaiman, Md Nasir; Mustapha, Norwati; Perumal, Thinagaran

    2017-10-01

    Gait recognition is widely used in many applications. In the application of the gait identification especially in people, the number of classes (people) is many which may comprise to more than 20. Due to the large amount of classes, the usage of single classification mapping (direct classification) may not be suitable as most of the existing algorithms are mostly designed for the binary classification. Furthermore, having many classes in a dataset may result in the possibility of having a high degree of overlapped class boundary. This paper discusses the application of multiclass classifier mappings such as one-vs-all (OvA), one-vs-one (OvO) and random correction code (RCC) on handheld based smartphone gait signal for person identification. The results is then compared with a single J48 decision tree for benchmark. From the result, it can be said that using multiclass classification mapping method thus partially improved the overall accuracy especially on OvO and RCC with width factor more than 4. For OvA, the accuracy result is worse than a single J48 due to a high number of classes.

  20. Recycling inflow method for simulations of spatially evolving turbulent boundary layers over rough surfaces

    Science.gov (United States)

    Yang, Xiang I. A.; Meneveau, Charles

    2016-01-01

    The technique by Lund et al. to generate turbulent inflow for simulations of developing boundary layers over smooth flat plates is extended to the case of surfaces with roughness elements. In the Lund et al. method, turbulent velocities on a sampling plane are rescaled and recycled back to the inlet as inflow boundary condition. To rescale mean and fluctuating velocities, appropriate length scales need be identified and for smooth surfaces, the viscous scale lν = ν/uτ (where ν is the kinematic viscosity and uτ is the friction velocity) is employed for the inner layer. Different from smooth surfaces, in rough wall boundary layers the length scale of the inner layer, i.e. the roughness sub-layer scale ld, must be determined by the geometric details of the surface roughness elements and the flow around them. In the proposed approach, it is determined by diagnosing dispersive stresses that quantify the spatial inhomogeneity caused by the roughness elements in the flow. The scale ld is used for rescaling in the inner layer, and the boundary layer thickness δ is used in the outer region. Both parts are then combined for recycling using a blending function. Unlike the blending function proposed by Lund et al. which transitions from the inner layer to the outer layer at approximately 0.2δ, here the location of blending is shifted upwards to enable simulations of very rough surfaces in which the roughness length may exceed the height of 0.2δ assumed in the traditional method. The extended rescaling-recycling method is tested in large eddy simulation of flow over surfaces with various types of roughness element shapes.

  1. An efficient numerical method for evolving microstructures with strong elastic inhomogeneity

    International Nuclear Information System (INIS)

    Jeong, Darae; Lee, Seunggyu; Kim, Junseok

    2015-01-01

    In this paper, we consider a fast and efficient numerical method for the modified Cahn–Hilliard equation with a logarithmic free energy for microstructure evolution. Even though it is physically more appropriate to use a logarithmic free energy, a quartic polynomial approximation is typically used for the logarithmic function due to a logarithmic singularity. In order to overcome the singularity problem, we regularize the logarithmic function and then apply an unconditionally stable scheme to the Cahn–Hilliard part in the model. We present computational results highlighting the different dynamic aspects from two different bulk free energy forms. We also demonstrate the robustness of the regularization of the logarithmic free energy, which implies the time-step restriction is based on accuracy and not stability. (paper)

  2. When everything is not everywhere but species evolve: an alternative method to model adaptive properties of marine ecosystems.

    Science.gov (United States)

    Sauterey, Boris; Ward, Ben A; Follows, Michael J; Bowler, Chris; Claessen, David

    2015-01-01

    The functional and taxonomic biogeography of marine microbial systems reflects the current state of an evolving system. Current models of marine microbial systems and biogeochemical cycles do not reflect this fundamental organizing principle. Here, we investigate the evolutionary adaptive potential of marine microbial systems under environmental change and introduce explicit Darwinian adaptation into an ocean modelling framework, simulating evolving phytoplankton communities in space and time. To this end, we adopt tools from adaptive dynamics theory, evaluating the fitness of invading mutants over annual timescales, replacing the resident if a fitter mutant arises. Using the evolutionary framework, we examine how community assembly, specifically the emergence of phytoplankton cell size diversity, reflects the combined effects of bottom-up and top-down controls. When compared with a species-selection approach, based on the paradigm that "Everything is everywhere, but the environment selects", we show that (i) the selected optimal trait values are similar; (ii) the patterns emerging from the adaptive model are more robust, but (iii) the two methods lead to different predictions in terms of emergent diversity. We demonstrate that explicitly evolutionary approaches to modelling marine microbial populations and functionality are feasible and practical in time-varying, space-resolving settings and provide a new tool for exploring evolutionary interactions on a range of timescales in the ocean.

  3. Health Impact Index. Development and Validation of a Method for Classifying Comorbid Disease Measured against Self-Reported Health.

    Directory of Open Access Journals (Sweden)

    Geir Fagerjord Lorem

    Full Text Available The objective of this study was to develop a method of classifying comorbid conditions that accounts for both the severity and joint effects of the diseases. The Tromsø Study is a cohort study with a longitudinal design utilizing a survey approach with physical examinations in the Tromsø municipality from 1974 to 2008, where in total 40051 subjects participated. We used Tromsø 4 as reference population and the Norwegian Institute of Public Health (FHI panel as validation population. Ordinal regression was used to assess the effect of comorbid disease on Self-Reported Health (SRH. The model is controlled for interaction between diseases, mental health, age, and gender. The health impact index estimated levels of SRH. The comparison of predicted and observed SRH showed no significant differences. Spearman's correlation showed that increasing levels of comorbidity were related to lower levels of SRH (RS = -0.36, p <.001. The Charlson Comorbidity Index(CCI was also associated with SRH (r = -.25, p <.001. When focusing on only individuals with a comorbid disease, the relation between SRH and the Health Impact Index (HII was strengthened (r = -.42, p <.001, while the association between SRH and CCI was attenuated (r = -.14, p <.001. CCI was designed to control for comorbid conditions when survival/mortality is the outcome of interest but is inaccurate when the outcome is SRH. We conclude that HII should be used when SRH is not available, and well-being or quality of survival/life is the outcome of interest.

  4. Novel method to classify hemodynamic response obtained using multi-channel fNIRS measurements into two groups: Exploring the combinations of channels

    Directory of Open Access Journals (Sweden)

    Hiroko eIchikawa

    2014-07-01

    Full Text Available Near-infrared spectroscopy (NIRS in psychiatric studies has widely demonstrated that cerebral hemodynamics differs among psychiatric patients. Recently we found that children with attention attention-deficit / hyperactivity disorder (ADHD and children with autism spectrum disorders (ASD showed different hemodynamic responses to their own mother’s face. Based on this finding, we may be able to classify their hemodynamic data into two those groups and predict which diagnostic group an unknown participant belongs to. In the present study, we proposed a novel statistical method for classifying the hemodynamic data of these two groups. By applying a support vector machine (SVM, we searched the combination of measurement channels at which the hemodynamic response differed between the two groups; ADHD and ASD. The SVM found the optimal subset of channels in each data set and successfully classified the ADHD data from the ASD data. For the 24-dimentional hemodynamic data, two optimal subsets classified the hemodynamic data with 84% classification accuracy while the subset contains all 24 channels classified with 62% classification accuracy. These results indicate the potential application of our novel method for classifying the hemodynamic data into two groups and revealing the combinations of channels that efficiently differentiate the two groups.

  5. Supervision and prognosis architecture based on dynamical classification method for the predictive maintenance of dynamical evolving systems

    International Nuclear Information System (INIS)

    Traore, M.; Chammas, A.; Duviella, E.

    2015-01-01

    In this paper, we are concerned by the improvement of the safety, availability and reliability of dynamical systems’ components subjected to slow degradations (slow drifts). We propose an architecture for efficient Predictive Maintenance (PM) according to the real time estimate of the future state of the components. The architecture is built on supervision and prognosis tools. The prognosis method is based on an appropriated supervision technique that consists in drift tracking of the dynamical systems using AUDyC (AUto-adaptive and Dynamical Clustering), that is an auto-adaptive dynamical classifier. Thus, due to the complexity and the dynamical of the considered systems, the Failure Mode Effect and Criticity Analysis (FMECA) is used to identify the key components of the systems. A component is defined as an element of the system that can be impacted by only one failure. A failure of a key component causes a long downtime of the system. From the FMECA, a Fault Tree Analysis (FTA) of the system are built to determine the propagation laws of a failure on the system by using a deductive method. The proposed architecture is implemented for the PM of a thermoregulator. The application on this real system highlights the interests and the performances of the proposed architecture

  6. Landscape object-based analysis of wetland plant functional types: the effects of spatial scale, vegetation classes and classifier methods

    Science.gov (United States)

    Dronova, I.; Gong, P.; Wang, L.; Clinton, N.; Fu, W.; Qi, S.

    2011-12-01

    Remote sensing-based vegetation classifications representing plant function such as photosynthesis and productivity are challenging in wetlands with complex cover and difficult field access. Recent advances in object-based image analysis (OBIA) and machine-learning algorithms offer new classification tools; however, few comparisons of different algorithms and spatial scales have been discussed to date. We applied OBIA to delineate wetland plant functional types (PFTs) for Poyang Lake, the largest freshwater lake in China and Ramsar wetland conservation site, from 30-m Landsat TM scene at the peak of spring growing season. We targeted major PFTs (C3 grasses, C3 forbs and different types of C4 grasses and aquatic vegetation) that are both key players in system's biogeochemical cycles and critical providers of waterbird habitat. Classification results were compared among: a) several object segmentation scales (with average object sizes 900-9000 m2); b) several families of statistical classifiers (including Bayesian, Logistic, Neural Network, Decision Trees and Support Vector Machines) and c) two hierarchical levels of vegetation classification, a generalized 3-class set and more detailed 6-class set. We found that classification benefited from object-based approach which allowed including object shape, texture and context descriptors in classification. While a number of classifiers achieved high accuracy at the finest pixel-equivalent segmentation scale, the highest accuracies and best agreement among algorithms occurred at coarser object scales. No single classifier was consistently superior across all scales, although selected algorithms of Neural Network, Logistic and K-Nearest Neighbors families frequently provided the best discrimination of classes at different scales. The choice of vegetation categories also affected classification accuracy. The 6-class set allowed for higher individual class accuracies but lower overall accuracies than the 3-class set because

  7. Evolving Evidence for the Value of Neuroimaging Methods and Biological Markers in Subjects Categorized with Subjective Cognitive Decline.

    Science.gov (United States)

    Lista, Simone; Molinuevo, Jose L; Cavedo, Enrica; Rami, Lorena; Amouyel, Philippe; Teipel, Stefan J; Garaci, Francesco; Toschi, Nicola; Habert, Marie-Odile; Blennow, Kaj; Zetterberg, Henrik; O'Bryant, Sid E; Johnson, Leigh; Galluzzi, Samantha; Bokde, Arun L W; Broich, Karl; Herholz, Karl; Bakardjian, Hovagim; Dubois, Bruno; Jessen, Frank; Carrillo, Maria C; Aisen, Paul S; Hampel, Harald

    2015-09-24

    There is evolving evidence that individuals categorized with subjective cognitive decline (SCD) are potentially at higher risk for developing objective and progressive cognitive impairment compared to cognitively healthy individuals without apparent subjective complaints. Interestingly, SCD, during advancing preclinical Alzheimer's disease (AD), may denote very early, subtle cognitive decline that cannot be identified using established standardized tests of cognitive performance. The substantial heterogeneity of existing SCD-related research data has led the Subjective Cognitive Decline Initiative (SCD-I) to accomplish an international consensus on the definition of a conceptual research framework on SCD in preclinical AD. In the area of biological markers, the cerebrospinal fluid signature of AD has been reported to be more prevalent in subjects with SCD compared to healthy controls; moreover, there is a pronounced atrophy, as demonstrated by magnetic resonance imaging, and an increased hypometabolism, as revealed by positron emission tomography, in characteristic brain regions affected by AD. In addition, SCD individuals carrying an apolipoprotein ɛ4 allele are more likely to display AD-phenotypic alterations. The urgent requirement to detect and diagnose AD as early as possible has led to the critical examination of the diagnostic power of biological markers, neurophysiology, and neuroimaging methods for AD-related risk and clinical progression in individuals defined with SCD. Observational studies on the predictive value of SCD for developing AD may potentially be of practical value, and an evidence-based, validated, qualified, and fully operationalized concept may inform clinical diagnostic practice and guide earlier designs in future therapy trials.

  8. New method of classifying human errors at nuclear power plants and the analysis results of applying this method to maintenance errors at domestic plants

    International Nuclear Information System (INIS)

    Takagawa, Kenichi; Miyazaki, Takamasa; Gofuku, Akio; Iida, Hiroyasu

    2007-01-01

    Since many of the adverse events that have occurred in nuclear power plants in Japan and abroad have been related to maintenance or operation, it is necessary to plan preventive measures based on detailed analyses of human errors made by maintenance workers or operators. Therefore, before planning preventive measures, we developed a new method of analyzing human errors. Since each human error is an unsafe action caused by some misjudgement made by a person, we decided to classify them into six categories according to the stage in the judgment process in which the error was made. By further classifying each error into either an omission-type or commission-type, we produced 12 categories of errors. Then, we divided them into the two categories of basic error tendencies and individual error tendencies, and categorized background factors into four categories: imperfect planning; imperfect facilities or tools; imperfect environment; and imperfect instructions or communication. We thus defined the factors in each category to make it easy to identify factors that caused the error. Then using this method, we studied the characteristics of human errors that involved maintenance workers and planners since many maintenance errors have occurred. Among the human errors made by workers (worker errors) during the implementation stage, the following three types were prevalent with approximately 80%: commission-type 'projection errors', omission-type comprehension errors' and commission type 'action errors'. The most common among the individual factors of worker errors was 'repetition or habit' (schema), based on the assumption of a typical situation, and the half number of the 'repetition or habit' cases (schema) were not influenced by any background factors. The most common background factor that contributed to the individual factor was 'imperfect work environment', followed by 'insufficient knowledge'. Approximately 80% of the individual factors were 'repetition or habit' or

  9. LCC: Light Curves Classifier

    Science.gov (United States)

    Vo, Martin

    2017-08-01

    Light Curves Classifier uses data mining and machine learning to obtain and classify desired objects. This task can be accomplished by attributes of light curves or any time series, including shapes, histograms, or variograms, or by other available information about the inspected objects, such as color indices, temperatures, and abundances. After specifying features which describe the objects to be searched, the software trains on a given training sample, and can then be used for unsupervised clustering for visualizing the natural separation of the sample. The package can be also used for automatic tuning parameters of used methods (for example, number of hidden neurons or binning ratio). Trained classifiers can be used for filtering outputs from astronomical databases or data stored locally. The Light Curve Classifier can also be used for simple downloading of light curves and all available information of queried stars. It natively can connect to OgleII, OgleIII, ASAS, CoRoT, Kepler, Catalina and MACHO, and new connectors or descriptors can be implemented. In addition to direct usage of the package and command line UI, the program can be used through a web interface. Users can create jobs for ”training” methods on given objects, querying databases and filtering outputs by trained filters. Preimplemented descriptors, classifier and connectors can be picked by simple clicks and their parameters can be tuned by giving ranges of these values. All combinations are then calculated and the best one is used for creating the filter. Natural separation of the data can be visualized by unsupervised clustering.

  10. Development of a simple method for classifying the degree of importance of components in nuclear power plants using probabilistic analysis technique

    International Nuclear Information System (INIS)

    Shimada, Yoshio; Miyazaki, Takamasa

    2006-01-01

    In order to analyze large amounts of trouble information of overseas nuclear power plants, it is necessary to select information that is significant in terms of both safety and reliability. In this research, a method of efficiently and simply classifying degrees of importance of components in terms of safety and reliability while paying attention to root-cause components appearing in the information was developed. Regarding safety, the reactor core damage frequency (CDF), which is used in the probabilistic analysis of a reactor, was used. Regarding reliability, the automatic plant trip probability (APTP), which is used in the probabilistic analysis of automatic reactor trips, was used. These two aspects were reflected in the development of criteria for classifying degrees of importance of components. By applying these criteria, a method of quantitatively and simply judging the significance of trouble information of overseas nuclear power plants was developed. (author)

  11. Urban Image Classification: Per-Pixel Classifiers, Sub-Pixel Analysis, Object-Based Image Analysis, and Geospatial Methods. 10; Chapter

    Science.gov (United States)

    Myint, Soe W.; Mesev, Victor; Quattrochi, Dale; Wentz, Elizabeth A.

    2013-01-01

    Remote sensing methods used to generate base maps to analyze the urban environment rely predominantly on digital sensor data from space-borne platforms. This is due in part from new sources of high spatial resolution data covering the globe, a variety of multispectral and multitemporal sources, sophisticated statistical and geospatial methods, and compatibility with GIS data sources and methods. The goal of this chapter is to review the four groups of classification methods for digital sensor data from space-borne platforms; per-pixel, sub-pixel, object-based (spatial-based), and geospatial methods. Per-pixel methods are widely used methods that classify pixels into distinct categories based solely on the spectral and ancillary information within that pixel. They are used for simple calculations of environmental indices (e.g., NDVI) to sophisticated expert systems to assign urban land covers. Researchers recognize however, that even with the smallest pixel size the spectral information within a pixel is really a combination of multiple urban surfaces. Sub-pixel classification methods therefore aim to statistically quantify the mixture of surfaces to improve overall classification accuracy. While within pixel variations exist, there is also significant evidence that groups of nearby pixels have similar spectral information and therefore belong to the same classification category. Object-oriented methods have emerged that group pixels prior to classification based on spectral similarity and spatial proximity. Classification accuracy using object-based methods show significant success and promise for numerous urban 3 applications. Like the object-oriented methods that recognize the importance of spatial proximity, geospatial methods for urban mapping also utilize neighboring pixels in the classification process. The primary difference though is that geostatistical methods (e.g., spatial autocorrelation methods) are utilized during both the pre- and post

  12. A method for recognition of coexisting environmental sound sources based on the Fisher’s linear discriminant classifier

    DEFF Research Database (Denmark)

    Creixell Mediante, Ester; Haddad, Karim; Song, Wookeun

    2015-01-01

    A method for sound recognition of coexisting environmental noise sources by applying pattern recognition techniques is developed. The investigated technique could benefit several areas of application, such as noise impact assessment, acoustic pollution mitigation and soundscape characterization...

  13. Clustering based gene expression feature selection method: A computational approach to enrich the classifier efficiency of differentially expressed genes

    KAUST Repository

    Abusamra, Heba; Bajic, Vladimir B.

    2016-01-01

    decrease the computational time and cost, but also improve the classification performance. Among different approaches of feature selection methods, however most of them suffer from several problems such as lack of robustness, validation issues etc. Here, we

  14. Methods development for measuring and classifying flammability/combustibility of refrigerants. Interim report, task 2 - test plan

    Energy Technology Data Exchange (ETDEWEB)

    Heinonen, E.W.; Tapscott, R.E. [Univ. of New Mexico, Albuquerque, NM (United States)

    1994-07-01

    Regulations on alternative refrigerants and concerns for the environment are forcing the refrigeration industry to consider the use of potentially flammable fluids to replace CFC fluids currently in use. The objectives of this program are to establish the conditions under which refrigerants and refrigerant blends exhibit flammability and to develop appropriate methods to measure flammability.

  15. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images.

    Science.gov (United States)

    Wang, Hongkai; Zhou, Zongwei; Li, Yingci; Chen, Zhonghua; Lu, Peiou; Wang, Wenzhi; Liu, Wanyu; Yu, Lijuan

    2017-12-01

    This study aimed to compare one state-of-the-art deep learning method and four classical machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer (NSCLC) from 18 F-FDG PET/CT images. Another objective was to compare the discriminative power of the recently popular PET/CT texture features with the widely used diagnostic features such as tumor size, CT value, SUV, image contrast, and intensity standard deviation. The four classical machine learning methods included random forests, support vector machines, adaptive boosting, and artificial neural network. The deep learning method was the convolutional neural networks (CNN). The five methods were evaluated using 1397 lymph nodes collected from PET/CT images of 168 patients, with corresponding pathology analysis results as gold standard. The comparison was conducted using 10 times 10-fold cross-validation based on the criterion of sensitivity, specificity, accuracy (ACC), and area under the ROC curve (AUC). For each classical method, different input features were compared to select the optimal feature set. Based on the optimal feature set, the classical methods were compared with CNN, as well as with human doctors from our institute. For the classical methods, the diagnostic features resulted in 81~85% ACC and 0.87~0.92 AUC, which were significantly higher than the results of texture features. CNN's sensitivity, specificity, ACC, and AUC were 84, 88, 86, and 0.91, respectively. There was no significant difference between the results of CNN and the best classical method. The sensitivity, specificity, and ACC of human doctors were 73, 90, and 82, respectively. All the five machine learning methods had higher sensitivities but lower specificities than human doctors. The present study shows that the performance of CNN is not significantly different from the best classical methods and human doctors for classifying mediastinal lymph node metastasis of NSCLC from PET/CT images

  16. Comparison of objective methods to classify the pattern of respiratory sinus arrhythmia during mechanical ventilation and paced spontaneous breathing

    International Nuclear Information System (INIS)

    Carvalho, N C; Beda, A; Granja-Filho, P; Jandre, F C; Giannella-Neto, A; De Abreu, M G; Spieth, P M

    2009-01-01

    Respiratory sinus arrhythmia (RSA) is a fluctuation of heart period that occurs during a respiratory cycle. It has been suggested that inspiratory heart period acceleration and expiratory deceleration during spontaneous ventilation (henceforth named positive RSA) improve the efficiency of gas exchange compared to the absence or the inversion of such a pattern (negative RSA). During mechanical ventilation (MV), for which maximizing the efficiency of gas exchange is of critical importance, the pattern of RSA is still the object of debate. In order to gain a better insight into this matter, we compared five different methods of RSA classification using the data of five mechanically ventilated piglets. The comparison was repeated using the data of 15 volunteers undergoing a protocol of paced spontaneous breathing, which is expected to result in a positive RSA pattern. The results showed that the agreement between the employed methods is limited, suggesting that the lack of a consensus about the RSA pattern during MV is, at least in part, of methodological origin. However, independently of the method used, the pattern of RSA within the respiratory cycle was not consistent among the subjects and conditions of MV considered. Also, the outcomes showed that even during paced spontaneous breathing a negative RSA pattern might be present, when a low respiratory frequency is imposed

  17. Method to classify the safety class of Structure, System and Components in a Defueled Condition of Nuclear Power Plant

    Energy Technology Data Exchange (ETDEWEB)

    Kim, Dong-Hak; Jeon, Dang-Hee [KHNP CRI, Daejeon (Korea, Republic of)

    2016-10-15

    During pre-decommissioning phase, licensing and engineering work need to change the design basis of the plant such as safety analysis report, downgrade of systems, technical specifications and program and procedures to change of NPP condition from in an operation condition to in a defueled condition. The many systems to need to operate in an operational condition will not be operated during in a defueled condition and the function of systems will be changed from in an operation condition to in a defueled condition. So a downgrade of systems may be needed and reclassifying the safety class of structure, system and component (SSC) may be conducted. By the reclassification of SSC, activity related with quality assurance and maintenance of SSC is affected. In this paper, the method to reclassify SSC in a defueled condition is studied. The many systems to need to operate in an operational condition will not be operated during in a defueled condition and the function of systems will be changed from in an operation condition to in a defueled condition. The operation of NPP during a defueled condition need to conduct licensing and engineering work need to change the design basis of the plant optimize by downgrading systems and reclassifying the safety class of SSC. In this paper, the method to reclassify safety class for a defueled condition is studied.

  18. Fractal dimension to classify the heart sound recordings with KNN and fuzzy c-mean clustering methods

    Science.gov (United States)

    Juniati, D.; Khotimah, C.; Wardani, D. E. K.; Budayasa, K.

    2018-01-01

    The heart abnormalities can be detected from heart sound. A heart sound can be heard directly with a stethoscope or indirectly by a phonocardiograph, a machine of the heart sound recording. This paper presents the implementation of fractal dimension theory to make a classification of phonocardiograms into a normal heart sound, a murmur, or an extrasystole. The main algorithm used to calculate the fractal dimension was Higuchi’s Algorithm. There were two steps to make a classification of phonocardiograms, feature extraction, and classification. For feature extraction, we used Discrete Wavelet Transform to decompose the signal of heart sound into several sub-bands depending on the selected level. After the decomposition process, the signal was processed using Fast Fourier Transform (FFT) to determine the spectral frequency. The fractal dimension of the FFT output was calculated using Higuchi Algorithm. The classification of fractal dimension of all phonocardiograms was done with KNN and Fuzzy c-mean clustering methods. Based on the research results, the best accuracy obtained was 86.17%, the feature extraction by DWT decomposition level 3 with the value of kmax 50, using 5-fold cross validation and the number of neighbors was 5 at K-NN algorithm. Meanwhile, for fuzzy c-mean clustering, the accuracy was 78.56%.

  19. Treatment response in psychotic patients classified according to social and clinical needs, drug side effects, and previous treatment; a method to identify functional remission

    DEFF Research Database (Denmark)

    Alenius, Malin; Hammarlund-Udenaes, Margareta; Honoré, Per Gustaf Hartvig

    2009-01-01

    , fewer psychotic symptoms, and higher rate of workers than those with the worst treatment outcome. CONCLUSION: In the evaluation, CANSEPT showed validity in discriminating the patients of interest and was well tolerated by the patients. CANSEPT could secure inclusion of correct patients in the clinic......BACKGROUND: Various approaches have been made over the years to classify psychotic patients according to inadequate treatment response, using terms such as treatment resistant or treatment refractory. Existing classifications have been criticized for overestimating positive symptoms......; underestimating residual symptoms, negative symptoms, and side effects; or being to open for individual interpretation. The aim of this study was to present and evaluate a new method of classification according to treatment response and, thus, to identify patients in functional remission. METHOD: A naturalistic...

  20. A computational method for the coupled solution of reaction-diffusion equations on evolving domains and manifolds: Application to a model of cell migration and chemotaxis.

    Science.gov (United States)

    MacDonald, G; Mackenzie, J A; Nolan, M; Insall, R H

    2016-03-15

    In this paper, we devise a moving mesh finite element method for the approximate solution of coupled bulk-surface reaction-diffusion equations on an evolving two dimensional domain. Fundamental to the success of the method is the robust generation of bulk and surface meshes. For this purpose, we use a novel moving mesh partial differential equation (MMPDE) approach. The developed method is applied to model problems with known analytical solutions; these experiments indicate second-order spatial and temporal accuracy. Coupled bulk-surface problems occur frequently in many areas; in particular, in the modelling of eukaryotic cell migration and chemotaxis. We apply the method to a model of the two-way interaction of a migrating cell in a chemotactic field, where the bulk region corresponds to the extracellular region and the surface to the cell membrane.

  1. Evolvable synthetic neural system

    Science.gov (United States)

    Curtis, Steven A. (Inventor)

    2009-01-01

    An evolvable synthetic neural system includes an evolvable neural interface operably coupled to at least one neural basis function. Each neural basis function includes an evolvable neural interface operably coupled to a heuristic neural system to perform high-level functions and an autonomic neural system to perform low-level functions. In some embodiments, the evolvable synthetic neural system is operably coupled to one or more evolvable synthetic neural systems in a hierarchy.

  2. Treatment response in psychotic patients classified according to social and clinical needs, drug side effects, and previous treatment; a method to identify functional remission.

    Science.gov (United States)

    Alenius, Malin; Hammarlund-Udenaes, Margareta; Hartvig, Per; Sundquist, Staffan; Lindström, Leif

    2009-01-01

    Various approaches have been made over the years to classify psychotic patients according to inadequate treatment response, using terms such as treatment resistant or treatment refractory. Existing classifications have been criticized for overestimating positive symptoms; underestimating residual symptoms, negative symptoms, and side effects; or being to open for individual interpretation. The aim of this study was to present and evaluate a new method of classification according to treatment response and, thus, to identify patients in functional remission. A naturalistic, cross-sectional study was performed using patient interviews and information from patient files. The new classification method CANSEPT, which combines the Camberwell Assessment of Need rating scale, the Udvalg for Kliniske Undersøgelser side effect rating scale (SE), and the patient's previous treatment history (PT), was used to group the patients according to treatment response. CANSEPT was evaluated by comparison of expected and observed results. In the patient population (n = 123), the patients in functional remission, as defined by CANSEPT, had higher quality of life, fewer hospitalizations, fewer psychotic symptoms, and higher rate of workers than those with the worst treatment outcome. In the evaluation, CANSEPT showed validity in discriminating the patients of interest and was well tolerated by the patients. CANSEPT could secure inclusion of correct patients in the clinic or in research.

  3. Comparison of Boolean analysis and standard phylogenetic methods using artificially evolved and natural mt-tRNA sequences from great apes.

    Science.gov (United States)

    Ari, Eszter; Ittzés, Péter; Podani, János; Thi, Quynh Chi Le; Jakó, Eena

    2012-04-01

    Boolean analysis (or BOOL-AN; Jakó et al., 2009. BOOL-AN: A method for comparative sequence analysis and phylogenetic reconstruction. Mol. Phylogenet. Evol. 52, 887-97.), a recently developed method for sequence comparison uses the Iterative Canonical Form of Boolean functions. It considers sequence information in a way entirely different from standard phylogenetic methods (i.e. Maximum Parsimony, Maximum-Likelihood, Neighbor-Joining, and Bayesian analysis). The performance and reliability of Boolean analysis were tested and compared with the standard phylogenetic methods, using artificially evolved - simulated - nucleotide sequences and the 22 mitochondrial tRNA genes of the great apes. At the outset, we assumed that the phylogeny of Hominidae is generally well established, and the guide tree of artificial sequence evolution can also be used as a benchmark. These offer a possibility to compare and test the performance of different phylogenetic methods. Trees were reconstructed by each method from 2500 simulated sequences and 22 mitochondrial tRNA sequences. We also introduced a special re-sampling method for Boolean analysis on permuted sequence sites, the P-BOOL-AN procedure. Considering the reliability values (branch support values of consensus trees and Robinson-Foulds distances) we used for simulated sequence trees produced by different phylogenetic methods, BOOL-AN appeared as the most reliable method. Although the mitochondrial tRNA sequences of great apes are relatively short (59-75 bases long) and the ratio of their constant characters is about 75%, BOOL-AN, P-BOOL-AN and the Bayesian approach produced the same tree-topology as the established phylogeny, while the outcomes of Maximum Parsimony, Maximum-Likelihood and Neighbor-Joining methods were equivocal. We conclude that Boolean analysis is a promising alternative to existing methods of sequence comparison for phylogenetic reconstruction and congruence analysis. Copyright © 2012 Elsevier Inc. All

  4. Classifying Returns as Extreme

    DEFF Research Database (Denmark)

    Christiansen, Charlotte

    2014-01-01

    I consider extreme returns for the stock and bond markets of 14 EU countries using two classification schemes: One, the univariate classification scheme from the previous literature that classifies extreme returns for each market separately, and two, a novel multivariate classification scheme tha...

  5. Intelligent Garbage Classifier

    Directory of Open Access Journals (Sweden)

    Ignacio Rodríguez Novelle

    2008-12-01

    Full Text Available IGC (Intelligent Garbage Classifier is a system for visual classification and separation of solid waste products. Currently, an important part of the separation effort is based on manual work, from household separation to industrial waste management. Taking advantage of the technologies currently available, a system has been built that can analyze images from a camera and control a robot arm and conveyor belt to automatically separate different kinds of waste.

  6. Classifying Linear Canonical Relations

    OpenAIRE

    Lorand, Jonathan

    2015-01-01

    In this Master's thesis, we consider the problem of classifying, up to conjugation by linear symplectomorphisms, linear canonical relations (lagrangian correspondences) from a finite-dimensional symplectic vector space to itself. We give an elementary introduction to the theory of linear canonical relations and present partial results toward the classification problem. This exposition should be accessible to undergraduate students with a basic familiarity with linear algebra.

  7. Stack filter classifiers

    Energy Technology Data Exchange (ETDEWEB)

    Porter, Reid B [Los Alamos National Laboratory; Hush, Don [Los Alamos National Laboratory

    2009-01-01

    Just as linear models generalize the sample mean and weighted average, weighted order statistic models generalize the sample median and weighted median. This analogy can be continued informally to generalized additive modeels in the case of the mean, and Stack Filters in the case of the median. Both of these model classes have been extensively studied for signal and image processing but it is surprising to find that for pattern classification, their treatment has been significantly one sided. Generalized additive models are now a major tool in pattern classification and many different learning algorithms have been developed to fit model parameters to finite data. However Stack Filters remain largely confined to signal and image processing and learning algorithms for classification are yet to be seen. This paper is a step towards Stack Filter Classifiers and it shows that the approach is interesting from both a theoretical and a practical perspective.

  8. Hybrid Neuro-Fuzzy Classifier Based On Nefclass Model

    Directory of Open Access Journals (Sweden)

    Bogdan Gliwa

    2011-01-01

    Full Text Available The paper presents hybrid neuro-fuzzy classifier, based on NEFCLASS model, which wasmodified. The presented classifier was compared to popular classifiers – neural networks andk-nearest neighbours. Efficiency of modifications in classifier was compared with methodsused in original model NEFCLASS (learning methods. Accuracy of classifier was testedusing 3 datasets from UCI Machine Learning Repository: iris, wine and breast cancer wisconsin.Moreover, influence of ensemble classification methods on classification accuracy waspresented.

  9. Logarithmic learning for generalized classifier neural network.

    Science.gov (United States)

    Ozyildirim, Buse Melis; Avci, Mutlu

    2014-12-01

    Generalized classifier neural network is introduced as an efficient classifier among the others. Unless the initial smoothing parameter value is close to the optimal one, generalized classifier neural network suffers from convergence problem and requires quite a long time to converge. In this work, to overcome this problem, a logarithmic learning approach is proposed. The proposed method uses logarithmic cost function instead of squared error. Minimization of this cost function reduces the number of iterations used for reaching the minima. The proposed method is tested on 15 different data sets and performance of logarithmic learning generalized classifier neural network is compared with that of standard one. Thanks to operation range of radial basis function included by generalized classifier neural network, proposed logarithmic approach and its derivative has continuous values. This makes it possible to adopt the advantage of logarithmic fast convergence by the proposed learning method. Due to fast convergence ability of logarithmic cost function, training time is maximally decreased to 99.2%. In addition to decrease in training time, classification performance may also be improved till 60%. According to the test results, while the proposed method provides a solution for time requirement problem of generalized classifier neural network, it may also improve the classification accuracy. The proposed method can be considered as an efficient way for reducing the time requirement problem of generalized classifier neural network. Copyright © 2014 Elsevier Ltd. All rights reserved.

  10. Evolvability Search: Directly Selecting for Evolvability in order to Study and Produce It

    DEFF Research Database (Denmark)

    Mengistu, Henok; Lehman, Joel Anthony; Clune, Jeff

    2016-01-01

    of evolvable digital phenotypes. Although some types of selection in evolutionary computation indirectly encourage evolvability, one unexplored possibility is to directly select for evolvability. To do so, we estimate an individual's future potential for diversity by calculating the behavioral diversity of its...... immediate offspring, and select organisms with increased offspring variation. While the technique is computationally expensive, we hypothesized that direct selection would better encourage evolvability than indirect methods. Experiments in two evolutionary robotics domains confirm this hypothesis: in both...... domains, such Evolvability Search produces solutions with higher evolvability than those produced with Novelty Search or traditional objective-based search algorithms. Further experiments demonstrate that the higher evolvability produced by Evolvability Search in a training environment also generalizes...

  11. Combining multiple classifiers for age classification

    CSIR Research Space (South Africa)

    Van Heerden, C

    2009-11-01

    Full Text Available The authors compare several different classifier combination methods on a single task, namely speaker age classification. This task is well suited to combination strategies, since significantly different feature classes are employed. Support vector...

  12. A CLASSIFIER SYSTEM USING SMOOTH GRAPH COLORING

    Directory of Open Access Journals (Sweden)

    JORGE FLORES CRUZ

    2017-01-01

    Full Text Available Unsupervised classifiers allow clustering methods with less or no human intervention. Therefore it is desirable to group the set of items with less data processing. This paper proposes an unsupervised classifier system using the model of soft graph coloring. This method was tested with some classic instances in the literature and the results obtained were compared with classifications made with human intervention, yielding as good or better results than supervised classifiers, sometimes providing alternative classifications that considers additional information that humans did not considered.

  13. Delineating slowly and rapidly evolving fractions of the Drosophila genome.

    Science.gov (United States)

    Keith, Jonathan M; Adams, Peter; Stephen, Stuart; Mattick, John S

    2008-05-01

    Evolutionary conservation is an important indicator of function and a major component of bioinformatic methods to identify non-protein-coding genes. We present a new Bayesian method for segmenting pairwise alignments of eukaryotic genomes while simultaneously classifying segments into slowly and rapidly evolving fractions. We also describe an information criterion similar to the Akaike Information Criterion (AIC) for determining the number of classes. Working with pairwise alignments enables detection of differences in conservation patterns among closely related species. We analyzed three whole-genome and three partial-genome pairwise alignments among eight Drosophila species. Three distinct classes of conservation level were detected. Sequences comprising the most slowly evolving component were consistent across a range of species pairs, and constituted approximately 62-66% of the D. melanogaster genome. Almost all (>90%) of the aligned protein-coding sequence is in this fraction, suggesting much of it (comprising the majority of the Drosophila genome, including approximately 56% of non-protein-coding sequences) is functional. The size and content of the most rapidly evolving component was species dependent, and varied from 1.6% to 4.8%. This fraction is also enriched for protein-coding sequence (while containing significant amounts of non-protein-coding sequence), suggesting it is under positive selection. We also classified segments according to conservation and GC content simultaneously. This analysis identified numerous sub-classes of those identified on the basis of conservation alone, but was nevertheless consistent with that classification. Software, data, and results available at www.maths.qut.edu.au/-keithj/. Genomic segments comprising the conservation classes available in BED format.

  14. Mentoring: An Evolving Relationship.

    Science.gov (United States)

    Block, Michelle; Florczak, Kristine L

    2017-04-01

    The column concerns itself with mentoring as an evolving relationship between mentor and mentee. The collegiate mentoring model, the transformational transcendence model, and the humanbecoming mentoring model are considered in light of a dialogue with mentors at a Midwest university and conclusions are drawn.

  15. Characterization of the State-of-the-art and Identification of Main Trends for Ecodesign Tools and Methods: Classifying Three Decades of Research and Implementation

    DEFF Research Database (Denmark)

    Pigosso, Daniela Cristina Antelmi; McAloone, T. C.; Rozenfeld, H.

    2015-01-01

    Ecodesign is a proactive management approach that integrates environmental considerations in product development and related processes (such as purchasing, marketing and research & development). Ecodesign aims to improve environmental performance of products throughout their life cycle, from raw...... material extraction and manufacturing to use and end-of-life. Over the last three decades, an intense development of new ecodesign methods and tools could be observed, but uptake by the industry remains a challenge. The purpose of this research is to perform a review of existing ecodesign tools and methods...... through a systematic literature review linked to bibliometric analyses, in order to explore the state of the art of ecodesign methods and tools and identify trends and opportunities in the field for the next decade....

  16. New Approach of Feature Extraction Method Based on the Raw Form and his Skeleton for Gujarati Handwritten Digits using Neural Networks Classifier

    Directory of Open Access Journals (Sweden)

    K. Moro

    2014-12-01

    Full Text Available This paper presents an optical character recognition (OCR system for Gujarati handwritten digits. One may find so much of work for latin writing, arabic, chines, etc. but Gujarati is a language for which hardly any work is traceable especially for handwritten characters. Here in this work we have proposed a method of feature extraction based on the raw form of the character and his skeleton and we have shown the advantage of using this method over other approaches mentioned in this article.

  17. Classifying the evolutionary and ecological features of neoplasms

    Science.gov (United States)

    Maley, Carlo C.; Aktipis, Athena; Graham, Trevor A.; Sottoriva, Andrea; Boddy, Amy M.; Janiszewska, Michalina; Silva, Ariosto S.; Gerlinger, Marco; Yuan, Yinyin; Pienta, Kenneth J.; Anderson, Karen S.; Gatenby, Robert; Swanton, Charles; Posada, David; Wu, Chung-I; Schiffman, Joshua D.; Hwang, E. Shelley; Polyak, Kornelia; Anderson, Alexander R. A.; Brown, Joel S.; Greaves, Mel; Shibata, Darryl

    2018-01-01

    Neoplasms change over time through a process of cell-level evolution, driven by genetic and epigenetic alterations. However, the ecology of the microenvironment of a neoplastic cell determines which changes provide adaptive benefits. There is widespread recognition of the importance of these evolutionary and ecological processes in cancer, but to date, no system has been proposed for drawing clinically relevant distinctions between how different tumours are evolving. On the basis of a consensus conference of experts in the fields of cancer evolution and cancer ecology, we propose a framework for classifying tumours that is based on four relevant components. These are the diversity of neoplastic cells (intratumoural heterogeneity) and changes over time in that diversity, which make up an evolutionary index (Evo-index), as well as the hazards to neoplastic cell survival and the resources available to neoplastic cells, which make up an ecological index (Eco-index). We review evidence demonstrating the importance of each of these factors and describe multiple methods that can be used to measure them. Development of this classification system holds promise for enabling clinicians to personalize optimal interventions based on the evolvability of the patient’s tumour. The Evo- and Eco-indices provide a common lexicon for communicating about how neoplasms change in response to interventions, with potential implications for clinical trials, personalized medicine and basic cancer research. PMID:28912577

  18. EVOLVE 2014 International Conference

    CERN Document Server

    Tantar, Emilia; Sun, Jian-Qiao; Zhang, Wei; Ding, Qian; Schütze, Oliver; Emmerich, Michael; Legrand, Pierrick; Moral, Pierre; Coello, Carlos

    2014-01-01

    This volume encloses research articles that were presented at the EVOLVE 2014 International Conference in Beijing, China, July 1–4, 2014.The book gathers contributions that emerged from the conference tracks, ranging from probability to set oriented numerics and evolutionary computation; all complemented by the bridging purpose of the conference, e.g. Complex Networks and Landscape Analysis, or by the more application oriented perspective. The novelty of the volume, when considering the EVOLVE series, comes from targeting also the practitioner’s view. This is supported by the Machine Learning Applied to Networks and Practical Aspects of Evolutionary Algorithms tracks, providing surveys on new application areas, as in the networking area and useful insights in the development of evolutionary techniques, from a practitioner’s perspective. Complementary to these directions, the conference tracks supporting the volume, follow on the individual advancements of the subareas constituting the scope of the confe...

  19. Evolving Procurement Organizations

    DEFF Research Database (Denmark)

    Bals, Lydia; Laine, Jari; Mugurusi, Godfrey

    Procurement has to find further levers and advance its contribution to corporate goals continuously. This places pressure on its organization in order to facilitate its performance. Therefore, procurement organizations constantly have to evolve in order to match these demands. A conceptual model...... and external contingency factors and having a more detailed look at the structural dimensions chosen, beyond the well-known characteristics of centralization, formalization, participation, specialization, standardization and size. From a theoretical perspective, it opens up insights that can be leveraged...

  20. Symbiotic Composition and Evolvability

    OpenAIRE

    Watson, Richard A.; Pollack, Jordan B.

    2001-01-01

    Several of the Major Transitions in natural evolution, such as the symbiogenic origin of eukaryotes from prokaryotes, share the feature that existing entities became the components of composite entities at a higher level of organisation. This composition of pre-adapted extant entities into a new whole is a fundamentally different source of variation from the gradual accumulation of small random variations, and it has some interesting consequences for issues of evolvability. In this paper we p...

  1. Evolvable Neural Software System

    Science.gov (United States)

    Curtis, Steven A.

    2009-01-01

    The Evolvable Neural Software System (ENSS) is composed of sets of Neural Basis Functions (NBFs), which can be totally autonomously created and removed according to the changing needs and requirements of the software system. The resulting structure is both hierarchical and self-similar in that a given set of NBFs may have a ruler NBF, which in turn communicates with other sets of NBFs. These sets of NBFs may function as nodes to a ruler node, which are also NBF constructs. In this manner, the synthetic neural system can exhibit the complexity, three-dimensional connectivity, and adaptability of biological neural systems. An added advantage of ENSS over a natural neural system is its ability to modify its core genetic code in response to environmental changes as reflected in needs and requirements. The neural system is fully adaptive and evolvable and is trainable before release. It continues to rewire itself while on the job. The NBF is a unique, bilevel intelligence neural system composed of a higher-level heuristic neural system (HNS) and a lower-level, autonomic neural system (ANS). Taken together, the HNS and the ANS give each NBF the complete capabilities of a biological neural system to match sensory inputs to actions. Another feature of the NBF is the Evolvable Neural Interface (ENI), which links the HNS and ANS. The ENI solves the interface problem between these two systems by actively adapting and evolving from a primitive initial state (a Neural Thread) to a complicated, operational ENI and successfully adapting to a training sequence of sensory input. This simulates the adaptation of a biological neural system in a developmental phase. Within the greater multi-NBF and multi-node ENSS, self-similar ENI s provide the basis for inter-NBF and inter-node connectivity.

  2. Evolved H II regions

    International Nuclear Information System (INIS)

    Churchwell, E.

    1975-01-01

    A probable evolutionary sequence of H II regions based on six distinct types of observed objects is suggested. Two examples which may deviate from this idealized sequence, are discussed. Even though a size-mean density relation of H II regions can be used as a rough indication of whether a nebula is very young or evolved, it is argued that such a relation is not likely to be useful for the quantitative assignment of ages to H II regions. Evolved H II regions appear to fit into one of four structural types: rings, core-halos, smooth structures, and irregular or filamentary structures. Examples of each type are given with their derived physical parameters. The energy balance in these nebulae is considered. The mass of ionized gas in evolved H II regions is in general too large to trace the nebula back to single compact H II regions. Finally, the morphological type of the Galaxy is considered from its H II region content. 2 tables, 2 figs., 29 refs

  3. Evolving phenotypic networks in silico.

    Science.gov (United States)

    François, Paul

    2014-11-01

    Evolved gene networks are constrained by natural selection. Their structures and functions are consequently far from being random, as exemplified by the multiple instances of parallel/convergent evolution. One can thus ask if features of actual gene networks can be recovered from evolutionary first principles. I review a method for in silico evolution of small models of gene networks aiming at performing predefined biological functions. I summarize the current implementation of the algorithm, insisting on the construction of a proper "fitness" function. I illustrate the approach on three examples: biochemical adaptation, ligand discrimination and vertebrate segmentation (somitogenesis). While the structure of the evolved networks is variable, dynamics of our evolved networks are usually constrained and present many similar features to actual gene networks, including properties that were not explicitly selected for. In silico evolution can thus be used to predict biological behaviours without a detailed knowledge of the mapping between genotype and phenotype. Copyright © 2014 The Author. Published by Elsevier Ltd.. All rights reserved.

  4. Classifying sows' activity types from acceleration patterns

    DEFF Research Database (Denmark)

    Cornou, Cecile; Lundbye-Christensen, Søren

    2008-01-01

    An automated method of classifying sow activity using acceleration measurements would allow the individual sow's behavior to be monitored throughout the reproductive cycle; applications for detecting behaviors characteristic of estrus and farrowing or to monitor illness and welfare can be foreseen....... This article suggests a method of classifying five types of activity exhibited by group-housed sows. The method involves the measurement of acceleration in three dimensions. The five activities are: feeding, walking, rooting, lying laterally and lying sternally. Four time series of acceleration (the three...

  5. Application of multivariate statistical methods to classify archaeological pottery from Tel-Alramad site, Syria, based on x-ray fluorescence analysis

    International Nuclear Information System (INIS)

    Bakraji, E. H.

    2007-01-01

    Radioisotopic x-ray fluorescence (XRF) analysis has been utilized to determine the elemental composition of 55 archaeological pottery samples by the determination of 17 chemical elements. Fifty-four of them came from the Tel-Alramad Site in Katana town, near Damascus city, Syria, and one sample came from Brazil. The XRF results have been processed using two multivariate statistical methods, cluster and factor analysis, in order to determine similarities and correlation between the selected samples based on their elemental composition. The methodology successfully separates the samples where four distinct chemical groups were identified. (author)

  6. Just-in-time classifiers for recurrent concepts.

    Science.gov (United States)

    Alippi, Cesare; Boracchi, Giacomo; Roveri, Manuel

    2013-04-01

    Just-in-time (JIT) classifiers operate in evolving environments by classifying instances and reacting to concept drift. In stationary conditions, a JIT classifier improves its accuracy over time by exploiting additional supervised information coming from the field. In nonstationary conditions, however, the classifier reacts as soon as concept drift is detected; the current classification setup is discarded and a suitable one activated to keep the accuracy high. We present a novel generation of JIT classifiers able to deal with recurrent concept drift by means of a practical formalization of the concept representation and the definition of a set of operators working on such representations. The concept-drift detection activity, which is crucial in promptly reacting to changes exactly when needed, is advanced by considering change-detection tests monitoring both inputs and classes distributions.

  7. Reinforcement Learning Based Artificial Immune Classifier

    Directory of Open Access Journals (Sweden)

    Mehmet Karakose

    2013-01-01

    Full Text Available One of the widely used methods for classification that is a decision-making process is artificial immune systems. Artificial immune systems based on natural immunity system can be successfully applied for classification, optimization, recognition, and learning in real-world problems. In this study, a reinforcement learning based artificial immune classifier is proposed as a new approach. This approach uses reinforcement learning to find better antibody with immune operators. The proposed new approach has many contributions according to other methods in the literature such as effectiveness, less memory cell, high accuracy, speed, and data adaptability. The performance of the proposed approach is demonstrated by simulation and experimental results using real data in Matlab and FPGA. Some benchmark data and remote image data are used for experimental results. The comparative results with supervised/unsupervised based artificial immune system, negative selection classifier, and resource limited artificial immune classifier are given to demonstrate the effectiveness of the proposed new method.

  8. The 'E' factor -- evolving endodontics.

    Science.gov (United States)

    Hunter, M J

    2013-03-01

    Endodontics is a constantly developing field, with new instruments, preparation techniques and sealants competing with trusted and traditional approaches to tooth restoration. Thus general dental practitioners must question and understand the significance of these developments before adopting new practices. In view of this, the aim of this article, and the associated presentation at the 2013 British Dental Conference & Exhibition, is to provide an overview of endodontic methods and constantly evolving best practice. The presentation will review current preparation techniques, comparing rotary versus reciprocation, and question current trends in restoration of the endodontically treated tooth.

  9. Fingerprint prediction using classifier ensembles

    CSIR Research Space (South Africa)

    Molale, P

    2011-11-01

    Full Text Available ); logistic discrimination (LgD), k-nearest neighbour (k-NN), artificial neural network (ANN), association rules (AR) decision tree (DT), naive Bayes classifier (NBC) and the support vector machine (SVM). The performance of several multiple classifier systems...

  10. Concurrent approach for evolving compact decision rule sets

    Science.gov (United States)

    Marmelstein, Robert E.; Hammack, Lonnie P.; Lamont, Gary B.

    1999-02-01

    The induction of decision rules from data is important to many disciplines, including artificial intelligence and pattern recognition. To improve the state of the art in this area, we introduced the genetic rule and classifier construction environment (GRaCCE). It was previously shown that GRaCCE consistently evolved decision rule sets from data, which were significantly more compact than those produced by other methods (such as decision tree algorithms). The primary disadvantage of GRaCCe, however, is its relatively poor run-time execution performance. In this paper, a concurrent version of the GRaCCE architecture is introduced, which improves the efficiency of the original algorithm. A prototype of the algorithm is tested on an in- house parallel processor configuration and the results are discussed.

  11. Classified

    CERN Multimedia

    Computer Security Team

    2011-01-01

    In the last issue of the Bulletin, we have discussed recent implications for privacy on the Internet. But privacy of personal data is just one facet of data protection. Confidentiality is another one. However, confidentiality and data protection are often perceived as not relevant in the academic environment of CERN.   But think twice! At CERN, your personal data, e-mails, medical records, financial and contractual documents, MARS forms, group meeting minutes (and of course your password!) are all considered to be sensitive, restricted or even confidential. And this is not all. Physics results, in particular when being preliminary and pending scrutiny, are sensitive, too. Just recently, an ATLAS collaborator copy/pasted the abstract of an ATLAS note onto an external public blog, despite the fact that this document was clearly marked as an "Internal Note". Such an act was not only embarrassing to the ATLAS collaboration, and had negative impact on CERN’s reputation --- i...

  12. Disassembly and Sanitization of Classified Matter

    International Nuclear Information System (INIS)

    Stockham, Dwight J.; Saad, Max P.

    2008-01-01

    , Pantex personnel have asked the DSO team to assist them with the destruction of their stored classified components. The DSO process is in full-scale operation and continues to grow and serve SNL/NM and DOE by providing a solution to this evolving disposal issue. For some time, SNL has incurred significant expenses for the management and storage of classified components. This project is estimated to save DOE and Sandia several hundreds of thousands of dollars while the excess inventory is eliminated. This innovative approach eliminates the need for long-term storage of classified weapons components and the associated monitoring and accounting expenditures

  13. Robust Framework to Combine Diverse Classifiers Assigning Distributed Confidence to Individual Classifiers at Class Level

    Directory of Open Access Journals (Sweden)

    Shehzad Khalid

    2014-01-01

    Full Text Available We have presented a classification framework that combines multiple heterogeneous classifiers in the presence of class label noise. An extension of m-Mediods based modeling is presented that generates model of various classes whilst identifying and filtering noisy training data. This noise free data is further used to learn model for other classifiers such as GMM and SVM. A weight learning method is then introduced to learn weights on each class for different classifiers to construct an ensemble. For this purpose, we applied genetic algorithm to search for an optimal weight vector on which classifier ensemble is expected to give the best accuracy. The proposed approach is evaluated on variety of real life datasets. It is also compared with existing standard ensemble techniques such as Adaboost, Bagging, and Random Subspace Methods. Experimental results show the superiority of proposed ensemble method as compared to its competitors, especially in the presence of class label noise and imbalance classes.

  14. Classifying Sluice Occurrences in Dialogue

    DEFF Research Database (Denmark)

    Baird, Austin; Hamza, Anissa; Hardt, Daniel

    2018-01-01

    perform manual annotation with acceptable inter-coder agreement. We build classifier models with Decision Trees and Naive Bayes, with accuracy of 67%. We deploy a classifier to automatically classify sluice occurrences in OpenSubtitles, resulting in a corpus with 1.7 million occurrences. This will support....... Despite this, the corpus can be of great use in research on sluicing and development of systems, and we are making the corpus freely available on request. Furthermore, we are in the process of improving the accuracy of sluice identification and annotation for the purpose of created a subsequent version...

  15. Evolving Procurement Organizations

    DEFF Research Database (Denmark)

    Bals, Lydia; Laiho, Aki; Laine, Jari

    Procurement has to find further levers and advance its contribution to corporate goals continuously. This places pressure on its organization in order to facilitate its performance. Therefore, Procurement organizations constantly have to evolve in order to match these demands. A conceptual model...... is presented and results of a first case study discussed. The findings highlight the importance of taking a contingency perspective on Procurement organization, understanding the internal and internal contingency factors. From a theoretical perspective, it opens up insights that can be furthermore leveraged...... in future studies in the fields of hybrid procurement organizations, global sourcing organizations as well as international procurement offices (IPOs). From a practical standpoint, an assessment of external and internal contingencies provides the opportunity to consciously match organization to its...

  16. Diffusion between evolving interfaces

    International Nuclear Information System (INIS)

    Juntunen, Janne; Merikoski, Juha

    2010-01-01

    Diffusion in an evolving environment is studied by continuous-time Monte Carlo simulations. Diffusion is modeled by continuous-time random walkers on a lattice, in a dynamic environment provided by bubbles between two one-dimensional interfaces driven symmetrically towards each other. For one-dimensional random walkers constrained by the interfaces, the bubble size distribution dominates diffusion. For two-dimensional random walkers, it is also controlled by the topography and dynamics of the interfaces. The results of the one-dimensional case are recovered in the limit where the interfaces are strongly driven. Even with simple hard-core repulsion between the interfaces and the particles, diffusion is found to depend strongly on the details of the dynamical rules of particles close to the interfaces.

  17. Classifying and evaluating architecture design methods

    NARCIS (Netherlands)

    Aksit, Mehmet; Tekinerdogan, B.

    1999-01-01

    The concept of software architecture has gained a wide popularity and is generally considered to play a fundamental role in coping with the inherent difficulties of the development of large-scale and complex software systems. This document first gives a definition of architectures. Second, a

  18. Classifying and Evaluating Architecture Design Methods

    NARCIS (Netherlands)

    Tekinerdogan, B.; Aksit, Mehmet; Aksit, Mehmet

    2002-01-01

    The concept of software architecture has gained a wide popularity and is generally considered to play a fundamental role in coping with the inherent difficulties of the development of large-scale and complex software systems. This chapter first gives a definition of architecture. Second, a

  19. The spinorial method of classifying supersymmetric backgrounds

    NARCIS (Netherlands)

    Gran, U.; Gutowski, J.; Papadopoulos, G.; Roest, D.

    2006-01-01

    We review how the classification of all supersymmetric backgrounds of IIB supergravity can be reduced to the evaluation of the Killing spinor equations and their integrability conditions, which contain the field equations, on five types of spinors. This is an extension of the work [hep-th/0503046

  20. The method and efficacy of support vector machine classifiers based on texture features and multi-resolution histogram from 18F-FDG PET-CT images for the evaluation of mediastinal lymph nodes in patients with lung cancer

    International Nuclear Information System (INIS)

    Gao, Xuan; Chu, Chunyu; Li, Yingci; Lu, Peiou; Wang, Wenzhi; Liu, Wanyu; Yu, Lijuan

    2015-01-01

    Highlights: • Three support vector machine classifiers were constructed from PET-CT images. • The areas under the ROC curve for SVM1, SVM2, and SVM3 were 0.689, 0.579, and 0.685, respectively. • The areas under curves for maximum short diameter and SUV max were 0.684 and 0.652, respectively. • The algorithm based on SVM was potential in the diagnosis of mediastinal lymph nodes. - Abstract: Objectives: In clinical practice, image analysis is dependent on simply visual perception and the diagnostic efficacy of this analysis pattern is limited for mediastinal lymph nodes in patients with lung cancer. In order to improve diagnostic efficacy, we developed a new computer-based algorithm and tested its diagnostic efficacy. Methods: 132 consecutive patients with lung cancer underwent 18 F-FDG PET/CT examination before treatment. After all data were imported into the database of an on-line medical image analysis platform, the diagnostic efficacy of visual analysis was first evaluated without knowing pathological results, and the maximum short diameter and maximum standardized uptake value (SUV max ) were measured. Then lymph nodes were segmented manually. Three classifiers based on support vector machine (SVM) were constructed from CT, PET, and combined PET-CT images, respectively. The diagnostic efficacy of SVM classifiers was obtained and evaluated. Results: According to ROC curves, the areas under curves for maximum short diameter and SUV max were 0.684 and 0.652, respectively. The areas under the ROC curve for SVM1, SVM2, and SVM3 were 0.689, 0.579, and 0.685, respectively. Conclusion: The algorithm based on SVM was potential in the diagnosis of mediastinal lymph nodes

  1. Classifier Fusion With Contextual Reliability Evaluation.

    Science.gov (United States)

    Liu, Zhunga; Pan, Quan; Dezert, Jean; Han, Jun-Wei; He, You

    2018-05-01

    Classifier fusion is an efficient strategy to improve the classification performance for the complex pattern recognition problem. In practice, the multiple classifiers to combine can have different reliabilities and the proper reliability evaluation plays an important role in the fusion process for getting the best classification performance. We propose a new method for classifier fusion with contextual reliability evaluation (CF-CRE) based on inner reliability and relative reliability concepts. The inner reliability, represented by a matrix, characterizes the probability of the object belonging to one class when it is classified to another class. The elements of this matrix are estimated from the -nearest neighbors of the object. A cautious discounting rule is developed under belief functions framework to revise the classification result according to the inner reliability. The relative reliability is evaluated based on a new incompatibility measure which allows to reduce the level of conflict between the classifiers by applying the classical evidence discounting rule to each classifier before their combination. The inner reliability and relative reliability capture different aspects of the classification reliability. The discounted classification results are combined with Dempster-Shafer's rule for the final class decision making support. The performance of CF-CRE have been evaluated and compared with those of main classical fusion methods using real data sets. The experimental results show that CF-CRE can produce substantially higher accuracy than other fusion methods in general. Moreover, CF-CRE is robust to the changes of the number of nearest neighbors chosen for estimating the reliability matrix, which is appealing for the applications.

  2. Histogram deconvolution - An aid to automated classifiers

    Science.gov (United States)

    Lorre, J. J.

    1983-01-01

    It is shown that N-dimensional histograms are convolved by the addition of noise in the picture domain. Three methods are described which provide the ability to deconvolve such noise-affected histograms. The purpose of the deconvolution is to provide automated classifiers with a higher quality N-dimensional histogram from which to obtain classification statistics.

  3. Assessment of Evolving TRMM-Based Real-Time Precipitation Estimation Methods and Their Impacts on Hydrologic Prediction in a High-Latitude Basin

    Science.gov (United States)

    Yong, Bin; Hong, Yang; Ren, Li-Liang; Gourley, Jonathan; Huffman, George J.; Chen, Xi; Wang, Wen; Khan, Sadiq I.

    2013-01-01

    The real-time availability of satellite-derived precipitation estimates provides hydrologists an opportunity to improve current hydrologic prediction capability for medium to large river basins. Due to the availability of new satellite data and upgrades to the precipitation algorithms, the Tropical Rainfall Measuring Mission (TRMM) Multi-satellite Precipitation Analysis real-time estimates (TMPA-RT) have been undergoing several important revisions over the past ten years. In this study, the changes of the relative accuracy and hydrologic potential of TMPA-RT estimates over its three major evolving periods were evaluated and inter-compared at daily, monthly and seasonal scales in the high-latitude Laohahe basin in China. Assessment results show that the performance of TMPA-RT in terms of precipitation estimation and streamflow simulation was significantly improved after 3 February 2005. Overestimation during winter months was noteworthy and consistent, which is suggested to be a consequence from interference of snow cover to the passive microwave retrievals. Rainfall estimated by the new version 6 of TMPA-RT starting from 1 October 2008 to present has higher correlations with independent gauge observations and tends to perform better in detecting rain compared to the prior periods, although it suffers larger mean error and relative bias. After a simple bias correction, this latest dataset of TMPA-RT exhibited the best capability in capturing hydrologic response among the three tested periods. In summary, this study demonstrated that there is an increasing potential in the use of TMPA-RT in hydrologic streamflow simulations over its three algorithm upgrade periods, but still with significant challenges during the winter snowing events.

  4. Quantum ensembles of quantum classifiers.

    Science.gov (United States)

    Schuld, Maria; Petruccione, Francesco

    2018-02-09

    Quantum machine learning witnesses an increasing amount of quantum algorithms for data-driven decision making, a problem with potential applications ranging from automated image recognition to medical diagnosis. Many of those algorithms are implementations of quantum classifiers, or models for the classification of data inputs with a quantum computer. Following the success of collective decision making with ensembles in classical machine learning, this paper introduces the concept of quantum ensembles of quantum classifiers. Creating the ensemble corresponds to a state preparation routine, after which the quantum classifiers are evaluated in parallel and their combined decision is accessed by a single-qubit measurement. This framework naturally allows for exponentially large ensembles in which - similar to Bayesian learning - the individual classifiers do not have to be trained. As an example, we analyse an exponentially large quantum ensemble in which each classifier is weighed according to its performance in classifying the training data, leading to new results for quantum as well as classical machine learning.

  5. IAEA safeguards and classified materials

    International Nuclear Information System (INIS)

    Pilat, J.F.; Eccleston, G.W.; Fearey, B.L.; Nicholas, N.J.; Tape, J.W.; Kratzer, M.

    1997-01-01

    The international community in the post-Cold War period has suggested that the International Atomic Energy Agency (IAEA) utilize its expertise in support of the arms control and disarmament process in unprecedented ways. The pledges of the US and Russian presidents to place excess defense materials, some of which are classified, under some type of international inspections raises the prospect of using IAEA safeguards approaches for monitoring classified materials. A traditional safeguards approach, based on nuclear material accountancy, would seem unavoidably to reveal classified information. However, further analysis of the IAEA's safeguards approaches is warranted in order to understand fully the scope and nature of any problems. The issues are complex and difficult, and it is expected that common technical understandings will be essential for their resolution. Accordingly, this paper examines and compares traditional safeguards item accounting of fuel at a nuclear power station (especially spent fuel) with the challenges presented by inspections of classified materials. This analysis is intended to delineate more clearly the problems as well as reveal possible approaches, techniques, and technologies that could allow the adaptation of safeguards to the unprecedented task of inspecting classified materials. It is also hoped that a discussion of these issues can advance ongoing political-technical debates on international inspections of excess classified materials

  6. Biodegradation of Poly(butylene succinate Powder in a Controlled Compost at 58 °C Evaluated by Naturally-Occurring Carbon 14 Amounts in Evolved CO2 Based on the ISO 14855-2 Method

    Directory of Open Access Journals (Sweden)

    Masahiro Funabashi

    2009-09-01

    Full Text Available The biodegradabilities of poly(butylene succinate (PBS powders in a controlled compost at 58 °C have been studied using a Microbial Oxidative Degradation Analyzer (MODA based on the ISO 14855-2 method, entitled “Determination of the ultimate aerobic biodegradability of plastic materials under controlled composting conditions—Method by analysis of evolved carbon dioxide—Part 2: Gravimetric measurement of carbon dioxide evolved in a laboratory-scale test”. The evolved CO2 was trapped by an additional aqueous Ba(OH2 solution. The trapped BaCO3 was transformed into graphite via a serial vaporization and reduction reaction using a gas-tight tube and vacuum manifold system. This graphite was analyzed by accelerated mass spectrometry (AMS to determine the percent modern carbon [pMC (sample] based on the 14C radiocarbon concentration. By using the theory that pMC (sample was the sum of the pMC (compost (109.87% and pMC (PBS (0% as the respective ratio in the determined period, the CO2 (respiration was calculated from only one reaction vessel. It was found that the biodegradabilities determined by the CO2 amount from PBS in the sample vessel were about 30% lower than those based on the ISO method. These differences between the ISO and AMS methods are caused by the fact that part of the carbons from PBS are changed into metabolites by the microorganisms in the compost, and not changed into CO2.

  7. A survey of decision tree classifier methodology

    Science.gov (United States)

    Safavian, S. R.; Landgrebe, David

    1991-01-01

    Decision tree classifiers (DTCs) are used successfully in many diverse areas such as radar signal classification, character recognition, remote sensing, medical diagnosis, expert systems, and speech recognition. Perhaps the most important feature of DTCs is their capability to break down a complex decision-making process into a collection of simpler decisions, thus providing a solution which is often easier to interpret. A survey of current methods is presented for DTC designs and the various existing issues. After considering potential advantages of DTCs over single-state classifiers, subjects of tree structure design, feature selection at each internal node, and decision and search strategies are discussed.

  8. Why did heterospory evolve?

    Science.gov (United States)

    Petersen, Kurt B; Burd, Martin

    2017-08-01

    The primitive land plant life cycle featured the production of spores of unimodal size, a condition called homospory. The evolution of bimodal size distributions with small male spores and large female spores, known as heterospory, was an innovation that occurred repeatedly in the history of land plants. The importance of desiccation-resistant spores for colonization of the land is well known, but the adaptive value of heterospory has never been well established. It was an addition to a sexual life cycle that already involved male and female gametes. Its role as a precursor to the evolution of seeds has received much attention, but this is an evolutionary consequence of heterospory that cannot explain the transition from homospory to heterospory (and the lack of evolutionary reversal from heterospory to homospory). Enforced outcrossing of gametophytes has often been mentioned in connection to heterospory, but we review the shortcomings of this argument as an explanation of the selective advantage of heterospory. Few alternative arguments concerning the selective forces favouring heterospory have been proposed, a paucity of attention that is surprising given the importance of this innovation in land plant evolution. In this review we highlight two ideas that may lead us to a better understanding of why heterospory evolved. First, models of optimal resource allocation - an approach that has been used for decades in evolutionary ecology to help understand parental investment and other life-history patterns - suggest that an evolutionary increase in spore size could reach a threshold at which small spores yielding small, sperm-producing gametophytes would return greater fitness per unit of resource investment than would large spores and bisexual gametophytes. With the advent of such microspores, megaspores would evolve under frequency-dependent selection. This argument can account for the appearance of heterospory in the Devonian, when increasingly tall and complex

  9. Evolving a photosynthetic organelle

    Directory of Open Access Journals (Sweden)

    Nakayama Takuro

    2012-04-01

    Full Text Available Abstract The evolution of plastids from cyanobacteria is believed to represent a singularity in the history of life. The enigmatic amoeba Paulinella and its 'recently' acquired photosynthetic inclusions provide a fascinating system through which to gain fresh insight into how endosymbionts become organelles. The plastids, or chloroplasts, of algae and plants evolved from cyanobacteria by endosymbiosis. This landmark event conferred on eukaryotes the benefits of photosynthesis - the conversion of solar energy into chemical energy - and in so doing had a huge impact on the course of evolution and the climate of Earth 1. From the present state of plastids, however, it is difficult to trace the evolutionary steps involved in this momentous development, because all modern-day plastids have fully integrated into their hosts. Paulinella chromatophora is a unicellular eukaryote that bears photosynthetic entities called chromatophores that are derived from cyanobacteria and has thus received much attention as a possible example of an organism in the early stages of organellogenesis. Recent studies have unlocked the genomic secrets of its chromatophore 23 and provided concrete evidence that the Paulinella chromatophore is a bona fide photosynthetic organelle 4. The question is how Paulinella can help us to understand the process by which an endosymbiont is converted into an organelle.

  10. Fat: an evolving issue

    Directory of Open Access Journals (Sweden)

    John R. Speakman

    2012-09-01

    Work on obesity is evolving, and obesity is a consequence of our evolutionary history. In the space of 50 years, we have become an obese species. The reasons why can be addressed at a number of different levels. These include separating between whether the primary cause lies on the food intake or energy expenditure side of the energy balance equation, and determining how genetic and environmental effects contribute to weight variation between individuals. Opinion on whether increased food intake or decreased energy expenditure drives the obesity epidemic is still divided, but recent evidence favours the idea that food intake, rather than altered expenditure, is most important. There is more of a consensus that genetics explains most (probably around 65% of weight variation between individuals. Recent advances in genome-wide association studies have identified many polymorphisms that are linked to obesity, yet much of the genetic variance remains unexplained. Finding the causes of this unexplained variation will be an impetus of genetic and epigenetic research on obesity over the next decade. Many environmental factors – including gut microbiota, stress and endocrine disruptors – have been linked to the risk of developing obesity. A better understanding of gene-by-environment interactions will also be key to understanding obesity in the years to come.

  11. Evolving a photosynthetic organelle.

    Science.gov (United States)

    Nakayama, Takuro; Archibald, John M

    2012-04-24

    The evolution of plastids from cyanobacteria is believed to represent a singularity in the history of life. The enigmatic amoeba Paulinella and its 'recently' acquired photosynthetic inclusions provide a fascinating system through which to gain fresh insight into how endosymbionts become organelles.The plastids, or chloroplasts, of algae and plants evolved from cyanobacteria by endosymbiosis. This landmark event conferred on eukaryotes the benefits of photosynthesis--the conversion of solar energy into chemical energy--and in so doing had a huge impact on the course of evolution and the climate of Earth 1. From the present state of plastids, however, it is difficult to trace the evolutionary steps involved in this momentous development, because all modern-day plastids have fully integrated into their hosts. Paulinella chromatophora is a unicellular eukaryote that bears photosynthetic entities called chromatophores that are derived from cyanobacteria and has thus received much attention as a possible example of an organism in the early stages of organellogenesis. Recent studies have unlocked the genomic secrets of its chromatophore 23 and provided concrete evidence that the Paulinella chromatophore is a bona fide photosynthetic organelle 4. The question is how Paulinella can help us to understand the process by which an endosymbiont is converted into an organelle.

  12. Communicability across evolving networks.

    Science.gov (United States)

    Grindrod, Peter; Parsons, Mark C; Higham, Desmond J; Estrada, Ernesto

    2011-04-01

    Many natural and technological applications generate time-ordered sequences of networks, defined over a fixed set of nodes; for example, time-stamped information about "who phoned who" or "who came into contact with who" arise naturally in studies of communication and the spread of disease. Concepts and algorithms for static networks do not immediately carry through to this dynamic setting. For example, suppose A and B interact in the morning, and then B and C interact in the afternoon. Information, or disease, may then pass from A to C, but not vice versa. This subtlety is lost if we simply summarize using the daily aggregate network given by the chain A-B-C. However, using a natural definition of a walk on an evolving network, we show that classic centrality measures from the static setting can be extended in a computationally convenient manner. In particular, communicability indices can be computed to summarize the ability of each node to broadcast and receive information. The computations involve basic operations in linear algebra, and the asymmetry caused by time's arrow is captured naturally through the noncommutativity of matrix-matrix multiplication. Illustrative examples are given for both synthetic and real-world communication data sets. We also discuss the use of the new centrality measures for real-time monitoring and prediction.

  13. Evolving Concepts of Asthma

    Science.gov (United States)

    Ray, Anuradha; Wenzel, Sally E.

    2015-01-01

    Our understanding of asthma has evolved over time from a singular disease to a complex of various phenotypes, with varied natural histories, physiologies, and responses to treatment. Early therapies treated most patients with asthma similarly, with bronchodilators and corticosteroids, but these therapies had varying degrees of success. Similarly, despite initial studies that identified an underlying type 2 inflammation in the airways of patients with asthma, biologic therapies targeted toward these type 2 pathways were unsuccessful in all patients. These observations led to increased interest in phenotyping asthma. Clinical approaches, both biased and later unbiased/statistical approaches to large asthma patient cohorts, identified a variety of patient characteristics, but they also consistently identified the importance of age of onset of disease and the presence of eosinophils in determining clinically relevant phenotypes. These paralleled molecular approaches to phenotyping that developed an understanding that not all patients share a type 2 inflammatory pattern. Using biomarkers to select patients with type 2 inflammation, repeated trials of biologics directed toward type 2 cytokine pathways saw newfound success, confirming the importance of phenotyping in asthma. Further research is needed to clarify additional clinical and molecular phenotypes, validate predictive biomarkers, and identify new areas for possible interventions. PMID:26161792

  14. UKAEA'S evolving contract philosophy

    International Nuclear Information System (INIS)

    Nicol, R. D.

    2003-01-01

    The United Kingdom Atomic Energy Authority (UKAEA) has gone through fundamental change over the last ten years. At the heart of this change has been UKAEA's relationship with the contracting and supply market. This paper describes the way in which UKAEA actively developed the market to support the decommissioning programme, and how the approach to contracting has evolved as external pressures and demands have changed. UKAEA's pro-active approach to industry has greatly assisted the development of a healthy, competitive market for services supporting decommissioning in the UK. There have been difficult changes and many challenges along the way, and some retrenchment was necessary to meet regulatory requirements. Nevertheless, UKAEA has sustained a high level of competition - now measured in terms of competed spend as a proportion of competable spend - with annual out-turns consistently over 80%. The prime responsibility for market development will pass to the new Nuclear Decommissioning Authority (NDA) in 2005, as the owner, on behalf of the Government, of the UK's civil nuclear liabilities. The preparatory work for the NDA indicates that the principles established by UKAEA will be carried forward. (author)

  15. Generalization in the XCSF classifier system: analysis, improvement, and extension.

    Science.gov (United States)

    Lanzi, Pier Luca; Loiacono, Daniele; Wilson, Stewart W; Goldberg, David E

    2007-01-01

    We analyze generalization in XCSF and introduce three improvements. We begin by showing that the types of generalizations evolved by XCSF can be influenced by the input range. To explain these results we present a theoretical analysis of the convergence of classifier weights in XCSF which highlights a broader issue. In XCSF, because of the mathematical properties of the Widrow-Hoff update, the convergence of classifier weights in a given subspace can be slow when the spread of the eigenvalues of the autocorrelation matrix associated with each classifier is large. As a major consequence, the system's accuracy pressure may act before classifier weights are adequately updated, so that XCSF may evolve piecewise constant approximations, instead of the intended, and more efficient, piecewise linear ones. We propose three different ways to update classifier weights in XCSF so as to increase the generalization capabilities of XCSF: one based on a condition-based normalization of the inputs, one based on linear least squares, and one based on the recursive version of linear least squares. Through a series of experiments we show that while all three approaches significantly improve XCSF, least squares approaches appear to be best performing and most robust. Finally we show how XCSF can be extended to include polynomial approximations.

  16. 3D Bayesian contextual classifiers

    DEFF Research Database (Denmark)

    Larsen, Rasmus

    2000-01-01

    We extend a series of multivariate Bayesian 2-D contextual classifiers to 3-D by specifying a simultaneous Gaussian distribution for the feature vectors as well as a prior distribution of the class variables of a pixel and its 6 nearest 3-D neighbours.......We extend a series of multivariate Bayesian 2-D contextual classifiers to 3-D by specifying a simultaneous Gaussian distribution for the feature vectors as well as a prior distribution of the class variables of a pixel and its 6 nearest 3-D neighbours....

  17. Knowledge Uncertainty and Composed Classifier

    Czech Academy of Sciences Publication Activity Database

    Klimešová, Dana; Ocelíková, E.

    2007-01-01

    Roč. 1, č. 2 (2007), s. 101-105 ISSN 1998-0140 Institutional research plan: CEZ:AV0Z10750506 Keywords : Boosting architecture * contextual modelling * composed classifier * knowledge management, * knowledge * uncertainty Subject RIV: IN - Informatics, Computer Science

  18. Correlation Dimension-Based Classifier

    Czech Academy of Sciences Publication Activity Database

    Jiřina, Marcel; Jiřina jr., M.

    2014-01-01

    Roč. 44, č. 12 (2014), s. 2253-2263 ISSN 2168-2267 R&D Projects: GA MŠk(CZ) LG12020 Institutional support: RVO:67985807 Keywords : classifier * multidimensional data * correlation dimension * scaling exponent * polynomial expansion Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 3.469, year: 2014

  19. An evolving approach to delirium: A mixed-methods process evaluation of a hospital-wide delirium program in New Zealand.

    Science.gov (United States)

    Alhaidari, Abdullah Ao; Allen-Narker, Rosalind Ac

    2017-06-01

    A process evaluation was carried out to assess and potentially improve the design and implementation of a hospital-wide delirium program. A mixed-methods sequential-explanatory design was used; retrospective chart reviews for 100 older (75+) medical inpatients were conducted to measure nurses', doctors' and coders' adherence to key program processes following which interviews were conducted to identify potential barriers to implementation. Delirium occurred in 49% of patients. Chart reviews revealed suboptimal adherence to the delirium risk assessment (66%), the Short Confusion Assessment Method (50% on admission, 58% during admission), documentation of delirium in clinical records (80%) and discharge letters (38%) and coding for delirium (49%). The major barriers to implementation identified were failure to recruit non-nursing staff, unclear goals and instructions, difficulties using the Short-CAM, time constraints with competing priorities and lack of outcome expectancy. A new delirium program was needed based on these findings. © 2017 AJA Inc.

  20. Disgust: Evolved function and structure

    NARCIS (Netherlands)

    Tybur, J.M.; Lieberman, D.; Kurzban, R.; DeScioli, P.

    2013-01-01

    Interest in and research on disgust has surged over the past few decades. The field, however, still lacks a coherent theoretical framework for understanding the evolved function or functions of disgust. Here we present such a framework, emphasizing 2 levels of analysis: that of evolved function and

  1. Natural selection promotes antigenic evolvability

    NARCIS (Netherlands)

    Graves, C.J.; Ros, V.I.D.; Stevenson, B.; Sniegowski, P.D.; Brisson, D.

    2013-01-01

    The hypothesis that evolvability - the capacity to evolve by natural selection - is itself the object of natural selection is highly intriguing but remains controversial due in large part to a paucity of direct experimental evidence. The antigenic variation mechanisms of microbial pathogens provide

  2. A Bayesian classifier for symbol recognition

    OpenAIRE

    Barrat , Sabine; Tabbone , Salvatore; Nourrissier , Patrick

    2007-01-01

    URL : http://www.buyans.com/POL/UploadedFile/134_9977.pdf; International audience; We present in this paper an original adaptation of Bayesian networks to symbol recognition problem. More precisely, a descriptor combination method, which enables to improve significantly the recognition rate compared to the recognition rates obtained by each descriptor, is presented. In this perspective, we use a simple Bayesian classifier, called naive Bayes. In fact, probabilistic graphical models, more spec...

  3. Measurably evolving populations

    DEFF Research Database (Denmark)

    Drummond, Alexei James; Pybus, Oliver George; Rambaut, Andrew

    2003-01-01

    The availability of nucleotide and amino acid sequences sampled at different points in time has fostered the development of new statistical methods that exploit this temporal dimension. Such sequences enable us to observe evolution in action and to estimate the rate and magnitude of evolutionary ...

  4. Classified facilities for environmental protection

    International Nuclear Information System (INIS)

    Anon.

    1993-02-01

    The legislation of the classified facilities governs most of the dangerous or polluting industries or fixed activities. It rests on the law of 9 July 1976 concerning facilities classified for environmental protection and its application decree of 21 September 1977. This legislation, the general texts of which appear in this volume 1, aims to prevent all the risks and the harmful effects coming from an installation (air, water or soil pollutions, wastes, even aesthetic breaches). The polluting or dangerous activities are defined in a list called nomenclature which subjects the facilities to a declaration or an authorization procedure. The authorization is delivered by the prefect at the end of an open and contradictory procedure after a public survey. In addition, the facilities can be subjected to technical regulations fixed by the Environment Minister (volume 2) or by the prefect for facilities subjected to declaration (volume 3). (A.B.)

  5. Methodical approaches to managing risks for endocrine diseases evolvement in children related to impacts of environmental factors occuring on areas aimed for development

    Directory of Open Access Journals (Sweden)

    K.P. Luzhetskiy

    2017-06-01

    Full Text Available It is vital to develop systems of preventing risk-associated pathology due to constantly high levels of endocrine diseases in children exposed to chemicals with trophic effects on endocrine system (lead, cadmium, manganese, chromium, nickel, benzene, phenol, formaldehyde, benzpyrene, chlorine-organic compounds, and nitrates. Applying risk management techniques is one of the most promising trends in prevention of diseases related to environmental impacts. We offer methodical approaches based on system combination of activities at various management levels aimed at improving risk-oriented model of surveillance and control. These approaches enable allowing for detected thropic risk factors in regional social-hygienic monitoring programs, implementing algorithms of case monitoring over exposed children population, and applying contemporary prevention technologies. Social-hygienic monitoring improvement at territorial level implies stricter control and more comprehensive lists of monitored components. This can be achieved by studying compounds which form risks for endocrine system, by working out scientific-methodological grounds for accounting chemical compounds which are trophic for endocrine system, as well as by refining volumes and contents of scheduled inspections performed at high risks objects together with laboratory examination of chemical compounds including those thropic for endocrine system. Local level includes algorithms and schemes of prevention activities aimed at early detection of endocrine disorders related to chemicals impacts. When we give grounds for personified technologies of endocrine diseases prevention (alimentary disorders, physical retardation and obesity related to impacts exerted by chemicals which are trophic for endocrine system we should remember that individual programs choice is based not only on their capacity to eliminate priority compounds determining total chemical load on a person faster but also on

  6. Energy-Efficient Neuromorphic Classifiers.

    Science.gov (United States)

    Martí, Daniel; Rigotti, Mattia; Seok, Mingoo; Fusi, Stefano

    2016-10-01

    Neuromorphic engineering combines the architectural and computational principles of systems neuroscience with semiconductor electronics, with the aim of building efficient and compact devices that mimic the synaptic and neural machinery of the brain. The energy consumptions promised by neuromorphic engineering are extremely low, comparable to those of the nervous system. Until now, however, the neuromorphic approach has been restricted to relatively simple circuits and specialized functions, thereby obfuscating a direct comparison of their energy consumption to that used by conventional von Neumann digital machines solving real-world tasks. Here we show that a recent technology developed by IBM can be leveraged to realize neuromorphic circuits that operate as classifiers of complex real-world stimuli. Specifically, we provide a set of general prescriptions to enable the practical implementation of neural architectures that compete with state-of-the-art classifiers. We also show that the energy consumption of these architectures, realized on the IBM chip, is typically two or more orders of magnitude lower than that of conventional digital machines implementing classifiers with comparable performance. Moreover, the spike-based dynamics display a trade-off between integration time and accuracy, which naturally translates into algorithms that can be flexibly deployed for either fast and approximate classifications, or more accurate classifications at the mere expense of longer running times and higher energy costs. This work finally proves that the neuromorphic approach can be efficiently used in real-world applications and has significant advantages over conventional digital devices when energy consumption is considered.

  7. EVOLVE : International Conference

    CERN Document Server

    Deutz, Andre; Schuetze, Oliver; Bäck, Thomas; Tantar, Emilia; Tantar, Alexandru-Adrian; Moral, Pierre; Legrand, Pierrick; Bouvry, Pascal; Coello, Carlos

    2013-01-01

    Numerical and computational methods are nowadays used in a wide range of contexts in complex systems research, biology, physics, and engineering.  Over the last decades different methodological schools have emerged with emphasis on different aspects of computation, such as nature-inspired algorithms, set oriented numerics, probabilistic systems and Monte Carlo methods. Due to the use of different terminologies and emphasis on different aspects of algorithmic performance there is a strong need for a more integrated view and opportunities for cross-fertilization across particular disciplines. These proceedings feature 20 original publications from distinguished authors in the cross-section of computational sciences, such as machine learning algorithms and probabilistic models, complex networks and fitness landscape analysis, set oriented numerics and cell mapping, evolutionary multiobjective optimization, diversity-oriented search, and the foundations of genetic programming algorithms. By presenting cutting ed...

  8. 76 FR 34761 - Classified National Security Information

    Science.gov (United States)

    2011-06-14

    ... MARINE MAMMAL COMMISSION Classified National Security Information [Directive 11-01] AGENCY: Marine... Commission's (MMC) policy on classified information, as directed by Information Security Oversight Office... of Executive Order 13526, ``Classified National Security Information,'' and 32 CFR part 2001...

  9. Optimization of short amino acid sequences classifier

    Science.gov (United States)

    Barcz, Aleksy; Szymański, Zbigniew

    This article describes processing methods used for short amino acid sequences classification. The data processed are 9-symbols string representations of amino acid sequences, divided into 49 data sets - each one containing samples labeled as reacting or not with given enzyme. The goal of the classification is to determine for a single enzyme, whether an amino acid sequence would react with it or not. Each data set is processed separately. Feature selection is performed to reduce the number of dimensions for each data set. The method used for feature selection consists of two phases. During the first phase, significant positions are selected using Classification and Regression Trees. Afterwards, symbols appearing at the selected positions are substituted with numeric values of amino acid properties taken from the AAindex database. In the second phase the new set of features is reduced using a correlation-based ranking formula and Gram-Schmidt orthogonalization. Finally, the preprocessed data is used for training LS-SVM classifiers. SPDE, an evolutionary algorithm, is used to obtain optimal hyperparameters for the LS-SVM classifier, such as error penalty parameter C and kernel-specific hyperparameters. A simple score penalty is used to adapt the SPDE algorithm to the task of selecting classifiers with best performance measures values.

  10. The evolving breast reconstruction

    DEFF Research Database (Denmark)

    Thomsen, Jørn Bo; Gunnarsson, Gudjon Leifur

    2014-01-01

    The aim of this editorial is to give an update on the use of the propeller thoracodorsal artery perforator flap (TAP/TDAP-flap) within the field of breast reconstruction. The TAP-flap can be dissected by a combined use of a monopolar cautery and a scalpel. Microsurgical instruments are generally...... not needed. The propeller TAP-flap can be designed in different ways, three of these have been published: (I) an oblique upwards design; (II) a horizontal design; (III) an oblique downward design. The latissimus dorsi-flap is a good and reliable option for breast reconstruction, but has been criticized...... for oncoplastic and reconstructive breast surgery and will certainly become an invaluable addition to breast reconstructive methods....

  11. Fisher classifier and its probability of error estimation

    Science.gov (United States)

    Chittineni, C. B.

    1979-01-01

    Computationally efficient expressions are derived for estimating the probability of error using the leave-one-out method. The optimal threshold for the classification of patterns projected onto Fisher's direction is derived. A simple generalization of the Fisher classifier to multiple classes is presented. Computational expressions are developed for estimating the probability of error of the multiclass Fisher classifier.

  12. Classifying spaces with virtually cyclic stabilizers for linear groups

    DEFF Research Database (Denmark)

    Degrijse, Dieter Dries; Köhl, Ralf; Petrosyan, Nansen

    2015-01-01

    We show that every discrete subgroup of GL(n, ℝ) admits a finite-dimensional classifying space with virtually cyclic stabilizers. Applying our methods to SL(3, ℤ), we obtain a four-dimensional classifying space with virtually cyclic stabilizers and a decomposition of the algebraic K-theory of its...

  13. Spacetimes containing slowly evolving horizons

    International Nuclear Information System (INIS)

    Kavanagh, William; Booth, Ivan

    2006-01-01

    Slowly evolving horizons are trapping horizons that are ''almost'' isolated horizons. This paper reviews their definition and discusses several spacetimes containing such structures. These include certain Vaidya and Tolman-Bondi solutions as well as (perturbatively) tidally distorted black holes. Taking into account the mass scales and orders of magnitude that arise in these calculations, we conjecture that slowly evolving horizons are the norm rather than the exception in astrophysical processes that involve stellar-scale black holes

  14. Natural selection promotes antigenic evolvability.

    Science.gov (United States)

    Graves, Christopher J; Ros, Vera I D; Stevenson, Brian; Sniegowski, Paul D; Brisson, Dustin

    2013-01-01

    The hypothesis that evolvability - the capacity to evolve by natural selection - is itself the object of natural selection is highly intriguing but remains controversial due in large part to a paucity of direct experimental evidence. The antigenic variation mechanisms of microbial pathogens provide an experimentally tractable system to test whether natural selection has favored mechanisms that increase evolvability. Many antigenic variation systems consist of paralogous unexpressed 'cassettes' that recombine into an expression site to rapidly alter the expressed protein. Importantly, the magnitude of antigenic change is a function of the genetic diversity among the unexpressed cassettes. Thus, evidence that selection favors among-cassette diversity is direct evidence that natural selection promotes antigenic evolvability. We used the Lyme disease bacterium, Borrelia burgdorferi, as a model to test the prediction that natural selection favors amino acid diversity among unexpressed vls cassettes and thereby promotes evolvability in a primary surface antigen, VlsE. The hypothesis that diversity among vls cassettes is favored by natural selection was supported in each B. burgdorferi strain analyzed using both classical (dN/dS ratios) and Bayesian population genetic analyses of genetic sequence data. This hypothesis was also supported by the conservation of highly mutable tandem-repeat structures across B. burgdorferi strains despite a near complete absence of sequence conservation. Diversification among vls cassettes due to natural selection and mutable repeat structures promotes long-term antigenic evolvability of VlsE. These findings provide a direct demonstration that molecular mechanisms that enhance evolvability of surface antigens are an evolutionary adaptation. The molecular evolutionary processes identified here can serve as a model for the evolution of antigenic evolvability in many pathogens which utilize similar strategies to establish chronic infections.

  15. Natural selection promotes antigenic evolvability.

    Directory of Open Access Journals (Sweden)

    Christopher J Graves

    Full Text Available The hypothesis that evolvability - the capacity to evolve by natural selection - is itself the object of natural selection is highly intriguing but remains controversial due in large part to a paucity of direct experimental evidence. The antigenic variation mechanisms of microbial pathogens provide an experimentally tractable system to test whether natural selection has favored mechanisms that increase evolvability. Many antigenic variation systems consist of paralogous unexpressed 'cassettes' that recombine into an expression site to rapidly alter the expressed protein. Importantly, the magnitude of antigenic change is a function of the genetic diversity among the unexpressed cassettes. Thus, evidence that selection favors among-cassette diversity is direct evidence that natural selection promotes antigenic evolvability. We used the Lyme disease bacterium, Borrelia burgdorferi, as a model to test the prediction that natural selection favors amino acid diversity among unexpressed vls cassettes and thereby promotes evolvability in a primary surface antigen, VlsE. The hypothesis that diversity among vls cassettes is favored by natural selection was supported in each B. burgdorferi strain analyzed using both classical (dN/dS ratios and Bayesian population genetic analyses of genetic sequence data. This hypothesis was also supported by the conservation of highly mutable tandem-repeat structures across B. burgdorferi strains despite a near complete absence of sequence conservation. Diversification among vls cassettes due to natural selection and mutable repeat structures promotes long-term antigenic evolvability of VlsE. These findings provide a direct demonstration that molecular mechanisms that enhance evolvability of surface antigens are an evolutionary adaptation. The molecular evolutionary processes identified here can serve as a model for the evolution of antigenic evolvability in many pathogens which utilize similar strategies to establish

  16. Classifying Coding DNA with Nucleotide Statistics

    Directory of Open Access Journals (Sweden)

    Nicolas Carels

    2009-10-01

    Full Text Available In this report, we compared the success rate of classification of coding sequences (CDS vs. introns by Codon Structure Factor (CSF and by a method that we called Universal Feature Method (UFM. UFM is based on the scoring of purine bias (Rrr and stop codon frequency. We show that the success rate of CDS/intron classification by UFM is higher than by CSF. UFM classifies ORFs as coding or non-coding through a score based on (i the stop codon distribution, (ii the product of purine probabilities in the three positions of nucleotide triplets, (iii the product of Cytosine (C, Guanine (G, and Adenine (A probabilities in the 1st, 2nd, and 3rd positions of triplets, respectively, (iv the probabilities of G in 1st and 2nd position of triplets and (v the distance of their GC3 vs. GC2 levels to the regression line of the universal correlation. More than 80% of CDSs (true positives of Homo sapiens (>250 bp, Drosophila melanogaster (>250 bp and Arabidopsis thaliana (>200 bp are successfully classified with a false positive rate lower or equal to 5%. The method releases coding sequences in their coding strand and coding frame, which allows their automatic translation into protein sequences with 95% confidence. The method is a natural consequence of the compositional bias of nucleotides in coding sequences.

  17. Robustness to Faults Promotes Evolvability: Insights from Evolving Digital Circuits.

    Science.gov (United States)

    Milano, Nicola; Nolfi, Stefano

    2016-01-01

    We demonstrate how the need to cope with operational faults enables evolving circuits to find more fit solutions. The analysis of the results obtained in different experimental conditions indicates that, in absence of faults, evolution tends to select circuits that are small and have low phenotypic variability and evolvability. The need to face operation faults, instead, drives evolution toward the selection of larger circuits that are truly robust with respect to genetic variations and that have a greater level of phenotypic variability and evolvability. Overall our results indicate that the need to cope with operation faults leads to the selection of circuits that have a greater probability to generate better circuits as a result of genetic variation with respect to a control condition in which circuits are not subjected to faults.

  18. Waste classifying and separation device

    International Nuclear Information System (INIS)

    Kakiuchi, Hiroki.

    1997-01-01

    A flexible plastic bags containing solid wastes of indefinite shape is broken and the wastes are classified. The bag cutting-portion of the device has an ultrasonic-type or a heater-type cutting means, and the cutting means moves in parallel with the transferring direction of the plastic bags. A classification portion separates and discriminates the plastic bag from the contents and conducts classification while rotating a classification table. Accordingly, the plastic bag containing solids of indefinite shape can be broken and classification can be conducted efficiently and reliably. The device of the present invention has a simple structure which requires small installation space and enables easy maintenance. (T.M.)

  19. Defining and Classifying Interest Groups

    DEFF Research Database (Denmark)

    Baroni, Laura; Carroll, Brendan; Chalmers, Adam

    2014-01-01

    The interest group concept is defined in many different ways in the existing literature and a range of different classification schemes are employed. This complicates comparisons between different studies and their findings. One of the important tasks faced by interest group scholars engaged...... in large-N studies is therefore to define the concept of an interest group and to determine which classification scheme to use for different group types. After reviewing the existing literature, this article sets out to compare different approaches to defining and classifying interest groups with a sample...... in the organizational attributes of specific interest group types. As expected, our comparison of coding schemes reveals a closer link between group attributes and group type in narrower classification schemes based on group organizational characteristics than those based on a behavioral definition of lobbying....

  20. Classifying smoking urges via machine learning.

    Science.gov (United States)

    Dumortier, Antoine; Beckjord, Ellen; Shiffman, Saul; Sejdić, Ervin

    2016-12-01

    Smoking is the largest preventable cause of death and diseases in the developed world, and advances in modern electronics and machine learning can help us deliver real-time intervention to smokers in novel ways. In this paper, we examine different machine learning approaches to use situational features associated with having or not having urges to smoke during a quit attempt in order to accurately classify high-urge states. To test our machine learning approaches, specifically, Bayes, discriminant analysis and decision tree learning methods, we used a dataset collected from over 300 participants who had initiated a quit attempt. The three classification approaches are evaluated observing sensitivity, specificity, accuracy and precision. The outcome of the analysis showed that algorithms based on feature selection make it possible to obtain high classification rates with only a few features selected from the entire dataset. The classification tree method outperformed the naive Bayes and discriminant analysis methods, with an accuracy of the classifications up to 86%. These numbers suggest that machine learning may be a suitable approach to deal with smoking cessation matters, and to predict smoking urges, outlining a potential use for mobile health applications. In conclusion, machine learning classifiers can help identify smoking situations, and the search for the best features and classifier parameters significantly improves the algorithms' performance. In addition, this study also supports the usefulness of new technologies in improving the effect of smoking cessation interventions, the management of time and patients by therapists, and thus the optimization of available health care resources. Future studies should focus on providing more adaptive and personalized support to people who really need it, in a minimum amount of time by developing novel expert systems capable of delivering real-time interventions. Copyright © 2016 Elsevier Ireland Ltd. All rights

  1. Gearbox Condition Monitoring Using Advanced Classifiers

    Directory of Open Access Journals (Sweden)

    P. Večeř

    2010-01-01

    Full Text Available New efficient and reliable methods for gearbox diagnostics are needed in automotive industry because of growing demand for production quality. This paper presents the application of two different classifiers for gearbox diagnostics – Kohonen Neural Networks and the Adaptive-Network-based Fuzzy Interface System (ANFIS. Two different practical applications are presented. In the first application, the tested gearboxes are separated into two classes according to their condition indicators. In the second example, ANFIS is applied to label the tested gearboxes with a Quality Index according to the condition indicators. In both applications, the condition indicators were computed from the vibration of the gearbox housing. 

  2. Double Ramp Loss Based Reject Option Classifier

    Science.gov (United States)

    2015-05-22

    of convex (DC) functions. To minimize it, we use DC programming approach [1]. The proposed method has following advantages: (1) the proposed loss LDR ...space constraints. We see that LDR does not put any restriction on ρ for it to be an upper bound of L0−d−1. 2.2 Risk Formulation Using LDR Let S = {(xn...classifier learnt using LDR based approach (C = 100, μ = 1, d = .2). Filled circles and triangles represent the support vectors. 4 Experimental Results We show

  3. A systematic comparison of supervised classifiers.

    Directory of Open Access Journals (Sweden)

    Diego Raphael Amancio

    Full Text Available Pattern recognition has been employed in a myriad of industrial, commercial and academic applications. Many techniques have been devised to tackle such a diversity of applications. Despite the long tradition of pattern recognition research, there is no technique that yields the best classification in all scenarios. Therefore, as many techniques as possible should be considered in high accuracy applications. Typical related works either focus on the performance of a given algorithm or compare various classification methods. In many occasions, however, researchers who are not experts in the field of machine learning have to deal with practical classification tasks without an in-depth knowledge about the underlying parameters. Actually, the adequate choice of classifiers and parameters in such practical circumstances constitutes a long-standing problem and is one of the subjects of the current paper. We carried out a performance study of nine well-known classifiers implemented in the Weka framework and compared the influence of the parameter configurations on the accuracy. The default configuration of parameters in Weka was found to provide near optimal performance for most cases, not including methods such as the support vector machine (SVM. In addition, the k-nearest neighbor method frequently allowed the best accuracy. In certain conditions, it was possible to improve the quality of SVM by more than 20% with respect to their default parameter configuration.

  4. A neighbourhood evolving network model

    International Nuclear Information System (INIS)

    Cao, Y.J.; Wang, G.Z.; Jiang, Q.Y.; Han, Z.X.

    2006-01-01

    Many social, technological, biological and economical systems are best described by evolved network models. In this short Letter, we propose and study a new evolving network model. The model is based on the new concept of neighbourhood connectivity, which exists in many physical complex networks. The statistical properties and dynamics of the proposed model is analytically studied and compared with those of Barabasi-Albert scale-free model. Numerical simulations indicate that this network model yields a transition between power-law and exponential scaling, while the Barabasi-Albert scale-free model is only one of its special (limiting) cases. Particularly, this model can be used to enhance the evolving mechanism of complex networks in the real world, such as some social networks development

  5. 6 CFR 7.23 - Emergency release of classified information.

    Science.gov (United States)

    2010-01-01

    ... Classified Information Non-disclosure Form. In emergency situations requiring immediate verbal release of... information through approved communication channels by the most secure and expeditious method possible, or by...

  6. Intelligent Recognition of Lung Nodule Combining Rule-based and C-SVM Classifiers

    Directory of Open Access Journals (Sweden)

    Bin Li

    2011-10-01

    Full Text Available Computer-aided detection(CAD system for lung nodules plays the important role in the diagnosis of lung cancer. In this paper, an improved intelligent recognition method of lung nodule in HRCT combing rule-based and costsensitive support vector machine(C-SVM classifiers is proposed for detecting both solid nodules and ground-glass opacity(GGO nodules(part solid and nonsolid. This method consists of several steps. Firstly, segmentation of regions of interest(ROIs, including pulmonary parenchyma and lung nodule candidates, is a difficult task. On one side, the presence of noise lowers the visibility of low-contrast objects. On the other side, different types of nodules, including small nodules, nodules connecting to vasculature or other structures, part-solid or nonsolid nodules, are complex, noisy, weak edge or difficult to define the boundary. In order to overcome the difficulties of obvious boundary-leak and slow evolvement speed problem in segmentatioin of weak edge, an overall segmentation method is proposed, they are: the lung parenchyma is extracted based on threshold and morphologic segmentation method; the image denoising and enhancing is realized by nonlinear anisotropic diffusion filtering(NADF method;candidate pulmonary nodules are segmented by the improved C-V level set method, in which the segmentation result of EM-based fuzzy threshold method is used as the initial contour of active contour model and a constrained energy term is added into the PDE of level set function. Then, lung nodules are classified by using the intelligent classifiers combining rules and C-SVM. Rule-based classification is first used to remove easily dismissible nonnodule objects, then C-SVM classification are used to further classify nodule candidates and reduce the number of false positive(FP objects. In order to increase the efficiency of SVM, an improved training method is used to train SVM, which uses the grid search method to search the optimal parameters

  7. Intelligent Recognition of Lung Nodule Combining Rule-based and C-SVM Classifiers

    Directory of Open Access Journals (Sweden)

    Bin Li

    2012-02-01

    Full Text Available Computer-aided detection(CAD system for lung nodules plays the important role in the diagnosis of lung cancer. In this paper, an improved intelligent recognition method of lung nodule in HRCT combing rule-based and cost-sensitive support vector machine(C-SVM classifiers is proposed for detecting both solid nodules and ground-glass opacity(GGO nodules(part solid and nonsolid. This method consists of several steps. Firstly, segmentation of regions of interest(ROIs, including pulmonary parenchyma and lung nodule candidates, is a difficult task. On one side, the presence of noise lowers the visibility of low-contrast objects. On the other side, different types of nodules, including small nodules, nodules connecting to vasculature or other structures, part-solid or nonsolid nodules, are complex, noisy, weak edge or difficult to define the boundary. In order to overcome the difficulties of obvious boundary-leak and slow evolvement speed problem in segmentatioin of weak edge, an overall segmentation method is proposed, they are: the lung parenchyma is extracted based on threshold and morphologic segmentation method; the image denoising and enhancing is realized by nonlinear anisotropic diffusion filtering(NADF method; candidate pulmonary nodules are segmented by the improved C-V level set method, in which the segmentation result of EM-based fuzzy threshold method is used as the initial contour of active contour model and a constrained energy term is added into the PDE of level set function. Then, lung nodules are classified by using the intelligent classifiers combining rules and C-SVM. Rule-based classification is first used to remove easily dismissible nonnodule objects, then C-SVM classification are used to further classify nodule candidates and reduce the number of false positive(FP objects. In order to increase the efficiency of SVM, an improved training method is used to train SVM, which uses the grid search method to search the optimal

  8. Multimodal fusion of polynomial classifiers for automatic person recgonition

    Science.gov (United States)

    Broun, Charles C.; Zhang, Xiaozheng

    2001-03-01

    With the prevalence of the information age, privacy and personalization are forefront in today's society. As such, biometrics are viewed as essential components of current evolving technological systems. Consumers demand unobtrusive and non-invasive approaches. In our previous work, we have demonstrated a speaker verification system that meets these criteria. However, there are additional constraints for fielded systems. The required recognition transactions are often performed in adverse environments and across diverse populations, necessitating robust solutions. There are two significant problem areas in current generation speaker verification systems. The first is the difficulty in acquiring clean audio signals in all environments without encumbering the user with a head- mounted close-talking microphone. Second, unimodal biometric systems do not work with a significant percentage of the population. To combat these issues, multimodal techniques are being investigated to improve system robustness to environmental conditions, as well as improve overall accuracy across the population. We propose a multi modal approach that builds on our current state-of-the-art speaker verification technology. In order to maintain the transparent nature of the speech interface, we focus on optical sensing technology to provide the additional modality-giving us an audio-visual person recognition system. For the audio domain, we use our existing speaker verification system. For the visual domain, we focus on lip motion. This is chosen, rather than static face or iris recognition, because it provides dynamic information about the individual. In addition, the lip dynamics can aid speech recognition to provide liveness testing. The visual processing method makes use of both color and edge information, combined within Markov random field MRF framework, to localize the lips. Geometric features are extracted and input to a polynomial classifier for the person recognition process. A late

  9. Composite Classifiers for Automatic Target Recognition

    National Research Council Canada - National Science Library

    Wang, Lin-Cheng

    1998-01-01

    ...) using forward-looking infrared (FLIR) imagery. Two existing classifiers, one based on learning vector quantization and the other on modular neural networks, are used as the building blocks for our composite classifiers...

  10. Aggregation Operator Based Fuzzy Pattern Classifier Design

    DEFF Research Database (Denmark)

    Mönks, Uwe; Larsen, Henrik Legind; Lohweg, Volker

    2009-01-01

    This paper presents a novel modular fuzzy pattern classifier design framework for intelligent automation systems, developed on the base of the established Modified Fuzzy Pattern Classifier (MFPC) and allows designing novel classifier models which are hardware-efficiently implementable....... The performances of novel classifiers using substitutes of MFPC's geometric mean aggregator are benchmarked in the scope of an image processing application against the MFPC to reveal classification improvement potentials for obtaining higher classification rates....

  11. 15 CFR 4.8 - Classified Information.

    Science.gov (United States)

    2010-01-01

    ... 15 Commerce and Foreign Trade 1 2010-01-01 2010-01-01 false Classified Information. 4.8 Section 4... INFORMATION Freedom of Information Act § 4.8 Classified Information. In processing a request for information..., the information shall be reviewed to determine whether it should remain classified. Ordinarily the...

  12. Evolving Random Forest for Preference Learning

    DEFF Research Database (Denmark)

    Abou-Zleikha, Mohamed; Shaker, Noor

    2015-01-01

    This paper introduces a novel approach for pairwise preference learning through a combination of an evolutionary method and random forest. Grammatical evolution is used to describe the structure of the trees in the Random Forest (RF) and to handle the process of evolution. Evolved random forests ...... obtained for predicting pairwise self-reports of users for the three emotional states engagement, frustration and challenge show very promising results that are comparable and in some cases superior to those obtained from state-of-the-art methods....

  13. Mercury⊕: An evidential reasoning image classifier

    Science.gov (United States)

    Peddle, Derek R.

    1995-12-01

    MERCURY⊕ is a multisource evidential reasoning classification software system based on the Dempster-Shafer theory of evidence. The design and implementation of this software package is described for improving the classification and analysis of multisource digital image data necessary for addressing advanced environmental and geoscience applications. In the remote-sensing context, the approach provides a more appropriate framework for classifying modern, multisource, and ancillary data sets which may contain a large number of disparate variables with different statistical properties, scales of measurement, and levels of error which cannot be handled using conventional Bayesian approaches. The software uses a nonparametric, supervised approach to classification, and provides a more objective and flexible interface to the evidential reasoning framework using a frequency-based method for computing support values from training data. The MERCURY⊕ software package has been implemented efficiently in the C programming language, with extensive use made of dynamic memory allocation procedures and compound linked list and hash-table data structures to optimize the storage and retrieval of evidence in a Knowledge Look-up Table. The software is complete with a full user interface and runs under Unix, Ultrix, VAX/VMS, MS-DOS, and Apple Macintosh operating system. An example of classifying alpine land cover and permafrost active layer depth in northern Canada is presented to illustrate the use and application of these ideas.

  14. Ship localization in Santa Barbara Channel using machine learning classifiers.

    Science.gov (United States)

    Niu, Haiqiang; Ozanich, Emma; Gerstoft, Peter

    2017-11-01

    Machine learning classifiers are shown to outperform conventional matched field processing for a deep water (600 m depth) ocean acoustic-based ship range estimation problem in the Santa Barbara Channel Experiment when limited environmental information is known. Recordings of three different ships of opportunity on a vertical array were used as training and test data for the feed-forward neural network and support vector machine classifiers, demonstrating the feasibility of machine learning methods to locate unseen sources. The classifiers perform well up to 10 km range whereas the conventional matched field processing fails at about 4 km range without accurate environmental information.

  15. Classifying polynomials and identity testing

    Indian Academy of Sciences (India)

    years, progress has been made in designing deterministic algorithms for restricted ... Research supported by J C Bose Fellowship ...... This method fails if T1 happens to have repeated ..... formulas, maximal-partition discrepancy and mixed-.

  16. An ensemble classifier to predict track geometry degradation

    International Nuclear Information System (INIS)

    Cárdenas-Gallo, Iván; Sarmiento, Carlos A.; Morales, Gilberto A.; Bolivar, Manuel A.; Akhavan-Tabatabaei, Raha

    2017-01-01

    Railway operations are inherently complex and source of several problems. In particular, track geometry defects are one of the leading causes of train accidents in the United States. This paper presents a solution approach which entails the construction of an ensemble classifier to forecast the degradation of track geometry. Our classifier is constructed by solving the problem from three different perspectives: deterioration, regression and classification. We considered a different model from each perspective and our results show that using an ensemble method improves the predictive performance. - Highlights: • We present an ensemble classifier to forecast the degradation of track geometry. • Our classifier considers three perspectives: deterioration, regression and classification. • We construct and test three models and our results show that using an ensemble method improves the predictive performance.

  17. Ranking in evolving complex networks

    Science.gov (United States)

    Liao, Hao; Mariani, Manuel Sebastian; Medo, Matúš; Zhang, Yi-Cheng; Zhou, Ming-Yang

    2017-05-01

    Complex networks have emerged as a simple yet powerful framework to represent and analyze a wide range of complex systems. The problem of ranking the nodes and the edges in complex networks is critical for a broad range of real-world problems because it affects how we access online information and products, how success and talent are evaluated in human activities, and how scarce resources are allocated by companies and policymakers, among others. This calls for a deep understanding of how existing ranking algorithms perform, and which are their possible biases that may impair their effectiveness. Many popular ranking algorithms (such as Google's PageRank) are static in nature and, as a consequence, they exhibit important shortcomings when applied to real networks that rapidly evolve in time. At the same time, recent advances in the understanding and modeling of evolving networks have enabled the development of a wide and diverse range of ranking algorithms that take the temporal dimension into account. The aim of this review is to survey the existing ranking algorithms, both static and time-aware, and their applications to evolving networks. We emphasize both the impact of network evolution on well-established static algorithms and the benefits from including the temporal dimension for tasks such as prediction of network traffic, prediction of future links, and identification of significant nodes.

  18. Adaptive Framework for Classification and Novel Class Detection over Evolving Data Streams with Limited Labeled Data.

    Energy Technology Data Exchange (ETDEWEB)

    Haque, Ahsanul [Univ. of Texas, Dallas, TX (United States); Khan, Latifur [Univ. of Texas, Dallas, TX (United States); Baron, Michael [Univ. of Texas, Dallas, TX (United States); Ingram, Joey Burton [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)

    2015-09-01

    Most approaches to classifying evolving data streams either divide the stream of data into fixed-size chunks or use gradual forgetting to address the problems of infinite length and concept drift. Finding the fixed size of the chunks or choosing a forgetting rate without prior knowledge about time-scale of change is not a trivial task. As a result, these approaches suffer from a trade-off between performance and sensitivity. To address this problem, we present a framework which uses change detection techniques on the classifier performance to determine chunk boundaries dynamically. Though this framework exhibits good performance, it is heavily dependent on the availability of true labels of data instances. However, labeled data instances are scarce in realistic settings and not readily available. Therefore, we present a second framework which is unsupervised in nature, and exploits change detection on classifier confidence values to determine chunk boundaries dynamically. In this way, it avoids the use of labeled data while still addressing the problems of infinite length and concept drift. Moreover, both of our proposed frameworks address the concept evolution problem by detecting outliers having similar values for the attributes. We provide theoretical proof that our change detection method works better than other state-of-the-art approaches in this particular scenario. Results from experiments on various benchmark and synthetic data sets also show the efficiency of our proposed frameworks.

  19. Local-global classifier fusion for screening chest radiographs

    Science.gov (United States)

    Ding, Meng; Antani, Sameer; Jaeger, Stefan; Xue, Zhiyun; Candemir, Sema; Kohli, Marc; Thoma, George

    2017-03-01

    Tuberculosis (TB) is a severe comorbidity of HIV and chest x-ray (CXR) analysis is a necessary step in screening for the infective disease. Automatic analysis of digital CXR images for detecting pulmonary abnormalities is critical for population screening, especially in medical resource constrained developing regions. In this article, we describe steps that improve previously reported performance of NLM's CXR screening algorithms and help advance the state of the art in the field. We propose a local-global classifier fusion method where two complementary classification systems are combined. The local classifier focuses on subtle and partial presentation of the disease leveraging information in radiology reports that roughly indicates locations of the abnormalities. In addition, the global classifier models the dominant spatial structure in the gestalt image using GIST descriptor for the semantic differentiation. Finally, the two complementary classifiers are combined using linear fusion, where the weight of each decision is calculated by the confidence probabilities from the two classifiers. We evaluated our method on three datasets in terms of the area under the Receiver Operating Characteristic (ROC) curve, sensitivity, specificity and accuracy. The evaluation demonstrates the superiority of our proposed local-global fusion method over any single classifier.

  20. Adaptive Regularization of Neural Classifiers

    DEFF Research Database (Denmark)

    Andersen, Lars Nonboe; Larsen, Jan; Hansen, Lars Kai

    1997-01-01

    We present a regularization scheme which iteratively adapts the regularization parameters by minimizing the validation error. It is suggested to use the adaptive regularization scheme in conjunction with optimal brain damage pruning to optimize the architecture and to avoid overfitting. Furthermo......, we propose an improved neural classification architecture eliminating an inherent redundancy in the widely used SoftMax classification network. Numerical results demonstrate the viability of the method...

  1. Evaluating the Performance of Multiple Classifier Systems: A Matrix Algebra Representation of Boolean Fusion Rules

    National Research Council Canada - National Science Library

    Hill, Justin

    2003-01-01

    ...., a logical OR, AND, or a majority vote of the classifiers in the system). An established method for evaluating a classifier is measuring some aspect of its Receiver Operating Characteristic (ROC...

  2. Error minimizing algorithms for nearest eighbor classifiers

    Energy Technology Data Exchange (ETDEWEB)

    Porter, Reid B [Los Alamos National Laboratory; Hush, Don [Los Alamos National Laboratory; Zimmer, G. Beate [TEXAS A& M

    2011-01-03

    Stack Filters define a large class of discrete nonlinear filter first introd uced in image and signal processing for noise removal. In recent years we have suggested their application to classification problems, and investigated their relationship to other types of discrete classifiers such as Decision Trees. In this paper we focus on a continuous domain version of Stack Filter Classifiers which we call Ordered Hypothesis Machines (OHM), and investigate their relationship to Nearest Neighbor classifiers. We show that OHM classifiers provide a novel framework in which to train Nearest Neighbor type classifiers by minimizing empirical error based loss functions. We use the framework to investigate a new cost sensitive loss function that allows us to train a Nearest Neighbor type classifier for low false alarm rate applications. We report results on both synthetic data and real-world image data.

  3. An evolving network model with community structure

    International Nuclear Information System (INIS)

    Li Chunguang; Maini, Philip K

    2005-01-01

    Many social and biological networks consist of communities-groups of nodes within which connections are dense, but between which connections are sparser. Recently, there has been considerable interest in designing algorithms for detecting community structures in real-world complex networks. In this paper, we propose an evolving network model which exhibits community structure. The network model is based on the inner-community preferential attachment and inter-community preferential attachment mechanisms. The degree distributions of this network model are analysed based on a mean-field method. Theoretical results and numerical simulations indicate that this network model has community structure and scale-free properties

  4. Robust Combining of Disparate Classifiers Through Order Statistics

    Science.gov (United States)

    Tumer, Kagan; Ghosh, Joydeep

    2001-01-01

    Integrating the outputs of multiple classifiers via combiners or meta-learners has led to substantial improvements in several difficult pattern recognition problems. In this article we investigate a family of combiners based on order statistics, for robust handling of situations where there are large discrepancies in performance of individual classifiers. Based on a mathematical modeling of how the decision boundaries are affected by order statistic combiners, we derive expressions for the reductions in error expected when simple output combination methods based on the the median, the maximum and in general, the ith order statistic, are used. Furthermore, we analyze the trim and spread combiners, both based on linear combinations of the ordered classifier outputs, and show that in the presence of uneven classifier performance, they often provide substantial gains over both linear and simple order statistics combiners. Experimental results on both real world data and standard public domain data sets corroborate these findings.

  5. Verification of classified fissile material using unclassified attributes

    International Nuclear Information System (INIS)

    Nicholas, N.J.; Fearey, B.L.; Puckett, J.M.; Tape, J.W.

    1998-01-01

    This paper reports on the most recent efforts of US technical experts to explore verification by IAEA of unclassified attributes of classified excess fissile material. Two propositions are discussed: (1) that multiple unclassified attributes could be declared by the host nation and then verified (and reverified) by the IAEA in order to provide confidence in that declaration of a classified (or unclassified) inventory while protecting classified or sensitive information; and (2) that attributes could be measured, remeasured, or monitored to provide continuity of knowledge in a nonintrusive and unclassified manner. They believe attributes should relate to characteristics of excess weapons materials and should be verifiable and authenticatable with methods usable by IAEA inspectors. Further, attributes (along with the methods to measure them) must not reveal any classified information. The approach that the authors have taken is as follows: (1) assume certain attributes of classified excess material, (2) identify passive signatures, (3) determine range of applicable measurement physics, (4) develop a set of criteria to assess and select measurement technologies, (5) select existing instrumentation for proof-of-principle measurements and demonstration, and (6) develop and design information barriers to protect classified information. While the attribute verification concepts and measurements discussed in this paper appear promising, neither the attribute verification approach nor the measurement technologies have been fully developed, tested, and evaluated

  6. Defending Malicious Script Attacks Using Machine Learning Classifiers

    Directory of Open Access Journals (Sweden)

    Nayeem Khan

    2017-01-01

    Full Text Available The web application has become a primary target for cyber criminals by injecting malware especially JavaScript to perform malicious activities for impersonation. Thus, it becomes an imperative to detect such malicious code in real time before any malicious activity is performed. This study proposes an efficient method of detecting previously unknown malicious java scripts using an interceptor at the client side by classifying the key features of the malicious code. Feature subset was obtained by using wrapper method for dimensionality reduction. Supervised machine learning classifiers were used on the dataset for achieving high accuracy. Experimental results show that our method can efficiently classify malicious code from benign code with promising results.

  7. Hierarchical mixtures of naive Bayes classifiers

    NARCIS (Netherlands)

    Wiering, M.A.

    2002-01-01

    Naive Bayes classifiers tend to perform very well on a large number of problem domains, although their representation power is quite limited compared to more sophisticated machine learning algorithms. In this pa- per we study combining multiple naive Bayes classifiers by using the hierar- chical

  8. Comparing classifiers for pronunciation error detection

    NARCIS (Netherlands)

    Strik, H.; Truong, K.; Wet, F. de; Cucchiarini, C.

    2007-01-01

    Providing feedback on pronunciation errors in computer assisted language learning systems requires that pronunciation errors be detected automatically. In the present study we compare four types of classifiers that can be used for this purpose: two acoustic-phonetic classifiers (one of which employs

  9. Feature extraction for dynamic integration of classifiers

    NARCIS (Netherlands)

    Pechenizkiy, M.; Tsymbal, A.; Puuronen, S.; Patterson, D.W.

    2007-01-01

    Recent research has shown the integration of multiple classifiers to be one of the most important directions in machine learning and data mining. In this paper, we present an algorithm for the dynamic integration of classifiers in the space of extracted features (FEDIC). It is based on the technique

  10. Wavelet classifier used for diagnosing shock absorbers in cars

    Directory of Open Access Journals (Sweden)

    Janusz GARDULSKI

    2007-01-01

    Full Text Available The paper discusses some commonly used methods of hydraulic absorbertesting. Disadvantages of the methods are described. A vibro-acoustic method is presented and recommended for practical use on existing test rigs. The method is based on continuous wavelet analysis combined with neural classifier and 25-neuron, one-way, three-layer back propagation network. The analysis satisfies the intended aim.

  11. A cardiorespiratory classifier of voluntary and involuntary electrodermal activity

    Directory of Open Access Journals (Sweden)

    Sejdic Ervin

    2010-02-01

    Full Text Available Abstract Background Electrodermal reactions (EDRs can be attributed to many origins, including spontaneous fluctuations of electrodermal activity (EDA and stimuli such as deep inspirations, voluntary mental activity and startling events. In fields that use EDA as a measure of psychophysiological state, the fact that EDRs may be elicited from many different stimuli is often ignored. This study attempts to classify observed EDRs as voluntary (i.e., generated from intentional respiratory or mental activity or involuntary (i.e., generated from startling events or spontaneous electrodermal fluctuations. Methods Eight able-bodied participants were subjected to conditions that would cause a change in EDA: music imagery, startling noises, and deep inspirations. A user-centered cardiorespiratory classifier consisting of 1 an EDR detector, 2 a respiratory filter and 3 a cardiorespiratory filter was developed to automatically detect a participant's EDRs and to classify the origin of their stimulation as voluntary or involuntary. Results Detected EDRs were classified with a positive predictive value of 78%, a negative predictive value of 81% and an overall accuracy of 78%. Without the classifier, EDRs could only be correctly attributed as voluntary or involuntary with an accuracy of 50%. Conclusions The proposed classifier may enable investigators to form more accurate interpretations of electrodermal activity as a measure of an individual's psychophysiological state.

  12. Design of a high-sensitivity classifier based on a genetic algorithm: application to computer-aided diagnosis

    International Nuclear Information System (INIS)

    Sahiner, Berkman; Chan, Heang-Ping; Petrick, Nicholas; Helvie, Mark A.; Goodsitt, Mitchell M.

    1998-01-01

    A genetic algorithm (GA) based feature selection method was developed for the design of high-sensitivity classifiers, which were tailored to yield high sensitivity with high specificity. The fitness function of the GA was based on the receiver operating characteristic (ROC) partial area index, which is defined as the average specificity above a given sensitivity threshold. The designed GA evolved towards the selection of feature combinations which yielded high specificity in the high-sensitivity region of the ROC curve, regardless of the performance at low sensitivity. This is a desirable quality of a classifier used for breast lesion characterization, since the focus in breast lesion characterization is to diagnose correctly as many benign lesions as possible without missing malignancies. The high-sensitivity classifier, formulated as the Fisher's linear discriminant using GA-selected feature variables, was employed to classify 255 biopsy-proven mammographic masses as malignant or benign. The mammograms were digitized at a pixel size of 0.1mmx0.1mm, and regions of interest (ROIs) containing the biopsied masses were extracted by an experienced radiologist. A recently developed image transformation technique, referred to as the rubber-band straightening transform, was applied to the ROIs. Texture features extracted from the spatial grey-level dependence and run-length statistics matrices of the transformed ROIs were used to distinguish malignant and benign masses. The classification accuracy of the high-sensitivity classifier was compared with that of linear discriminant analysis with stepwise feature selection (LDA sfs ). With proper GA training, the ROC partial area of the high-sensitivity classifier above a true-positive fraction of 0.95 was significantly larger than that of LDA sfs , although the latter provided a higher total area (A z ) under the ROC curve. By setting an appropriate decision threshold, the high-sensitivity classifier and LDA sfs correctly

  13. Deconvolution When Classifying Noisy Data Involving Transformations

    KAUST Repository

    Carroll, Raymond

    2012-09-01

    In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.

  14. Deconvolution When Classifying Noisy Data Involving Transformations.

    Science.gov (United States)

    Carroll, Raymond; Delaigle, Aurore; Hall, Peter

    2012-09-01

    In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.

  15. Deconvolution When Classifying Noisy Data Involving Transformations

    KAUST Repository

    Carroll, Raymond; Delaigle, Aurore; Hall, Peter

    2012-01-01

    In the present study, we consider the problem of classifying spatial data distorted by a linear transformation or convolution and contaminated by additive random noise. In this setting, we show that classifier performance can be improved if we carefully invert the data before the classifier is applied. However, the inverse transformation is not constructed so as to recover the original signal, and in fact, we show that taking the latter approach is generally inadvisable. We introduce a fully data-driven procedure based on cross-validation, and use several classifiers to illustrate numerical properties of our approach. Theoretical arguments are given in support of our claims. Our procedure is applied to data generated by light detection and ranging (Lidar) technology, where we improve on earlier approaches to classifying aerosols. This article has supplementary materials online.

  16. Peripartum hysterectomy: an evolving picture.

    LENUS (Irish Health Repository)

    Turner, Michael J

    2012-02-01

    Peripartum hysterectomy (PH) is one of the obstetric catastrophes. Evidence is emerging that the role of PH in modern obstetrics is evolving. Improving management of postpartum hemorrhage and newer surgical techniques should decrease PH for uterine atony. Rising levels of repeat elective cesarean deliveries should decrease PH following uterine scar rupture in labor. Increasing cesarean rates, however, have led to an increase in the number of PHs for morbidly adherent placenta. In the case of uterine atony or rupture where PH is required, a subtotal PH is often sufficient. In the case of pathological placental localization involving the cervix, however, a total hysterectomy is required. Furthermore, the involvement of other pelvic structures may prospectively make the diagnosis difficult and the surgery challenging. If resources permit, PH for pathological placental localization merits a multidisciplinary approach. Despite advances in clinical practice, it is likely that peripartum hysterectomy will be more challenging for obstetricians in the future.

  17. Infrared spectroscopy of evolved objects

    International Nuclear Information System (INIS)

    Aitken, D.K.; Roche, P.F.

    1984-01-01

    In this review, the authors are concerned with spectroscopic observations of evolved objects made in the wavelength range 1-300μm. Spectroscopic observations can conveniently be divided into studies of narrow lines, bands and broader continua. The vibrational frequencies of molecular groups fall mainly in this spectral region and appear as vibration-rotation bands from the gas phase, and as less structured, but often broader, features from the solid state. Many ionic lines, including recombination lines of abundant species and fine structure lines of astrophysically important ions also appear in this region. The continuum can arise from a number of mechanisms - photospheric emission, radiation from dust, free-free transitions in ionized gas and non-thermal processes. (Auth.)

  18. Intuitive Action Set Formation in Learning Classifier Systems with Memory Registers

    NARCIS (Netherlands)

    Simões, L.F.; Schut, M.C.; Haasdijk, E.W.

    2008-01-01

    An important design goal in Learning Classifier Systems (LCS) is to equally reinforce those classifiers which cause the level of reward supplied by the environment. In this paper, we propose a new method for action set formation in LCS. When applied to a Zeroth Level Classifier System with Memory

  19. SpectraClassifier 1.0: a user friendly, automated MRS-based classifier-development system

    Directory of Open Access Journals (Sweden)

    Julià-Sapé Margarida

    2010-02-01

    Full Text Available Abstract Background SpectraClassifier (SC is a Java solution for designing and implementing Magnetic Resonance Spectroscopy (MRS-based classifiers. The main goal of SC is to allow users with minimum background knowledge of multivariate statistics to perform a fully automated pattern recognition analysis. SC incorporates feature selection (greedy stepwise approach, either forward or backward, and feature extraction (PCA. Fisher Linear Discriminant Analysis is the method of choice for classification. Classifier evaluation is performed through various methods: display of the confusion matrix of the training and testing datasets; K-fold cross-validation, leave-one-out and bootstrapping as well as Receiver Operating Characteristic (ROC curves. Results SC is composed of the following modules: Classifier design, Data exploration, Data visualisation, Classifier evaluation, Reports, and Classifier history. It is able to read low resolution in-vivo MRS (single-voxel and multi-voxel and high resolution tissue MRS (HRMAS, processed with existing tools (jMRUI, INTERPRET, 3DiCSI or TopSpin. In addition, to facilitate exchanging data between applications, a standard format capable of storing all the information needed for a dataset was developed. Each functionality of SC has been specifically validated with real data with the purpose of bug-testing and methods validation. Data from the INTERPRET project was used. Conclusions SC is a user-friendly software designed to fulfil the needs of potential users in the MRS community. It accepts all kinds of pre-processed MRS data types and classifies them semi-automatically, allowing spectroscopists to concentrate on interpretation of results with the use of its visualisation tools.

  20. Representative Vector Machines: A Unified Framework for Classical Classifiers.

    Science.gov (United States)

    Gui, Jie; Liu, Tongliang; Tao, Dacheng; Sun, Zhenan; Tan, Tieniu

    2016-08-01

    Classifier design is a fundamental problem in pattern recognition. A variety of pattern classification methods such as the nearest neighbor (NN) classifier, support vector machine (SVM), and sparse representation-based classification (SRC) have been proposed in the literature. These typical and widely used classifiers were originally developed from different theory or application motivations and they are conventionally treated as independent and specific solutions for pattern classification. This paper proposes a novel pattern classification framework, namely, representative vector machines (or RVMs for short). The basic idea of RVMs is to assign the class label of a test example according to its nearest representative vector. The contributions of RVMs are twofold. On one hand, the proposed RVMs establish a unified framework of classical classifiers because NN, SVM, and SRC can be interpreted as the special cases of RVMs with different definitions of representative vectors. Thus, the underlying relationship among a number of classical classifiers is revealed for better understanding of pattern classification. On the other hand, novel and advanced classifiers are inspired in the framework of RVMs. For example, a robust pattern classification method called discriminant vector machine (DVM) is motivated from RVMs. Given a test example, DVM first finds its k -NNs and then performs classification based on the robust M-estimator and manifold regularization. Extensive experimental evaluations on a variety of visual recognition tasks such as face recognition (Yale and face recognition grand challenge databases), object categorization (Caltech-101 dataset), and action recognition (Action Similarity LAbeliNg) demonstrate the advantages of DVM over other classifiers.

  1. A Topic Model Approach to Representing and Classifying Football Plays

    KAUST Repository

    Varadarajan, Jagannadan

    2013-09-09

    We address the problem of modeling and classifying American Football offense teams’ plays in video, a challenging example of group activity analysis. Automatic play classification will allow coaches to infer patterns and tendencies of opponents more ef- ficiently, resulting in better strategy planning in a game. We define a football play as a unique combination of player trajectories. To this end, we develop a framework that uses player trajectories as inputs to MedLDA, a supervised topic model. The joint maximiza- tion of both likelihood and inter-class margins of MedLDA in learning the topics allows us to learn semantically meaningful play type templates, as well as, classify different play types with 70% average accuracy. Furthermore, this method is extended to analyze individual player roles in classifying each play type. We validate our method on a large dataset comprising 271 play clips from real-world football games, which will be made publicly available for future comparisons.

  2. LOCALIZATION AND RECOGNITION OF DYNAMIC HAND GESTURES BASED ON HIERARCHY OF MANIFOLD CLASSIFIERS

    OpenAIRE

    M. Favorskaya; A. Nosov; A. Popov

    2015-01-01

    Generally, the dynamic hand gestures are captured in continuous video sequences, and a gesture recognition system ought to extract the robust features automatically. This task involves the highly challenging spatio-temporal variations of dynamic hand gestures. The proposed method is based on two-level manifold classifiers including the trajectory classifiers in any time instants and the posture classifiers of sub-gestures in selected time instants. The trajectory classifiers contain skin dete...

  3. Orthogonally Evolved AI to Improve Difficulty Adjustment in Video Games

    DEFF Research Database (Denmark)

    Hintze, Arend; Olson, Randal; Lehman, Joel Anthony

    2016-01-01

    Computer games are most engaging when their difficulty is well matched to the player's ability, thereby providing an experience in which the player is neither overwhelmed nor bored. In games where the player interacts with computer-controlled opponents, the difficulty of the game can be adjusted...... not only by changing the distribution of opponents or game resources, but also through modifying the skill of the opponents. Applying evolutionary algorithms to evolve the artificial intelligence that controls opponent agents is one established method for adjusting opponent difficulty. Less-evolved agents...... (i.e. agents subject to fewer generations of evolution) make for easier opponents, while highly-evolved agents are more challenging to overcome. In this publication we test a new approach for difficulty adjustment in games: orthogonally evolved AI, where the player receives support from collaborating...

  4. High dimensional classifiers in the imbalanced case

    DEFF Research Database (Denmark)

    Bak, Britta Anker; Jensen, Jens Ledet

    We consider the binary classification problem in the imbalanced case where the number of samples from the two groups differ. The classification problem is considered in the high dimensional case where the number of variables is much larger than the number of samples, and where the imbalance leads...... to a bias in the classification. A theoretical analysis of the independence classifier reveals the origin of the bias and based on this we suggest two new classifiers that can handle any imbalance ratio. The analytical results are supplemented by a simulation study, where the suggested classifiers in some...

  5. Arabic Handwriting Recognition Using Neural Network Classifier

    African Journals Online (AJOL)

    pc

    2018-03-05

    Mar 5, 2018 ... an OCR using Neural Network classifier preceded by a set of preprocessing .... Artificial Neural Networks (ANNs), which we adopt in this research, consist of ... advantage and disadvantages of each technique. In [9],. Khemiri ...

  6. Classifiers based on optimal decision rules

    KAUST Repository

    Amin, Talha

    2013-11-25

    Based on dynamic programming approach we design algorithms for sequential optimization of exact and approximate decision rules relative to the length and coverage [3, 4]. In this paper, we use optimal rules to construct classifiers, and study two questions: (i) which rules are better from the point of view of classification-exact or approximate; and (ii) which order of optimization gives better results of classifier work: length, length+coverage, coverage, or coverage+length. Experimental results show that, on average, classifiers based on exact rules are better than classifiers based on approximate rules, and sequential optimization (length+coverage or coverage+length) is better than the ordinary optimization (length or coverage).

  7. Classifiers based on optimal decision rules

    KAUST Repository

    Amin, Talha M.; Chikalov, Igor; Moshkov, Mikhail; Zielosko, Beata

    2013-01-01

    Based on dynamic programming approach we design algorithms for sequential optimization of exact and approximate decision rules relative to the length and coverage [3, 4]. In this paper, we use optimal rules to construct classifiers, and study two questions: (i) which rules are better from the point of view of classification-exact or approximate; and (ii) which order of optimization gives better results of classifier work: length, length+coverage, coverage, or coverage+length. Experimental results show that, on average, classifiers based on exact rules are better than classifiers based on approximate rules, and sequential optimization (length+coverage or coverage+length) is better than the ordinary optimization (length or coverage).

  8. Neural Network Classifiers for Local Wind Prediction.

    Science.gov (United States)

    Kretzschmar, Ralf; Eckert, Pierre; Cattani, Daniel; Eggimann, Fritz

    2004-05-01

    This paper evaluates the quality of neural network classifiers for wind speed and wind gust prediction with prediction lead times between +1 and +24 h. The predictions were realized based on local time series and model data. The selection of appropriate input features was initiated by time series analysis and completed by empirical comparison of neural network classifiers trained on several choices of input features. The selected input features involved day time, yearday, features from a single wind observation device at the site of interest, and features derived from model data. The quality of the resulting classifiers was benchmarked against persistence for two different sites in Switzerland. The neural network classifiers exhibited superior quality when compared with persistence judged on a specific performance measure, hit and false-alarm rates.

  9. CERN internal communication is evolving

    CERN Multimedia

    2016-01-01

    CERN news will now be regularly updated on the CERN People page (see here).      Dear readers, All over the world, communication is becoming increasingly instantaneous, with news published in real time on websites and social networks. In order to keep pace with these changes, CERN's internal communication is evolving too. From now on, you will be informed of what’s happening at CERN more often via the “CERN people” page, which will frequently be updated with news. The Bulletin is following this trend too: twice a month, we will compile the most important articles published on the CERN site, with a brand-new layout. You will receive an e-mail every two weeks as soon as this new form of the Bulletin is available. If you have interesting news or stories to share, tell us about them through the form at: https://communications.web.cern.ch/got-story-cern-website​. You can also find out about news from CERN in real time...

  10. Economies Evolve by Energy Dispersal

    Directory of Open Access Journals (Sweden)

    Stanley Salthe

    2009-10-01

    Full Text Available Economic activity can be regarded as an evolutionary process governed by the 2nd law of thermodynamics. The universal law, when formulated locally as an equation of motion, reveals that a growing economy develops functional machinery and organizes hierarchically in such a way as to tend to equalize energy density differences within the economy and in respect to the surroundings it is open to. Diverse economic activities result in flows of energy that will preferentially channel along the most steeply descending paths, leveling a non-Euclidean free energy landscape. This principle of 'maximal energy dispersal‘, equivalent to the maximal rate of entropy production, gives rise to economic laws and regularities. The law of diminishing returns follows from the diminishing free energy while the relation between supply and demand displays a quest for a balance among interdependent energy densities. Economic evolution is dissipative motion where the driving forces and energy flows are inseparable from each other. When there are multiple degrees of freedom, economic growth and decline are inherently impossible to forecast in detail. Namely, trajectories of an evolving economy are non-integrable, i.e. unpredictable in detail because a decision by a player will affect also future decisions of other players. We propose that decision making is ultimately about choosing from various actions those that would reduce most effectively subjectively perceived energy gradients.

  11. Recommendation in evolving online networks

    Science.gov (United States)

    Hu, Xiao; Zeng, An; Shang, Ming-Sheng

    2016-02-01

    Recommender system is an effective tool to find the most relevant information for online users. By analyzing the historical selection records of users, recommender system predicts the most likely future links in the user-item network and accordingly constructs a personalized recommendation list for each user. So far, the recommendation process is mostly investigated in static user-item networks. In this paper, we propose a model which allows us to examine the performance of the state-of-the-art recommendation algorithms in evolving networks. We find that the recommendation accuracy in general decreases with time if the evolution of the online network fully depends on the recommendation. Interestingly, some randomness in users' choice can significantly improve the long-term accuracy of the recommendation algorithm. When a hybrid recommendation algorithm is applied, we find that the optimal parameter gradually shifts towards the diversity-favoring recommendation algorithm, indicating that recommendation diversity is essential to keep a high long-term recommendation accuracy. Finally, we confirm our conclusions by studying the recommendation on networks with the real evolution data.

  12. Evolving Capabilities for Virtual Globes

    Science.gov (United States)

    Glennon, A.

    2006-12-01

    Though thin-client spatial visualization software like Google Earth and NASA World Wind enjoy widespread popularity, a common criticism is their general lack of analytical functionality. This concern, however, is rapidly being addressed; standard and advanced geographic information system (GIS) capabilities are being developed for virtual globes--though not centralized into a single implementation or software package. The innovation is mostly originating from the user community. Three such capabilities relevant to the earth science, education, and emergency management communities are modeling dynamic spatial phenomena, real-time data collection and visualization, and multi-input collaborative databases. Modeling dynamic spatial phenomena has been facilitated through joining virtual globe geometry definitions--like KML--to relational databases. Real-time data collection uses short scripts to transform user-contributed data into a format usable by virtual globe software. Similarly, collaborative data collection for virtual globes has become possible by dynamically referencing online, multi-person spreadsheets. Examples of these functions include mapping flows within a karst watershed, real-time disaster assessment and visualization, and a collaborative geyser eruption spatial decision support system. Virtual globe applications will continue to evolve further analytical capabilities, more temporal data handling, and from nano to intergalactic scales. This progression opens education and research avenues in all scientific disciplines.

  13. Consistency Analysis of Nearest Subspace Classifier

    OpenAIRE

    Wang, Yi

    2015-01-01

    The Nearest subspace classifier (NSS) finds an estimation of the underlying subspace within each class and assigns data points to the class that corresponds to its nearest subspace. This paper mainly studies how well NSS can be generalized to new samples. It is proved that NSS is strongly consistent under certain assumptions. For completeness, NSS is evaluated through experiments on various simulated and real data sets, in comparison with some other linear model based classifiers. It is also ...

  14. 29 CFR 1910.307 - Hazardous (classified) locations.

    Science.gov (United States)

    2010-07-01

    ... equipment at the location. (c) Electrical installations. Equipment, wiring methods, and installations of... covers the requirements for electric equipment and wiring in locations that are classified depending on... provisions of this section. (4) Division and zone classification. In Class I locations, an installation must...

  15. Diagnosis of Broiler Livers by Classifying Image Patches

    DEFF Research Database (Denmark)

    Jørgensen, Anders; Fagertun, Jens; Moeslund, Thomas B.

    2017-01-01

    The manual health inspection are becoming the bottleneck at poultry processing plants. We present a computer vision method for automatic diagnosis of broiler livers. The non-rigid livers, of varying shape and sizes, are classified in patches by a convolutional neural network, outputting maps...

  16. Data Stream Classification Based on the Gamma Classifier

    Directory of Open Access Journals (Sweden)

    Abril Valeria Uriarte-Arcia

    2015-01-01

    Full Text Available The ever increasing data generation confronts us with the problem of handling online massive amounts of information. One of the biggest challenges is how to extract valuable information from these massive continuous data streams during single scanning. In a data stream context, data arrive continuously at high speed; therefore the algorithms developed to address this context must be efficient regarding memory and time management and capable of detecting changes over time in the underlying distribution that generated the data. This work describes a novel method for the task of pattern classification over a continuous data stream based on an associative model. The proposed method is based on the Gamma classifier, which is inspired by the Alpha-Beta associative memories, which are both supervised pattern recognition models. The proposed method is capable of handling the space and time constrain inherent to data stream scenarios. The Data Streaming Gamma classifier (DS-Gamma classifier implements a sliding window approach to provide concept drift detection and a forgetting mechanism. In order to test the classifier, several experiments were performed using different data stream scenarios with real and synthetic data streams. The experimental results show that the method exhibits competitive performance when compared to other state-of-the-art algorithms.

  17. Evaluation of three classifiers in mapping forest stand types using ...

    African Journals Online (AJOL)

    EJIRO

    applied for classification of the image. Supervised classification technique using maximum likelihood algorithm is the most commonly and widely used method for land cover classification (Jia and Richards, 2006). In Australia, the maximum likelihood classifier was effectively used to map different forest stand types with high.

  18. Gene-expression Classifier in Papillary Thyroid Carcinoma

    DEFF Research Database (Denmark)

    Londero, Stefano Christian; Jespersen, Marie Louise; Krogdahl, Annelise

    2016-01-01

    BACKGROUND: No reliable biomarker for metastatic potential in the risk stratification of papillary thyroid carcinoma exists. We aimed to develop a gene-expression classifier for metastatic potential. MATERIALS AND METHODS: Genome-wide expression analyses were used. Development cohort: freshly...

  19. Nonparametric, Coupled ,Bayesian ,Dictionary ,and Classifier Learning for Hyperspectral Classification.

    Science.gov (United States)

    Akhtar, Naveed; Mian, Ajmal

    2017-10-03

    We present a principled approach to learn a discriminative dictionary along a linear classifier for hyperspectral classification. Our approach places Gaussian Process priors over the dictionary to account for the relative smoothness of the natural spectra, whereas the classifier parameters are sampled from multivariate Gaussians. We employ two Beta-Bernoulli processes to jointly infer the dictionary and the classifier. These processes are coupled under the same sets of Bernoulli distributions. In our approach, these distributions signify the frequency of the dictionary atom usage in representing class-specific training spectra, which also makes the dictionary discriminative. Due to the coupling between the dictionary and the classifier, the popularity of the atoms for representing different classes gets encoded into the classifier. This helps in predicting the class labels of test spectra that are first represented over the dictionary by solving a simultaneous sparse optimization problem. The labels of the spectra are predicted by feeding the resulting representations to the classifier. Our approach exploits the nonparametric Bayesian framework to automatically infer the dictionary size--the key parameter in discriminative dictionary learning. Moreover, it also has the desirable property of adaptively learning the association between the dictionary atoms and the class labels by itself. We use Gibbs sampling to infer the posterior probability distributions over the dictionary and the classifier under the proposed model, for which, we derive analytical expressions. To establish the effectiveness of our approach, we test it on benchmark hyperspectral images. The classification performance is compared with the state-of-the-art dictionary learning-based classification methods.

  20. Silicon nanowire arrays as learning chemical vapour classifiers

    International Nuclear Information System (INIS)

    Niskanen, A O; Colli, A; White, R; Li, H W; Spigone, E; Kivioja, J M

    2011-01-01

    Nanowire field-effect transistors are a promising class of devices for various sensing applications. Apart from detecting individual chemical or biological analytes, it is especially interesting to use multiple selective sensors to look at their collective response in order to perform classification into predetermined categories. We show that non-functionalised silicon nanowire arrays can be used to robustly classify different chemical vapours using simple statistical machine learning methods. We were able to distinguish between acetone, ethanol and water with 100% accuracy while methanol, ethanol and 2-propanol were classified with 96% accuracy in ambient conditions.

  1. Neural network classifier of attacks in IP telephony

    Science.gov (United States)

    Safarik, Jakub; Voznak, Miroslav; Mehic, Miralem; Partila, Pavol; Mikulec, Martin

    2014-05-01

    Various types of monitoring mechanism allow us to detect and monitor behavior of attackers in VoIP networks. Analysis of detected malicious traffic is crucial for further investigation and hardening the network. This analysis is typically based on statistical methods and the article brings a solution based on neural network. The proposed algorithm is used as a classifier of attacks in a distributed monitoring network of independent honeypot probes. Information about attacks on these honeypots is collected on a centralized server and then classified. This classification is based on different mechanisms. One of them is based on the multilayer perceptron neural network. The article describes inner structure of used neural network and also information about implementation of this network. The learning set for this neural network is based on real attack data collected from IP telephony honeypot called Dionaea. We prepare the learning set from real attack data after collecting, cleaning and aggregation of this information. After proper learning is the neural network capable to classify 6 types of most commonly used VoIP attacks. Using neural network classifier brings more accurate attack classification in a distributed system of honeypots. With this approach is possible to detect malicious behavior in a different part of networks, which are logically or geographically divided and use the information from one network to harden security in other networks. Centralized server for distributed set of nodes serves not only as a collector and classifier of attack data, but also as a mechanism for generating a precaution steps against attacks.

  2. Detection of microaneurysms in retinal images using an ensemble classifier

    Directory of Open Access Journals (Sweden)

    M.M. Habib

    2017-01-01

    Full Text Available This paper introduces, and reports on the performance of, a novel combination of algorithms for automated microaneurysm (MA detection in retinal images. The presence of MAs in retinal images is a pathognomonic sign of Diabetic Retinopathy (DR which is one of the leading causes of blindness amongst the working age population. An extensive survey of the literature is presented and current techniques in the field are summarised. The proposed technique first detects an initial set of candidates using a Gaussian Matched Filter and then classifies this set to reduce the number of false positives. A Tree Ensemble classifier is used with a set of 70 features (the most commons features in the literature. A new set of 32 MA groundtruth images (with a total of 256 labelled MAs based on images from the MESSIDOR dataset is introduced as a public dataset for benchmarking MA detection algorithms. We evaluate our algorithm on this dataset as well as another public dataset (DIARETDB1 v2.1 and compare it against the best available alternative. Results show that the proposed classifier is superior in terms of eliminating false positive MA detection from the initial set of candidates. The proposed method achieves an ROC score of 0.415 compared to 0.2636 achieved by the best available technique. Furthermore, results show that the classifier model maintains consistent performance across datasets, illustrating the generalisability of the classifier and that overfitting does not occur.

  3. Dynamic cluster generation for a fuzzy classifier with ellipsoidal regions.

    Science.gov (United States)

    Abe, S

    1998-01-01

    In this paper, we discuss a fuzzy classifier with ellipsoidal regions that dynamically generates clusters. First, for the data belonging to a class we define a fuzzy rule with an ellipsoidal region. Namely, using the training data for each class, we calculate the center and the covariance matrix of the ellipsoidal region for the class. Then we tune the fuzzy rules, i.e., the slopes of the membership functions, successively until there is no improvement in the recognition rate of the training data. Then if the number of the data belonging to a class that are misclassified into another class exceeds a prescribed number, we define a new cluster to which those data belong and the associated fuzzy rule. Then we tune the newly defined fuzzy rules in the similar way as stated above, fixing the already obtained fuzzy rules. We iterate generation of clusters and tuning of the newly generated fuzzy rules until the number of the data belonging to a class that are misclassified into another class does not exceed the prescribed number. We evaluate our method using thyroid data, Japanese Hiragana data of vehicle license plates, and blood cell data. By dynamic cluster generation, the generalization ability of the classifier is improved and the recognition rate of the fuzzy classifier for the test data is the best among the neural network classifiers and other fuzzy classifiers if there are no discrete input variables.

  4. Idiopathic pulmonary fibrosis: evolving concepts.

    Science.gov (United States)

    Ryu, Jay H; Moua, Teng; Daniels, Craig E; Hartman, Thomas E; Yi, Eunhee S; Utz, James P; Limper, Andrew H

    2014-08-01

    Idiopathic pulmonary fibrosis (IPF) occurs predominantly in middle-aged and older adults and accounts for 20% to 30% of interstitial lung diseases. It is usually progressive, resulting in respiratory failure and death. Diagnostic criteria for IPF have evolved over the years, and IPF is currently defined as a disease characterized by the histopathologic pattern of usual interstitial pneumonia occurring in the absence of an identifiable cause of lung injury. Understanding of the pathogenesis of IPF has shifted away from chronic inflammation and toward dysregulated fibroproliferative repair in response to alveolar epithelial injury. Idiopathic pulmonary fibrosis is likely a heterogeneous disorder caused by various interactions between genetic components and environmental exposures. High-resolution computed tomography can be diagnostic in the presence of typical findings such as bilateral reticular opacities associated with traction bronchiectasis/bronchiolectasis in a predominantly basal and subpleural distribution, along with subpleural honeycombing. In other circumstances, a surgical lung biopsy may be needed. The clinical course of IPF can be unpredictable and may be punctuated by acute deteriorations (acute exacerbation). Although progress continues in unraveling the mechanisms of IPF, effective therapy has remained elusive. Thus, clinicians and patients need to reach informed decisions regarding management options including lung transplant. The findings in this review were based on a literature search of PubMed using the search terms idiopathic pulmonary fibrosis and usual interstitial pneumonia, limited to human studies in the English language published from January 1, 2000, through December 31, 2013, and supplemented by key references published before the year 2000. Copyright © 2014 Mayo Foundation for Medical Education and Research. Published by Elsevier Inc. All rights reserved.

  5. Evolving expectations from international organisations

    International Nuclear Information System (INIS)

    Ruiz Lopez, C.

    2008-01-01

    The author stated that implementation of the geological disposal concept requires a strategy that provides national decision makers with sufficient confidence in the level of long-term safety and protection ultimately achieved. The concept of protection against harm has a broader meaning than radiological protection in terms of risk and dose. It includes the protection of the environment and socio-economic interests of communities. She recognised that a number of countries have established regulatory criteria already, and others are now discussing what constitutes a proper regulatory test and suitable time frame for judging the safety of long-term disposal. Each regulatory programme seeks to define reasonable tests of repository performance, using protection criteria and safety approaches consistent with the culture, values and expectations of the citizens of the country concerned. This means that there are differences in how protection and safety are addressed in national approaches to regulation and in the bases used for that. However, as was recognised in the Cordoba Workshop, it would be important to reach a minimum level of consistency and be able to explain the differences. C. Ruiz-Lopez presented an overview of the development of international guidance from ICRP, IAEA and NEA from the Cordoba workshop up to now, and positions of independent National Advisory Bodies. The evolution of these guidelines over time demonstrates an evolving understanding of long-term implications, with the recognition that dose and risk constraints should not be seen as measures of detriment beyond a few hundred years, the emphasis on sound engineering practices, and the introduction of new concepts and approaches which take into account social and economical aspects (e.g. constrained optimisation, BAT, managerial principles). In its new recommendations, ICRP (draft 2006) recognizes. in particular, that decision making processes may depend on other societal concerns and considers

  6. Verification of the Accountability Method as a Means to Classify Radioactive Wastes Processed Using THOR Fluidized Bed Steam Reforming at the Studsvik Processing Facility in Erwin, Tennessee, USA - 13087

    Energy Technology Data Exchange (ETDEWEB)

    Olander, Jonathan [Studsvik Processing Facility Erwin, 151 T.C. Runnion Rd., Erwin, TN 37650 (United States); Myers, Corey [Studsvik, Inc., 5605 Glenridge Drive, Suite 705, Atlanta, GA 30342 (United States)

    2013-07-01

    Studsviks' Processing Facility Erwin (SPFE) has been treating Low-Level Radioactive Waste using its patented THOR process for over 13 years. Studsvik has been mixing and processing wastes of the same waste classification but different chemical and isotopic characteristics for the full extent of this period as a general matter of operations. Studsvik utilizes the accountability method to track the movement of radionuclides from acceptance of waste, through processing, and finally in the classification of waste for disposal. Recently the NRC has proposed to revise the 1995 Branch Technical Position on Concentration Averaging and Encapsulation (1995 BTP on CA) with additional clarification (draft BTP on CA). The draft BTP on CA has paved the way for large scale blending of higher activity and lower activity waste to produce a single waste for the purpose of classification. With the onset of blending in the waste treatment industry, there is concern from the public and state regulators as to the robustness of the accountability method and the ability of processors to prevent the inclusion of hot spots in waste. To address these concerns and verify the accountability method as applied by the SPFE, as well as the SPFE's ability to control waste package classification, testing of actual waste packages was performed. Testing consisted of a comprehensive dose rate survey of a container of processed waste. Separately, the waste package was modeled chemically and radiologically. Comparing the observed and theoretical data demonstrated that actual dose rates were lower than, but consistent with, modeled dose rates. Moreover, the distribution of radioactivity confirms that the SPFE can produce a radiologically homogeneous waste form. The results of the study demonstrate: 1) the accountability method as applied by the SPFE is valid and produces expected results; 2) the SPFE can produce a radiologically homogeneous waste; and 3) the SPFE can effectively control the

  7. Verification of the Accountability Method as a Means to Classify Radioactive Wastes Processed Using THOR Fluidized Bed Steam Reforming at the Studsvik Processing Facility in Erwin, Tennessee, USA - 13087

    International Nuclear Information System (INIS)

    Olander, Jonathan; Myers, Corey

    2013-01-01

    Studsviks' Processing Facility Erwin (SPFE) has been treating Low-Level Radioactive Waste using its patented THOR process for over 13 years. Studsvik has been mixing and processing wastes of the same waste classification but different chemical and isotopic characteristics for the full extent of this period as a general matter of operations. Studsvik utilizes the accountability method to track the movement of radionuclides from acceptance of waste, through processing, and finally in the classification of waste for disposal. Recently the NRC has proposed to revise the 1995 Branch Technical Position on Concentration Averaging and Encapsulation (1995 BTP on CA) with additional clarification (draft BTP on CA). The draft BTP on CA has paved the way for large scale blending of higher activity and lower activity waste to produce a single waste for the purpose of classification. With the onset of blending in the waste treatment industry, there is concern from the public and state regulators as to the robustness of the accountability method and the ability of processors to prevent the inclusion of hot spots in waste. To address these concerns and verify the accountability method as applied by the SPFE, as well as the SPFE's ability to control waste package classification, testing of actual waste packages was performed. Testing consisted of a comprehensive dose rate survey of a container of processed waste. Separately, the waste package was modeled chemically and radiologically. Comparing the observed and theoretical data demonstrated that actual dose rates were lower than, but consistent with, modeled dose rates. Moreover, the distribution of radioactivity confirms that the SPFE can produce a radiologically homogeneous waste form. The results of the study demonstrate: 1) the accountability method as applied by the SPFE is valid and produces expected results; 2) the SPFE can produce a radiologically homogeneous waste; and 3) the SPFE can effectively control the waste package

  8. FY1995 evolvable hardware chip; 1995 nendo shinkasuru hardware chip

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1997-03-01

    This project aims at the development of 'Evolvable Hardware' (EHW) which can adapt its hardware structure to the environment to attain better hardware performance, under the control of genetic algorithms. EHW is a key technology to explore the new application area requiring real-time performance and on-line adaptation. 1. Development of EHW-LSI for function level hardware evolution, which includes 15 DSPs in one chip. 2. Application of the EHW to the practical industrial applications such as data compression, ATM control, digital mobile communication. 3. Two patents : (1) the architecture and the processing method for programmable EHW-LSI. (2) The method of data compression for loss-less data, using EHW. 4. The first international conference for evolvable hardware was held by authors: Intl. Conf. on Evolvable Systems (ICES96). It was determined at ICES96 that ICES will be held every two years between Japan and Europe. So the new society has been established by us. (NEDO)

  9. The evolution of resource adaptation: how generalist and specialist consumers evolve.

    Science.gov (United States)

    Ma, Junling; Levin, Simon A

    2006-07-01

    Why and how specialist and generalist strategies evolve are important questions in evolutionary ecology. In this paper, with the method of adaptive dynamics and evolutionary branching, we identify conditions that select for specialist and generalist strategies. Generally, generalist strategies evolve if there is a switching benefit; specialists evolve if there is a switching cost. If the switching cost is large, specialists always evolve. If the switching cost is small, even though the consumer will first evolve toward a generalist strategy, it will eventually branch into two specialists.

  10. Detection and Classification of Transformer Winding Mechanical Faults Using UWB Sensors and Bayesian Classifier

    Science.gov (United States)

    Alehosseini, Ali; A. Hejazi, Maryam; Mokhtari, Ghassem; B. Gharehpetian, Gevork; Mohammadi, Mohammad

    2015-06-01

    In this paper, the Bayesian classifier is used to detect and classify the radial deformation and axial displacement of transformer windings. The proposed method is tested on a model of transformer for different volumes of radial deformation and axial displacement. In this method, ultra-wideband (UWB) signal is sent to the simplified model of the transformer winding. The received signal from the winding model is recorded and used for training and testing of Bayesian classifier in different axial displacement and radial deformation states of the winding. It is shown that the proposed method has a good accuracy to detect and classify the axial displacement and radial deformation of the winding.

  11. Data characteristics that determine classifier performance

    CSIR Research Space (South Africa)

    Van der Walt, Christiaan M

    2006-11-01

    Full Text Available available at [11]. The kNN uses a LinearNN nearest neighbour search algorithm with an Euclidean distance metric [8]. The optimal k value is determined by performing 10-fold cross-validation. An optimal k value between 1 and 10 is used for Experiments 1... classifiers. 10-fold cross-validation is used to evaluate and compare the performance of the classifiers on the different data sets. 3.1. Artificial data generation Multivariate Gaussian distributions are used to generate artificial data sets. We use d...

  12. A Customizable Text Classifier for Text Mining

    Directory of Open Access Journals (Sweden)

    Yun-liang Zhang

    2007-12-01

    Full Text Available Text mining deals with complex and unstructured texts. Usually a particular collection of texts that is specified to one or more domains is necessary. We have developed a customizable text classifier for users to mine the collection automatically. It derives from the sentence category of the HNC theory and corresponding techniques. It can start with a few texts, and it can adjust automatically or be adjusted by user. The user can also control the number of domains chosen and decide the standard with which to choose the texts based on demand and abundance of materials. The performance of the classifier varies with the user's choice.

  13. A systems biology-based classifier for hepatocellular carcinoma diagnosis.

    Directory of Open Access Journals (Sweden)

    Yanqiong Zhang

    Full Text Available AIM: The diagnosis of hepatocellular carcinoma (HCC in the early stage is crucial to the application of curative treatments which are the only hope for increasing the life expectancy of patients. Recently, several large-scale studies have shed light on this problem through analysis of gene expression profiles to identify markers correlated with HCC progression. However, those marker sets shared few genes in common and were poorly validated using independent data. Therefore, we developed a systems biology based classifier by combining the differential gene expression with topological features of human protein interaction networks to enhance the ability of HCC diagnosis. METHODS AND RESULTS: In the Oncomine platform, genes differentially expressed in HCC tissues relative to their corresponding normal tissues were filtered by a corrected Q value cut-off and Concept filters. The identified genes that are common to different microarray datasets were chosen as the candidate markers. Then, their networks were analyzed by GeneGO Meta-Core software and the hub genes were chosen. After that, an HCC diagnostic classifier was constructed by Partial Least Squares modeling based on the microarray gene expression data of the hub genes. Validations of diagnostic performance showed that this classifier had high predictive accuracy (85.88∼92.71% and area under ROC curve (approximating 1.0, and that the network topological features integrated into this classifier contribute greatly to improving the predictive performance. Furthermore, it has been demonstrated that this modeling strategy is not only applicable to HCC, but also to other cancers. CONCLUSION: Our analysis suggests that the systems biology-based classifier that combines the differential gene expression and topological features of human protein interaction network may enhance the diagnostic performance of HCC classifier.

  14. Evolving Technologies: A View to Tomorrow

    Science.gov (United States)

    Tamarkin, Molly; Rodrigo, Shelley

    2011-01-01

    Technology leaders must participate in strategy creation as well as operational delivery within higher education institutions. The future of higher education--the view to tomorrow--is irrevocably integrated and intertwined with evolving technologies. This article focuses on two specific evolving technologies: (1) alternative IT sourcing; and (2)…

  15. Un método probabilístico para las clasificaciones estadísticas de jugadores en baloncesto. (A probabilistic method to statistically classify players in basketball.

    Directory of Open Access Journals (Sweden)

    José Antonio Martínez García

    2010-01-01

    Full Text Available ResumenEn esta investigación presentamos una nueva forma de interpretar las estadísticas individuales de la Liga ACB de baloncesto. Para ello, proponemos un enfoque probabilístico de los números individuales obtenidos por cada jugador al final de la temporada regular. Esto convierte a cada valor conseguido en un estimador del valor real teórico, por lo que tiene un error asociado que, en función de su magnitud, influye en los rankings de líderes estadísticos de la ACB. Asimismo, realizamos una aproximación paramétrica para cuantificar un tamaño de error máximo admisible, que debe servir como criterio para considerar si un jugador debe ser incluido en los rankings de cada apartado estadístico. Dada la importancia creciente que la utilización de la estadística está teniendo en el baloncesto profesional, este método presenta una contribución novedosa al análisis del desempeño de los jugadores, análisis que repercute en su valor económico y mediático, es decir, en el valor de mercado de éstos.AbstractWe introduce a method to re-elaborate the rankings of individual stats in the ACB League. The method is based on a probabilistic approach to interpret the individual performance achieved by each basketball player at the end of the regular season. Therefore, each individual record is an estimate of the real value of the parameter, with the corresponding associated error. The size of this error influences the final elaborated ranking. Under a parametric approach, we quantify the size of a maximum admissible error. Because of the growing interest of statistics in basketball, our proposal is a valuable contribution to analyse the performance of players, which is highly related to their market value.

  16. 75 FR 37253 - Classified National Security Information

    Science.gov (United States)

    2010-06-28

    ... ``Secret.'' (3) Each interior page of a classified document shall be marked at the top and bottom either... ``(TS)'' for Top Secret, ``(S)'' for Secret, and ``(C)'' for Confidential will be used. (2) Portions... from the informational text. (1) Conspicuously place the overall classification at the top and bottom...

  17. 75 FR 707 - Classified National Security Information

    Science.gov (United States)

    2010-01-05

    ... classified at one of the following three levels: (1) ``Top Secret'' shall be applied to information, the... exercise this authority. (2) ``Top Secret'' original classification authority may be delegated only by the... official has been delegated ``Top Secret'' original classification authority by the agency head. (4) Each...

  18. Neural Network Classifier Based on Growing Hyperspheres

    Czech Academy of Sciences Publication Activity Database

    Jiřina Jr., Marcel; Jiřina, Marcel

    2000-01-01

    Roč. 10, č. 3 (2000), s. 417-428 ISSN 1210-0552. [Neural Network World 2000. Prague, 09.07.2000-12.07.2000] Grant - others:MŠMT ČR(CZ) VS96047; MPO(CZ) RP-4210 Institutional research plan: AV0Z1030915 Keywords : neural network * classifier * hyperspheres * big -dimensional data Subject RIV: BA - General Mathematics

  19. Classifying web pages with visual features

    NARCIS (Netherlands)

    de Boer, V.; van Someren, M.; Lupascu, T.; Filipe, J.; Cordeiro, J.

    2010-01-01

    To automatically classify and process web pages, current systems use the textual content of those pages, including both the displayed content and the underlying (HTML) code. However, a very important feature of a web page is its visual appearance. In this paper, we show that using generic visual

  20. Adapting Morphology to Multiple Tasks in Evolved Virtual Creatures

    DEFF Research Database (Denmark)

    Lessin, Dan; Fussell, Don; Miikkulainen, Risto

    2014-01-01

    The ESP method for evolving virtual creatures (Lessin et al., 2013) consisted of an encapsulation mechanism to preserve learned skills, a human-designed syllabus to build higherlevel skills by combining lower-level skills systematically, and a pandemonium mechanism to resolve conflicts between...

  1. Classifying features in CT imagery: accuracy for some single- and multiple-species classifiers

    Science.gov (United States)

    Daniel L. Schmoldt; Jing He; A. Lynn Abbott

    1998-01-01

    Our current approach to automatically label features in CT images of hardwood logs classifies each pixel of an image individually. These feature classifiers use a back-propagation artificial neural network (ANN) and feature vectors that include a small, local neighborhood of pixels and the distance of the target pixel to the center of the log. Initially, this type of...

  2. How does cognition evolve? Phylogenetic comparative psychology.

    Science.gov (United States)

    MacLean, Evan L; Matthews, Luke J; Hare, Brian A; Nunn, Charles L; Anderson, Rindy C; Aureli, Filippo; Brannon, Elizabeth M; Call, Josep; Drea, Christine M; Emery, Nathan J; Haun, Daniel B M; Herrmann, Esther; Jacobs, Lucia F; Platt, Michael L; Rosati, Alexandra G; Sandel, Aaron A; Schroepfer, Kara K; Seed, Amanda M; Tan, Jingzhi; van Schaik, Carel P; Wobber, Victoria

    2012-03-01

    Now more than ever animal studies have the potential to test hypotheses regarding how cognition evolves. Comparative psychologists have developed new techniques to probe the cognitive mechanisms underlying animal behavior, and they have become increasingly skillful at adapting methodologies to test multiple species. Meanwhile, evolutionary biologists have generated quantitative approaches to investigate the phylogenetic distribution and function of phenotypic traits, including cognition. In particular, phylogenetic methods can quantitatively (1) test whether specific cognitive abilities are correlated with life history (e.g., lifespan), morphology (e.g., brain size), or socio-ecological variables (e.g., social system), (2) measure how strongly phylogenetic relatedness predicts the distribution of cognitive skills across species, and (3) estimate the ancestral state of a given cognitive trait using measures of cognitive performance from extant species. Phylogenetic methods can also be used to guide the selection of species comparisons that offer the strongest tests of a priori predictions of cognitive evolutionary hypotheses (i.e., phylogenetic targeting). Here, we explain how an integration of comparative psychology and evolutionary biology will answer a host of questions regarding the phylogenetic distribution and history of cognitive traits, as well as the evolutionary processes that drove their evolution.

  3. How does cognition evolve? Phylogenetic comparative psychology

    Science.gov (United States)

    Matthews, Luke J.; Hare, Brian A.; Nunn, Charles L.; Anderson, Rindy C.; Aureli, Filippo; Brannon, Elizabeth M.; Call, Josep; Drea, Christine M.; Emery, Nathan J.; Haun, Daniel B. M.; Herrmann, Esther; Jacobs, Lucia F.; Platt, Michael L.; Rosati, Alexandra G.; Sandel, Aaron A.; Schroepfer, Kara K.; Seed, Amanda M.; Tan, Jingzhi; van Schaik, Carel P.; Wobber, Victoria

    2014-01-01

    Now more than ever animal studies have the potential to test hypotheses regarding how cognition evolves. Comparative psychologists have developed new techniques to probe the cognitive mechanisms underlying animal behavior, and they have become increasingly skillful at adapting methodologies to test multiple species. Meanwhile, evolutionary biologists have generated quantitative approaches to investigate the phylogenetic distribution and function of phenotypic traits, including cognition. In particular, phylogenetic methods can quantitatively (1) test whether specific cognitive abilities are correlated with life history (e.g., lifespan), morphology (e.g., brain size), or socio-ecological variables (e.g., social system), (2) measure how strongly phylogenetic relatedness predicts the distribution of cognitive skills across species, and (3) estimate the ancestral state of a given cognitive trait using measures of cognitive performance from extant species. Phylogenetic methods can also be used to guide the selection of species comparisons that offer the strongest tests of a priori predictions of cognitive evolutionary hypotheses (i.e., phylogenetic targeting). Here, we explain how an integration of comparative psychology and evolutionary biology will answer a host of questions regarding the phylogenetic distribution and history of cognitive traits, as well as the evolutionary processes that drove their evolution. PMID:21927850

  4. Classifier fusion for VoIP attacks classification

    Science.gov (United States)

    Safarik, Jakub; Rezac, Filip

    2017-05-01

    SIP is one of the most successful protocols in the field of IP telephony communication. It establishes and manages VoIP calls. As the number of SIP implementation rises, we can expect a higher number of attacks on the communication system in the near future. This work aims at malicious SIP traffic classification. A number of various machine learning algorithms have been developed for attack classification. The paper presents a comparison of current research and the use of classifier fusion method leading to a potential decrease in classification error rate. Use of classifier combination makes a more robust solution without difficulties that may affect single algorithms. Different voting schemes, combination rules, and classifiers are discussed to improve the overall performance. All classifiers have been trained on real malicious traffic. The concept of traffic monitoring depends on the network of honeypot nodes. These honeypots run in several networks spread in different locations. Separation of honeypots allows us to gain an independent and trustworthy attack information.

  5. Learning to classify wakes from local sensory information

    Science.gov (United States)

    Alsalman, Mohamad; Colvert, Brendan; Kanso, Eva; Kanso Team

    2017-11-01

    Aquatic organisms exhibit remarkable abilities to sense local flow signals contained in their fluid environment and to surmise the origins of these flows. For example, fish can discern the information contained in various flow structures and utilize this information for obstacle avoidance and prey tracking. Flow structures created by flapping and swimming bodies are well characterized in the fluid dynamics literature; however, such characterization relies on classical methods that use an external observer to reconstruct global flow fields. The reconstructed flows, or wakes, are then classified according to the unsteady vortex patterns. Here, we propose a new approach for wake identification: we classify the wakes resulting from a flapping airfoil by applying machine learning algorithms to local flow information. In particular, we simulate the wakes of an oscillating airfoil in an incoming flow, extract the downstream vorticity information, and train a classifier to learn the different flow structures and classify new ones. This data-driven approach provides a promising framework for underwater navigation and detection in application to autonomous bio-inspired vehicles.

  6. Human Activity Recognition by Combining a Small Number of Classifiers.

    Science.gov (United States)

    Nazabal, Alfredo; Garcia-Moreno, Pablo; Artes-Rodriguez, Antonio; Ghahramani, Zoubin

    2016-09-01

    We consider the problem of daily human activity recognition (HAR) using multiple wireless inertial sensors, and specifically, HAR systems with a very low number of sensors, each one providing an estimation of the performed activities. We propose new Bayesian models to combine the output of the sensors. The models are based on a soft outputs combination of individual classifiers to deal with the small number of sensors. We also incorporate the dynamic nature of human activities as a first-order homogeneous Markov chain. We develop both inductive and transductive inference methods for each model to be employed in supervised and semisupervised situations, respectively. Using different real HAR databases, we compare our classifiers combination models against a single classifier that employs all the signals from the sensors. Our models exhibit consistently a reduction of the error rate and an increase of robustness against sensor failures. Our models also outperform other classifiers combination models that do not consider soft outputs and an Markovian structure of the human activities.

  7. Qualitative Functional Decomposition Analysis of Evolved Neuromorphic Flight Controllers

    Directory of Open Access Journals (Sweden)

    Sanjay K. Boddhu

    2012-01-01

    Full Text Available In the previous work, it was demonstrated that one can effectively employ CTRNN-EH (a neuromorphic variant of EH method methodology to evolve neuromorphic flight controllers for a flapping wing robot. This paper describes a novel frequency grouping-based analysis technique, developed to qualitatively decompose the evolved controllers into explainable functional control blocks. A summary of the previous work related to evolving flight controllers for two categories of the controller types, called autonomous and nonautonomous controllers, is provided, and the applicability of the newly developed decomposition analysis for both controller categories is demonstrated. Further, the paper concludes with appropriate discussion of ongoing work and implications for possible future work related to employing the CTRNN-EH methodology and the decomposition analysis techniques presented in this paper.

  8. A Bayesian Classifier for X-Ray Pulsars Recognition

    Directory of Open Access Journals (Sweden)

    Hao Liang

    2016-01-01

    Full Text Available Recognition for X-ray pulsars is important for the problem of spacecraft’s attitude determination by X-ray Pulsar Navigation (XPNAV. By using the nonhomogeneous Poisson model of the received photons and the minimum recognition error criterion, a classifier based on the Bayesian theorem is proposed. For X-ray pulsars recognition with unknown Doppler frequency and initial phase, the features of every X-ray pulsar are extracted and the unknown parameters are estimated using the Maximum Likelihood (ML method. Besides that, a method to recognize unknown X-ray pulsars or X-ray disturbances is proposed. Simulation results certificate the validity of the proposed Bayesian classifier.

  9. Lung Nodule Image Classification Based on Local Difference Pattern and Combined Classifier.

    Science.gov (United States)

    Mao, Keming; Deng, Zhuofu

    2016-01-01

    This paper proposes a novel lung nodule classification method for low-dose CT images. The method includes two stages. First, Local Difference Pattern (LDP) is proposed to encode the feature representation, which is extracted by comparing intensity difference along circular regions centered at the lung nodule. Then, the single-center classifier is trained based on LDP. Due to the diversity of feature distribution for different class, the training images are further clustered into multiple cores and the multicenter classifier is constructed. The two classifiers are combined to make the final decision. Experimental results on public dataset show the superior performance of LDP and the combined classifier.

  10. Lung Nodule Image Classification Based on Local Difference Pattern and Combined Classifier

    Directory of Open Access Journals (Sweden)

    Keming Mao

    2016-01-01

    Full Text Available This paper proposes a novel lung nodule classification method for low-dose CT images. The method includes two stages. First, Local Difference Pattern (LDP is proposed to encode the feature representation, which is extracted by comparing intensity difference along circular regions centered at the lung nodule. Then, the single-center classifier is trained based on LDP. Due to the diversity of feature distribution for different class, the training images are further clustered into multiple cores and the multicenter classifier is constructed. The two classifiers are combined to make the final decision. Experimental results on public dataset show the superior performance of LDP and the combined classifier.

  11. Classifying Dementia Using Local Binary Patterns from Different Regions in Magnetic Resonance Images

    Directory of Open Access Journals (Sweden)

    Ketil Oppedal

    2015-01-01

    Full Text Available Dementia is an evolving challenge in society, and no disease-modifying treatment exists. Diagnosis can be demanding and MR imaging may aid as a noninvasive method to increase prediction accuracy. We explored the use of 2D local binary pattern (LBP extracted from FLAIR and T1 MR images of the brain combined with a Random Forest classifier in an attempt to discern patients with Alzheimer's disease (AD, Lewy body dementia (LBD, and normal controls (NC. Analysis was conducted in areas with white matter lesions (WML and all of white matter (WM. Results from 10-fold nested cross validation are reported as mean accuracy, precision, and recall with standard deviation in brackets. The best result we achieved was in the two-class problem NC versus AD + LBD with total accuracy of 0.98 (0.04. In the three-class problem AD versus LBD versus NC and the two-class problem AD versus LBD, we achieved 0.87 (0.08 and 0.74 (0.16, respectively. The performance using 3DT1 images was notably better than when using FLAIR images. The results from the WM region gave similar results as in the WML region. Our study demonstrates that LBP texture analysis in brain MR images can be successfully used for computer based dementia diagnosis.

  12. Self-organizing map classifier for stressed speech recognition

    Science.gov (United States)

    Partila, Pavol; Tovarek, Jaromir; Voznak, Miroslav

    2016-05-01

    This paper presents a method for detecting speech under stress using Self-Organizing Maps. Most people who are exposed to stressful situations can not adequately respond to stimuli. Army, police, and fire department occupy the largest part of the environment that are typical of an increased number of stressful situations. The role of men in action is controlled by the control center. Control commands should be adapted to the psychological state of a man in action. It is known that the psychological changes of the human body are also reflected physiologically, which consequently means the stress effected speech. Therefore, it is clear that the speech stress recognizing system is required in the security forces. One of the possible classifiers, which are popular for its flexibility, is a self-organizing map. It is one type of the artificial neural networks. Flexibility means independence classifier on the character of the input data. This feature is suitable for speech processing. Human Stress can be seen as a kind of emotional state. Mel-frequency cepstral coefficients, LPC coefficients, and prosody features were selected for input data. These coefficients were selected for their sensitivity to emotional changes. The calculation of the parameters was performed on speech recordings, which can be divided into two classes, namely the stress state recordings and normal state recordings. The benefit of the experiment is a method using SOM classifier for stress speech detection. Results showed the advantage of this method, which is input data flexibility.

  13. Comparing cosmic web classifiers using information theory

    International Nuclear Information System (INIS)

    Leclercq, Florent; Lavaux, Guilhem; Wandelt, Benjamin; Jasche, Jens

    2016-01-01

    We introduce a decision scheme for optimally choosing a classifier, which segments the cosmic web into different structure types (voids, sheets, filaments, and clusters). Our framework, based on information theory, accounts for the design aims of different classes of possible applications: (i) parameter inference, (ii) model selection, and (iii) prediction of new observations. As an illustration, we use cosmographic maps of web-types in the Sloan Digital Sky Survey to assess the relative performance of the classifiers T-WEB, DIVA and ORIGAMI for: (i) analyzing the morphology of the cosmic web, (ii) discriminating dark energy models, and (iii) predicting galaxy colors. Our study substantiates a data-supported connection between cosmic web analysis and information theory, and paves the path towards principled design of analysis procedures for the next generation of galaxy surveys. We have made the cosmic web maps, galaxy catalog, and analysis scripts used in this work publicly available.

  14. Design of Robust Neural Network Classifiers

    DEFF Research Database (Denmark)

    Larsen, Jan; Andersen, Lars Nonboe; Hintz-Madsen, Mads

    1998-01-01

    This paper addresses a new framework for designing robust neural network classifiers. The network is optimized using the maximum a posteriori technique, i.e., the cost function is the sum of the log-likelihood and a regularization term (prior). In order to perform robust classification, we present...... a modified likelihood function which incorporates the potential risk of outliers in the data. This leads to the introduction of a new parameter, the outlier probability. Designing the neural classifier involves optimization of network weights as well as outlier probability and regularization parameters. We...... suggest to adapt the outlier probability and regularisation parameters by minimizing the error on a validation set, and a simple gradient descent scheme is derived. In addition, the framework allows for constructing a simple outlier detector. Experiments with artificial data demonstrate the potential...

  15. Comparing cosmic web classifiers using information theory

    Energy Technology Data Exchange (ETDEWEB)

    Leclercq, Florent [Institute of Cosmology and Gravitation (ICG), University of Portsmouth, Dennis Sciama Building, Burnaby Road, Portsmouth PO1 3FX (United Kingdom); Lavaux, Guilhem; Wandelt, Benjamin [Institut d' Astrophysique de Paris (IAP), UMR 7095, CNRS – UPMC Université Paris 6, Sorbonne Universités, 98bis boulevard Arago, F-75014 Paris (France); Jasche, Jens, E-mail: florent.leclercq@polytechnique.org, E-mail: lavaux@iap.fr, E-mail: j.jasche@tum.de, E-mail: wandelt@iap.fr [Excellence Cluster Universe, Technische Universität München, Boltzmannstrasse 2, D-85748 Garching (Germany)

    2016-08-01

    We introduce a decision scheme for optimally choosing a classifier, which segments the cosmic web into different structure types (voids, sheets, filaments, and clusters). Our framework, based on information theory, accounts for the design aims of different classes of possible applications: (i) parameter inference, (ii) model selection, and (iii) prediction of new observations. As an illustration, we use cosmographic maps of web-types in the Sloan Digital Sky Survey to assess the relative performance of the classifiers T-WEB, DIVA and ORIGAMI for: (i) analyzing the morphology of the cosmic web, (ii) discriminating dark energy models, and (iii) predicting galaxy colors. Our study substantiates a data-supported connection between cosmic web analysis and information theory, and paves the path towards principled design of analysis procedures for the next generation of galaxy surveys. We have made the cosmic web maps, galaxy catalog, and analysis scripts used in this work publicly available.

  16. Detection of Fundus Lesions Using Classifier Selection

    Science.gov (United States)

    Nagayoshi, Hiroto; Hiramatsu, Yoshitaka; Sako, Hiroshi; Himaga, Mitsutoshi; Kato, Satoshi

    A system for detecting fundus lesions caused by diabetic retinopathy from fundus images is being developed. The system can screen the images in advance in order to reduce the inspection workload on doctors. One of the difficulties that must be addressed in completing this system is how to remove false positives (which tend to arise near blood vessels) without decreasing the detection rate of lesions in other areas. To overcome this difficulty, we developed classifier selection according to the position of a candidate lesion, and we introduced new features that can distinguish true lesions from false positives. A system incorporating classifier selection and these new features was tested in experiments using 55 fundus images with some lesions and 223 images without lesions. The results of the experiments confirm the effectiveness of the proposed system, namely, degrees of sensitivity and specificity of 98% and 81%, respectively.

  17. Classifying objects in LWIR imagery via CNNs

    Science.gov (United States)

    Rodger, Iain; Connor, Barry; Robertson, Neil M.

    2016-10-01

    The aim of the presented work is to demonstrate enhanced target recognition and improved false alarm rates for a mid to long range detection system, utilising a Long Wave Infrared (LWIR) sensor. By exploiting high quality thermal image data and recent techniques in machine learning, the system can provide automatic target recognition capabilities. A Convolutional Neural Network (CNN) is trained and the classifier achieves an overall accuracy of > 95% for 6 object classes related to land defence. While the highly accurate CNN struggles to recognise long range target classes, due to low signal quality, robust target discrimination is achieved for challenging candidates. The overall performance of the methodology presented is assessed using human ground truth information, generating classifier evaluation metrics for thermal image sequences.

  18. Construction of Pancreatic Cancer Classifier Based on SVM Optimized by Improved FOA

    Science.gov (United States)

    Ma, Xiaoqi

    2015-01-01

    A novel method is proposed to establish the pancreatic cancer classifier. Firstly, the concept of quantum and fruit fly optimal algorithm (FOA) are introduced, respectively. Then FOA is improved by quantum coding and quantum operation, and a new smell concentration determination function is defined. Finally, the improved FOA is used to optimize the parameters of support vector machine (SVM) and the classifier is established by optimized SVM. In order to verify the effectiveness of the proposed method, SVM and other classification methods have been chosen as the comparing methods. The experimental results show that the proposed method can improve the classifier performance and cost less time. PMID:26543867

  19. Learning for VMM + WTA Embedded Classifiers

    Science.gov (United States)

    2016-03-31

    Learning for VMM + WTA Embedded Classifiers Jennifer Hasler and Sahil Shah Electrical and Computer Engineering Georgia Institute of Technology...enabling correct classification of each novel acoustic signal (generator, idle car, and idle truck ). The classification structure requires, after...measured on our SoC FPAA IC. The test input is composed of signals from urban environment for 3 objects (generator, idle car, and idle truck

  20. Bayes classifiers for imbalanced traffic accidents datasets.

    Science.gov (United States)

    Mujalli, Randa Oqab; López, Griselda; Garach, Laura

    2016-03-01

    Traffic accidents data sets are usually imbalanced, where the number of instances classified under the killed or severe injuries class (minority) is much lower than those classified under the slight injuries class (majority). This, however, supposes a challenging problem for classification algorithms and may cause obtaining a model that well cover the slight injuries instances whereas the killed or severe injuries instances are misclassified frequently. Based on traffic accidents data collected on urban and suburban roads in Jordan for three years (2009-2011); three different data balancing techniques were used: under-sampling which removes some instances of the majority class, oversampling which creates new instances of the minority class and a mix technique that combines both. In addition, different Bayes classifiers were compared for the different imbalanced and balanced data sets: Averaged One-Dependence Estimators, Weightily Average One-Dependence Estimators, and Bayesian networks in order to identify factors that affect the severity of an accident. The results indicated that using the balanced data sets, especially those created using oversampling techniques, with Bayesian networks improved classifying a traffic accident according to its severity and reduced the misclassification of killed and severe injuries instances. On the other hand, the following variables were found to contribute to the occurrence of a killed causality or a severe injury in a traffic accident: number of vehicles involved, accident pattern, number of directions, accident type, lighting, surface condition, and speed limit. This work, to the knowledge of the authors, is the first that aims at analyzing historical data records for traffic accidents occurring in Jordan and the first to apply balancing techniques to analyze injury severity of traffic accidents. Copyright © 2015 Elsevier Ltd. All rights reserved.

  1. SVM classifier on chip for melanoma detection.

    Science.gov (United States)

    Afifi, Shereen; GholamHosseini, Hamid; Sinha, Roopak

    2017-07-01

    Support Vector Machine (SVM) is a common classifier used for efficient classification with high accuracy. SVM shows high accuracy for classifying melanoma (skin cancer) clinical images within computer-aided diagnosis systems used by skin cancer specialists to detect melanoma early and save lives. We aim to develop a medical low-cost handheld device that runs a real-time embedded SVM-based diagnosis system for use in primary care for early detection of melanoma. In this paper, an optimized SVM classifier is implemented onto a recent FPGA platform using the latest design methodology to be embedded into the proposed device for realizing online efficient melanoma detection on a single system on chip/device. The hardware implementation results demonstrate a high classification accuracy of 97.9% and a significant acceleration factor of 26 from equivalent software implementation on an embedded processor, with 34% of resources utilization and 2 watts for power consumption. Consequently, the implemented system meets crucial embedded systems constraints of high performance and low cost, resources utilization and power consumption, while achieving high classification accuracy.

  2. A method to classify neutrino events according to there completeness

    International Nuclear Information System (INIS)

    Armenise, N.; Iaselli, G.

    1984-01-01

    Complete neutrino events are separated from the total sample with a discriminant analysis in a many fold space described in the text. Two new powerfull variables are found which discriminate with high efficiency and tag the event type as far as the completeness is concerned

  3. Apparatus and method for classifying fuel pellets for nuclear reactor

    International Nuclear Information System (INIS)

    Wilks, R.S.; Breakey, G.A.; Castner, R.P.; Sternheim, E.; Sturges, R.H. Jr.; Taleff, A.

    1984-01-01

    Control for the operation of a mechanical handling and gauging system for nuclear fuel pellets is claimed. The pellets are inspected for diameters, lengths, surface flaws and weights in successive stations. The control includes, a computer for commanding the operation of the system and its electronics and for storing and processing the complex data derived at the required high rate. In measuring the diameter, the computer enables the measurement of a calibration pellet, stores that calibration data and computes and stores diameter-correction factors and their addresses along a pellet. To each diameter measurement a correction factor is applied at the appropriate address. The computer commands verification that all critical parts of the system and control are set for inspection and that each pellet is positioned for inspection. During each cycle of inspection, the measurement operation proceeds normally irrespective of whether or not a pellet is present in each station. If a pellet is not positioned in a station, a measurement is recorded, but the recorded measurement indicates maloperation. In measuring diameter and length a light pattern including successive shadows of slices transverse for diameter or longitudinal for length are projected on a photodiode array. The light pattern is scanned electronically by a train of pulses. The pulses are counted during the scan of the lighted diodes. For evaluation of diameter the maximum diameter count and the number of slices for which the diameter exceeds a predetermined minimum is determined. For acceptance, the maximum must be less than a maximum level and the minimum must exceed a set number. For evaluation of length, the maximum length is determined. For acceptance, the length must be within maximum and minimum limits

  4. Bell Operator Method to Classify Local Realistic Theories

    International Nuclear Information System (INIS)

    Nagata, Koji

    2010-01-01

    We review the historical fact of multipartite Bell inequalities with an arbitrary number of settings. An explicit local realistic model for the values of a correlation function, given in a two-setting Bell experiment (two-setting model), works only for the specific set of settings in the given experiment, but cannot construct a local realistic model for the values of a correlation function, given in a continuous-infinite settings Bell experiment (infinite-setting model), even though there exist two-setting models for all directions in space. Hence, the two-setting model does not have the property that the infinite-setting model has. Here, we show that an explicit two-setting model cannot construct a local realistic model for the values of a correlation function, given in an M-setting Bell experiment (M-setting model), even though there exist two-setting models for the M measurement directions chosen in the given M-setting experiment. Hence, the two-setting model does not have the property that the M-setting model has. (general)

  5. Improving Naive Bayes with Online Feature Selection for Quick Adaptation to Evolving Feature Usefulness

    Energy Technology Data Exchange (ETDEWEB)

    Pon, R K; Cardenas, A F; Buttler, D J

    2007-09-19

    The definition of what makes an article interesting varies from user to user and continually evolves even for a single user. As a result, for news recommendation systems, useless document features can not be determined a priori and all features are usually considered for interestingness classification. Consequently, the presence of currently useless features degrades classification performance [1], particularly over the initial set of news articles being classified. The initial set of document is critical for a user when considering which particular news recommendation system to adopt. To address these problems, we introduce an improved version of the naive Bayes classifier with online feature selection. We use correlation to determine the utility of each feature and take advantage of the conditional independence assumption used by naive Bayes for online feature selection and classification. The augmented naive Bayes classifier performs 28% better than the traditional naive Bayes classifier in recommending news articles from the Yahoo! RSS feeds.

  6. Evolving autonomous learning in cognitive networks.

    Science.gov (United States)

    Sheneman, Leigh; Hintze, Arend

    2017-12-01

    There are two common approaches for optimizing the performance of a machine: genetic algorithms and machine learning. A genetic algorithm is applied over many generations whereas machine learning works by applying feedback until the system meets a performance threshold. These methods have been previously combined, particularly in artificial neural networks using an external objective feedback mechanism. We adapt this approach to Markov Brains, which are evolvable networks of probabilistic and deterministic logic gates. Prior to this work MB could only adapt from one generation to the other, so we introduce feedback gates which augment their ability to learn during their lifetime. We show that Markov Brains can incorporate these feedback gates in such a way that they do not rely on an external objective feedback signal, but instead can generate internal feedback that is then used to learn. This results in a more biologically accurate model of the evolution of learning, which will enable us to study the interplay between evolution and learning and could be another step towards autonomously learning machines.

  7. Evolving application of biomimetic nanostructured hydroxyapatite

    Directory of Open Access Journals (Sweden)

    Norberto Roveri

    2010-11-01

    Full Text Available Norberto Roveri, Michele IafiscoLaboratory of Environmental and Biological Structural Chemistry (LEBSC, Dipartimento di Chimica ‘G. Ciamician’, Alma Mater Studiorum, Università di Bologna, Bologna, ItalyAbstract: By mimicking Nature, we can design and synthesize inorganic smart materials that are reactive to biological tissues. These smart materials can be utilized to design innovative third-generation biomaterials, which are able to not only optimize their interaction with biological tissues and environment, but also mimic biogenic materials in their functionalities. The biomedical applications involve increasing the biomimetic levels from chemical composition, structural organization, morphology, mechanical behavior, nanostructure, and bulk and surface chemical–physical properties until the surface becomes bioreactive and stimulates cellular materials. The chemical–physical characteristics of biogenic hydroxyapatites from bone and tooth have been described, in order to point out the elective sides, which are important to reproduce the design of a new biomimetic synthetic hydroxyapatite. This review outlines the evolving applications of biomimetic synthetic calcium phosphates, details the main characteristics of bone and tooth, where the calcium phosphates are present, and discusses the chemical–physical characteristics of biomimetic calcium phosphates, methods of synthesizing them, and some of their biomedical applications.Keywords: hydroxyapatite, nanocrystals, biomimetism, biomaterials, drug delivery, remineralization

  8. Performance analysis of a Principal Component Analysis ensemble classifier for Emotiv headset P300 spellers.

    Science.gov (United States)

    Elsawy, Amr S; Eldawlatly, Seif; Taher, Mohamed; Aly, Gamal M

    2014-01-01

    The current trend to use Brain-Computer Interfaces (BCIs) with mobile devices mandates the development of efficient EEG data processing methods. In this paper, we demonstrate the performance of a Principal Component Analysis (PCA) ensemble classifier for P300-based spellers. We recorded EEG data from multiple subjects using the Emotiv neuroheadset in the context of a classical oddball P300 speller paradigm. We compare the performance of the proposed ensemble classifier to the performance of traditional feature extraction and classifier methods. Our results demonstrate the capability of the PCA ensemble classifier to classify P300 data recorded using the Emotiv neuroheadset with an average accuracy of 86.29% on cross-validation data. In addition, offline testing of the recorded data reveals an average classification accuracy of 73.3% that is significantly higher than that achieved using traditional methods. Finally, we demonstrate the effect of the parameters of the P300 speller paradigm on the performance of the method.

  9. Sex determination: ways to evolve a hermaphrodite.

    OpenAIRE

    Braendle , Christian; Félix , Marie-Anne

    2006-01-01

    Most species of the nematode genus Caenorhabditis reproduce through males and females; C. elegans and C. briggsae, however, produce self-fertile hermaphrodites instead of females. These transitions to hermaphroditism evolved convergently through distinct modifications of germline sex determination mechanisms.

  10. WSC-07: Evolving the Web Services Challenge

    NARCIS (Netherlands)

    Blake, M. Brian; Cheung, William K.W.; Jaeger, Michael C.; Wombacher, Andreas

    Service-oriented architecture (SOA) is an evolving architectural paradigm where businesses can expose their capabilities as modular, network-accessible software services. By decomposing capabilities into modular services, organizations can share their offerings at multiple levels of granularity

  11. Marshal: Maintaining Evolving Models, Phase I

    Data.gov (United States)

    National Aeronautics and Space Administration — SIFT proposes to design and develop the Marshal system, a mixed-initiative tool for maintaining task models over the course of evolving missions. Marshal-enabled...

  12. Satcom access in the Evolved Packet Core

    NARCIS (Netherlands)

    Cano Soveri, M.D.; Norp, A.H.J.; Popova, M.P.

    2011-01-01

    Satellite communications (Satcom) networks are increasingly integrating with terrestrial communications networks, namely Next Generation Networks (NGN). In the area of NGN the Evolved Packet Core (EPC) is a new network architecture that can support multiple access technologies. When Satcom is

  13. Satcom access in the evolved packet core

    NARCIS (Netherlands)

    Cano, M.D.; Norp, A.H.J.; Popova, M.P.

    2012-01-01

    Satellite communications (Satcom) networks are increasingly integrating with terrestrial communications networks, namely Next Generation Networks (NGN). In the area of NGN the Evolved Packet Core (EPC) is a new network architecture that can support multiple access technologies. When Satcom is

  14. Evolving effective incremental SAT solvers with GP

    OpenAIRE

    Bader, Mohamed; Poli, R.

    2008-01-01

    Hyper-Heuristics could simply be defined as heuristics to choose other heuristics, and it is a way of combining existing heuristics to generate new ones. In a Hyper-Heuristic framework, the framework is used for evolving effective incremental (Inc*) solvers for SAT. We test the evolved heuristics (IncHH) against other known local search heuristics on a variety of benchmark SAT problems.

  15. A Novel Cascade Classifier for Automatic Microcalcification Detection.

    Directory of Open Access Journals (Sweden)

    Seung Yeon Shin

    Full Text Available In this paper, we present a novel cascaded classification framework for automatic detection of individual and clusters of microcalcifications (μC. Our framework comprises three classification stages: i a random forest (RF classifier for simple features capturing the second order local structure of individual μCs, where non-μC pixels in the target mammogram are efficiently eliminated; ii a more complex discriminative restricted Boltzmann machine (DRBM classifier for μC candidates determined in the RF stage, which automatically learns the detailed morphology of μC appearances for improved discriminative power; and iii a detector to detect clusters of μCs from the individual μC detection results, using two different criteria. From the two-stage RF-DRBM classifier, we are able to distinguish μCs using explicitly computed features, as well as learn implicit features that are able to further discriminate between confusing cases. Experimental evaluation is conducted on the original Mammographic Image Analysis Society (MIAS and mini-MIAS databases, as well as our own Seoul National University Bundang Hospital digital mammographic database. It is shown that the proposed method outperforms comparable methods in terms of receiver operating characteristic (ROC and precision-recall curves for detection of individual μCs and free-response receiver operating characteristic (FROC curve for detection of clustered μCs.

  16. Application of the Naive Bayesian Classifier to optimize treatment decisions

    International Nuclear Information System (INIS)

    Kazmierska, Joanna; Malicki, Julian

    2008-01-01

    Background and purpose: To study the accuracy, specificity and sensitivity of the Naive Bayesian Classifier (NBC) in the assessment of individual risk of cancer relapse or progression after radiotherapy (RT). Materials and methods: Data of 142 brain tumour patients irradiated from 2000 to 2005 were analyzed. Ninety-six attributes related to disease, patient and treatment were chosen. Attributes in binary form consisted of the training set for NBC learning. NBC calculated an individual conditional probability of being assigned to: relapse or progression (1), or no relapse or progression (0) group. Accuracy, attribute selection and quality of classifier were determined by comparison with actual treatment results, leave-one-out and cross validation methods, respectively. Clinical setting test utilized data of 35 patients. Treatment results at classification were unknown and were compared with classification results after 3 months. Results: High classification accuracy (84%), specificity (0.87) and sensitivity (0.80) were achieved, both for classifier training and in progressive clinical evaluation. Conclusions: NBC is a useful tool to support the assessment of individual risk of relapse or progression in patients diagnosed with brain tumour undergoing RT postoperatively

  17. Entropy based classifier for cross-domain opinion mining

    Directory of Open Access Journals (Sweden)

    Jyoti S. Deshmukh

    2018-01-01

    Full Text Available In recent years, the growth of social network has increased the interest of people in analyzing reviews and opinions for products before they buy them. Consequently, this has given rise to the domain adaptation as a prominent area of research in sentiment analysis. A classifier trained from one domain often gives poor results on data from another domain. Expression of sentiment is different in every domain. The labeling cost of each domain separately is very high as well as time consuming. Therefore, this study has proposed an approach that extracts and classifies opinion words from one domain called source domain and predicts opinion words of another domain called target domain using a semi-supervised approach, which combines modified maximum entropy and bipartite graph clustering. A comparison of opinion classification on reviews on four different product domains is presented. The results demonstrate that the proposed method performs relatively well in comparison to the other methods. Comparison of SentiWordNet of domain-specific and domain-independent words reveals that on an average 72.6% and 88.4% words, respectively, are correctly classified.

  18. The Protection of Classified Information: The Legal Framework

    National Research Council Canada - National Science Library

    Elsea, Jennifer K

    2006-01-01

    Recent incidents involving leaks of classified information have heightened interest in the legal framework that governs security classification, access to classified information, and penalties for improper disclosure...

  19. Deep Feature Learning and Cascaded Classifier for Large Scale Data

    DEFF Research Database (Denmark)

    Prasoon, Adhish

    from data rather than having a predefined feature set. We explore deep learning approach of convolutional neural network (CNN) for segmenting three dimensional medical images. We propose a novel system integrating three 2D CNNs, which have a one-to-one association with the xy, yz and zx planes of 3D......This thesis focuses on voxel/pixel classification based approaches for image segmentation. The main application is segmentation of articular cartilage in knee MRIs. The first major contribution of the thesis deals with large scale machine learning problems. Many medical imaging problems need huge...... amount of training data to cover sufficient biological variability. Learning methods scaling badly with number of training data points cannot be used in such scenarios. This may restrict the usage of many powerful classifiers having excellent generalization ability. We propose a cascaded classifier which...

  20. Evolved Representation and Computational Creativity

    Directory of Open Access Journals (Sweden)

    Ashraf Fouad Hafez Ismail

    2001-01-01

    or design methods, but each individual computational design system has only one or very few different representations available.Whatever the choice of the representation, it is likely to influence the outcome of the design process. In any representation, some designs may be more difficult to represent than others, and some designs may not be representable at all.The same applies if the design process is implemented in a computer program. If a design cannot be represented with a given representation, it cannot be the outcome of a design process using this representation. As is the case for human designers, it is also possible that the representation influences a computational design process such that it is easier for the program to find some designs than others. Depending on the design process used, this might make those designs a more likely outcome of the design process. This is for example the case with stochastic optimization processes, like evolutionary systems and simulated annealing. In these cases, the representation is likely to introduce a bias into the design process.The selection of the representation is therefore of high importance in the development of a computational design system. Obviously, while choosing the representation the programmer has to ensure that all or as many as possible potentially ‘interesting’ designs can be represented. But it is also generally desirable to minimize the bias introduced by the representation. In contrast to the user-provided design criteria, the bias caused by the representation influences the outcome of the design process in an implicit way which is not obvious to the user, and is difficult to predict and control.The idea developed in this research is that it is possible to turn the bias caused by the representation into a virtue, by deliberately choosing or modifying the representation to influence the design process in a certain desired way. The resulting ‘focusing’ of the search process is connected to the

  1. Application of SVM classifier in thermographic image classification for early detection of breast cancer

    Science.gov (United States)

    Oleszkiewicz, Witold; Cichosz, Paweł; Jagodziński, Dariusz; Matysiewicz, Mateusz; Neumann, Łukasz; Nowak, Robert M.; Okuniewski, Rafał

    2016-09-01

    This article presents the application of machine learning algorithms for early detection of breast cancer on the basis of thermographic images. Supervised learning model: Support vector machine (SVM) and Sequential Minimal Optimization algorithm (SMO) for the training of SVM classifier were implemented. The SVM classifier was included in a client-server application which enables to create a training set of examinations and to apply classifiers (including SVM) for the diagnosis and early detection of the breast cancer. The sensitivity and specificity of SVM classifier were calculated based on the thermographic images from studies. Furthermore, the heuristic method for SVM's parameters tuning was proposed.

  2. Classifying spaces of degenerating polarized Hodge structures

    CERN Document Server

    Kato, Kazuya

    2009-01-01

    In 1970, Phillip Griffiths envisioned that points at infinity could be added to the classifying space D of polarized Hodge structures. In this book, Kazuya Kato and Sampei Usui realize this dream by creating a logarithmic Hodge theory. They use the logarithmic structures begun by Fontaine-Illusie to revive nilpotent orbits as a logarithmic Hodge structure. The book focuses on two principal topics. First, Kato and Usui construct the fine moduli space of polarized logarithmic Hodge structures with additional structures. Even for a Hermitian symmetric domain D, the present theory is a refinem

  3. Cubical sets as a classifying topos

    DEFF Research Database (Denmark)

    Spitters, Bas

    Coquand’s cubical set model for homotopy type theory provides the basis for a computational interpretation of the univalence axiom and some higher inductive types, as implemented in the cubical proof assistant. We show that the underlying cube category is the opposite of the Lawvere theory of De...... Morgan algebras. The topos of cubical sets itself classifies the theory of ‘free De Morgan algebras’. This provides us with a topos with an internal ‘interval’. Using this interval we construct a model of type theory following van den Berg and Garner. We are currently investigating the precise relation...

  4. Statistical and Machine-Learning Classifier Framework to Improve Pulse Shape Discrimination System Design

    Energy Technology Data Exchange (ETDEWEB)

    Wurtz, R. [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States); Kaplan, A. [Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)

    2015-10-28

    Pulse shape discrimination (PSD) is a variety of statistical classifier. Fully-­realized statistical classifiers rely on a comprehensive set of tools for designing, building, and implementing. PSD advances rely on improvements to the implemented algorithm. PSD advances can be improved by using conventional statistical classifier or machine learning methods. This paper provides the reader with a glossary of classifier-­building elements and their functions in a fully-­designed and operational classifier framework that can be used to discover opportunities for improving PSD classifier projects. This paper recommends reporting the PSD classifier’s receiver operating characteristic (ROC) curve and its behavior at a gamma rejection rate (GRR) relevant for realistic applications.

  5. Biomimetic molecular design tools that learn, evolve, and adapt

    Directory of Open Access Journals (Sweden)

    David A Winkler

    2017-06-01

    Full Text Available A dominant hallmark of living systems is their ability to adapt to changes in the environment by learning and evolving. Nature does this so superbly that intensive research efforts are now attempting to mimic biological processes. Initially this biomimicry involved developing synthetic methods to generate complex bioactive natural products. Recent work is attempting to understand how molecular machines operate so their principles can be copied, and learning how to employ biomimetic evolution and learning methods to solve complex problems in science, medicine and engineering. Automation, robotics, artificial intelligence, and evolutionary algorithms are now converging to generate what might broadly be called in silico-based adaptive evolution of materials. These methods are being applied to organic chemistry to systematize reactions, create synthesis robots to carry out unit operations, and to devise closed loop flow self-optimizing chemical synthesis systems. Most scientific innovations and technologies pass through the well-known “S curve”, with slow beginning, an almost exponential growth in capability, and a stable applications period. Adaptive, evolving, machine learning-based molecular design and optimization methods are approaching the period of very rapid growth and their impact is already being described as potentially disruptive. This paper describes new developments in biomimetic adaptive, evolving, learning computational molecular design methods and their potential impacts in chemistry, engineering, and medicine.

  6. Biomimetic molecular design tools that learn, evolve, and adapt

    Science.gov (United States)

    2017-01-01

    A dominant hallmark of living systems is their ability to adapt to changes in the environment by learning and evolving. Nature does this so superbly that intensive research efforts are now attempting to mimic biological processes. Initially this biomimicry involved developing synthetic methods to generate complex bioactive natural products. Recent work is attempting to understand how molecular machines operate so their principles can be copied, and learning how to employ biomimetic evolution and learning methods to solve complex problems in science, medicine and engineering. Automation, robotics, artificial intelligence, and evolutionary algorithms are now converging to generate what might broadly be called in silico-based adaptive evolution of materials. These methods are being applied to organic chemistry to systematize reactions, create synthesis robots to carry out unit operations, and to devise closed loop flow self-optimizing chemical synthesis systems. Most scientific innovations and technologies pass through the well-known “S curve”, with slow beginning, an almost exponential growth in capability, and a stable applications period. Adaptive, evolving, machine learning-based molecular design and optimization methods are approaching the period of very rapid growth and their impact is already being described as potentially disruptive. This paper describes new developments in biomimetic adaptive, evolving, learning computational molecular design methods and their potential impacts in chemistry, engineering, and medicine. PMID:28694872

  7. Analysis and minimization of overtraining effect in rule-based classifiers for computer-aided diagnosis

    International Nuclear Information System (INIS)

    Li Qiang; Doi Kunio

    2006-01-01

    Computer-aided diagnostic (CAD) schemes have been developed to assist radiologists detect various lesions in medical images. In CAD schemes, classifiers play a key role in achieving a high lesion detection rate and a low false-positive rate. Although many popular classifiers such as linear discriminant analysis and artificial neural networks have been employed in CAD schemes for reduction of false positives, a rule-based classifier has probably been the simplest and most frequently used one since the early days of development of various CAD schemes. However, with existing rule-based classifiers, there are major disadvantages that significantly reduce their practicality and credibility. The disadvantages include manual design, poor reproducibility, poor evaluation methods such as resubstitution, and a large overtraining effect. An automated rule-based classifier with a minimized overtraining effect can overcome or significantly reduce the extent of the above-mentioned disadvantages. In this study, we developed an 'optimal' method for the selection of cutoff thresholds and a fully automated rule-based classifier. Experimental results performed with Monte Carlo simulation and a real lung nodule CT data set demonstrated that the automated threshold selection method can completely eliminate overtraining effect in the procedure of cutoff threshold selection, and thus can minimize overall overtraining effect in the constructed rule-based classifier. We believe that this threshold selection method is very useful in the construction of automated rule-based classifiers with minimized overtraining effect

  8. A multiscale curvature algorithm for classifying discrete return LiDAR in forested environments

    Science.gov (United States)

    Jeffrey S. Evans; Andrew T. Hudak

    2007-01-01

    One prerequisite to the use of light detection and ranging (LiDAR) across disciplines is differentiating ground from nonground returns. The objective was to automatically and objectively classify points within unclassified LiDAR point clouds, with few model parameters and minimal postprocessing. Presented is an automated method for classifying LiDAR returns as ground...

  9. STATISTICAL TOOLS FOR CLASSIFYING GALAXY GROUP DYNAMICS

    International Nuclear Information System (INIS)

    Hou, Annie; Parker, Laura C.; Harris, William E.; Wilman, David J.

    2009-01-01

    The dynamical state of galaxy groups at intermediate redshifts can provide information about the growth of structure in the universe. We examine three goodness-of-fit tests, the Anderson-Darling (A-D), Kolmogorov, and χ 2 tests, in order to determine which statistical tool is best able to distinguish between groups that are relaxed and those that are dynamically complex. We perform Monte Carlo simulations of these three tests and show that the χ 2 test is profoundly unreliable for groups with fewer than 30 members. Power studies of the Kolmogorov and A-D tests are conducted to test their robustness for various sample sizes. We then apply these tests to a sample of the second Canadian Network for Observational Cosmology Redshift Survey (CNOC2) galaxy groups and find that the A-D test is far more reliable and powerful at detecting real departures from an underlying Gaussian distribution than the more commonly used χ 2 and Kolmogorov tests. We use this statistic to classify a sample of the CNOC2 groups and find that 34 of 106 groups are inconsistent with an underlying Gaussian velocity distribution, and thus do not appear relaxed. In addition, we compute velocity dispersion profiles (VDPs) for all groups with more than 20 members and compare the overall features of the Gaussian and non-Gaussian groups, finding that the VDPs of the non-Gaussian groups are distinct from those classified as Gaussian.

  10. Genetic programming for evolving due-date assignment models in job shop environments.

    Science.gov (United States)

    Nguyen, Su; Zhang, Mengjie; Johnston, Mark; Tan, Kay Chen

    2014-01-01

    Due-date assignment plays an important role in scheduling systems and strongly influences the delivery performance of job shops. Because of the stochastic and dynamic nature of job shops, the development of general due-date assignment models (DDAMs) is complicated. In this study, two genetic programming (GP) methods are proposed to evolve DDAMs for job shop environments. The experimental results show that the evolved DDAMs can make more accurate estimates than other existing dynamic DDAMs with promising reusability. In addition, the evolved operation-based DDAMs show better performance than the evolved DDAMs employing aggregate information of jobs and machines.

  11. Comprehensive benchmarking and ensemble approaches for metagenomic classifiers.

    Science.gov (United States)

    McIntyre, Alexa B R; Ounit, Rachid; Afshinnekoo, Ebrahim; Prill, Robert J; Hénaff, Elizabeth; Alexander, Noah; Minot, Samuel S; Danko, David; Foox, Jonathan; Ahsanuddin, Sofia; Tighe, Scott; Hasan, Nur A; Subramanian, Poorani; Moffat, Kelly; Levy, Shawn; Lonardi, Stefano; Greenfield, Nick; Colwell, Rita R; Rosen, Gail L; Mason, Christopher E

    2017-09-21

    One of the main challenges in metagenomics is the identification of microorganisms in clinical and environmental samples. While an extensive and heterogeneous set of computational tools is available to classify microorganisms using whole-genome shotgun sequencing data, comprehensive comparisons of these methods are limited. In this study, we use the largest-to-date set of laboratory-generated and simulated controls across 846 species to evaluate the performance of 11 metagenomic classifiers. Tools were characterized on the basis of their ability to identify taxa at the genus, species, and strain levels, quantify relative abundances of taxa, and classify individual reads to the species level. Strikingly, the number of species identified by the 11 tools can differ by over three orders of magnitude on the same datasets. Various strategies can ameliorate taxonomic misclassification, including abundance filtering, ensemble approaches, and tool intersection. Nevertheless, these strategies were often insufficient to completely eliminate false positives from environmental samples, which are especially important where they concern medically relevant species. Overall, pairing tools with different classification strategies (k-mer, alignment, marker) can combine their respective advantages. This study provides positive and negative controls, titrated standards, and a guide for selecting tools for metagenomic analyses by comparing ranges of precision, accuracy, and recall. We show that proper experimental design and analysis parameters can reduce false positives, provide greater resolution of species in complex metagenomic samples, and improve the interpretation of results.

  12. Classifying the metal dependence of uncharacterized nitrogenases

    Directory of Open Access Journals (Sweden)

    Shawn E Mcglynn

    2013-01-01

    Full Text Available Nitrogenase enzymes have evolved complex iron-sulfur (Fe-S containing cofactors that most commonly contain molybdenum (MoFe, Nif as a heterometal but also exist as vanadium (VFe, Vnf and heterometal independent (Fe-only, Anf forms. All three varieties are capable of the reduction of dinitrogen (N2 to ammonia (NH3 but exhibit differences in catalytic rates and substrate specificity unique to metal type. Recently, N2 reduction activity was observed in archaeal methanotrophs and methanogens that encode for nitrogenase homologs which do not cluster phylogenetically with previously characterized nitrogenases. To gain insight into the metal cofactors of these uncharacterized nitrogenase homologs, predicted three-dimensional structures of the nitrogenase active site metal-cofactor binding subunits NifD, VnfD, and AnfD were generated and compared. Dendograms based on structural similarity indicate nitrogenase homologs cluster based on heterometal content and that uncharacterized nitrogenase D homologs cluster with NifD, providing evidence that the structure of the enzyme has evolved in response to metal utilization. Characterization of the structural environment of the nitrogenase active site revealed amino acid variations that are unique to each class of nitrogenase as defined by heterometal cofactor content; uncharacterized nitrogenases contain amino acids near the active site most similar to NifD. Together, these results suggest that uncharacterized nitrogenase homologs present in numerous anaerobic methanogens, archaeal methanotrophs, and firmicutes bind FeMo-co in their active site, and add to growing evidence that diversification of metal utilization likely occurred in an anaerobic habitat.

  13. 36 CFR 1256.46 - National security-classified information.

    Science.gov (United States)

    2010-07-01

    ... 36 Parks, Forests, and Public Property 3 2010-07-01 2010-07-01 false National security-classified... Restrictions § 1256.46 National security-classified information. In accordance with 5 U.S.C. 552(b)(1), NARA... properly classified under the provisions of the pertinent Executive Order on Classified National Security...

  14. Quantum mechanics in an evolving Hilbert space

    Science.gov (United States)

    Artacho, Emilio; O'Regan, David D.

    2017-03-01

    Many basis sets for electronic structure calculations evolve with varying external parameters, such as moving atoms in dynamic simulations, giving rise to extra derivative terms in the dynamical equations. Here we revisit these derivatives in the context of differential geometry, thereby obtaining a more transparent formalization, and a geometrical perspective for better understanding the resulting equations. The effect of the evolution of the basis set within the spanned Hilbert space separates explicitly from the effect of the turning of the space itself when moving in parameter space, as the tangent space turns when moving in a curved space. New insights are obtained using familiar concepts in that context such as the Riemann curvature. The differential geometry is not strictly that for curved spaces as in general relativity, a more adequate mathematical framework being provided by fiber bundles. The language used here, however, will be restricted to tensors and basic quantum mechanics. The local gauge implied by a smoothly varying basis set readily connects with Berry's formalism for geometric phases. Generalized expressions for the Berry connection and curvature are obtained for a parameter-dependent occupied Hilbert space spanned by nonorthogonal Wannier functions. The formalism is applicable to basis sets made of atomic-like orbitals and also more adaptative moving basis functions (such as in methods using Wannier functions as intermediate or support bases), but should also apply to other situations in which nonorthogonal functions or related projectors should arise. The formalism is applied to the time-dependent quantum evolution of electrons for moving atoms. The geometric insights provided here allow us to propose new finite-difference time integrators, and also better understand those already proposed.

  15. Two channel EEG thought pattern classifier.

    Science.gov (United States)

    Craig, D A; Nguyen, H T; Burchey, H A

    2006-01-01

    This paper presents a real-time electro-encephalogram (EEG) identification system with the goal of achieving hands free control. With two EEG electrodes placed on the scalp of the user, EEG signals are amplified and digitised directly using a ProComp+ encoder and transferred to the host computer through the RS232 interface. Using a real-time multilayer neural network, the actual classification for the control of a powered wheelchair has a very fast response. It can detect changes in the user's thought pattern in 1 second. Using only two EEG electrodes at positions O(1) and C(4) the system can classify three mental commands (forward, left and right) with an accuracy of more than 79 %

  16. Classifying Drivers' Cognitive Load Using EEG Signals.

    Science.gov (United States)

    Barua, Shaibal; Ahmed, Mobyen Uddin; Begum, Shahina

    2017-01-01

    A growing traffic safety issue is the effect of cognitive loading activities on traffic safety and driving performance. To monitor drivers' mental state, understanding cognitive load is important since while driving, performing cognitively loading secondary tasks, for example talking on the phone, can affect the performance in the primary task, i.e. driving. Electroencephalography (EEG) is one of the reliable measures of cognitive load that can detect the changes in instantaneous load and effect of cognitively loading secondary task. In this driving simulator study, 1-back task is carried out while the driver performs three different simulated driving scenarios. This paper presents an EEG based approach to classify a drivers' level of cognitive load using Case-Based Reasoning (CBR). The results show that for each individual scenario as well as using data combined from the different scenarios, CBR based system achieved approximately over 70% of classification accuracy.

  17. Classifying prion and prion-like phenomena.

    Science.gov (United States)

    Harbi, Djamel; Harrison, Paul M

    2014-01-01

    The universe of prion and prion-like phenomena has expanded significantly in the past several years. Here, we overview the challenges in classifying this data informatically, given that terms such as "prion-like", "prion-related" or "prion-forming" do not have a stable meaning in the scientific literature. We examine the spectrum of proteins that have been described in the literature as forming prions, and discuss how "prion" can have a range of meaning, with a strict definition being for demonstration of infection with in vitro-derived recombinant prions. We suggest that although prion/prion-like phenomena can largely be apportioned into a small number of broad groups dependent on the type of transmissibility evidence for them, as new phenomena are discovered in the coming years, a detailed ontological approach might be necessary that allows for subtle definition of different "flavors" of prion / prion-like phenomena.

  18. Business process modeling for processing classified documents using RFID technology

    Directory of Open Access Journals (Sweden)

    Koszela Jarosław

    2016-01-01

    Full Text Available The article outlines the application of the processing approach to the functional description of the designed IT system supporting the operations of the secret office, which processes classified documents. The article describes the application of the method of incremental modeling of business processes according to the BPMN model to the description of the processes currently implemented (“as is” in a manual manner and target processes (“to be”, using the RFID technology for the purpose of their automation. Additionally, the examples of applying the method of structural and dynamic analysis of the processes (process simulation to verify their correctness and efficiency were presented. The extension of the process analysis method is a possibility of applying the warehouse of processes and process mining methods.

  19. Evolving Intelligent Systems Methodology and Applications

    CERN Document Server

    Angelov, Plamen; Kasabov, Nik

    2010-01-01

    From theory to techniques, the first all-in-one resource for EIS. There is a clear demand in advanced process industries, defense, and Internet and communication (VoIP) applications for intelligent yet adaptive/evolving systems. Evolving Intelligent Systems is the first self- contained volume that covers this newly established concept in its entirety, from a systematic methodology to case studies to industrial applications. Featuring chapters written by leading world experts, it addresses the progress, trends, and major achievements in this emerging research field, with a strong emphasis on th

  20. Interactively Evolving Compositional Sound Synthesis Networks

    DEFF Research Database (Denmark)

    Jónsson, Björn Þór; Hoover, Amy K.; Risi, Sebastian

    2015-01-01

    the space of potential sounds that can be generated through such compositional sound synthesis networks (CSSNs). To study the effect of evolution on subjective appreciation, participants in a listener study ranked evolved timbres by personal preference, resulting in preferences skewed toward the first......While the success of electronic music often relies on the uniqueness and quality of selected timbres, many musicians struggle with complicated and expensive equipment and techniques to create their desired sounds. Instead, this paper presents a technique for producing novel timbres that are evolved...

  1. Classifying Transition Behaviour in Postural Activity Monitoring

    Directory of Open Access Journals (Sweden)

    James BRUSEY

    2009-10-01

    Full Text Available A few accelerometers positioned on different parts of the body can be used to accurately classify steady state behaviour, such as walking, running, or sitting. Such systems are usually built using supervised learning approaches. Transitions between postures are, however, difficult to deal with using posture classification systems proposed to date, since there is no label set for intermediary postures and also the exact point at which the transition occurs can sometimes be hard to pinpoint. The usual bypass when using supervised learning to train such systems is to discard a section of the dataset around each transition. This leads to poorer classification performance when the systems are deployed out of the laboratory and used on-line, particularly if the regimes monitored involve fast paced activity changes. Time-based filtering that takes advantage of sequential patterns is a potential mechanism to improve posture classification accuracy in such real-life applications. Also, such filtering should reduce the number of event messages needed to be sent across a wireless network to track posture remotely, hence extending the system’s life. To support time-based filtering, understanding transitions, which are the major event generators in a classification system, is a key. This work examines three approaches to post-process the output of a posture classifier using time-based filtering: a naïve voting scheme, an exponentially weighted voting scheme, and a Bayes filter. Best performance is obtained from the exponentially weighted voting scheme although it is suspected that a more sophisticated treatment of the Bayes filter might yield better results.

  2. Reducing variability in the output of pattern classifiers using histogram shaping

    International Nuclear Information System (INIS)

    Gupta, Shalini; Kan, Chih-Wen; Markey, Mia K.

    2010-01-01

    Purpose: The authors present a novel technique based on histogram shaping to reduce the variability in the output and (sensitivity, specificity) pairs of pattern classifiers with identical ROC curves, but differently distributed outputs. Methods: The authors identify different sources of variability in the output of linear pattern classifiers with identical ROC curves, which also result in classifiers with differently distributed outputs. They theoretically develop a novel technique based on the matching of the histograms of these differently distributed pattern classifier outputs to reduce the variability in their (sensitivity, specificity) pairs at fixed decision thresholds, and to reduce the variability in their actual output values. They empirically demonstrate the efficacy of the proposed technique by means of analyses on the simulated data and real world mammography data. Results: For the simulated data, with three different known sources of variability, and for the real world mammography data with unknown sources of variability, the proposed classifier output calibration technique significantly reduced the variability in the classifiers' (sensitivity, specificity) pairs at fixed decision thresholds. Furthermore, for classifiers with monotonically or approximately monotonically related output variables, the histogram shaping technique also significantly reduced the variability in their actual output values. Conclusions: Classifier output calibration based on histogram shaping can be successfully employed to reduce the variability in the output values and (sensitivity, specificity) pairs of pattern classifiers with identical ROC curves, but differently distributed outputs.

  3. Drosophila olfactory receptors as classifiers for volatiles from disparate real world applications

    International Nuclear Information System (INIS)

    Nowotny, Thomas; De Bruyne, Marien; Warr, Coral G; Berna, Amalia Z; Trowell, Stephen C

    2014-01-01

    Olfactory receptors evolved to provide animals with ecologically and behaviourally relevant information. The resulting extreme sensitivity and discrimination has proven useful to humans, who have therefore co-opted some animals’ sense of smell. One aim of machine olfaction research is to replace the use of animal noses and one avenue of such research aims to incorporate olfactory receptors into artificial noses. Here, we investigate how well the olfactory receptors of the fruit fly, Drosophila melanogaster, perform in classifying volatile odourants that they would not normally encounter. We collected a large number of in vivo recordings from individual Drosophila olfactory receptor neurons in response to an ecologically relevant set of 36 chemicals related to wine (‘wine set’) and an ecologically irrelevant set of 35 chemicals related to chemical hazards (‘industrial set’), each chemical at a single concentration. Resampled response sets were used to classify the chemicals against all others within each set, using a standard linear support vector machine classifier and a wrapper approach. Drosophila receptors appear highly capable of distinguishing chemicals that they have not evolved to process. In contrast to previous work with metal oxide sensors, Drosophila receptors achieved the best recognition accuracy if the outputs of all 20 receptor types were used. (paper)

  4. Just-in-time adaptive classifiers-part II: designing the classifier.

    Science.gov (United States)

    Alippi, Cesare; Roveri, Manuel

    2008-12-01

    Aging effects, environmental changes, thermal drifts, and soft and hard faults affect physical systems by changing their nature and behavior over time. To cope with a process evolution adaptive solutions must be envisaged to track its dynamics; in this direction, adaptive classifiers are generally designed by assuming the stationary hypothesis for the process generating the data with very few results addressing nonstationary environments. This paper proposes a methodology based on k-nearest neighbor (NN) classifiers for designing adaptive classification systems able to react to changing conditions just-in-time (JIT), i.e., exactly when it is needed. k-NN classifiers have been selected for their computational-free training phase, the possibility to easily estimate the model complexity k and keep under control the computational complexity of the classifier through suitable data reduction mechanisms. A JIT classifier requires a temporal detection of a (possible) process deviation (aspect tackled in a companion paper) followed by an adaptive management of the knowledge base (KB) of the classifier to cope with the process change. The novelty of the proposed approach resides in the general framework supporting the real-time update of the KB of the classification system in response to novel information coming from the process both in stationary conditions (accuracy improvement) and in nonstationary ones (process tracking) and in providing a suitable estimate of k. It is shown that the classification system grants consistency once the change targets the process generating the data in a new stationary state, as it is the case in many real applications.

  5. Nonlinear Knowledge in Kernel-Based Multiple Criteria Programming Classifier

    Science.gov (United States)

    Zhang, Dongling; Tian, Yingjie; Shi, Yong

    Kernel-based Multiple Criteria Linear Programming (KMCLP) model is used as classification methods, which can learn from training examples. Whereas, in traditional machine learning area, data sets are classified only by prior knowledge. Some works combine the above two classification principle to overcome the defaults of each approach. In this paper, we propose a model to incorporate the nonlinear knowledge into KMCLP in order to solve the problem when input consists of not only training example, but also nonlinear prior knowledge. In dealing with real world case breast cancer diagnosis, the model shows its better performance than the model solely based on training data.

  6. Classifying BCI signals from novice users with extreme learning machine

    Directory of Open Access Journals (Sweden)

    Rodríguez-Bermúdez Germán

    2017-07-01

    Full Text Available Brain computer interface (BCI allows to control external devices only with the electrical activity of the brain. In order to improve the system, several approaches have been proposed. However it is usual to test algorithms with standard BCI signals from experts users or from repositories available on Internet. In this work, extreme learning machine (ELM has been tested with signals from 5 novel users to compare with standard classification algorithms. Experimental results show that ELM is a suitable method to classify electroencephalogram signals from novice users.

  7. On the Benefits of Divergent Search for Evolved Representations

    DEFF Research Database (Denmark)

    Lehman, Joel; Risi, Sebastian; Stanley, Kenneth O

    2012-01-01

    Evolved representations in evolutionary computation are often fragile, which can impede representation-dependent mechanisms such as self-adaptation. In contrast, evolved representations in nature are robust, evolvable, and creatively exploit available representational features. This paper provide...

  8. Preface: evolving rotifers, evolving science: Proceedings of the XIV International Rotifer Symposium

    Czech Academy of Sciences Publication Activity Database

    Devetter, Miloslav; Fontaneto, D.; Jersabek, Ch.D.; Welch, D.B.M.; May, L.; Walsh, E.J.

    2017-01-01

    Roč. 796, č. 1 (2017), s. 1-6 ISSN 0018-8158 Institutional support: RVO:60077344 Keywords : evolving rotifers * 14th International Rotifer Symposium * evolving science Subject RIV: EG - Zoology OBOR OECD: Zoology Impact factor: 2.056, year: 2016

  9. Identification of flooded area from satellite images using Hybrid Kohonen Fuzzy C-Means sigma classifier

    Directory of Open Access Journals (Sweden)

    Krishna Kant Singh

    2017-06-01

    Full Text Available A novel neuro fuzzy classifier Hybrid Kohonen Fuzzy C-Means-σ (HKFCM-σ is proposed in this paper. The proposed classifier is a hybridization of Kohonen Clustering Network (KCN with FCM-σ clustering algorithm. The network architecture of HKFCM-σ is similar to simple KCN network having only two layers, i.e., input and output layer. However, the selection of winner neuron is done based on FCM-σ algorithm. Thus, embedding the features of both, a neural network and a fuzzy clustering algorithm in the classifier. This hybridization results in a more efficient, less complex and faster classifier for classifying satellite images. HKFCM-σ is used to identify the flooding that occurred in Kashmir area in September 2014. The HKFCM-σ classifier is applied on pre and post flooding Landsat 8 OLI images of Kashmir to detect the areas that were flooded due to the heavy rainfalls of September, 2014. The classifier is trained using the mean values of the various spectral indices like NDVI, NDWI, NDBI and first component of Principal Component Analysis. The error matrix was computed to test the performance of the method. The method yields high producer’s accuracy, consumer’s accuracy and kappa coefficient value indicating that the proposed classifier is highly effective and efficient.

  10. Views on Evolvability of Embedded Systems

    NARCIS (Netherlands)

    Laar, P. van de; Punter, T.

    2011-01-01

    Evolvability, the ability to respond effectively to change, represents a major challenge to today's high-end embedded systems, such as those developed in the medical domain by Philips Healthcare. These systems are typically developed by multi-disciplinary teams, located around the world, and are in

  11. Views on evolvability of embedded systems

    NARCIS (Netherlands)

    Laar, van de P.J.L.J.; Punter, H.T.

    2011-01-01

    Evolvability, the ability to respond effectively to change, represents a major challenge to today's high-end embedded systems, such as those developed in the medical domain by Philips Healthcare. These systems are typically developed by multi-disciplinary teams, located around the world, and are in

  12. Designing Garments to Evolve Over Time

    DEFF Research Database (Denmark)

    Riisberg, Vibeke; Grose, Lynda

    2017-01-01

    This paper proposes a REDO of the current fashion paradigm by investigating how garments might be designed to evolve over time. The purpose is to discuss ways of expanding the traditional role of the designer to include temporal dimensions of creating, producing and using clothes and to suggest...... to a REDO of design education, to further research and the future fashion and textile industry....

  13. EVOLVING AN EMPIRICAL METHODOLOGY DOR DETERMINING ...

    African Journals Online (AJOL)

    The uniqueness of this approach, is that it can be applied to any forest or dynamic feature on the earth, and can enjoy universal application as well. KEY WORDS: Evolving empirical methodology, innovative mathematical model, appropriate interval, remote sensing, forest environment planning and management. Global Jnl ...

  14. Continual Learning through Evolvable Neural Turing Machines

    DEFF Research Database (Denmark)

    Lüders, Benno; Schläger, Mikkel; Risi, Sebastian

    2016-01-01

    Continual learning, i.e. the ability to sequentially learn tasks without catastrophic forgetting of previously learned ones, is an important open challenge in machine learning. In this paper we take a step in this direction by showing that the recently proposed Evolving Neural Turing Machine (ENTM...

  15. Did Language Evolve Like the Vertebrate Eye?

    Science.gov (United States)

    Botha, Rudolf P.

    2002-01-01

    Offers a critical appraisal of the way in which the idea that human language or some of its features evolved like the vertebrate eye by natural selection is articulated in Pinker and Bloom's (1990) selectionist account of language evolution. Argues that this account is less than insightful because it fails to draw some of the conceptual…

  16. Bias and Stability of Single Variable Classifiers for Feature Ranking and Selection.

    Science.gov (United States)

    Fakhraei, Shobeir; Soltanian-Zadeh, Hamid; Fotouhi, Farshad

    2014-11-01

    Feature rankings are often used for supervised dimension reduction especially when discriminating power of each feature is of interest, dimensionality of dataset is extremely high, or computational power is limited to perform more complicated methods. In practice, it is recommended to start dimension reduction via simple methods such as feature rankings before applying more complex approaches. Single Variable Classifier (SVC) ranking is a feature ranking based on the predictive performance of a classifier built using only a single feature. While benefiting from capabilities of classifiers, this ranking method is not as computationally intensive as wrappers. In this paper, we report the results of an extensive study on the bias and stability of such feature ranking method. We study whether the classifiers influence the SVC rankings or the discriminative power of features themselves has a dominant impact on the final rankings. We show the common intuition of using the same classifier for feature ranking and final classification does not always result in the best prediction performance. We then study if heterogeneous classifiers ensemble approaches provide more unbiased rankings and if they improve final classification performance. Furthermore, we calculate an empirical prediction performance loss for using the same classifier in SVC feature ranking and final classification from the optimal choices.

  17. On the statistical assessment of classifiers using DNA microarray data

    Directory of Open Access Journals (Sweden)

    Carella M

    2006-08-01

    Full Text Available Abstract Background In this paper we present a method for the statistical assessment of cancer predictors which make use of gene expression profiles. The methodology is applied to a new data set of microarray gene expression data collected in Casa Sollievo della Sofferenza Hospital, Foggia – Italy. The data set is made up of normal (22 and tumor (25 specimens extracted from 25 patients affected by colon cancer. We propose to give answers to some questions which are relevant for the automatic diagnosis of cancer such as: Is the size of the available data set sufficient to build accurate classifiers? What is the statistical significance of the associated error rates? In what ways can accuracy be considered dependant on the adopted classification scheme? How many genes are correlated with the pathology and how many are sufficient for an accurate colon cancer classification? The method we propose answers these questions whilst avoiding the potential pitfalls hidden in the analysis and interpretation of microarray data. Results We estimate the generalization error, evaluated through the Leave-K-Out Cross Validation error, for three different classification schemes by varying the number of training examples and the number of the genes used. The statistical significance of the error rate is measured by using a permutation test. We provide a statistical analysis in terms of the frequencies of the genes involved in the classification. Using the whole set of genes, we found that the Weighted Voting Algorithm (WVA classifier learns the distinction between normal and tumor specimens with 25 training examples, providing e = 21% (p = 0.045 as an error rate. This remains constant even when the number of examples increases. Moreover, Regularized Least Squares (RLS and Support Vector Machines (SVM classifiers can learn with only 15 training examples, with an error rate of e = 19% (p = 0.035 and e = 18% (p = 0.037 respectively. Moreover, the error rate

  18. EVOLVE : a Bridge between Probability, Set Oriented Numerics, and Evolutionary Computation II

    CERN Document Server

    Coello, Carlos; Tantar, Alexandru-Adrian; Tantar, Emilia; Bouvry, Pascal; Moral, Pierre; Legrand, Pierrick; EVOLVE 2012

    2013-01-01

    This book comprises a selection of papers from the EVOLVE 2012 held in Mexico City, Mexico. The aim of the EVOLVE is to build a bridge between probability, set oriented numerics and evolutionary computing, as to identify new common and challenging research aspects. The conference is also intended to foster a growing interest for robust and efficient methods with a sound theoretical background. EVOLVE is intended to unify theory-inspired methods and cutting-edge techniques ensuring performance guarantee factors. By gathering researchers with different backgrounds, a unified view and vocabulary can emerge where the theoretical advancements may echo in different domains. Summarizing, the EVOLVE focuses on challenging aspects arising at the passage from theory to new paradigms and aims to provide a unified view while raising questions related to reliability,  performance guarantees and modeling. The papers of the EVOLVE 2012 make a contribution to this goal. 

  19. FY1995 evolvable hardware chip; 1995 nendo shinkasuru hardware chip

    Energy Technology Data Exchange (ETDEWEB)

    NONE

    1997-03-01

    This project aims at the development of 'Evolvable Hardware' (EHW) which can adapt its hardware structure to the environment to attain better hardware performance, under the control of genetic algorithms. EHW is a key technology to explore the new application area requiring real-time performance and on-line adaptation. 1. Development of EHW-LSI for function level hardware evolution, which includes 15 DSPs in one chip. 2. Application of the EHW to the practical industrial applications such as data compression, ATM control, digital mobile communication. 3. Two patents : (1) the architecture and the processing method for programmable EHW-LSI. (2) The method of data compression for loss-less data, using EHW. 4. The first international conference for evolvable hardware was held by authors: Intl. Conf. on Evolvable Systems (ICES96). It was determined at ICES96 that ICES will be held every two years between Japan and Europe. So the new society has been established by us. (NEDO)

  20. Design of the tool for periodic not evolvent profiles

    Directory of Open Access Journals (Sweden)

    Anisimov Roman

    2017-01-01

    Full Text Available The new approach to profiling of the tool for processing of parts with periodic not evolvent profiles are considered in the article The discriminatory analysis of periodic profiles including repetition of profile both in the plane of perpendicular axis of part, and in the plane of passing along part of axis is offered. In the basis of the offered profiling method the idea of space shaping by rated surface of product of tool surface lies. The big advantage of the offered approach in profiling is its combination with the analysis of parameters of process of engineering work. It allows to predict the accuracy and surface quality of product with not evolvent periodic profile. While using the offered approach the pinion cutter for processing of wheels with internal triangular teeths and mill for processing of the screw of the counter of consumption of liquid, complex profile of which consists of several formings, have been received

  1. Classifying Adverse Events in the Dental Office.

    Science.gov (United States)

    Kalenderian, Elsbeth; Obadan-Udoh, Enihomo; Maramaldi, Peter; Etolue, Jini; Yansane, Alfa; Stewart, Denice; White, Joel; Vaderhobli, Ram; Kent, Karla; Hebballi, Nutan B; Delattre, Veronique; Kahn, Maria; Tokede, Oluwabunmi; Ramoni, Rachel B; Walji, Muhammad F

    2017-06-30

    Dentists strive to provide safe and effective oral healthcare. However, some patients may encounter an adverse event (AE) defined as "unnecessary harm due to dental treatment." In this research, we propose and evaluate two systems for categorizing the type and severity of AEs encountered at the dental office. Several existing medical AE type and severity classification systems were reviewed and adapted for dentistry. Using data collected in previous work, two initial dental AE type and severity classification systems were developed. Eight independent reviewers performed focused chart reviews, and AEs identified were used to evaluate and modify these newly developed classifications. A total of 958 charts were independently reviewed. Among the reviewed charts, 118 prospective AEs were found and 101 (85.6%) were verified as AEs through a consensus process. At the end of the study, a final AE type classification comprising 12 categories, and an AE severity classification comprising 7 categories emerged. Pain and infection were the most common AE types representing 73% of the cases reviewed (56% and 17%, respectively) and 88% were found to cause temporary, moderate to severe harm to the patient. Adverse events found during the chart review process were successfully classified using the novel dental AE type and severity classifications. Understanding the type of AEs and their severity are important steps if we are to learn from and prevent patient harm in the dental office.

  2. Is it important to classify ischaemic stroke?

    LENUS (Irish Health Repository)

    Iqbal, M

    2012-02-01

    Thirty-five percent of all ischemic events remain classified as cryptogenic. This study was conducted to ascertain the accuracy of diagnosis of ischaemic stroke based on information given in the medical notes. It was tested by applying the clinical information to the (TOAST) criteria. Hundred and five patients presented with acute stroke between Jan-Jun 2007. Data was collected on 90 patients. Male to female ratio was 39:51 with age range of 47-93 years. Sixty (67%) patients had total\\/partial anterior circulation stroke; 5 (5.6%) had a lacunar stroke and in 25 (28%) the mechanism of stroke could not be identified. Four (4.4%) patients with small vessel disease were anticoagulated; 5 (5.6%) with atrial fibrillation received antiplatelet therapy and 2 (2.2%) patients with atrial fibrillation underwent CEA. This study revealed deficiencies in the clinical assessment of patients and treatment was not tailored to the mechanism of stroke in some patients.

  3. Stress fracture development classified by bone scintigraphy

    International Nuclear Information System (INIS)

    Zwas, S.T.; Elkanovich, R.; Frank, G.; Aharonson, Z.

    1985-01-01

    There is no consensus on classifying stress fractures (SF) appearing on bone scans. The authors present a system of classification based on grading the severity and development of bone lesions by visual inspection, according to three main scintigraphic criteria: focality and size, intensity of uptake compare to adjacent bone, and local medular extension. Four grades of development (I-IV) were ranked, ranging from ill defined slightly increased cortical uptake to well defined regions with markedly increased uptake extending transversely bicortically. 310 male subjects aged 19-2, suffering several weeks from leg pains occurring during intensive physical training underwent bone scans of the pelvis and lower extremities using Tc-99-m-MDP. 76% of the scans were positive with 354 lesions, of which 88% were in th4e mild (I-II) grades and 12% in the moderate (III) and severe (IV) grades. Post-treatment scans were obtained in 65 cases having 78 lesions during 1- to 6-month intervals. Complete resolution was found after 1-2 months in 36% of the mild lesions but in only 12% of the moderate and severe ones, and after 3-6 months in 55% of the mild lesions and 15% of the severe ones. 75% of the moderate and severe lesions showed residual uptake in various stages throughout the follow-up period. Early recognition and treatment of mild SF lesions in this study prevented protracted disability and progression of the lesions and facilitated complete healing

  4. Case base classification on digital mammograms: improving the performance of case base classifier

    Science.gov (United States)

    Raman, Valliappan; Then, H. H.; Sumari, Putra; Venkatesa Mohan, N.

    2011-10-01

    Breast cancer continues to be a significant public health problem in the world. Early detection is the key for improving breast cancer prognosis. The aim of the research presented here is in twofold. First stage of research involves machine learning techniques, which segments and extracts features from the mass of digital mammograms. Second level is on problem solving approach which includes classification of mass by performance based case base classifier. In this paper we build a case-based Classifier in order to diagnose mammographic images. We explain different methods and behaviors that have been added to the classifier to improve the performance of the classifier. Currently the initial Performance base Classifier with Bagging is proposed in the paper and it's been implemented and it shows an improvement in specificity and sensitivity.

  5. Correcting Classifiers for Sample Selection Bias in Two-Phase Case-Control Studies

    Science.gov (United States)

    Theis, Fabian J.

    2017-01-01

    Epidemiological studies often utilize stratified data in which rare outcomes or exposures are artificially enriched. This design can increase precision in association tests but distorts predictions when applying classifiers on nonstratified data. Several methods correct for this so-called sample selection bias, but their performance remains unclear especially for machine learning classifiers. With an emphasis on two-phase case-control studies, we aim to assess which corrections to perform in which setting and to obtain methods suitable for machine learning techniques, especially the random forest. We propose two new resampling-based methods to resemble the original data and covariance structure: stochastic inverse-probability oversampling and parametric inverse-probability bagging. We compare all techniques for the random forest and other classifiers, both theoretically and on simulated and real data. Empirical results show that the random forest profits from only the parametric inverse-probability bagging proposed by us. For other classifiers, correction is mostly advantageous, and methods perform uniformly. We discuss consequences of inappropriate distribution assumptions and reason for different behaviors between the random forest and other classifiers. In conclusion, we provide guidance for choosing correction methods when training classifiers on biased samples. For random forests, our method outperforms state-of-the-art procedures if distribution assumptions are roughly fulfilled. We provide our implementation in the R package sambia. PMID:29312464

  6. Interface Prostheses With Classifier-Feedback-Based User Training.

    Science.gov (United States)

    Fang, Yinfeng; Zhou, Dalin; Li, Kairu; Liu, Honghai

    2017-11-01

    It is evident that user training significantly affects performance of pattern-recognition-based myoelectric prosthetic device control. Despite plausible classification accuracy on offline datasets, online accuracy usually suffers from the changes in physiological conditions and electrode displacement. The user ability in generating consistent electromyographic (EMG) patterns can be enhanced via proper user training strategies in order to improve online performance. This study proposes a clustering-feedback strategy that provides real-time feedback to users by means of a visualized online EMG signal input as well as the centroids of the training samples, whose dimensionality is reduced to minimal number by dimension reduction. Clustering feedback provides a criterion that guides users to adjust motion gestures and muscle contraction forces intentionally. The experiment results have demonstrated that hand motion recognition accuracy increases steadily along the progress of the clustering-feedback-based user training, while conventional classifier-feedback methods, i.e., label feedback, hardly achieve any improvement. The result concludes that the use of proper classifier feedback can accelerate the process of user training, and implies prosperous future for the amputees with limited or no experience in pattern-recognition-based prosthetic device manipulation.It is evident that user training significantly affects performance of pattern-recognition-based myoelectric prosthetic device control. Despite plausible classification accuracy on offline datasets, online accuracy usually suffers from the changes in physiological conditions and electrode displacement. The user ability in generating consistent electromyographic (EMG) patterns can be enhanced via proper user training strategies in order to improve online performance. This study proposes a clustering-feedback strategy that provides real-time feedback to users by means of a visualized online EMG signal input as well

  7. 41 CFR 105-62.102 - Authority to originally classify.

    Science.gov (United States)

    2010-07-01

    ... originally classify. (a) Top secret, secret, and confidential. The authority to originally classify information as Top Secret, Secret, or Confidential may be exercised only by the Administrator and is delegable...

  8. Naive Bayesian classifiers for multinomial features: a theoretical analysis

    CSIR Research Space (South Africa)

    Van Dyk, E

    2007-11-01

    Full Text Available The authors investigate the use of naive Bayesian classifiers for multinomial feature spaces and derive error estimates for these classifiers. The error analysis is done by developing a mathematical model to estimate the probability density...

  9. Ensemble of classifiers based network intrusion detection system performance bound

    CSIR Research Space (South Africa)

    Mkuzangwe, Nenekazi NP

    2017-11-01

    Full Text Available This paper provides a performance bound of a network intrusion detection system (NIDS) that uses an ensemble of classifiers. Currently researchers rely on implementing the ensemble of classifiers based NIDS before they can determine the performance...

  10. Fast Most Similar Neighbor (MSN) classifiers for Mixed Data

    OpenAIRE

    Hernández Rodríguez, Selene

    2010-01-01

    The k nearest neighbor (k-NN) classifier has been extensively used in Pattern Recognition because of its simplicity and its good performance. However, in large datasets applications, the exhaustive k-NN classifier becomes impractical. Therefore, many fast k-NN classifiers have been developed; most of them rely on metric properties (usually the triangle inequality) to reduce the number of prototype comparisons. Hence, the existing fast k-NN classifiers are applicable only when the comparison f...

  11. The evolving definition of systemic arterial hypertension.

    Science.gov (United States)

    Ram, C Venkata S; Giles, Thomas D

    2010-05-01

    Systemic hypertension is an important risk factor for premature cardiovascular disease. Hypertension also contributes to excessive morbidity and mortality. Whereas excellent therapeutic options are available to treat hypertension, there is an unsettled issue about the very definition of hypertension. At what level of blood pressure should we treat hypertension? Does the definition of hypertension change in the presence of co-morbid conditions? This article covers in detail the evolving concepts in the diagnosis and management of hypertension.

  12. The evolving epidemiology of inflammatory bowel disease.

    LENUS (Irish Health Repository)

    Shanahan, Fergus

    2009-07-01

    Epidemiologic studies in inflammatory bowel disease (IBD) include assessments of disease burden and evolving patterns of disease presentation. Although it is hoped that sound epidemiologic studies provide aetiological clues, traditional risk factor-based epidemiology has provided limited insights into either Crohn\\'s disease or ulcerative colitis etiopathogenesis. In this update, we will summarize how the changing epidemiology of IBD associated with modernization can be reconciled with current concepts of disease mechanisms and will discuss studies of clinically significant comorbidity in IBD.

  13. Development and the evolvability of human limbs

    OpenAIRE

    Young, Nathan M.; Wagner, Günter P.; Hallgrímsson, Benedikt

    2010-01-01

    The long legs and short arms of humans are distinctive for a primate, the result of selection acting in opposite directions on each limb at different points in our evolutionary history. This mosaic pattern challenges our understanding of the relationship of development and evolvability because limbs are serially homologous and genetic correlations should act as a significant constraint on their independent evolution. Here we test a developmental model of limb covariation in anthropoid primate...

  14. Quantum games on evolving random networks

    OpenAIRE

    Pawela, Łukasz

    2015-01-01

    We study the advantages of quantum strategies in evolutionary social dilemmas on evolving random networks. We focus our study on the two-player games: prisoner's dilemma, snowdrift and stag-hunt games. The obtained result show the benefits of quantum strategies for the prisoner's dilemma game. For the other two games, we obtain regions of parameters where the quantum strategies dominate, as well as regions where the classical strategies coexist.

  15. The Evolving Leadership Path of Visual Analytics

    Energy Technology Data Exchange (ETDEWEB)

    Kluse, Michael; Peurrung, Anthony J.; Gracio, Deborah K.

    2012-01-02

    This is a requested book chapter for an internationally authored book on visual analytics and related fields, coordianted by a UK university and to be published by Springer in 2012. This chapter is an overview of the leadship strategies that PNNL's Jim Thomas and other stakeholders used to establish visual analytics as a field, and how those strategies may evolve in the future.

  16. Higher School Marketing Strategy Formation: Classifying the Factors

    Directory of Open Access Journals (Sweden)

    N. K. Shemetova

    2012-01-01

    Full Text Available The paper deals with the main trends of higher school management strategy formation. The author specifies the educational changes in the modern information society determining the strategy options. For each professional training level the author denotes the set of strategic factors affecting the educational service consumers and, therefore, the effectiveness of the higher school marketing. The given factors are classified from the stand-points of the providers and consumers of educational service (enrollees, students, graduates and postgraduates. The research methods include the statistic analysis and general methods of scientific analysis, synthesis, induction, deduction, comparison, and classification. The author is convinced that the university management should develop the necessary prerequisites for raising the graduates’ competitiveness in the labor market, and stimulate the active marketing policies of the relating subdivisions and departments. In author’s opinion, the above classification of marketing strategy factors can be used as the system of values for educational service providers. 

  17. Evolving artificial metalloenzymes via random mutagenesis

    Science.gov (United States)

    Yang, Hao; Swartz, Alan M.; Park, Hyun June; Srivastava, Poonam; Ellis-Guardiola, Ken; Upp, David M.; Lee, Gihoon; Belsare, Ketaki; Gu, Yifan; Zhang, Chen; Moellering, Raymond E.; Lewis, Jared C.

    2018-03-01

    Random mutagenesis has the potential to optimize the efficiency and selectivity of protein catalysts without requiring detailed knowledge of protein structure; however, introducing synthetic metal cofactors complicates the expression and screening of enzyme libraries, and activity arising from free cofactor must be eliminated. Here we report an efficient platform to create and screen libraries of artificial metalloenzymes (ArMs) via random mutagenesis, which we use to evolve highly selective dirhodium cyclopropanases. Error-prone PCR and combinatorial codon mutagenesis enabled multiplexed analysis of random mutations, including at sites distal to the putative ArM active site that are difficult to identify using targeted mutagenesis approaches. Variants that exhibited significantly improved selectivity for each of the cyclopropane product enantiomers were identified, and higher activity than previously reported ArM cyclopropanases obtained via targeted mutagenesis was also observed. This improved selectivity carried over to other dirhodium-catalysed transformations, including N-H, S-H and Si-H insertion, demonstrating that ArMs evolved for one reaction can serve as starting points to evolve catalysts for others.

  18. CMIP6 Data Citation of Evolving Data

    Directory of Open Access Journals (Sweden)

    Martina Stockhause

    2017-06-01

    Full Text Available Data citations have become widely accepted. Technical infrastructures as well as principles and recommendations for data citation are in place but best practices or guidelines for their implementation are not yet available. On the other hand, the scientific climate community requests early citations on evolving data for credit, e.g. for CMIP6 (Coupled Model Intercomparison Project Phase 6. The data citation concept for CMIP6 is presented. The main challenges lie in limited resources, a strict project timeline and the dependency on changes of the data dissemination infrastructure ESGF (Earth System Grid Federation to meet the data citation requirements. Therefore a pragmatic, flexible and extendible approach for the CMIP6 data citation service was developed, consisting of a citation for the full evolving data superset and a data cart approach for citing the concrete used data subset. This two citation approach can be implemented according to the RDA recommendations for evolving data. Because of resource constraints and missing project policies, the implementation of the second part of the citation concept is postponed to CMIP7.

  19. Three data partitioning strategies for building local classifiers (Chapter 14)

    NARCIS (Netherlands)

    Zliobaite, I.; Okun, O.; Valentini, G.; Re, M.

    2011-01-01

    Divide-and-conquer approach has been recognized in multiple classifier systems aiming to utilize local expertise of individual classifiers. In this study we experimentally investigate three strategies for building local classifiers that are based on different routines of sampling data for training.

  20. Recognition of pornographic web pages by classifying texts and images.

    Science.gov (United States)

    Hu, Weiming; Wu, Ou; Chen, Zhouyao; Fu, Zhouyu; Maybank, Steve

    2007-06-01

    With the rapid development of the World Wide Web, people benefit more and more from the sharing of information. However, Web pages with obscene, harmful, or illegal content can be easily accessed. It is important to recognize such unsuitable, offensive, or pornographic Web pages. In this paper, a novel framework for recognizing pornographic Web pages is described. A C4.5 decision tree is used to divide Web pages, according to content representations, into continuous text pages, discrete text pages, and image pages. These three categories of Web pages are handled, respectively, by a continuous text classifier, a discrete text classifier, and an algorithm that fuses the results from the image classifier and the discrete text classifier. In the continuous text classifier, statistical and semantic features are used to recognize pornographic texts. In the discrete text classifier, the naive Bayes rule is used to calculate the probability that a discrete text is pornographic. In the image classifier, the object's contour-based features are extracted to recognize pornographic images. In the text and image fusion algorithm, the Bayes theory is used to combine the recognition results from images and texts. Experimental results demonstrate that the continuous text classifier outperforms the traditional keyword-statistics-based classifier, the contour-based image classifier outperforms the traditional skin-region-based image classifier, the results obtained by our fusion algorithm outperform those by either of the individual classifiers, and our framework can be adapted to different categories of Web pages.

  1. 32 CFR 2400.28 - Dissemination of classified information.

    Science.gov (United States)

    2010-07-01

    ... 32 National Defense 6 2010-07-01 2010-07-01 false Dissemination of classified information. 2400.28... SECURITY PROGRAM Safeguarding § 2400.28 Dissemination of classified information. Heads of OSTP offices... originating official may prescribe specific restrictions on dissemination of classified information when...

  2. Immunohistochemical analysis of breast tissue microarray images using contextual classifiers

    Directory of Open Access Journals (Sweden)

    Stephen J McKenna

    2013-01-01

    Full Text Available Background: Tissue microarrays (TMAs are an important tool in translational research for examining multiple cancers for molecular and protein markers. Automatic immunohistochemical (IHC scoring of breast TMA images remains a challenging problem. Methods: A two-stage approach that involves localization of regions of invasive and in-situ carcinoma followed by ordinal IHC scoring of nuclei in these regions is proposed. The localization stage classifies locations on a grid as tumor or non-tumor based on local image features. These classifications are then refined using an auto-context algorithm called spin-context. Spin-context uses a series of classifiers to integrate image feature information with spatial context information in the form of estimated class probabilities. This is achieved in a rotationally-invariant manner. The second stage estimates ordinal IHC scores in terms of the strength of staining and the proportion of nuclei stained. These estimates take the form of posterior probabilities, enabling images with uncertain scores to be referred for pathologist review. Results: The method was validated against manual pathologist scoring on two nuclear markers, progesterone receptor (PR and estrogen receptor (ER. Errors for PR data were consistently lower than those achieved with ER data. Scoring was in terms of estimated proportion of cells that were positively stained (scored on an ordinal scale of 0-6 and perceived strength of staining (scored on an ordinal scale of 0-3. Average absolute differences between predicted scores and pathologist-assigned scores were 0.74 for proportion of cells and 0.35 for strength of staining (PR. Conclusions: The use of context information via spin-context improved the precision and recall of tumor localization. The combination of the spin-context localization method with the automated scoring method resulted in reduced IHC scoring errors.

  3. Link Prediction in Evolving Networks Based on Popularity of Nodes.

    Science.gov (United States)

    Wang, Tong; He, Xing-Sheng; Zhou, Ming-Yang; Fu, Zhong-Qian

    2017-08-02

    Link prediction aims to uncover the underlying relationship behind networks, which could be utilized to predict missing edges or identify the spurious edges. The key issue of link prediction is to estimate the likelihood of potential links in networks. Most classical static-structure based methods ignore the temporal aspects of networks, limited by the time-varying features, such approaches perform poorly in evolving networks. In this paper, we propose a hypothesis that the ability of each node to attract links depends not only on its structural importance, but also on its current popularity (activeness), since active nodes have much more probability to attract future links. Then a novel approach named popularity based structural perturbation method (PBSPM) and its fast algorithm are proposed to characterize the likelihood of an edge from both existing connectivity structure and current popularity of its two endpoints. Experiments on six evolving networks show that the proposed methods outperform state-of-the-art methods in accuracy and robustness. Besides, visual results and statistical analysis reveal that the proposed methods are inclined to predict future edges between active nodes, rather than edges between inactive nodes.

  4. Evolving Systems: Adaptive Key Component Control and Inheritance of Passivity and Dissipativity

    Science.gov (United States)

    Frost, S. A.; Balas, M. J.

    2010-01-01

    We propose a new framework called Evolving Systems to describe the self-assembly, or autonomous assembly, of actively controlled dynamical subsystems into an Evolved System with a higher purpose. Autonomous assembly of large, complex flexible structures in space is a target application for Evolving Systems. A critical requirement for autonomous assembling structures is that they remain stable during and after assembly. The fundamental topic of inheritance of stability, dissipativity, and passivity in Evolving Systems is the primary focus of this research. In this paper, we develop an adaptive key component controller to restore stability in Nonlinear Evolving Systems that would otherwise fail to inherit the stability traits of their components. We provide sufficient conditions for the use of this novel control method and demonstrate its use on an illustrative example.

  5. Peat classified as slowly renewable biomass fuel

    International Nuclear Information System (INIS)

    2001-01-01

    thousands of years. The report states also that peat should be classified as biomass fuel instead of biofuels, such as wood, or fossil fuels such as coal. According to the report peat is a renewable biomass fuel like biofuels, but due to slow accumulation it should be considered as slowly renewable fuel. The report estimates that bonding of carbon in both virgin and forest drained peatlands are so high that it can compensate the emissions formed in combustion of energy peat

  6. REPTREE CLASSIFIER FOR IDENTIFYING LINK SPAM IN WEB SEARCH ENGINES

    Directory of Open Access Journals (Sweden)

    S.K. Jayanthi

    2013-01-01

    Full Text Available Search Engines are used for retrieving the information from the web. Most of the times, the importance is laid on top 10 results sometimes it may shrink as top 5, because of the time constraint and reliability on the search engines. Users believe that top 10 or 5 of total results are more relevant. Here comes the problem of spamdexing. It is a method to deceive the search result quality. Falsified metrics such as inserting enormous amount of keywords or links in website may take that website to the top 10 or 5 positions. This paper proposes a classifier based on the Reptree (Regression tree representative. As an initial step Link-based features such as neighbors, pagerank, truncated pagerank, trustrank and assortativity related attributes are inferred. Based on this features, tree is constructed. The tree uses the feature inference to differentiate spam sites from legitimate sites. WEBSPAM-UK-2007 dataset is taken as a base. It is preprocessed and converted into five datasets FEATA, FEATB, FEATC, FEATD and FEATE. Only link based features are taken for experiments. This paper focus on link spam alone. Finally a representative tree is created which will more precisely classify the web spam entries. Results are given. Regression tree classification seems to perform well as shown through experiments.

  7. Speaker gender identification based on majority vote classifiers

    Science.gov (United States)

    Mezghani, Eya; Charfeddine, Maha; Nicolas, Henri; Ben Amar, Chokri

    2017-03-01

    Speaker gender identification is considered among the most important tools in several multimedia applications namely in automatic speech recognition, interactive voice response systems and audio browsing systems. Gender identification systems performance is closely linked to the selected feature set and the employed classification model. Typical techniques are based on selecting the best performing classification method or searching optimum tuning of one classifier parameters through experimentation. In this paper, we consider a relevant and rich set of features involving pitch, MFCCs as well as other temporal and frequency-domain descriptors. Five classification models including decision tree, discriminant analysis, nave Bayes, support vector machine and k-nearest neighbor was experimented. The three best perming classifiers among the five ones will contribute by majority voting between their scores. Experimentations were performed on three different datasets spoken in three languages: English, German and Arabic in order to validate language independency of the proposed scheme. Results confirm that the presented system has reached a satisfying accuracy rate and promising classification performance thanks to the discriminating abilities and diversity of the used features combined with mid-level statistics.

  8. Classifying magnetic resonance image modalities with convolutional neural networks

    Science.gov (United States)

    Remedios, Samuel; Pham, Dzung L.; Butman, John A.; Roy, Snehashis

    2018-02-01

    Magnetic Resonance (MR) imaging allows the acquisition of images with different contrast properties depending on the acquisition protocol and the magnetic properties of tissues. Many MR brain image processing techniques, such as tissue segmentation, require multiple MR contrasts as inputs, and each contrast is treated differently. Thus it is advantageous to automate the identification of image contrasts for various purposes, such as facilitating image processing pipelines, and managing and maintaining large databases via content-based image retrieval (CBIR). Most automated CBIR techniques focus on a two-step process: extracting features from data and classifying the image based on these features. We present a novel 3D deep convolutional neural network (CNN)- based method for MR image contrast classification. The proposed CNN automatically identifies the MR contrast of an input brain image volume. Specifically, we explored three classification problems: (1) identify T1-weighted (T1-w), T2-weighted (T2-w), and fluid-attenuated inversion recovery (FLAIR) contrasts, (2) identify pre vs postcontrast T1, (3) identify pre vs post-contrast FLAIR. A total of 3418 image volumes acquired from multiple sites and multiple scanners were used. To evaluate each task, the proposed model was trained on 2137 images and tested on the remaining 1281 images. Results showed that image volumes were correctly classified with 97.57% accuracy.

  9. A new method for classifying distal radius fracture: the IDEAL classification Um novo método de classificação para as fraturas da extremidade distal do rádio – a classificação IDEAL

    Directory of Open Access Journals (Sweden)

    João Carlos Belloti

    2013-01-01

    Full Text Available OBJECTIVES: To describe the new IDEAL method from classifying distal radius fractures. METHODS: IDEAL classification system is based on the most important literature evidences about clinical and radiographic characteristics that influence in the treatment and prognosis for patients that suffered from a distal radius fractures. In this method, we classify the fracture in patients first consultation, in which we collect demographical (age and trauma energy and radiographic characteristics ( fracture deviation, articular fracture, and associated lesions. For each feature a score is attributed for grouping purposes. Group I - Stable fractures, good prognosis; Group II - potentially unstable fractures, commonly treated by surgical methods. Prognosis depends on surgeons' success after method choice. Group III - complex and instable fractures, poor outcome is expected. CONCLUSION: IDEAL classification staging rationale was presented, which is based on the best available evidence. The evidence of its scientific plausibility will be settled with the assessment of the classification reliability and its capacity to aid in therapeutical decisions and as a tool to predict prognosis. Further studies are under development to support these properties. OBJETIVOS: Descrição do método de Classificação IDEAL - para as fraturas da extremidade distal do rádio. MÉTODOS: O sistema de classificação IDEAL fundamenta-se nas principais evidências da literatura sobre fatores clínicos e radiográficos que influenciam o tratamento e prognóstico das fraturas do rádio distal. Classificamos as fraturas no atendimento inicial do paciente mediante a verificação de dois dados epidemiológicos e três dados radiográficos: Idade do paciente, energia do trauma, desvio dos fragmentos, incongruência articular e lesões associadas. RESULTADOS: Conforme a pontuação obtida, agrupamos os casos em três grupos: Grupo I - fraturas estáveis com bom prognóstico, Grupo II

  10. A Simple Neural Network Contextual Classifier

    DEFF Research Database (Denmark)

    Nielsen, Allan Aasbjerg; Tidemann, J.

    1997-01-01

    I. Kanellopoulos, G.G. Wilkinson, F. Roli and J. Austin (Eds.)Proceedings of European Union Environment and Climate Programme Concerted Action COMPARES (COnnectionist Methods in Pre-processing and Analysis of REmote Sensing data)....

  11. Evolving cell models for systems and synthetic biology.

    Science.gov (United States)

    Cao, Hongqing; Romero-Campero, Francisco J; Heeb, Stephan; Cámara, Miguel; Krasnogor, Natalio

    2010-03-01

    This paper proposes a new methodology for the automated design of cell models for systems and synthetic biology. Our modelling framework is based on P systems, a discrete, stochastic and modular formal modelling language. The automated design of biological models comprising the optimization of the model structure and its stochastic kinetic constants is performed using an evolutionary algorithm. The evolutionary algorithm evolves model structures by combining different modules taken from a predefined module library and then it fine-tunes the associated stochastic kinetic constants. We investigate four alternative objective functions for the fitness calculation within the evolutionary algorithm: (1) equally weighted sum method, (2) normalization method, (3) randomly weighted sum method, and (4) equally weighted product method. The effectiveness of the methodology is tested on four case studies of increasing complexity including negative and positive autoregulation as well as two gene networks implementing a pulse generator and a bandwidth detector. We provide a systematic analysis of the evolutionary algorithm's results as well as of the resulting evolved cell models.

  12. Detecting Dutch political tweets : A classifier based on voting system using supervised learning

    NARCIS (Netherlands)

    de Mello Araújo, Eric Fernandes; Ebbelaar, Dave

    The task of classifying political tweets has been shown to be very difficult, with controversial results in many works and with non-replicable methods. Most of the works with this goal use rule-based methods to identify political tweets. We propose here two methods, being one rule-based approach,

  13. Evolving spectral transformations for multitemporal information extraction using evolutionary computation

    Science.gov (United States)

    Momm, Henrique; Easson, Greg

    2011-01-01

    Remote sensing plays an important role in assessing temporal changes in land features. The challenge often resides in the conversion of large quantities of raw data into actionable information in a timely and cost-effective fashion. To address this issue, research was undertaken to develop an innovative methodology integrating biologically-inspired algorithms with standard image classification algorithms to improve information extraction from multitemporal imagery. Genetic programming was used as the optimization engine to evolve feature-specific candidate solutions in the form of nonlinear mathematical expressions of the image spectral channels (spectral indices). The temporal generalization capability of the proposed system was evaluated by addressing the task of building rooftop identification from a set of images acquired at different dates in a cross-validation approach. The proposed system generates robust solutions (kappa values > 0.75 for stage 1 and > 0.4 for stage 2) despite the statistical differences between the scenes caused by land use and land cover changes coupled with variable environmental conditions, and the lack of radiometric calibration between images. Based on our results, the use of nonlinear spectral indices enhanced the spectral differences between features improving the clustering capability of standard classifiers and providing an alternative solution for multitemporal information extraction.

  14. Revealing effective classifiers through network comparison

    Science.gov (United States)

    Gallos, Lazaros K.; Fefferman, Nina H.

    2014-11-01

    The ability to compare complex systems can provide new insight into the fundamental nature of the processes captured, in ways that are otherwise inaccessible to observation. Here, we introduce the n-tangle method to directly compare two networks for structural similarity, based on the distribution of edge density in network subgraphs. We demonstrate that this method can efficiently introduce comparative analysis into network science and opens the road for many new applications. For example, we show how the construction of a “phylogenetic tree” across animal taxa according to their social structure can reveal commonalities in the behavioral ecology of the populations, or how students create similar networks according to the University size. Our method can be expanded to study many additional properties, such as network classification, changes during time evolution, convergence of growth models, and detection of structural changes during damage.

  15. Evolutions in clinical reasoning assessment: The Evolving Script Concordance Test.

    Science.gov (United States)

    Cooke, Suzette; Lemay, Jean-François; Beran, Tanya

    2017-08-01

    Script concordance testing (SCT) is a method of assessment of clinical reasoning. We developed a new type of SCT case design, the evolving SCT (E-SCT), whereby the patient's clinical story is "evolving" and with thoughtful integration of new information at each stage, decisions related to clinical decision-making become increasingly clear. We aimed to: (1) determine whether an E-SCT could differentiate clinical reasoning ability among junior residents (JR), senior residents (SR), and pediatricians, (2) evaluate the reliability of an E-SCT, and (3) obtain qualitative feedback from participants to help inform the potential acceptability of the E-SCT. A 12-case E-SCT, embedded within a 24-case pediatric SCT (PaedSCT), was administered to 91 pediatric residents (JR: n = 50; SR: n = 41). A total of 21 pediatricians served on the panel of experts (POE). A one-way analysis of variance (ANOVA) was conducted across the levels of experience. Participants' feedback on the E-SCT was obtained with a post-test survey and analyzed using two methods: percentage preference and thematic analysis. Statistical differences existed across levels of training: F = 19.31 (df = 2); p decision-making process. The E-SCT demonstrated very good reliability and was effective in distinguishing clinical reasoning ability across three levels of experience. Participants found the E-SCT engaging and representative of real-life clinical reasoning and decision-making processes. We suggest that further refinement and utilization of the evolving style case will enhance SCT as a robust, engaging, and relevant method for the assessment of clinical reasoning.

  16. Evolvability Is an Evolved Ability: The Coding Concept as the Arch-Unit of Natural Selection.

    Science.gov (United States)

    Janković, Srdja; Ćirković, Milan M

    2016-03-01

    Physical processes that characterize living matter are qualitatively distinct in that they involve encoding and transfer of specific types of information. Such information plays an active part in the control of events that are ultimately linked to the capacity of the system to persist and multiply. This algorithmicity of life is a key prerequisite for its Darwinian evolution, driven by natural selection acting upon stochastically arising variations of the encoded information. The concept of evolvability attempts to define the total capacity of a system to evolve new encoded traits under appropriate conditions, i.e., the accessible section of total morphological space. Since this is dependent on previously evolved regulatory networks that govern information flow in the system, evolvability itself may be regarded as an evolved ability. The way information is physically written, read and modified in living cells (the "coding concept") has not changed substantially during the whole history of the Earth's biosphere. This biosphere, be it alone or one of many, is, accordingly, itself a product of natural selection, since the overall evolvability conferred by its coding concept (nucleic acids as information carriers with the "rulebook of meanings" provided by codons, as well as all the subsystems that regulate various conditional information-reading modes) certainly played a key role in enabling this biosphere to survive up to the present, through alterations of planetary conditions, including at least five catastrophic events linked to major mass extinctions. We submit that, whatever the actual prebiotic physical and chemical processes may have been on our home planet, or may, in principle, occur at some time and place in the Universe, a particular coding concept, with its respective potential to give rise to a biosphere, or class of biospheres, of a certain evolvability, may itself be regarded as a unit (indeed the arch-unit) of natural selection.

  17. Revealing evolved massive stars with Spitzer

    Science.gov (United States)

    Gvaramadze, V. V.; Kniazev, A. Y.; Fabrika, S.

    2010-06-01

    Massive evolved stars lose a large fraction of their mass via copious stellar wind or instant outbursts. During certain evolutionary phases, they can be identified by the presence of their circumstellar nebulae. In this paper, we present the results of a search for compact nebulae (reminiscent of circumstellar nebulae around evolved massive stars) using archival 24-μm data obtained with the Multiband Imaging Photometer for Spitzer. We have discovered 115 nebulae, most of which bear a striking resemblance to the circumstellar nebulae associated with luminous blue variables (LBVs) and late WN-type (WNL) Wolf-Rayet (WR) stars in the Milky Way and the Large Magellanic Cloud (LMC). We interpret this similarity as an indication that the central stars of detected nebulae are either LBVs or related evolved massive stars. Our interpretation is supported by follow-up spectroscopy of two dozen of these central stars, most of which turn out to be either candidate LBVs (cLBVs), blue supergiants or WNL stars. We expect that the forthcoming spectroscopy of the remaining objects from our list, accompanied by the spectrophotometric monitoring of the already discovered cLBVs, will further increase the known population of Galactic LBVs. This, in turn, will have profound consequences for better understanding the LBV phenomenon and its role in the transition between hydrogen-burning O stars and helium-burning WR stars. We also report on the detection of an arc-like structure attached to the cLBV HD 326823 and an arc associated with the LBV R99 (HD 269445) in the LMC. Partially based on observations collected at the German-Spanish Astronomical Centre, Calar Alto, jointly operated by the Max-Planck-Institut für Astronomie Heidelberg and the Instituto de Astrofísica de Andalucía (CSIC). E-mail: vgvaram@mx.iki.rssi.ru (VVG); akniazev@saao.ac.za (AYK); fabrika@sao.ru (SF)

  18. Open-Ended Behavioral Complexity for Evolved Virtual Creatures

    DEFF Research Database (Denmark)

    Lessin, Dan; Fussell, Don; Miikkulainen, Risto

    2013-01-01

    notable exception to this progress. Despite the potential benefits, there has been no clear increase in the behavioral complexity of evolved virtual creatures (EVCs) beyond the light following demonstrated in Sims' original work. This paper presents an open-ended method to move beyond this limit, making...... creature with behavioral complexity that clearly exceeds previously achieved levels. ESP thus demonstrates that EVCs may indeed have the potential to one day rival the behavioral complexity--and therefore the entertainment value--of their non-virtual counterparts....

  19. Radio Imaging of Envelopes of Evolved Stars

    Science.gov (United States)

    Cotton, Bill

    2018-04-01

    This talk will cover imaging of stellar envelopes using radio VLBI techniques; special attention will be paid to the technical differences between radio and optical/IR interferomery. Radio heterodyne receivers allow a straightforward way to derive spectral cubes and full polarization observations. Milliarcsecond resolution of very bright, i.e. non thermal, emission of molecular masers in the envelopes of evolved stars can be achieved using VLBI techniques with baselines of thousands of km. Emission from SiO, H2O and OH masers are commonly seen at increasing distance from the photosphere. The very narrow maser lines allow accurate measurements of the velocity field within the emitting region.

  20. Mobile computing acceptance grows as applications evolve.

    Science.gov (United States)

    Porn, Louis M; Patrick, Kelly

    2002-01-01

    Handheld devices are becoming more cost-effective to own, and their use in healthcare environments is increasing. Handheld devices currently are being used for e-prescribing, charge capture, and accessing daily schedules and reference tools. Future applications may include education on medications, dictation, order entry, and test-results reporting. Selecting the right handheld device requires careful analysis of current and future applications, as well as vendor expertise. It is important to recognize the technology will continue to evolve over the next three years.

  1. Evolved Minimal Frustration in Multifunctional Biomolecules.

    Science.gov (United States)

    Röder, Konstantin; Wales, David J

    2018-05-25

    Protein folding is often viewed in terms of a funnelled potential or free energy landscape. A variety of experiments now indicate the existence of multifunnel landscapes, associated with multifunctional biomolecules. Here, we present evidence that these systems have evolved to exhibit the minimal number of funnels required to fulfil their cellular functions, suggesting an extension to the principle of minimum frustration. We find that minimal disruptive mutations result in additional funnels, and the associated structural ensembles become more diverse. The same trends are observed in an atomic cluster. These observations suggest guidelines for rational design of engineered multifunctional biomolecules.

  2. SALT Spectroscopy of Evolved Massive Stars

    Science.gov (United States)

    Kniazev, A. Y.; Gvaramadze, V. V.; Berdnikov, L. N.

    2017-06-01

    Long-slit spectroscopy with the Southern African Large Telescope (SALT) of central stars of mid-infrared nebulae detected with the Spitzer Space Telescope and Wide-Field Infrared Survey Explorer (WISE) led to the discovery of numerous candidate luminous blue variables (cLBVs) and other rare evolved massive stars. With the recent advent of the SALT fiber-fed high-resolution echelle spectrograph (HRS), a new perspective for the study of these interesting objects is appeared. Using the HRS we obtained spectra of a dozen newly identified massive stars. Some results on the recently identified cLBV Hen 3-729 are presented.

  3. How large a training set is needed to develop a classifier for microarray data?

    Science.gov (United States)

    Dobbin, Kevin K; Zhao, Yingdong; Simon, Richard M

    2008-01-01

    A common goal of gene expression microarray studies is the development of a classifier that can be used to divide patients into groups with different prognoses, or with different expected responses to a therapy. These types of classifiers are developed on a training set, which is the set of samples used to train a classifier. The question of how many samples are needed in the training set to produce a good classifier from high-dimensional microarray data is challenging. We present a model-based approach to determining the sample size required to adequately train a classifier. It is shown that sample size can be determined from three quantities: standardized fold change, class prevalence, and number of genes or features on the arrays. Numerous examples and important experimental design issues are discussed. The method is adapted to address ex post facto determination of whether the size of a training set used to develop a classifier was adequate. An interactive web site for performing the sample size calculations is provided. We showed that sample size calculations for classifier development from high-dimensional microarray data are feasible, discussed numerous important considerations, and presented examples.

  4. Evolution of networks for body plan patterning; interplay of modularity, robustness and evolvability.

    Directory of Open Access Journals (Sweden)

    Kirsten H Ten Tusscher

    2011-10-01

    Full Text Available A major goal of evolutionary developmental biology (evo-devo is to understand how multicellular body plans of increasing complexity have evolved, and how the corresponding developmental programs are genetically encoded. It has been repeatedly argued that key to the evolution of increased body plan complexity is the modularity of the underlying developmental gene regulatory networks (GRNs. This modularity is considered essential for network robustness and evolvability. In our opinion, these ideas, appealing as they may sound, have not been sufficiently tested. Here we use computer simulations to study the evolution of GRNs' underlying body plan patterning. We select for body plan segmentation and differentiation, as these are considered to be major innovations in metazoan evolution. To allow modular networks to evolve, we independently select for segmentation and differentiation. We study both the occurrence and relation of robustness, evolvability and modularity of evolved networks. Interestingly, we observed two distinct evolutionary strategies to evolve a segmented, differentiated body plan. In the first strategy, first segments and then differentiation domains evolve (SF strategy. In the second scenario segments and domains evolve simultaneously (SS strategy. We demonstrate that under indirect selection for robustness the SF strategy becomes dominant. In addition, as a byproduct of this larger robustness, the SF strategy is also more evolvable. Finally, using a combined functional and architectural approach, we determine network modularity. We find that while SS networks generate segments and domains in an integrated manner, SF networks use largely independent modules to produce segments and domains. Surprisingly, we find that widely used, purely architectural methods for determining network modularity completely fail to establish this higher modularity of SF networks. Finally, we observe that, as a free side effect of evolving segmentation

  5. BOOK REVIEW: OPENING SCIENCE, THE EVOLVING GUIDE ...

    Science.gov (United States)

    The way we get our funding, collaborate, do our research, and get the word out has evolved over hundreds of years but we can imagine a more open science world, largely facilitated by the internet. The movement towards this more open way of doing and presenting science is coming, and it is not taking hundreds of years. If you are interested in these trends, and would like to find out more about where this is all headed and what it means to you, consider downloding Opening Science, edited by Sönke Bartling and Sascha Friesike, subtitled The Evolving Guide on How the Internet is Changing Research, Collaboration, and Scholarly Publishing. In 26 chapters by various authors from a range of disciplines the book explores the developing world of open science, starting from the first scientific revolution and bringing us to the next scientific revolution, sometimes referred to as “Science 2.0”. Some of the articles deal with the impact of the changing landscape of how science is done, looking at the impact of open science on Academia, or journal publishing, or medical research. Many of the articles look at the uses, pitfalls, and impact of specific tools, like microblogging (think Twitter), social networking, and reference management. There is lots of discussion and definition of terms you might use or misuse like “altmetrics” and “impact factor”. Science will probably never be completely open, and Twitter will probably never replace the journal article,

  6. Evolving NASA's Earth Science Data Systems

    Science.gov (United States)

    Walter, J.; Behnke, J.; Murphy, K. J.; Lowe, D. R.

    2013-12-01

    NASA's Earth Science Data and Information System Project (ESDIS) is charged with managing, maintaining, and evolving NASA's Earth Observing System Data and Information System (EOSDIS) and is responsible for processing, archiving, and distributing NASA Earth science data. The system supports a multitude of missions and serves diverse science research and other user communities. Keeping up with ever-changing information technology and figuring out how to leverage those changes across such a large system in order to continuously improve and meet the needs of a diverse user community is a significant challenge. Maintaining and evolving the system architecture and infrastructure is a continuous and multi-layered effort. It requires a balance between a "top down" management paradigm that provides a coherent system view and maintaining the managerial, technological, and functional independence of the individual system elements. This presentation will describe some of the key elements of the current system architecture, some of the strategies and processes we employ to meet these challenges, current and future challenges, and some ideas for meeting those challenges.

  7. The Comet Cometh: Evolving Developmental Systems.

    Science.gov (United States)

    Jaeger, Johannes; Laubichler, Manfred; Callebaut, Werner

    In a recent opinion piece, Denis Duboule has claimed that the increasing shift towards systems biology is driving evolutionary and developmental biology apart, and that a true reunification of these two disciplines within the framework of evolutionary developmental biology (EvoDevo) may easily take another 100 years. He identifies methodological, epistemological, and social differences as causes for this supposed separation. Our article provides a contrasting view. We argue that Duboule's prediction is based on a one-sided understanding of systems biology as a science that is only interested in functional, not evolutionary, aspects of biological processes. Instead, we propose a research program for an evolutionary systems biology, which is based on local exploration of the configuration space in evolving developmental systems. We call this approach-which is based on reverse engineering, simulation, and mathematical analysis-the natural history of configuration space. We discuss a number of illustrative examples that demonstrate the past success of local exploration, as opposed to global mapping, in different biological contexts. We argue that this pragmatic mode of inquiry can be extended and applied to the mathematical analysis of the developmental repertoire and evolutionary potential of evolving developmental mechanisms and that evolutionary systems biology so conceived provides a pragmatic epistemological framework for the EvoDevo synthesis.

  8. Classifying images using restricted Boltzmann machines and convolutional neural networks

    Science.gov (United States)

    Zhao, Zhijun; Xu, Tongde; Dai, Chenyu

    2017-07-01

    To improve the feature recognition ability of deep model transfer learning, we propose a hybrid deep transfer learning method for image classification based on restricted Boltzmann machines (RBM) and convolutional neural networks (CNNs). It integrates learning abilities of two models, which conducts subject classification by exacting structural higher-order statistics features of images. While the method transfers the trained convolutional neural networks to the target datasets, fully-connected layers can be replaced by restricted Boltzmann machine layers; then the restricted Boltzmann machine layers and Softmax classifier are retrained, and BP neural network can be used to fine-tuned the hybrid model. The restricted Boltzmann machine layers has not only fully integrated the whole feature maps, but also learns the statistical features of target datasets in the view of the biggest logarithmic likelihood, thus removing the effects caused by the content differences between datasets. The experimental results show that the proposed method has improved the accuracy of image classification, outperforming other methods on Pascal VOC2007 and Caltech101 datasets.

  9. Passive Sonar Target Detection Using Statistical Classifier and Adaptive Threshold

    Directory of Open Access Journals (Sweden)

    Hamed Komari Alaie

    2018-01-01

    Full Text Available This paper presents the results of an experimental investigation about target detecting with passive sonar in Persian Gulf. Detecting propagated sounds in the water is one of the basic challenges of the researchers in sonar field. This challenge will be complex in shallow water (like Persian Gulf and noise less vessels. Generally, in passive sonar, the targets are detected by sonar equation (with constant threshold that increases the detection error in shallow water. The purpose of this study is proposed a new method for detecting targets in passive sonars using adaptive threshold. In this method, target signal (sound is processed in time and frequency domain. For classifying, Bayesian classification is used and posterior distribution is estimated by Maximum Likelihood Estimation algorithm. Finally, target was detected by combining the detection points in both domains using Least Mean Square (LMS adaptive filter. Results of this paper has showed that the proposed method has improved true detection rate by about 24% when compared other the best detection method.

  10. Classifying lipoproteins based on their polar profiles.

    Science.gov (United States)

    Polanco, Carlos; Castañón-González, Jorge Alberto; Buhse, Thomas; Uversky, Vladimir N; Amkie, Rafael Zonana

    2016-01-01

    The lipoproteins are an important group of cargo proteins known for their unique capability to transport lipids. By applying the Polarity index algorithm, which has a metric that only considers the polar profile of the linear sequences of the lipoprotein group, we obtained an analytical and structural differentiation of all the lipoproteins found in UniProt Database. Also, the functional groups of lipoproteins, and particularly of the set of lipoproteins relevant to atherosclerosis, were analyzed with the same method to reveal their structural preference, and the results of Polarity index analysis were verified by an alternate test, the Cumulative Distribution Function algorithm, applied to the same groups of lipoproteins.

  11. Knowledge extraction from evolving spiking neural networks with rank order population coding.

    Science.gov (United States)

    Soltic, Snjezana; Kasabov, Nikola

    2010-12-01

    This paper demonstrates how knowledge can be extracted from evolving spiking neural networks with rank order population coding. Knowledge discovery is a very important feature of intelligent systems. Yet, a disproportionally small amount of research is centered on the issue of knowledge extraction from spiking neural networks which are considered to be the third generation of artificial neural networks. The lack of knowledge representation compatibility is becoming a major detriment to end users of these networks. We show that a high-level knowledge can be obtained from evolving spiking neural networks. More specifically, we propose a method for fuzzy rule extraction from an evolving spiking network with rank order population coding. The proposed method was used for knowledge discovery on two benchmark taste recognition problems where the knowledge learnt by an evolving spiking neural network was extracted in the form of zero-order Takagi-Sugeno fuzzy IF-THEN rules.

  12. Use of GMM and SCMS for Accurate Road Centerline Extraction from the Classified Image

    Directory of Open Access Journals (Sweden)

    Zelang Miao

    2015-01-01

    Full Text Available The extraction of road centerline from the classified image is a fundamental image analysis technology. Common problems encountered in road centerline extraction include low ability for coping with the general case, production of undesired objects, and inefficiency. To tackle these limitations, this paper presents a novel accurate centerline extraction method using Gaussian mixture model (GMM and subspace constraint mean shift (SCMS. The proposed method consists of three main steps. GMM is first used to partition the classified image into several clusters. The major axis of the ellipsoid of each cluster is extracted and deemed to be taken as the initial centerline. Finally, the initial result is adjusted using SCMS to produce precise road centerline. Both simulated and real datasets are used to validate the proposed method. Preliminary results demonstrate that the proposed method provides a comparatively robust solution for accurate centerline extraction from a classified image.

  13. Effective Heart Disease Detection Based on Quantitative Computerized Traditional Chinese Medicine Using Representation Based Classifiers

    Directory of Open Access Journals (Sweden)

    Ting Shu

    2017-01-01

    Full Text Available At present, heart disease is the number one cause of death worldwide. Traditionally, heart disease is commonly detected using blood tests, electrocardiogram, cardiac computerized tomography scan, cardiac magnetic resonance imaging, and so on. However, these traditional diagnostic methods are time consuming and/or invasive. In this paper, we propose an effective noninvasive computerized method based on facial images to quantitatively detect heart disease. Specifically, facial key block color features are extracted from facial images and analyzed using the Probabilistic Collaborative Representation Based Classifier. The idea of facial key block color analysis is founded in Traditional Chinese Medicine. A new dataset consisting of 581 heart disease and 581 healthy samples was experimented by the proposed method. In order to optimize the Probabilistic Collaborative Representation Based Classifier, an analysis of its parameters was performed. According to the experimental results, the proposed method obtains the highest accuracy compared with other classifiers and is proven to be effective at heart disease detection.

  14. Classifying emotion in Twitter using Bayesian network

    Science.gov (United States)

    Surya Asriadie, Muhammad; Syahrul Mubarok, Mohamad; Adiwijaya

    2018-03-01

    Language is used to express not only facts, but also emotions. Emotions are noticeable from behavior up to the social media statuses written by a person. Analysis of emotions in a text is done in a variety of media such as Twitter. This paper studies classification of emotions on twitter using Bayesian network because of its ability to model uncertainty and relationships between features. The result is two models based on Bayesian network which are Full Bayesian Network (FBN) and Bayesian Network with Mood Indicator (BNM). FBN is a massive Bayesian network where each word is treated as a node. The study shows the method used to train FBN is not very effective to create the best model and performs worse compared to Naive Bayes. F1-score for FBN is 53.71%, while for Naive Bayes is 54.07%. BNM is proposed as an alternative method which is based on the improvement of Multinomial Naive Bayes and has much lower computational complexity compared to FBN. Even though it’s not better compared to FBN, the resulting model successfully improves the performance of Multinomial Naive Bayes. F1-Score for Multinomial Naive Bayes model is 51.49%, while for BNM is 52.14%.

  15. A proposed defect tracking model for classifying the inserted defect reports to enhance software quality control.

    Science.gov (United States)

    Sultan, Torky; Khedr, Ayman E; Sayed, Mostafa

    2013-01-01

    NONE DECLARED Defect tracking systems play an important role in the software development organizations as they can store historical information about defects. There are many research in defect tracking models and systems to enhance their capabilities to be more specifically tracking, and were adopted with new technology. Furthermore, there are different studies in classifying bugs in a step by step method to have clear perception and applicable method in detecting such bugs. This paper shows a new proposed defect tracking model for the purpose of classifying the inserted defects reports in a step by step method for more enhancement of the software quality.

  16. Lightweight Active Object Retrieval with Weak Classifiers.

    Science.gov (United States)

    Czúni, László; Rashad, Metwally

    2018-03-07

    In the last few years, there has been a steadily growing interest in autonomous vehicles and robotic systems. While many of these agents are expected to have limited resources, these systems should be able to dynamically interact with other objects in their environment. We present an approach where lightweight sensory and processing techniques, requiring very limited memory and processing power, can be successfully applied to the task of object retrieval using sensors of different modalities. We use the Hough framework to fuse optical and orientation information of the different views of the objects. In the presented spatio-temporal perception technique, we apply active vision, where, based on the analysis of initial measurements, the direction of the next view is determined to increase the hit-rate of retrieval. The performance of the proposed methods is shown on three datasets loaded with heavy noise.

  17. Lightweight Active Object Retrieval with Weak Classifiers

    Directory of Open Access Journals (Sweden)

    László Czúni

    2018-03-01

    Full Text Available In the last few years, there has been a steadily growing interest in autonomous vehicles and robotic systems. While many of these agents are expected to have limited resources, these systems should be able to dynamically interact with other objects in their environment. We present an approach where lightweight sensory and processing techniques, requiring very limited memory and processing power, can be successfully applied to the task of object retrieval using sensors of different modalities. We use the Hough framework to fuse optical and orientation information of the different views of the objects. In the presented spatio-temporal perception technique, we apply active vision, where, based on the analysis of initial measurements, the direction of the next view is determined to increase the hit-rate of retrieval. The performance of the proposed methods is shown on three datasets loaded with heavy noise.

  18. A Supervised Multiclass Classifier for an Autocoding System

    Directory of Open Access Journals (Sweden)

    Yukako Toko

    2017-11-01

    Full Text Available Classification is often required in various contexts, including in the field of official statistics. In the previous study, we have developed a multiclass classifier that can classify short text descriptions with high accuracy. The algorithm borrows the concept of the naïve Bayes classifier and is so simple that its structure is easily understandable. The proposed classifier has the following two advantages. First, the processing times for both learning and classifying are extremely practical. Second, the proposed classifier yields high-accuracy results for a large portion of a dataset. We have previously developed an autocoding system for the Family Income and Expenditure Survey in Japan that has a better performing classifier. While the original system was developed in Perl in order to improve the efficiency of the coding process of short Japanese texts, the proposed system is implemented in the R programming language in order to explore versatility and is modified to make the system easily applicable to English text descriptions, in consideration of the increasing number of R users in the field of official statistics. We are planning to publish the proposed classifier as an R-package. The proposed classifier would be generally applicable to other classification tasks including coding activities in the field of official statistics, and it would contribute greatly to improving their efficiency.

  19. A general evolving model for growing bipartite networks

    International Nuclear Information System (INIS)

    Tian, Lixin; He, Yinghuan; Liu, Haijun; Du, Ruijin

    2012-01-01

    In this Letter, we propose and study an inner evolving bipartite network model. Significantly, we prove that the degree distribution of two different kinds of nodes both obey power-law form with adjustable exponents. Furthermore, the joint degree distribution of any two nodes for bipartite networks model is calculated analytically by the mean-field method. The result displays that such bipartite networks are nearly uncorrelated networks, which is different from one-mode networks. Numerical simulations and empirical results are given to verify the theoretical results. -- Highlights: ► We proposed a general evolving bipartite network model which was based on priority connection, reconnection and breaking edges. ► We prove that the degree distribution of two different kinds of nodes both obey power-law form with adjustable exponents. ► The joint degree distribution of any two nodes for bipartite networks model is calculated analytically by the mean-field method. ► The result displays that such bipartite networks are nearly uncorrelated networks, which is different from one-mode networks.

  20. Proposing an adaptive mutation to improve XCSF performance to classify ADHD and BMD patients

    Science.gov (United States)

    Sadatnezhad, Khadijeh; Boostani, Reza; Ghanizadeh, Ahmad

    2010-12-01

    There is extensive overlap of clinical symptoms observed among children with bipolar mood disorder (BMD) and those with attention deficit hyperactivity disorder (ADHD). Thus, diagnosis according to clinical symptoms cannot be very accurate. It is therefore desirable to develop quantitative criteria for automatic discrimination between these disorders. This study is aimed at designing an efficient decision maker to accurately classify ADHD and BMD patients by analyzing their electroencephalogram (EEG) signals. In this study, 22 channels of EEGs have been recorded from 21 subjects with ADHD and 22 individuals with BMD. Several informative features, such as fractal dimension, band power and autoregressive coefficients, were extracted from the recorded signals. Considering the multimodal overlapping distribution of the obtained features, linear discriminant analysis (LDA) was used to reduce the input dimension in a more separable space to make it more appropriate for the proposed classifier. A piecewise linear classifier based on the extended classifier system for function approximation (XCSF) was modified by developing an adaptive mutation rate, which was proportional to the genotypic content of best individuals and their fitness in each generation. The proposed operator controlled the trade-off between exploration and exploitation while maintaining the diversity in the classifier's population to avoid premature convergence. To assess the effectiveness of the proposed scheme, the extracted features were applied to support vector machine, LDA, nearest neighbor and XCSF classifiers. To evaluate the method, a noisy environment was simulated with different noise amplitudes. It is shown that the results of the proposed technique are more robust as compared to conventional classifiers. Statistical tests demonstrate that the proposed classifier is a promising method for discriminating between ADHD and BMD patients.

  1. Learning multiscale and deep representations for classifying remotely sensed imagery

    Science.gov (United States)

    Zhao, Wenzhi; Du, Shihong

    2016-03-01

    It is widely agreed that spatial features can be combined with spectral properties for improving interpretation performances on very-high-resolution (VHR) images in urban areas. However, many existing methods for extracting spatial features can only generate low-level features and consider limited scales, leading to unpleasant classification results. In this study, multiscale convolutional neural network (MCNN) algorithm was presented to learn spatial-related deep features for hyperspectral remote imagery classification. Unlike traditional methods for extracting spatial features, the MCNN first transforms the original data sets into a pyramid structure containing spatial information at multiple scales, and then automatically extracts high-level spatial features using multiscale training data sets. Specifically, the MCNN has two merits: (1) high-level spatial features can be effectively learned by using the hierarchical learning structure and (2) multiscale learning scheme can capture contextual information at different scales. To evaluate the effectiveness of the proposed approach, the MCNN was applied to classify the well-known hyperspectral data sets and compared with traditional methods. The experimental results shown a significant increase in classification accuracies especially for urban areas.

  2. Instance Selection for Classifier Performance Estimation in Meta Learning

    Directory of Open Access Journals (Sweden)

    Marcin Blachnik

    2017-11-01

    Full Text Available Building an accurate prediction model is challenging and requires appropriate model selection. This process is very time consuming but can be accelerated with meta-learning–automatic model recommendation by estimating the performances of given prediction models without training them. Meta-learning utilizes metadata extracted from the dataset to effectively estimate the accuracy of the model in question. To achieve that goal, metadata descriptors must be gathered efficiently and must be informative to allow the precise estimation of prediction accuracy. In this paper, a new type of metadata descriptors is analyzed. These descriptors are based on the compression level obtained from the instance selection methods at the data-preprocessing stage. To verify their suitability, two types of experiments on real-world datasets have been conducted. In the first one, 11 instance selection methods were examined in order to validate the compression–accuracy relation for three classifiers: k-nearest neighbors (kNN, support vector machine (SVM, and random forest. From this analysis, two methods are recommended (instance-based learning type 2 (IB2, and edited nearest neighbor (ENN which are then compared with the state-of-the-art metaset descriptors. The obtained results confirm that the two suggested compression-based meta-features help to predict accuracy of the base model much more accurately than the state-of-the-art solution.

  3. Evolvability as a Quality Attribute of Software Architectures

    NARCIS (Netherlands)

    Ciraci, S.; van den Broek, P.M.; Duchien, Laurence; D'Hondt, Maja; Mens, Tom

    We review the definition of evolvability as it appears on the literature. In particular, the concept of software evolvability is compared with other system quality attributes, such as adaptability, maintainability and modifiability.

  4. Multivariate analysis of quantitative traits can effectively classify rapeseed germplasm

    Directory of Open Access Journals (Sweden)

    Jankulovska Mirjana

    2014-01-01

    Full Text Available In this study, the use of different multivariate approaches to classify rapeseed genotypes based on quantitative traits has been presented. Tree regression analysis, PCA analysis and two-way cluster analysis were applied in order todescribe and understand the extent of genetic variability in spring rapeseed genotype by trait data. The traits which highly influenced seed and oil yield in rapeseed were successfully identified by the tree regression analysis. Principal predictor for both response variables was number of pods per plant (NP. NP and 1000 seed weight could help in the selection of high yielding genotypes. High values for both traits and oil content could lead to high oil yielding genotypes. These traits may serve as indirect selection criteria and can lead to improvement of seed and oil yield in rapeseed. Quantitative traits that explained most of the variability in the studied germplasm were classified using principal component analysis. In this data set, five PCs were identified, out of which the first three PCs explained 63% of the total variance. It helped in facilitating the choice of variables based on which the genotypes’ clustering could be performed. The two-way cluster analysissimultaneously clustered genotypes and quantitative traits. The final number of clusters was determined using bootstrapping technique. This approach provided clear overview on the variability of the analyzed genotypes. The genotypes that have similar performance regarding the traits included in this study can be easily detected on the heatmap. Genotypes grouped in the clusters 1 and 8 had high values for seed and oil yield, and relatively short vegetative growth duration period and those in cluster 9, combined moderate to low values for vegetative growth duration and moderate to high seed and oil yield. These genotypes should be further exploited and implemented in the rapeseed breeding program. The combined application of these multivariate methods

  5. Deep Learning to Classify Radiology Free-Text Reports.

    Science.gov (United States)

    Chen, Matthew C; Ball, Robyn L; Yang, Lingyao; Moradzadeh, Nathaniel; Chapman, Brian E; Larson, David B; Langlotz, Curtis P; Amrhein, Timothy J; Lungren, Matthew P

    2018-03-01

    Purpose To evaluate the performance of a deep learning convolutional neural network (CNN) model compared with a traditional natural language processing (NLP) model in extracting pulmonary embolism (PE) findings from thoracic computed tomography (CT) reports from two institutions. Materials and Methods Contrast material-enhanced CT examinations of the chest performed between January 1, 1998, and January 1, 2016, were selected. Annotations by two human radiologists were made for three categories: the presence, chronicity, and location of PE. Classification of performance of a CNN model with an unsupervised learning algorithm for obtaining vector representations of words was compared with the open-source application PeFinder. Sensitivity, specificity, accuracy, and F1 scores for both the CNN model and PeFinder in the internal and external validation sets were determined. Results The CNN model demonstrated an accuracy of 99% and an area under the curve value of 0.97. For internal validation report data, the CNN model had a statistically significant larger F1 score (0.938) than did PeFinder (0.867) when classifying findings as either PE positive or PE negative, but no significant difference in sensitivity, specificity, or accuracy was found. For external validation report data, no statistical difference between the performance of the CNN model and PeFinder was found. Conclusion A deep learning CNN model can classify radiology free-text reports with accuracy equivalent to or beyond that of an existing traditional NLP model. © RSNA, 2017 Online supplemental material is available for this article.

  6. Evolving colon injury management: a review.

    Science.gov (United States)

    Greer, Lauren T; Gillern, Suzanne M; Vertrees, Amy E

    2013-02-01

    The colon is the second most commonly injured intra-abdominal organ in penetrating trauma. Management of traumatic colon injuries has evolved significantly over the past 200 years. Traumatic colon injuries can have a wide spectrum of severity, presentation, and management options. There is strong evidence that most non-destructive colon injuries can be successfully managed with primary repair or primary anastomosis. The management of destructive colon injuries remains controversial with most favoring resection with primary anastomosis and others favor colonic diversion in specific circumstances. The historical management of traumatic colon injuries, common mechanisms of injury, demographics, presentation, assessment, diagnosis, management, and complications of traumatic colon injuries both in civilian and military practice are reviewed. The damage control revolution has added another layer of complexity to management with continued controversy.

  7. Pulmonary Sporotrichosis: An Evolving Clinical Paradigm.

    Science.gov (United States)

    Aung, Ar K; Spelman, Denis W; Thompson, Philip J

    2015-10-01

    In recent decades, sporotrichosis, caused by thermally dimorphic fungi Sporothrix schenckii complex, has become an emerging infection in many parts of the world. Pulmonary infection with S. schenckii still remains relatively uncommon, possibly due to underrecognition. Pulmonary sporotrichosis presents with distinct clinical and radiological patterns in both immunocompetent and immunocompromised hosts and can often result in significant morbidity and mortality despite treatment. Current understanding regarding S. schenckii biology, epidemiology, immunopathology, clinical diagnostics, and treatment options has been evolving in the recent years with increased availability of molecular sequencing techniques. However, this changing knowledge has not yet been fully translated into a better understanding of the clinical aspects of pulmonary sporotrichosis, as such current management guidelines remain unsupported by high-level clinical evidence. This article examines recent advances in the knowledge of sporotrichosis and its application to the difficult challenges of managing pulmonary sporotrichosis. Thieme Medical Publishers 333 Seventh Avenue, New York, NY 10001, USA.

  8. Resiliently evolving supply-demand networks

    Science.gov (United States)

    Rubido, Nicolás; Grebogi, Celso; Baptista, Murilo S.

    2014-01-01

    The ability to design a transport network such that commodities are brought from suppliers to consumers in a steady, optimal, and stable way is of great importance for distribution systems nowadays. In this work, by using the circuit laws of Kirchhoff and Ohm, we provide the exact capacities of the edges that an optimal supply-demand network should have to operate stably under perturbations, i.e., without overloading. The perturbations we consider are the evolution of the connecting topology, the decentralization of hub sources or sinks, and the intermittence of supplier and consumer characteristics. We analyze these conditions and the impact of our results, both on the current United Kingdom power-grid structure and on numerically generated evolving archetypal network topologies.

  9. Development and the evolvability of human limbs.

    Science.gov (United States)

    Young, Nathan M; Wagner, Günter P; Hallgrímsson, Benedikt

    2010-02-23

    The long legs and short arms of humans are distinctive for a primate, the result of selection acting in opposite directions on each limb at different points in our evolutionary history. This mosaic pattern challenges our understanding of the relationship of development and evolvability because limbs are serially homologous and genetic correlations should act as a significant constraint on their independent evolution. Here we test a developmental model of limb covariation in anthropoid primates and demonstrate that both humans and apes exhibit significantly reduced integration between limbs when compared to quadrupedal monkeys. This result indicates that fossil hominins likely escaped constraints on independent limb variation via reductions to genetic pleiotropy in an ape-like last common ancestor (LCA). This critical change in integration among hominoids, which is reflected in macroevolutionary differences in the disparity between limb lengths, facilitated selection for modern human limb proportions and demonstrates how development helps shape evolutionary change.

  10. Evolving spiking networks with variable resistive memories.

    Science.gov (United States)

    Howard, Gerard; Bull, Larry; de Lacy Costello, Ben; Gale, Ella; Adamatzky, Andrew

    2014-01-01

    Neuromorphic computing is a brainlike information processing paradigm that requires adaptive learning mechanisms. A spiking neuro-evolutionary system is used for this purpose; plastic resistive memories are implemented as synapses in spiking neural networks. The evolutionary design process exploits parameter self-adaptation and allows the topology and synaptic weights to be evolved for each network in an autonomous manner. Variable resistive memories are the focus of this research; each synapse has its own conductance profile which modifies the plastic behaviour of the device and may be altered during evolution. These variable resistive networks are evaluated on a noisy robotic dynamic-reward scenario against two static resistive memories and a system containing standard connections only. The results indicate that the extra behavioural degrees of freedom available to the networks incorporating variable resistive memories enable them to outperform the comparative synapse types.

  11. Life cycle planning: An evolving concept

    International Nuclear Information System (INIS)

    Moore, P.J.R.; Gorman, I.G.

    1994-01-01

    Life-cycle planning is an evolving concept in the management of oil and gas projects. BHP Petroleum now interprets this idea to include all development planning from discovery and field appraisal to final abandonment and includes safety, environmental, technical, plant, regulatory, and staffing issues. This article describes in the context of the Timor Sea, how despite initial successes and continuing facilities upgrades, BHPP came to perceive that current operations could be the victim of early development successes, particularly in the areas of corrosion and maintenance. The search for analogies elsewhere lead to the UK North Sea, including the experiences of Britoil and BP, both of which performed detailed Life of Field studies in the later eighties. These materials have been used to construct a format and content for total Life-cycle plans in general and the social changes required to ensure their successful application in Timor Sea operations and deployment throughout Australia

  12. Argentina and Brazil: an evolving nuclear relationship

    International Nuclear Information System (INIS)

    Redick, J.R.

    1990-01-01

    Argentina and Brazil have Latin America's most advanced nuclear research and power programs. Both nations reject the Non-Proliferation Treaty (NPT), and have not formally embraced the Tlatelolco Treaty creating a regional nuclear-weapon-free zone. Disturbing ambiguities persist regarding certain indigenous nuclear facilities and growing nuclear submarine and missile capabilities. For these, and other reasons, the two nations are widely considered potential nuclear weapon states. However both nations have been active supporters of the International Atomic Energy Agency (IAEA) and have, in recent years, assumed a generally responsible position in regard to their own nuclear export activities (requiring IAEA safeguards). Most important, however, has been the advent of bilateral nuclear cooperation. This paper considers the evolving nuclear relationship in the context of recent and dramatic political change in Argentina and Brazil. It discusses current political and nuclear developments and the prospects for maintaining and expanding present bilateral cooperation into an effective non-proliferation arrangement. (author)

  13. Classifying PML risk with disease modifying therapies.

    Science.gov (United States)

    Berger, Joseph R

    2017-02-01

    To catalogue the risk of PML with the currently available disease modifying therapies (DMTs) for multiple sclerosis (MS). All DMTs perturb the immune system in some fashion. Natalizumab, a highly effective DMT, has been associated with a significant risk of PML. Fingolimod and dimethyl fumarate have also been unquestionably associated with a risk of PML in the MS population. Concerns about PML risk with other DMTs have arisen due to their mechanism of action and pharmacological parallel to other agents with known PML risk. A method of contextualizing PML risk for DMTs is warranted. Classification of PML risk was predicated on three criteria:: 1) whether the underlying condition being treated predisposes to PML in the absence of the drug; 2) the latency from initiation of the drug to the development of PML; and 3) the frequency with which PML is observed. Among the DMTs, natalizumab occupies a place of its own with respect to PML risk. Significantly lesser degrees of risk exist for fingolimod and dimethyl fumarate. Whether PML will be observed with other DMTs in use for MS, such as, rituximab, teriflunomide, and alemtuzumab, remains uncertain. A logical classification for stratifying DMT PML risk is important for both the physician and patient in contextualizing risk/benefit ratios. As additional experience accumulates regarding PML and the DMTs, this early effort will undoubtedly require revisiting. Copyright © 2016 Elsevier B.V. All rights reserved.

  14. Classifying the Diversity of Bus Mapping Systems

    Science.gov (United States)

    Said, Mohd Shahmy Mohd; Forrest, David

    2018-05-01

    This study represents the first stage of an investigation into understanding the nature of different approaches to mapping bus routes and bus network, and how they may best be applied in different public transport situations. In many cities, bus services represent an important facet of easing traffic congestion and reducing pollution. However, with the entrenched car culture in many countries, persuading people to change their mode of transport is a major challenge. To promote this modal shift, people need to know what services are available and where (and when) they go. Bus service maps provide an invaluable element of providing suitable public transport information, but are often overlooked by transport planners, and are under-researched by cartographers. The method here consists of the creation of a map evaluation form and performing assessment of published bus networks maps. The analyses were completed by a combination of quantitative and qualitative data analysis of various aspects of cartographic design and classification. This paper focuses on the resulting classification, which is illustrated by a series of examples. This classification will facilitate more in depth investigations into the details of cartographic design for such maps and help direct areas for user evaluation.

  15. The genotype-phenotype map of an evolving digital organism

    OpenAIRE

    Fortuna, Miguel A.; Zaman, Luis; Ofria, Charles; Wagner, Andreas

    2017-01-01

    To understand how evolving systems bring forth novel and useful phenotypes, it is essential to understand the relationship between genotypic and phenotypic change. Artificial evolving systems can help us understand whether the genotype-phenotype maps of natural evolving systems are highly unusual, and it may help create evolvable artificial systems. Here we characterize the genotype-phenotype map of digital organisms in Avida, a platform for digital evolution. We consider digital organisms fr...

  16. A Change Impact Analysis to Characterize Evolving Program Behaviors

    Science.gov (United States)

    Rungta, Neha Shyam; Person, Suzette; Branchaud, Joshua

    2012-01-01

    Change impact analysis techniques estimate the potential effects of changes made to software. Directed Incremental Symbolic Execution (DiSE) is an intraprocedural technique for characterizing the impact of software changes on program behaviors. DiSE first estimates the impact of the changes on the source code using program slicing techniques, and then uses the impact sets to guide symbolic execution to generate path conditions that characterize impacted program behaviors. DiSE, however, cannot reason about the flow of impact between methods and will fail to generate path conditions for certain impacted program behaviors. In this work, we present iDiSE, an extension to DiSE that performs an interprocedural analysis. iDiSE combines static and dynamic calling context information to efficiently generate impacted program behaviors across calling contexts. Information about impacted program behaviors is useful for testing, verification, and debugging of evolving programs. We present a case-study of our implementation of the iDiSE algorithm to demonstrate its efficiency at computing impacted program behaviors. Traditional notions of coverage are insufficient for characterizing the testing efforts used to validate evolving program behaviors because they do not take into account the impact of changes to the code. In this work we present novel definitions of impacted coverage metrics that are useful for evaluating the testing effort required to test evolving programs. We then describe how the notions of impacted coverage can be used to configure techniques such as DiSE and iDiSE in order to support regression testing related tasks. We also discuss how DiSE and iDiSE can be configured for debugging finding the root cause of errors introduced by changes made to the code. In our empirical evaluation we demonstrate that the configurations of DiSE and iDiSE can be used to support various software maintenance tasks

  17. A Naive-Bayes classifier for damage detection in engineering materials

    Energy Technology Data Exchange (ETDEWEB)

    Addin, O. [Laboratory of Intelligent Systems, Institute of Advanced Technology, Universiti Putra Malaysia, 43400 Serdang, Selangor (Malaysia); Sapuan, S.M. [Department of Mechanical and Manufacturing Engineering, Universiti Putra Malaysia, 43400 Serdang, Selangor (Malaysia)]. E-mail: sapuan@eng.upm.edu.my; Mahdi, E. [Department of Aerospace Engineering, Universiti Putra Malaysia, 43400 Serdang, Selangor (Malaysia); Othman, M. [Department of Communication Technology and Networks, Universiti Putra Malaysia, 43400 Serdang, Selangor (Malaysia)

    2007-07-01

    This paper is intended to introduce the Bayesian network in general and the Naive-Bayes classifier in particular as one of the most successful classification systems to simulate damage detection in engineering materials. A method for feature subset selection has also been introduced too. The method is based on mean and maximum values of the amplitudes of waves after dividing them into folds then grouping them by a clustering algorithm (e.g. k-means algorithm). The Naive-Bayes classifier and the feature sub-set selection method were analyzed and tested on two sets of data. The data sets were conducted based on artificial damages created in quasi isotopic laminated composites of the AS4/3501-6 graphite/epoxy system and ball bearing of the type 6204 with a steel cage. The Naive-Bayes classifier and the proposed feature subset selection algorithm have been shown as efficient techniques for damage detection in engineering materials.

  18. Feature weighting using particle swarm optimization for learning vector quantization classifier

    Science.gov (United States)

    Dongoran, A.; Rahmadani, S.; Zarlis, M.; Zakarias

    2018-03-01

    This paper discusses and proposes a method of feature weighting in classification assignments on competitive learning artificial neural network LVQ. The weighting feature method is the search for the weight of an attribute using the PSO so as to give effect to the resulting output. This method is then applied to the LVQ-Classifier and tested on the 3 datasets obtained from the UCI Machine Learning repository. Then an accuracy analysis will be generated by two approaches. The first approach using LVQ1, referred to as LVQ-Classifier and the second approach referred to as PSOFW-LVQ, is a proposed model. The result shows that the PSO algorithm is capable of finding attribute weights that increase LVQ-classifier accuracy.

  19. 18 CFR 3a.12 - Authority to classify official information.

    Science.gov (United States)

    2010-04-01

    ... efficient administration. (b) The authority to classify information or material originally as Top Secret is... classify information or material originally as Secret is exercised only by: (1) Officials who have Top... information or material originally as Confidential is exercised by officials who have Top Secret or Secret...

  20. Using Neural Networks to Classify Digitized Images of Galaxies

    Science.gov (United States)

    Goderya, S. N.; McGuire, P. C.

    2000-12-01

    Automated classification of Galaxies into Hubble types is of paramount importance to study the large scale structure of the Universe, particularly as survey projects like the Sloan Digital Sky Survey complete their data acquisition of one million galaxies. At present it is not possible to find robust and efficient artificial intelligence based galaxy classifiers. In this study we will summarize progress made in the development of automated galaxy classifiers using neural networks as machine learning tools. We explore the Bayesian linear algorithm, the higher order probabilistic network, the multilayer perceptron neural network and Support Vector Machine Classifier. The performance of any machine classifier is dependant on the quality of the parameters that characterize the different groups of galaxies. Our effort is to develop geometric and invariant moment based parameters as input to the machine classifiers instead of the raw pixel data. Such an approach reduces the dimensionality of the classifier considerably, and removes the effects of scaling and rotation, and makes it easier to solve for the unknown parameters in the galaxy classifier. To judge the quality of training and classification we develop the concept of Mathews coefficients for the galaxy classification community. Mathews coefficients are single numbers that quantify classifier performance even with unequal prior probabilities of the classes.

  1. Performance of classification confidence measures in dynamic classifier systems

    Czech Academy of Sciences Publication Activity Database

    Štefka, D.; Holeňa, Martin

    2013-01-01

    Roč. 23, č. 4 (2013), s. 299-319 ISSN 1210-0552 R&D Projects: GA ČR GA13-17187S Institutional support: RVO:67985807 Keywords : classifier combining * dynamic classifier systems * classification confidence Subject RIV: IN - Informatics, Computer Science Impact factor: 0.412, year: 2013

  2. 32 CFR 2400.30 - Reproduction of classified information.

    Science.gov (United States)

    2010-07-01

    ... 32 National Defense 6 2010-07-01 2010-07-01 false Reproduction of classified information. 2400.30... SECURITY PROGRAM Safeguarding § 2400.30 Reproduction of classified information. Documents or portions of... the originator or higher authority. Any stated prohibition against reproduction shall be strictly...

  3. Dynamic integration of classifiers in the space of principal components

    NARCIS (Netherlands)

    Tsymbal, A.; Pechenizkiy, M.; Puuronen, S.; Patterson, D.W.; Kalinichenko, L.A.; Manthey, R.; Thalheim, B.; Wloka, U.

    2003-01-01

    Recent research has shown the integration of multiple classifiers to be one of the most important directions in machine learning and data mining. It was shown that, for an ensemble to be successful, it should consist of accurate and diverse base classifiers. However, it is also important that the

  4. Classifier-guided sampling for discrete variable, discontinuous design space exploration: Convergence and computational performance

    Energy Technology Data Exchange (ETDEWEB)

    Backlund, Peter B. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Shahan, David W. [HRL Labs., LLC, Malibu, CA (United States); Seepersad, Carolyn Conner [Univ. of Texas, Austin, TX (United States)

    2014-04-22

    A classifier-guided sampling (CGS) method is introduced for solving engineering design optimization problems with discrete and/or continuous variables and continuous and/or discontinuous responses. The method merges concepts from metamodel-guided sampling and population-based optimization algorithms. The CGS method uses a Bayesian network classifier for predicting the performance of new designs based on a set of known observations or training points. Unlike most metamodeling techniques, however, the classifier assigns a categorical class label to a new design, rather than predicting the resulting response in continuous space, and thereby accommodates nondifferentiable and discontinuous functions of discrete or categorical variables. The CGS method uses these classifiers to guide a population-based sampling process towards combinations of discrete and/or continuous variable values with a high probability of yielding preferred performance. Accordingly, the CGS method is appropriate for discrete/discontinuous design problems that are ill-suited for conventional metamodeling techniques and too computationally expensive to be solved by population-based algorithms alone. In addition, the rates of convergence and computational properties of the CGS method are investigated when applied to a set of discrete variable optimization problems. Results show that the CGS method significantly improves the rate of convergence towards known global optima, on average, when compared to genetic algorithms.

  5. Stability of halophilic proteins: from dipeptide attributes to discrimination classifier.

    Science.gov (United States)

    Zhang, Guangya; Huihua, Ge; Yi, Lin

    2013-02-01

    To investigate the molecular features responsible for protein halophilicity is of great significance for understanding the structure basis of protein halo-stability and would help to develop a practical strategy for designing halophilic proteins. In this work, we have systematically analyzed the dipeptide composition of the halophilic and non-halophilic protein sequences. We observed the halophilic proteins contained more DA, RA, AD, RR, AP, DD, PD, EA, VG and DV at the expense of LK, IL, II, IA, KK, IS, KA, GK, RK and AI. We identified some macromolecular signatures of halo-adaptation, and thought the dipeptide composition might contain more information than amino acid composition. Based on the dipeptide composition, we have developed a machine learning method for classifying halophilic and non-halophilic proteins for the first time. The accuracy of our method for the training dataset was 100.0%, and for the 10-fold cross-validation was 93.1%. We also discussed the influence of some specific dipeptides on prediction accuracy. Copyright © 2012 Elsevier B.V. All rights reserved.

  6. SAR Target Recognition Based on Multi-feature Multiple Representation Classifier Fusion

    Directory of Open Access Journals (Sweden)

    Zhang Xinzheng

    2017-10-01

    Full Text Available In this paper, we present a Synthetic Aperture Radar (SAR image target recognition algorithm based on multi-feature multiple representation learning classifier fusion. First, it extracts three features from the SAR images, namely principal component analysis, wavelet transform, and Two-Dimensional Slice Zernike Moments (2DSZM features. Second, we harness the sparse representation classifier and the cooperative representation classifier with the above-mentioned features to get six predictive labels. Finally, we adopt classifier fusion to obtain the final recognition decision. We researched three different classifier fusion algorithms in our experiments, and the results demonstrate thatusing Bayesian decision fusion gives thebest recognition performance. The method based on multi-feature multiple representation learning classifier fusion integrates the discrimination of multi-features and combines the sparse and cooperative representation classification performance to gain complementary advantages and to improve recognition accuracy. The experiments are based on the Moving and Stationary Target Acquisition and Recognition (MSTAR database,and they demonstrate the effectiveness of the proposed approach.

  7. Ensembles of novelty detection classifiers for structural health monitoring using guided waves

    Science.gov (United States)

    Dib, Gerges; Karpenko, Oleksii; Koricho, Ermias; Khomenko, Anton; Haq, Mahmoodul; Udpa, Lalita

    2018-01-01

    Guided wave structural health monitoring uses sparse sensor networks embedded in sophisticated structures for defect detection and characterization. The biggest challenge of those sensor networks is developing robust techniques for reliable damage detection under changing environmental and operating conditions (EOC). To address this challenge, we develop a novelty classifier for damage detection based on one class support vector machines. We identify appropriate features for damage detection and introduce a feature aggregation method which quadratically increases the number of available training observations. We adopt a two-level voting scheme by using an ensemble of classifiers and predictions. Each classifier is trained on a different segment of the guided wave signal, and each classifier makes an ensemble of predictions based on a single observation. Using this approach, the classifier can be trained using a small number of baseline signals. We study the performance using Monte-Carlo simulations of an analytical model and data from impact damage experiments on a glass fiber composite plate. We also demonstrate the classifier performance using two types of baseline signals: fixed and rolling baseline training set. The former requires prior knowledge of baseline signals from all EOC, while the latter does not and leverages the fact that EOC vary slowly over time and can be modeled as a Gaussian process.

  8. An ensemble of dissimilarity based classifiers for Mackerel gender determination

    International Nuclear Information System (INIS)

    Blanco, A; Rodriguez, R; Martinez-Maranon, I

    2014-01-01

    Mackerel is an infravalored fish captured by European fishing vessels. A manner to add value to this specie can be achieved by trying to classify it attending to its sex. Colour measurements were performed on Mackerel females and males (fresh and defrozen) extracted gonads to obtain differences between sexes. Several linear and non linear classifiers such as Support Vector Machines (SVM), k Nearest Neighbors (k-NN) or Diagonal Linear Discriminant Analysis (DLDA) can been applied to this problem. However, theyare usually based on Euclidean distances that fail to reflect accurately the sample proximities. Classifiers based on non-Euclidean dissimilarities misclassify a different set of patterns. We combine different kind of dissimilarity based classifiers. The diversity is induced considering a set of complementary dissimilarities for each model. The experimental results suggest that our algorithm helps to improve classifiers based on a single dissimilarity

  9. An ensemble of dissimilarity based classifiers for Mackerel gender determination

    Science.gov (United States)

    Blanco, A.; Rodriguez, R.; Martinez-Maranon, I.

    2014-03-01

    Mackerel is an infravalored fish captured by European fishing vessels. A manner to add value to this specie can be achieved by trying to classify it attending to its sex. Colour measurements were performed on Mackerel females and males (fresh and defrozen) extracted gonads to obtain differences between sexes. Several linear and non linear classifiers such as Support Vector Machines (SVM), k Nearest Neighbors (k-NN) or Diagonal Linear Discriminant Analysis (DLDA) can been applied to this problem. However, theyare usually based on Euclidean distances that fail to reflect accurately the sample proximities. Classifiers based on non-Euclidean dissimilarities misclassify a different set of patterns. We combine different kind of dissimilarity based classifiers. The diversity is induced considering a set of complementary dissimilarities for each model. The experimental results suggest that our algorithm helps to improve classifiers based on a single dissimilarity.

  10. Exploring Land Use and Land Cover of Geotagged Social-Sensing Images Using Naive Bayes Classifier

    Directory of Open Access Journals (Sweden)

    Asamaporn Sitthi

    2016-09-01

    Full Text Available Online social media crowdsourced photos contain a vast amount of visual information about the physical properties and characteristics of the earth’s surface. Flickr is an important online social media platform for users seeking this information. Each day, users generate crowdsourced geotagged digital imagery containing an immense amount of information. In this paper, geotagged Flickr images are used for automatic extraction of low-level land use/land cover (LULC features. The proposed method uses a naive Bayes classifier with color, shape, and color index descriptors. The classified images are mapped using a majority filtering approach. The classifier performance in overall accuracy, kappa coefficient, precision, recall, and f-measure was 87.94%, 82.89%, 88.20%, 87.90%, and 88%, respectively. Labeled-crowdsourced images were filtered into a spatial tile of a 30 m × 30 m resolution using the majority voting method to reduce geolocation uncertainty from the crowdsourced data. These tile datasets were used as training and validation samples to classify Landsat TM5 images. The supervised maximum likelihood method was used for the LULC classification. The results show that the geotagged Flickr images can classify LULC types with reasonable accuracy and that the proposed approach improves LULC classification efficiency if a sufficient spatial distribution of crowdsourced data exists.

  11. Parameterization of a fuzzy classifier for the diagnosis of an industrial process

    International Nuclear Information System (INIS)

    Toscano, R.; Lyonnet, P.

    2002-01-01

    The aim of this paper is to present a classifier based on a fuzzy inference system. For this classifier, we propose a parameterization method, which is not necessarily based on an iterative training. This approach can be seen as a pre-parameterization, which allows the determination of the rules base and the parameters of the membership functions. We also present a continuous and derivable version of the previous classifier and suggest an iterative learning algorithm based on a gradient method. An example using the learning basis IRIS, which is a benchmark for classification problems, is presented showing the performances of this classifier. Finally this classifier is applied to the diagnosis of a DC motor showing the utility of this method. However in many cases the total knowledge necessary to the synthesis of the fuzzy diagnosis system (FDS) is not, in general, directly available. It must be extracted from an often-considerable mass of information. For this reason, a general methodology for the design of a FDS is presented and illustrated on a non-linear plant

  12. An adaptive optimal ensemble classifier via bagging and rank aggregation with applications to high dimensional data

    Directory of Open Access Journals (Sweden)

    Datta Susmita

    2010-08-01

    Full Text Available Abstract Background Generally speaking, different classifiers tend to work well for certain types of data and conversely, it is usually not known a priori which algorithm will be optimal in any given classification application. In addition, for most classification problems, selecting the best performing classification algorithm amongst a number of competing algorithms is a difficult task for various reasons. As for example, the order of performance may depend on the performance measure employed for such a comparison. In this work, we present a novel adaptive ensemble classifier constructed by combining bagging and rank aggregation that is capable of adaptively changing its performance depending on the type of data that is being classified. The attractive feature of the proposed classifier is its multi-objective nature where the classification results can be simultaneously optimized with respect to several performance measures, for example, accuracy, sensitivity and specificity. We also show that our somewhat complex strategy has better predictive performance as judged on test samples than a more naive approach that attempts to directly identify the optimal classifier based on the training data performances of the individual classifiers. Results We illustrate the proposed method with two simulated and two real-data examples. In all cases, the ensemble classifier performs at the level of the best individual classifier comprising the ensemble or better. Conclusions For complex high-dimensional datasets resulting from present day high-throughput experiments, it may be wise to consider a number of classification algorithms combined with dimension reduction techniques rather than a fixed standard algorithm set a priori.

  13. Incremental Frequent Subgraph Mining on Large Evolving Graphs

    KAUST Repository

    Abdelhamid, Ehab

    2017-08-22

    Frequent subgraph mining is a core graph operation used in many domains, such as graph data management and knowledge exploration, bioinformatics and security. Most existing techniques target static graphs. However, modern applications, such as social networks, utilize large evolving graphs. Mining these graphs using existing techniques is infeasible, due to the high computational cost. In this paper, we propose IncGM+, a fast incremental approach for continuous frequent subgraph mining problem on a single large evolving graph. We adapt the notion of “fringe” to the graph context, that is the set of subgraphs on the border between frequent and infrequent subgraphs. IncGM+ maintains fringe subgraphs and exploits them to prune the search space. To boost the efficiency, we propose an efficient index structure to maintain selected embeddings with minimal memory overhead. These embeddings are utilized to avoid redundant expensive subgraph isomorphism operations. Moreover, the proposed system supports batch updates. Using large real-world graphs, we experimentally verify that IncGM+ outperforms existing methods by up to three orders of magnitude, scales to much larger graphs and consumes less memory.

  14. Evolving Stochastic Learning Algorithm based on Tsallis entropic index

    Science.gov (United States)

    Anastasiadis, A. D.; Magoulas, G. D.

    2006-03-01

    In this paper, inspired from our previous algorithm, which was based on the theory of Tsallis statistical mechanics, we develop a new evolving stochastic learning algorithm for neural networks. The new algorithm combines deterministic and stochastic search steps by employing a different adaptive stepsize for each network weight, and applies a form of noise that is characterized by the nonextensive entropic index q, regulated by a weight decay term. The behavior of the learning algorithm can be made more stochastic or deterministic depending on the trade off between the temperature T and the q values. This is achieved by introducing a formula that defines a time-dependent relationship between these two important learning parameters. Our experimental study verifies that there are indeed improvements in the convergence speed of this new evolving stochastic learning algorithm, which makes learning faster than using the original Hybrid Learning Scheme (HLS). In addition, experiments are conducted to explore the influence of the entropic index q and temperature T on the convergence speed and stability of the proposed method.

  15. Correspondence analysis: a method for classifying similar patterns of violence against women Análise de correspondência: um método para classificação de mulheres com perfil semelhante de vitimização

    Directory of Open Access Journals (Sweden)

    Jurema Corrêa da Mota

    2008-06-01

    Full Text Available Violence against woman has received relatively little debate in society. It includes physical, psychological, and sexual abuse that jeopardizes the victim's health. Multivariate correspondence analysis and cluster analysis were applied to crimes reported to the Integrated Women's Aid Center in Rio de Janeiro, Brazil, to investigate associations between injury and define criteria for classifying the aggressions. Three groups of abuse were identified, differing according to the nature (physical, psychological, or sexual and severity of the crimes. Less serious crimes consisted of threats and moderate physical injuries. The intermediate severity group included serious physical assault and threats. More serious crimes included death threats, rape, and sexual assault. The method thus allowed classification of the crimes in three groups according to severity.A violência contra a mulher é uma questão ainda pouco debatida na sociedade, abrangendo um conjunto de agressões físicas, psicológicas e sexuais que contribuem para a depreciação da saúde da vítima. Aplicou-se a técnica de análise de correspondência multivariada, seguida da técnica de análise de cluster aos crimes registrados no Centro Integrado de Atendimento à Mulher, Rio de Janeiro, Brasil, com o objetivo de investigar o padrão de associação entre os agravos e estabelecer critérios para a classificação das agressões. Identificaram-se três grupos que se distinguem pela natureza do crime (físico, psicológico e sexual e pelos níveis de gravidade. O menos grave é formado pelos crimes de lesão corporal leve e ameaça. O de gravidade intermediária reúne crimes de lesão corporal grave e ameaça. No de maior gravidade estão os crimes de ameaça de morte, estupro e abuso sexual. O método permitiu a classificação dos crimes em três grupos, que podem ser ordenados de acordo com o grau de severidade que guardam entre si.

  16. The evolving energy budget of accretionary wedges

    Science.gov (United States)

    McBeck, Jessica; Cooke, Michele; Maillot, Bertrand; Souloumiac, Pauline

    2017-04-01

    The energy budget of evolving accretionary systems reveals how deformational processes partition energy as faults slip, topography uplifts, and layer-parallel shortening produces distributed off-fault deformation. The energy budget provides a quantitative framework for evaluating the energetic contribution or consumption of diverse deformation mechanisms. We investigate energy partitioning in evolving accretionary prisms by synthesizing data from physical sand accretion experiments and numerical accretion simulations. We incorporate incremental strain fields and cumulative force measurements from two suites of experiments to design numerical simulations that represent accretionary wedges with stronger and weaker detachment faults. One suite of the physical experiments includes a basal glass bead layer and the other does not. Two physical experiments within each suite implement different boundary conditions (stable base versus moving base configuration). Synthesizing observations from the differing base configurations reduces the influence of sidewall friction because the force vector produced by sidewall friction points in opposite directions depending on whether the base is fixed or moving. With the numerical simulations, we calculate the energy budget at two stages of accretion: at the maximum force preceding the development of the first thrust pair, and at the minimum force following the development of the pair. To identify the appropriate combination of material and fault properties to apply in the simulations, we systematically vary the Young's modulus and the fault static and dynamic friction coefficients in numerical accretion simulations, and identify the set of parameters that minimizes the misfit between the normal force measured on the physical backwall and the numerically simulated force. Following this derivation of the appropriate material and fault properties, we calculate the components of the work budget in the numerical simulations and in the

  17. Predicting protein subcellular locations using hierarchical ensemble of Bayesian classifiers based on Markov chains

    Directory of Open Access Journals (Sweden)

    Eils Roland

    2006-06-01

    Full Text Available Abstract Background The subcellular location of a protein is closely related to its function. It would be worthwhile to develop a method to predict the subcellular location for a given protein when only the amino acid sequence of the protein is known. Although many efforts have been made to predict subcellular location from sequence information only, there is the need for further research to improve the accuracy of prediction. Results A novel method called HensBC is introduced to predict protein subcellular location. HensBC is a recursive algorithm which constructs a hierarchical ensemble of classifiers. The classifiers used are Bayesian classifiers based on Markov chain models. We tested our method on six various datasets; among them are Gram-negative bacteria dataset, data for discriminating outer membrane proteins and apoptosis proteins dataset. We observed that our method can predict the subcellular location with high accuracy. Another advantage of the proposed method is that it can improve the accuracy of the prediction of some classes with few sequences in training and is therefore useful for datasets with imbalanced distribution of classes. Conclusion This study introduces an algorithm which uses only the primary sequence of a protein to predict its subcellular location. The proposed recursive scheme represents an interesting methodology for learning and combining classifiers. The method is computationally efficient and competitive with the previously reported approaches in terms of prediction accuracies as empirical results indicate. The code for the software is available upon request.

  18. A Generic multi-dimensional feature extraction method using multiobjective genetic programming.

    Science.gov (United States)

    Zhang, Yang; Rockett, Peter I

    2009-01-01

    In this paper, we present a generic feature extraction method for pattern classification using multiobjective genetic programming. This not only evolves the (near-)optimal set of mappings from a pattern space to a multi-dimensional decision space, but also simultaneously optimizes the dimensionality of that decision space. The presented framework evolves vector-to-vector feature extractors that maximize class separability. We demonstrate the efficacy of our approach by making statistically-founded comparisons with a wide variety of established classifier paradigms over a range of datasets and find that for most of the pairwise comparisons, our evolutionary method delivers statistically smaller misclassification errors. At very worst, our method displays no statistical difference in a few pairwise comparisons with established classifier/dataset combinations; crucially, none of the misclassification results produced by our method is worse than any comparator classifier. Although principally focused on feature extraction, feature selection is also performed as an implicit side effect; we show that both feature extraction and selection are important to the success of our technique. The presented method has the practical consequence of obviating the need to exhaustively evaluate a large family of conventional classifiers when faced with a new pattern recognition problem in order to attain a good classification accuracy.

  19. On the Critical Role of Divergent Selection in Evolvability

    Directory of Open Access Journals (Sweden)

    Joel Lehman

    2016-08-01

    Full Text Available An ambitious goal in evolutionary robotics is to evolve increasingly complex robotic behaviors with minimal human design effort. Reaching this goal requires evolutionary algorithms that can unlock from genetic encodings their latent potential for evolvability. One issue clouding this goal is conceptual confusion about evolvability, which often obscures the aspects of evolvability that are important or desirable. The danger from such confusion is that it may establish unrealistic goals for evolvability that prove unproductive in practice. An important issue separate from conceptual confusion is the common misalignment between selection and evolvability in evolutionary robotics. While more expressive encodings can represent higher-level adaptations (e.g. sexual reproduction or developmental systems that increase long-term evolutionary potential (i.e. evolvability, realizing such potential requires gradients of fitness and evolvability to align. In other words, selection is often a critical factor limiting increasing evolvability. Thus, drawing from a series of recent papers, this article seeks to both (1 clarify and focus the ways in which the term evolvability is used within artificial evolution, and (2 argue for the importance of one type of selection, i.e. divergent selection, for enabling evolvability. The main argument is that there is a fundamental connection between divergent selection and evolvability (on both the individual and population level that does not hold for typical goal-oriented selection. The conclusion is that selection pressure plays a critical role in realizing the potential for evolvability, and that divergent selection in particular provides a principled mechanism for encouraging evolvability in artificial evolution.

  20. Approximating centrality in evolving graphs: toward sublinearity

    Science.gov (United States)

    Priest, Benjamin W.; Cybenko, George

    2017-05-01

    The identification of important nodes is a ubiquitous problem in the analysis of social networks. Centrality indices (such as degree centrality, closeness centrality, betweenness centrality, PageRank, and others) are used across many domains to accomplish this task. However, the computation of such indices is expensive on large graphs. Moreover, evolving graphs are becoming increasingly important in many applications. It is therefore desirable to develop on-line algorithms that can approximate centrality measures using memory sublinear in the size of the graph. We discuss the challenges facing the semi-streaming computation of many centrality indices. In particular, we apply recent advances in the streaming and sketching literature to provide a preliminary streaming approximation algorithm for degree centrality utilizing CountSketch and a multi-pass semi-streaming approximation algorithm for closeness centrality leveraging a spanner obtained through iteratively sketching the vertex-edge adjacency matrix. We also discuss possible ways forward for approximating betweenness centrality, as well as spectral measures of centrality. We provide a preliminary result using sketched low-rank approximations to approximate the output of the HITS algorithm.

  1. Functional Topology of Evolving Urban Drainage Networks

    Science.gov (United States)

    Yang, Soohyun; Paik, Kyungrock; McGrath, Gavan S.; Urich, Christian; Krueger, Elisabeth; Kumar, Praveen; Rao, P. Suresh C.

    2017-11-01

    We investigated the scaling and topology of engineered urban drainage networks (UDNs) in two cities, and further examined UDN evolution over decades. UDN scaling was analyzed using two power law scaling characteristics widely employed for river networks: (1) Hack's law of length (L)-area (A) [L∝Ah] and (2) exceedance probability distribution of upstream contributing area (δ) [P>(A≥δ>)˜aδ-ɛ]. For the smallest UDNs ((A≥δ>) plots for river networks are abruptly truncated, those for UDNs display exponential tempering [P>(A≥δ>)=aδ-ɛexp⁡>(-cδ>)]. The tempering parameter c decreases as the UDNs grow, implying that the distribution evolves in time to resemble those for river networks. However, the power law exponent ɛ for large UDNs tends to be greater than the range reported for river networks. Differences in generative processes and engineering design constraints contribute to observed differences in the evolution of UDNs and river networks, including subnet heterogeneity and nonrandom branching.

  2. An Evolving Worldview: Making Open Source Easy

    Science.gov (United States)

    Rice, Z.

    2017-12-01

    NASA Worldview is an interactive interface for browsing full-resolution, global satellite imagery. Worldview supports an open data policy so that academia, private industries and the general public can use NASA's satellite data to address Earth science related issues. Worldview was open sourced in 2014. By shifting to an open source approach, the Worldview application has evolved to better serve end-users. Project developers are able to have discussions with end-users and community developers to understand issues and develop new features. Community developers are able to track upcoming features, collaborate on them and make their own contributions. Developers who discover issues are able to address those issues and submit a fix. This reduces the time it takes for a project developer to reproduce an issue or develop a new feature. Getting new developers to contribute to the project has been one of the most important and difficult aspects of open sourcing Worldview. After witnessing potential outside contributors struggle, a focus has been made on making the installation of Worldview simple to reduce the initial learning curve and make contributing code easy. One way we have addressed this is through a simplified setup process. Our setup documentation includes a set of prerequisites and a set of straightforward commands to clone, configure, install and run. This presentation will emphasize our focus to simplify and standardize Worldview's open source code so that more people are able to contribute. The more people who contribute, the better the application will become over time.

  3. Extreme insular dwarfism evolved in a mammoth.

    Science.gov (United States)

    Herridge, Victoria L; Lister, Adrian M

    2012-08-22

    The insular dwarfism seen in Pleistocene elephants has come to epitomize the island rule; yet our understanding of this phenomenon is hampered by poor taxonomy. For Mediterranean dwarf elephants, where the most extreme cases of insular dwarfism are observed, a key systematic question remains unresolved: are all taxa phyletic dwarfs of a single mainland species Palaeoloxodon antiquus (straight-tusked elephant), or are some referable to Mammuthus (mammoths)? Ancient DNA and geochronological evidence have been used to support a Mammuthus origin for the Cretan 'Palaeoloxodon' creticus, but these studies have been shown to be flawed. On the basis of existing collections and recent field discoveries, we present new, morphological evidence for the taxonomic status of 'P'. creticus, and show that it is indeed a mammoth, most probably derived from Early Pleistocene Mammuthus meridionalis or possibly Late Pliocene Mammuthus rumanus. We also show that Mammuthus creticus is smaller than other known insular dwarf mammoths, and is similar in size to the smallest dwarf Palaeoloxodon species from Sicily and Malta, making it the smallest mammoth species known to have existed. These findings indicate that extreme insular dwarfism has evolved to a similar degree independently in two elephant lineages.

  4. An evolving network model with modular growth

    International Nuclear Information System (INIS)

    Zou Zhi-Yun; Liu Peng; Lei Li; Gao Jian-Zhi

    2012-01-01

    In this paper, we propose an evolving network model growing fast in units of module, according to the analysis of the evolution characteristics in real complex networks. Each module is a small-world network containing several interconnected nodes and the nodes between the modules are linked by preferential attachment on degree of nodes. We study the modularity measure of the proposed model, which can be adjusted by changing the ratio of the number of inner-module edges and the number of inter-module edges. In view of the mean-field theory, we develop an analytical function of the degree distribution, which is verified by a numerical example and indicates that the degree distribution shows characteristics of the small-world network and the scale-free network distinctly at different segments. The clustering coefficient and the average path length of the network are simulated numerically, indicating that the network shows the small-world property and is affected little by the randomness of the new module. (interdisciplinary physics and related areas of science and technology)

  5. A local-world evolving hypernetwork model

    International Nuclear Information System (INIS)

    Yang Guang-Yong; Liu Jian-Guo

    2014-01-01

    Complex hypernetworks are ubiquitous in the real system. It is very important to investigate the evolution mechanisms. In this paper, we present a local-world evolving hypernetwork model by taking into account the hyperedge growth and local-world hyperedge preferential attachment mechanisms. At each time step, a newly added hyperedge encircles a new coming node and a number of nodes from a randomly selected local world. The number of the selected nodes from the local world obeys the uniform distribution and its mean value is m. The analytical and simulation results show that the hyperdegree approximately obeys the power-law form and the exponent of hyperdegree distribution is γ = 2 + 1/m. Furthermore, we numerically investigate the node degree, hyperedge degree, clustering coefficient, as well as the average distance, and find that the hypernetwork model shares the scale-free and small-world properties, which shed some light for deeply understanding the evolution mechanism of the real systems. (interdisciplinary physics and related areas of science and technology)

  6. Orbital Decay in Binaries with Evolved Stars

    Science.gov (United States)

    Sun, Meng; Arras, Phil; Weinberg, Nevin N.; Troup, Nicholas; Majewski, Steven R.

    2018-01-01

    Two mechanisms are often invoked to explain tidal friction in binary systems. The ``dynamical tide” is the resonant excitation of internal gravity waves by the tide, and their subsequent damping by nonlinear fluid processes or thermal diffusion. The ``equilibrium tide” refers to non-resonant excitation of fluid motion in the star’s convection zone, with damping by interaction with the turbulent eddies. There have been numerous studies of these processes in main sequence stars, but less so on the subgiant and red giant branches. Motivated by the newly discovered close binary systems in the Apache Point Observatory Galactic Evolution Experiment (APOGEE-1), we have performed calculations of both the dynamical and equilibrium tide processes for stars over a range of mass as the star’s cease core hydrogen burning and evolve to shell burning. Even for stars which had a radiative core on the main sequence, the dynamical tide may have very large amplitude in the newly radiative core in post-main sequence, giving rise to wave breaking. The resulting large dynamical tide dissipation rate is compared to the equilibrium tide, and the range of secondary masses and orbital periods over which rapid orbital decay may occur will be discussed, as well as applications to close APOGEE binaries.

  7. Diverticular Disease: Traditional and Evolving Paradigms.

    Science.gov (United States)

    Lamanna, Lenore; Moran, Patricia E

    Diverticular disease includes diverticulosis, which are sac protrusions of the intestinal mucosa, and diverticulitis, inflammation of the diverticula. Diverticular disease is listed as one of the top 10 leading physician diagnoses for gastrointestinal disorders in outpatient clinic visits in the United States. There are several classifications of diverticular disease ranging from asymptomatic diverticulosis to diverticulitis with complications. Several theories are linked to the development of diverticula which includes the physiology of the colon itself, collagen cross-linking, and recently challenged, low-fiber intake. The differential diagnoses of lower abdominal pain in addition to diverticular disease have overlapping signs and symptoms, which can make a diagnosis challenging. Identification of the distinct signs and symptoms of each classification will assist the practitioner in making the correct diagnosis and lead to appropriate management. The findings from recent studies have changed the paradigm of diverticular disease. The purpose of this article is to discuss traditional dogma and evolving concepts in the pathophysiology, prevention, and management of diverticular disease. Practitioners must be knowledgeable about diverticular disease for improved outcomes.

  8. Minority games, evolving capitals and replicator dynamics

    International Nuclear Information System (INIS)

    Galla, Tobias; Zhang, Yi-Cheng

    2009-01-01

    We discuss a simple version of the minority game (MG) in which agents hold only one strategy each, but in which their capitals evolve dynamically according to their success and in which the total trading volume varies in time accordingly. This feature is known to be crucial for MGs to reproduce stylized facts of real market data. The stationary states and phase diagram of the model can be computed, and we show that the ergodicity breaking phase transition common for MGs, and marked by a divergence of the integrated response, is present also in this simplified model. An analogous majority game turns out to be relatively void of interesting features, and the total capital is found to diverge in time. Introducing a restraining force leads to a model akin to the replicator dynamics of evolutionary game theory, and we demonstrate that here a different type of phase transition is observed. Finally we briefly discuss the relation of this model with one strategy per player to more sophisticated minority games with dynamical capitals and several trading strategies per agent

  9. An evolving model of online bipartite networks

    Science.gov (United States)

    Zhang, Chu-Xu; Zhang, Zi-Ke; Liu, Chuang

    2013-12-01

    Understanding the structure and evolution of online bipartite networks is a significant task since they play a crucial role in various e-commerce services nowadays. Recently, various attempts have been tried to propose different models, resulting in either power-law or exponential degree distributions. However, many empirical results show that the user degree distribution actually follows a shifted power-law distribution, the so-called Mandelbrot’s law, which cannot be fully described by previous models. In this paper, we propose an evolving model, considering two different user behaviors: random and preferential attachment. Extensive empirical results on two real bipartite networks, Delicious and CiteULike, show that the theoretical model can well characterize the structure of real networks for both user and object degree distributions. In addition, we introduce a structural parameter p, to demonstrate that the hybrid user behavior leads to the shifted power-law degree distribution, and the region of power-law tail will increase with the increment of p. The proposed model might shed some lights in understanding the underlying laws governing the structure of real online bipartite networks.

  10. The Evolving Classification of Pulmonary Hypertension.

    Science.gov (United States)

    Foshat, Michelle; Boroumand, Nahal

    2017-05-01

    - An explosion of information on pulmonary hypertension has occurred during the past few decades. The perception of this disease has shifted from purely clinical to incorporate new knowledge of the underlying pathology. This transfer has occurred in light of advancements in pathophysiology, histology, and molecular medical diagnostics. - To update readers about the evolving understanding of the etiology and pathogenesis of pulmonary hypertension and to demonstrate how pathology has shaped the current classification. - Information presented at the 5 World Symposia on pulmonary hypertension held since 1973, with the last meeting occurring in 2013, was used in this review. - Pulmonary hypertension represents a heterogeneous group of disorders that are differentiated based on differences in clinical, hemodynamic, and histopathologic features. Early concepts of pulmonary hypertension were largely influenced by pharmacotherapy, hemodynamic function, and clinical presentation of the disease. The initial nomenclature for pulmonary hypertension segregated the clinical classifications from pathologic subtypes. Major restructuring of this disease classification occurred between the first and second symposia, which was the first to unite clinical and pathologic information in the categorization scheme. Additional changes were introduced in subsequent meetings, particularly between the third and fourth World Symposia meetings, when additional pathophysiologic information was gained. Discoveries in molecular diagnostics significantly progressed the understanding of idiopathic pulmonary arterial hypertension. Continued advancements in imaging modalities, mechanistic pathogenicity, and molecular biomarkers will enable physicians to define pulmonary hypertension phenotypes based on the pathobiology and allow for treatment customization.

  11. Novel Two-Step Classifier for Torsades de Pointes Risk Stratification from Direct Features

    Directory of Open Access Journals (Sweden)

    Jaimit Parikh

    2017-11-01

    Full Text Available While pre-clinical Torsades de Pointes (TdP risk classifiers had initially been based on drug-induced block of hERG potassium channels, it is now well established that improved risk prediction can be achieved by considering block of non-hERG ion channels. The current multi-channel TdP classifiers can be categorized into two classes. First, the classifiers that take as input the values of drug-induced block of ion channels (direct features. Second, the classifiers that are built on features extracted from output of the drug-induced multi-channel blockage simulations in the in-silico models (derived features. The classifiers built on derived features have thus far not consistently provided increased prediction accuracies, and hence casts doubt on the value of such approaches given the cost of including biophysical detail. Here, we propose a new two-step method for TdP risk classification, referred to as Multi-Channel Blockage at Early After Depolarization (MCB@EAD. In the first step, we classified the compound that produced insufficient hERG block as non-torsadogenic. In the second step, the role of non-hERG channels to modulate TdP risk are considered by constructing classifiers based on direct or derived features at critical hERG block concentrations that generates EADs in the computational cardiac cell models. MCB@EAD provides comparable or superior TdP risk classification of the drugs from the direct features in tests against published methods. TdP risk for the drugs highly correlated to the propensity to generate EADs in the model. However, the derived features of the biophysical models did not improve the predictive capability for TdP risk assessment.

  12. Feature extraction using convolutional neural network for classifying breast density in mammographic images

    Science.gov (United States)

    Thomaz, Ricardo L.; Carneiro, Pedro C.; Patrocinio, Ana C.

    2017-03-01

    Breast cancer is the leading cause of death for women in most countries. The high levels of mortality relate mostly to late diagnosis and to the direct proportionally relationship between breast density and breast cancer development. Therefore, the correct assessment of breast density is important to provide better screening for higher risk patients. However, in modern digital mammography the discrimination among breast densities is highly complex due to increased contrast and visual information for all densities. Thus, a computational system for classifying breast density might be a useful tool for aiding medical staff. Several machine-learning algorithms are already capable of classifying small number of classes with good accuracy. However, machinelearning algorithms main constraint relates to the set of features extracted and used for classification. Although well-known feature extraction techniques might provide a good set of features, it is a complex task to select an initial set during design of a classifier. Thus, we propose feature extraction using a Convolutional Neural Network (CNN) for classifying breast density by a usual machine-learning classifier. We used 307 mammographic images downsampled to 260x200 pixels to train a CNN and extract features from a deep layer. After training, the activation of 8 neurons from a deep fully connected layer are extracted and used as features. Then, these features are feedforward to a single hidden layer neural network that is cross-validated using 10-folds to classify among four classes of breast density. The global accuracy of this method is 98.4%, presenting only 1.6% of misclassification. However, the small set of samples and memory constraints required the reuse of data in both CNN and MLP-NN, therefore overfitting might have influenced the results even though we cross-validated the network. Thus, although we presented a promising method for extracting features and classifying breast density, a greater database is

  13. Fault Diagnosis for Distribution Networks Using Enhanced Support Vector Machine Classifier with Classical Multidimensional Scaling

    Directory of Open Access Journals (Sweden)

    Ming-Yuan Cho

    2017-09-01

    Full Text Available In this paper, a new fault diagnosis techniques based on time domain reflectometry (TDR method with pseudo-random binary sequence (PRBS stimulus and support vector machine (SVM classifier has been investigated to recognize the different types of fault in the radial distribution feeders. This novel technique has considered the amplitude of reflected signals and the peaks of cross-correlation (CCR between the reflected and incident wave for generating fault current dataset for SVM. Furthermore, this multi-layer enhanced SVM classifier is combined with classical multidimensional scaling (CMDS feature extraction algorithm and kernel parameter optimization to increase training speed and improve overall classification accuracy. The proposed technique has been tested on a radial distribution feeder to identify ten different types of fault considering 12 input features generated by using Simulink software and MATLAB Toolbox. The success rate of SVM classifier is over 95% which demonstrates the effectiveness and the high accuracy of proposed method.

  14. Feature and score fusion based multiple classifier selection for iris recognition.

    Science.gov (United States)

    Islam, Md Rabiul

    2014-01-01

    The aim of this work is to propose a new feature and score fusion based iris recognition approach where voting method on Multiple Classifier Selection technique has been applied. Four Discrete Hidden Markov Model classifiers output, that is, left iris based unimodal system, right iris based unimodal system, left-right iris feature fusion based multimodal system, and left-right iris likelihood ratio score fusion based multimodal system, is combined using voting method to achieve the final recognition result. CASIA-IrisV4 database has been used to measure the performance of the proposed system with various dimensions. Experimental results show the versatility of the proposed system of four different classifiers with various dimensions. Finally, recognition accuracy of the proposed system has been compared with existing N hamming distance score fusion approach proposed by Ma et al., log-likelihood ratio score fusion approach proposed by Schmid et al., and single level feature fusion approach proposed by Hollingsworth et al.

  15. Class-specific Error Bounds for Ensemble Classifiers

    Energy Technology Data Exchange (ETDEWEB)

    Prenger, R; Lemmond, T; Varshney, K; Chen, B; Hanley, W

    2009-10-06

    The generalization error, or probability of misclassification, of ensemble classifiers has been shown to be bounded above by a function of the mean correlation between the constituent (i.e., base) classifiers and their average strength. This bound suggests that increasing the strength and/or decreasing the correlation of an ensemble's base classifiers may yield improved performance under the assumption of equal error costs. However, this and other existing bounds do not directly address application spaces in which error costs are inherently unequal. For applications involving binary classification, Receiver Operating Characteristic (ROC) curves, performance curves that explicitly trade off false alarms and missed detections, are often utilized to support decision making. To address performance optimization in this context, we have developed a lower bound for the entire ROC curve that can be expressed in terms of the class-specific strength and correlation of the base classifiers. We present empirical analyses demonstrating the efficacy of these bounds in predicting relative classifier performance. In addition, we specify performance regions of the ROC curve that are naturally delineated by the class-specific strengths of the base classifiers and show that each of these regions can be associated with a unique set of guidelines for performance optimization of binary classifiers within unequal error cost regimes.

  16. Frog sound identification using extended k-nearest neighbor classifier

    Science.gov (United States)

    Mukahar, Nordiana; Affendi Rosdi, Bakhtiar; Athiar Ramli, Dzati; Jaafar, Haryati

    2017-09-01

    Frog sound identification based on the vocalization becomes important for biological research and environmental monitoring. As a result, different types of feature extractions and classifiers have been employed to evaluate the accuracy of frog sound identification. This paper presents a frog sound identification with Extended k-Nearest Neighbor (EKNN) classifier. The EKNN classifier integrates the nearest neighbors and mutual sharing of neighborhood concepts, with the aims of improving the classification performance. It makes a prediction based on who are the nearest neighbors of the testing sample and who consider the testing sample as their nearest neighbors. In order to evaluate the classification performance in frog sound identification, the EKNN classifier is compared with competing classifier, k -Nearest Neighbor (KNN), Fuzzy k -Nearest Neighbor (FKNN) k - General Nearest Neighbor (KGNN)and Mutual k -Nearest Neighbor (MKNN) on the recorded sounds of 15 frog species obtained in Malaysia forest. The recorded sounds have been segmented using Short Time Energy and Short Time Average Zero Crossing Rate (STE+STAZCR), sinusoidal modeling (SM), manual and the combination of Energy (E) and Zero Crossing Rate (ZCR) (E+ZCR) while the features are extracted by Mel Frequency Cepstrum Coefficient (MFCC). The experimental results have shown that the EKNCN classifier exhibits the best performance in terms of accuracy compared to the competing classifiers, KNN, FKNN, GKNN and MKNN for all cases.

  17. Development of multicriteria models to classify energy efficiency alternatives

    International Nuclear Information System (INIS)

    Neves, Luis Pires; Antunes, Carlos Henggeler; Dias, Luis Candido; Martins, Antonio Gomes

    2005-01-01

    This paper aims at describing a novel constructive approach to develop decision support models to classify energy efficiency initiatives, including traditional Demand-Side Management and Market Transformation initiatives, overcoming the limitations and drawbacks of Cost-Benefit Analysis. A multicriteria approach based on the ELECTRE-TRI method is used, focusing on four perspectives: - an independent Agency with the aim of promoting energy efficiency; - Distribution-only utilities under a regulated framework; - the Regulator; - Supply companies in a competitive liberalized market. These perspectives were chosen after a system analysis of the decision situation regarding the implementation of energy efficiency initiatives, looking for the main roles and power relations, with the purpose of structuring the decision problem by identifying the actors, the decision makers, the decision paradigm, and the relevant criteria. The multicriteria models developed allow considering different kinds of impacts, but avoiding difficult measurements and unit conversions due to the nature of the multicriteria method chosen. The decision is then based on all the significant effects of the initiative, both positive and negative ones, including ancillary effects often forgotten in cost-benefit analysis. The ELECTRE-TRI, as most multicriteria methods, provides to the Decision Maker the ability of controlling the relevance each impact can have on the final decision. The decision support process encompasses a robustness analysis, which, together with a good documentation of the parameters supplied into the model, should support sound decisions. The models were tested with a set of real-world initiatives and compared with possible decisions based on Cost-Benefit analysis

  18. Unsupervised online classifier in sleep scoring for sleep deprivation studies.

    Science.gov (United States)

    Libourel, Paul-Antoine; Corneyllie, Alexandra; Luppi, Pierre-Hervé; Chouvet, Guy; Gervasoni, Damien

    2015-05-01

    This study was designed to evaluate an unsupervised adaptive algorithm for real-time detection of sleep and wake states in rodents. We designed a Bayesian classifier that automatically extracts electroencephalogram (EEG) and electromyogram (EMG) features and categorizes non-overlapping 5-s epochs into one of the three major sleep and wake states without any human supervision. This sleep-scoring algorithm is coupled online with a new device to perform selective paradoxical sleep deprivation (PSD). Controlled laboratory settings for chronic polygraphic sleep recordings and selective PSD. Ten adult Sprague-Dawley rats instrumented for chronic polysomnographic recordings. The performance of the algorithm is evaluated by comparison with the score obtained by a human expert reader. Online detection of PS is then validated with a PSD protocol with duration of 72 hours. Our algorithm gave a high concordance with human scoring with an average κ coefficient > 70%. Notably, the specificity to detect PS reached 92%. Selective PSD using real-time detection of PS strongly reduced PS amounts, leaving only brief PS bouts necessary for the detection of PS in EEG and EMG signals (4.7 ± 0.7% over 72 h, versus 8.9 ± 0.5% in baseline), and was followed by a significant PS rebound (23.3 ± 3.3% over 150 minutes). Our fully unsupervised data-driven algorithm overcomes some limitations of the other automated methods such as the selection of representative descriptors or threshold settings. When used online and coupled with our sleep deprivation device, it represents a better option for selective PSD than other methods like the tedious gentle handling or the platform method. © 2015 Associated Professional Sleep Societies, LLC.

  19. Medical Dataset Classification: A Machine Learning Paradigm Integrating Particle Swarm Optimization with Extreme Learning Machine Classifier

    Directory of Open Access Journals (Sweden)

    C. V. Subbulakshmi

    2015-01-01

    Full Text Available Medical data classification is a prime data mining problem being discussed about for a decade that has attracted several researchers around the world. Most classifiers are designed so as to learn from the data itself using a training process, because complete expert knowledge to determine classifier parameters is impracticable. This paper proposes a hybrid methodology based on machine learning paradigm. This paradigm integrates the successful exploration mechanism called self-regulated learning capability of the particle swarm optimization (PSO algorithm with the extreme learning machine (ELM classifier. As a recent off-line learning method, ELM is a single-hidden layer feedforward neural network (FFNN, proved to be an excellent classifier with large number of hidden layer neurons. In this research, PSO is used to determine the optimum set of parameters for the ELM, thus reducing the number of hidden layer neurons, and it further improves the network generalization performance. The proposed method is experimented on five benchmarked datasets of the UCI Machine Learning Repository for handling medical dataset classification. Simulation results show that the proposed approach is able to achieve good generalization performance, compared to the results of other classifiers.

  20. Localization and Recognition of Dynamic Hand Gestures Based on Hierarchy of Manifold Classifiers

    Science.gov (United States)

    Favorskaya, M.; Nosov, A.; Popov, A.

    2015-05-01

    Generally, the dynamic hand gestures are captured in continuous video sequences, and a gesture recognition system ought to extract the robust features automatically. This task involves the highly challenging spatio-temporal variations of dynamic hand gestures. The proposed method is based on two-level manifold classifiers including the trajectory classifiers in any time instants and the posture classifiers of sub-gestures in selected time instants. The trajectory classifiers contain skin detector, normalized skeleton representation of one or two hands, and motion history representing by motion vectors normalized through predetermined directions (8 and 16 in our case). Each dynamic gesture is separated into a set of sub-gestures in order to predict a trajectory and remove those samples of gestures, which do not satisfy to current trajectory. The posture classifiers involve the normalized skeleton representation of palm and fingers and relative finger positions using fingertips. The min-max criterion is used for trajectory recognition, and the decision tree technique was applied for posture recognition of sub-gestures. For experiments, a dataset "Multi-modal Gesture Recognition Challenge 2013: Dataset and Results" including 393 dynamic hand-gestures was chosen. The proposed method yielded 84-91% recognition accuracy, in average, for restricted set of dynamic gestures.

  1. LOCALIZATION AND RECOGNITION OF DYNAMIC HAND GESTURES BASED ON HIERARCHY OF MANIFOLD CLASSIFIERS

    Directory of Open Access Journals (Sweden)

    M. Favorskaya

    2015-05-01

    Full Text Available Generally, the dynamic hand gestures are captured in continuous video sequences, and a gesture recognition system ought to extract the robust features automatically. This task involves the highly challenging spatio-temporal variations of dynamic hand gestures. The proposed method is based on two-level manifold classifiers including the trajectory classifiers in any time instants and the posture classifiers of sub-gestures in selected time instants. The trajectory classifiers contain skin detector, normalized skeleton representation of one or two hands, and motion history representing by motion vectors normalized through predetermined directions (8 and 16 in our case. Each dynamic gesture is separated into a set of sub-gestures in order to predict a trajectory and remove those samples of gestures, which do not satisfy to current trajectory. The posture classifiers involve the normalized skeleton representation of palm and fingers and relative finger positions using fingertips. The min-max criterion is used for trajectory recognition, and the decision tree technique was applied for posture recognition of sub-gestures. For experiments, a dataset “Multi-modal Gesture Recognition Challenge 2013: Dataset and Results” including 393 dynamic hand-gestures was chosen. The proposed method yielded 84–91% recognition accuracy, in average, for restricted set of dynamic gestures.

  2. The Complete Gabor-Fisher Classifier for Robust Face Recognition

    Directory of Open Access Journals (Sweden)

    Štruc Vitomir

    2010-01-01

    Full Text Available Abstract This paper develops a novel face recognition technique called Complete Gabor Fisher Classifier (CGFC. Different from existing techniques that use Gabor filters for deriving the Gabor face representation, the proposed approach does not rely solely on Gabor magnitude information but effectively uses features computed based on Gabor phase information as well. It represents one of the few successful attempts found in the literature of combining Gabor magnitude and phase information for robust face recognition. The novelty of the proposed CGFC technique comes from (1 the introduction of a Gabor phase-based face representation and (2 the combination of the recognition technique using the proposed representation with classical Gabor magnitude-based methods into a unified framework. The proposed face recognition framework is assessed in a series of face verification and identification experiments performed on the XM2VTS, Extended YaleB, FERET, and AR databases. The results of the assessment suggest that the proposed technique clearly outperforms state-of-the-art face recognition techniques from the literature and that its performance is almost unaffected by the presence of partial occlusions of the facial area, changes in facial expression, or severe illumination changes.

  3. Transforming Musical Signals through a Genre Classifying Convolutional Neural Network

    Science.gov (United States)

    Geng, S.; Ren, G.; Ogihara, M.

    2017-05-01

    Convolutional neural networks (CNNs) have been successfully applied on both discriminative and generative modeling for music-related tasks. For a particular task, the trained CNN contains information representing the decision making or the abstracting process. One can hope to manipulate existing music based on this 'informed' network and create music with new features corresponding to the knowledge obtained by the network. In this paper, we propose a method to utilize the stored information from a CNN trained on musical genre classification task. The network was composed of three convolutional layers, and was trained to classify five-second song clips into five different genres. After training, randomly selected clips were modified by maximizing the sum of outputs from the network layers. In addition to the potential of such CNNs to produce interesting audio transformation, more information about the network and the original music could be obtained from the analysis of the generated features since these features indicate how the network 'understands' the music.

  4. An Informed Framework for Training Classifiers from Social Media

    Directory of Open Access Journals (Sweden)

    Dong Seon Cheng

    2016-04-01

    Full Text Available Extracting information from social media has become a major focus of companies and researchers in recent years. Aside from the study of the social aspects, it has also been found feasible to exploit the collaborative strength of crowds to help solve classical machine learning problems like object recognition. In this work, we focus on the generally underappreciated problem of building effective datasets for training classifiers by automatically assembling data from social media. We detail some of the challenges of this approach and outline a framework that uses expanded search queries to retrieve more qualified data. In particular, we concentrate on collaboratively tagged media on the social platform Flickr, and on the problem of image classification to evaluate our approach. Finally, we describe a novel entropy-based method to incorporate an information-theoretic principle to guide our framework. Experimental validation against well-known public datasets shows the viability of this approach and marks an improvement over the state of the art in terms of simplicity and performance.

  5. Executed Movement Using EEG Signals through a Naive Bayes Classifier

    Directory of Open Access Journals (Sweden)

    Juliano Machado

    2014-11-01

    Full Text Available Recent years have witnessed a rapid development of brain-computer interface (BCI technology. An independent BCI is a communication system for controlling a device by human intension, e.g., a computer, a wheelchair or a neuroprosthes is, not depending on the brain’s normal output pathways of peripheral nerves and muscles, but on detectable signals that represent responsive or intentional brain activities. This paper presents a comparative study of the usage of the linear discriminant analysis (LDA and the naive Bayes (NB classifiers on describing both right- and left-hand movement through electroencephalographic signal (EEG acquisition. For the analysis, we considered the following input features: the energy of the segments of a band pass-filtered signal with the frequency band in sensorimotor rhythms and the components of the spectral energy obtained through the Welch method. We also used the common spatial pattern (CSP filter, so as to increase the discriminatory activity among movement classes. By using the database generated by this experiment, we obtained hit rates up to 70%. The results are compatible with previous studies.

  6. Salient Region Detection via Feature Combination and Discriminative Classifier

    Directory of Open Access Journals (Sweden)

    Deming Kong

    2015-01-01

    Full Text Available We introduce a novel approach to detect salient regions of an image via feature combination and discriminative classifier. Our method, which is based on hierarchical image abstraction, uses the logistic regression approach to map the regional feature vector to a saliency score. Four saliency cues are used in our approach, including color contrast in a global context, center-boundary priors, spatially compact color distribution, and objectness, which is as an atomic feature of segmented region in the image. By mapping a four-dimensional regional feature to fifteen-dimensional feature vector, we can linearly separate the salient regions from the clustered background by finding an optimal linear combination of feature coefficients in the fifteen-dimensional feature space and finally fuse the saliency maps across multiple levels. Furthermore, we introduce the weighted salient image center into our saliency analysis task. Extensive experiments on two large benchmark datasets show that the proposed approach achieves the best performance over several state-of-the-art approaches.

  7. Classified model and characteristics of strategies at tourist companies

    Directory of Open Access Journals (Sweden)

    I.V. Saukh

    2017-12-01

    Full Text Available The research is devoted to the assessment of the scientific approaches to the identification of classification features of the strategy and its types distinguished in accordance with the mentioned features. The research object is the activities of tourist companies and this determines the choice of strategies typical for the tourism field. It is substantiated that the scientific approaches to the classification of strategies are various in specific literature because of obscurity in the strategy definition, vagueness and plurality of its classified features. Due to the current research the authors have improved the classified model of strategies for tourist companies that will result in making effective management decisions directed to the development of enterprise potential under conditions of unstable and unpredictable external environment. The paper singles out the peculiarities of functioning the tourism branch, which are the following : high sensitivity to the changes in external environment; the high level of competition in the field; dynamics and the lack of necessity for the use of «far-seeing» strategies; insufficiency of information provision for the application of traditional western models and matric methods of strategy development; time gap between obtaining the service and its consumption; a great number of intermediaries; seasonal swings in demands; the sudden shift of external environment caused by cyclicity, globalization, political decisions of separate countries and etc. The article shows essential differences in the development of financial strategies of small-scale enterprises and stock companies of tourist business. It is substantiated that small-scale enterprises develop strategies directed to a higher level of personal services, occupational competence, ability and experience in designing, the best knowledge of regional conditions and flexible decisions caused by the peculiarities of the received orders. Taking into

  8. Public participation at Fernald: FERMCO's evolving role

    International Nuclear Information System (INIS)

    Williams, J.B.; Fellman, R.W.; Brettschneider, D.J.

    1995-01-01

    In an effort to improve public involvement in the site restoration decision making process, the DOE has established site specific advisory boards, of which the Fernald Citizens Task Force is one. The Fernald Task Force is focused on making recommendations in four areas: (1) What should be the future use of the site? (2) Determinations of cleanup levels (how clean is clean?) (3) Where should the wastes be disposed of? (4) What should be the cleanup priorities? Because these questions are being asked very early in the decision-making process, the answers are necessarily qualified, and are based on a combination of preliminary data, assumptions, and professional judgment. The requirement to make progress in the absence of accurate data has necessitated FERMCO and the Task Force to employ an approach similar to sensitivity analysis, in which a range of possible data values are evaluated and the relative importance of the various factors is assessed. Because of its charter to provide recommendations of future site use, the Task Force has developed a sitewide perspective, compared to the more common operable unit specific focus of public participation under CERCLA. The relationship between FERMCO and the Task Force is evolving toward one of partnership with DOE in managing the obstacles and hidden opportunities for success. The Task Force likely will continue to participate in the Fernald project long after its initial recommendations have been made. DOE already has made the commitment that the process of public participation will extend into the Remedial Design phase. There is substantial reason for optimism that continuing the Task Force process through the design phase will assist in developing the appropriate balance of cost and engineered protectiveness

  9. Modeling promoter grammars with evolving hidden Markov models

    DEFF Research Database (Denmark)

    Won, Kyoung-Jae; Sandelin, Albin; Marstrand, Troels Torben

    2008-01-01

    MOTIVATION: Describing and modeling biological features of eukaryotic promoters remains an important and challenging problem within computational biology. The promoters of higher eukaryotes in particular display a wide variation in regulatory features, which are difficult to model. Often several...... factors are involved in the regulation of a set of co-regulated genes. If so, promoters can be modeled with connected regulatory features, where the network of connections is characteristic for a particular mode of regulation. RESULTS: With the goal of automatically deciphering such regulatory structures......, we present a method that iteratively evolves an ensemble of regulatory grammars using a hidden Markov Model (HMM) architecture composed of interconnected blocks representing transcription factor binding sites (TFBSs) and background regions of promoter sequences. The ensemble approach reduces the risk...

  10. DNA motif alignment by evolving a population of Markov chains.

    Science.gov (United States)

    Bi, Chengpeng

    2009-01-30

    Deciphering cis-regulatory elements or de novo motif-finding in genomes still remains elusive although much algorithmic effort has been expended. The Markov chain Monte Carlo (MCMC) method such as Gibbs motif samplers has been widely employed to solve the de novo motif-finding problem through sequence local alignment. Nonetheless, the MCMC-based motif samplers still suffer from local maxima like EM. Therefore, as a prerequisite for finding good local alignments, these motif algorithms are often independently run a multitude of times, but without information exchange between different chains. Hence it would be worth a new algorithm design enabling such information exchange. This paper presents a novel motif-finding algorithm by evolving a population of Markov chains with information exchange (PMC), each of which is initialized as a random alignment and run by the Metropolis-Hastings sampler (MHS). It is progressively updated through a series of local alignments stochastically sampled. Explicitly, the PMC motif algorithm performs stochastic sampling as specified by a population-based proposal distribution rather than individual ones, and adaptively evolves the population as a whole towards a global maximum. The alignment information exchange is accomplished by taking advantage of the pooled motif site distributions. A distinct method for running multiple independent Markov chains (IMC) without information exchange, or dubbed as the IMC motif algorithm, is also devised to compare with its PMC counterpart. Experimental studies demonstrate that the performance could be improved if pooled information were used to run a population of motif samplers. The new PMC algorithm was able to improve the convergence and outperformed other popular algorithms tested using simulated and biological motif sequences.

  11. Classifying hot water chemistry: Application of MULTIVARIATE STATISTICS

    OpenAIRE

    Sumintadireja, Prihadi; Irawan, Dasapta Erwin; Rezky, Yuanno; Gio, Prana Ugiana; Agustin, Anggita

    2016-01-01

    This file is the dataset for the following paper "Classifying hot water chemistry: Application of MULTIVARIATE STATISTICS". Authors: Prihadi Sumintadireja1, Dasapta Erwin Irawan1, Yuano Rezky2, Prana Ugiana Gio3, Anggita Agustin1

  12. DECISION TREE CLASSIFIERS FOR STAR/GALAXY SEPARATION

    International Nuclear Information System (INIS)

    Vasconcellos, E. C.; Ruiz, R. S. R.; De Carvalho, R. R.; Capelato, H. V.; Gal, R. R.; LaBarbera, F. L.; Frago Campos Velho, H.; Trevisan, M.

    2011-01-01

    We study the star/galaxy classification efficiency of 13 different decision tree algorithms applied to photometric objects in the Sloan Digital Sky Survey Data Release Seven (SDSS-DR7). Each algorithm is defined by a set of parameters which, when varied, produce different final classification trees. We extensively explore the parameter space of each algorithm, using the set of 884,126 SDSS objects with spectroscopic data as the training set. The efficiency of star-galaxy separation is measured using the completeness function. We find that the Functional Tree algorithm (FT) yields the best results as measured by the mean completeness in two magnitude intervals: 14 ≤ r ≤ 21 (85.2%) and r ≥ 19 (82.1%). We compare the performance of the tree generated with the optimal FT configuration to the classifications provided by the SDSS parametric classifier, 2DPHOT, and Ball et al. We find that our FT classifier is comparable to or better in completeness over the full magnitude range 15 ≤ r ≤ 21, with much lower contamination than all but the Ball et al. classifier. At the faintest magnitudes (r > 19), our classifier is the only one that maintains high completeness (>80%) while simultaneously achieving low contamination (∼2.5%). We also examine the SDSS parametric classifier (psfMag - modelMag) to see if the dividing line between stars and galaxies can be adjusted to improve the classifier. We find that currently stars in close pairs are often misclassified as galaxies, and suggest a new cut to improve the classifier. Finally, we apply our FT classifier to separate stars from galaxies in the full set of 69,545,326 SDSS photometric objects in the magnitude range 14 ≤ r ≤ 21.

  13. FERAL : Network-based classifier with application to breast cancer outcome prediction

    NARCIS (Netherlands)

    Allahyar, A.; De Ridder, J.

    2015-01-01

    Motivation: Breast cancer outcome prediction based on gene expression profiles is an important strategy for personalize patient care. To improve performance and consistency of discovered markers of the initial molecular classifiers, network-based outcome prediction methods (NOPs) have been proposed.

  14. Gas chimney detection based on improving the performance of combined multilayer perceptron and support vector classifier

    NARCIS (Netherlands)

    Hashemi, H.; Tax, D.M.J.; Duin, R.P.W.; Javaherian, A.; De Groot, P.

    2008-01-01

    Seismic object detection is a relatively new field in which 3-D bodies are visualized and spatial relationships between objects of different origins are studied in order to extract geologic information. In this paper, we propose a method for finding an optimal classifier with the help of a

  15. Evolvable designs of experiments applications for circuits

    CERN Document Server

    Iordache, Octavian

    2009-01-01

    Adopting a groundbreaking approach, the highly regarded author shows how to design methods for planning increasingly complex experiments. He begins with a brief introduction to standard quality methods and the technology in standard electric circuits. The book then gives numerous examples of how to apply the proposed methodology in a series of real-life case studies. Although these case studies are taken from the printed circuit board industry, the methods are equally applicable to other fields of engineering.

  16. Evolving R Coronae Borealis Stars with MESA

    Science.gov (United States)

    Clayton, Geoffrey C.; Lauer, Amber; Chatzopoulos, Emmanouil; Frank, Juhan

    2018-01-01

    being a WD. Solving the mystery of how the RCB stars evolve will lead to a better understanding of other important types of stellar merger events such as Type Ia SNe.

  17. The evolving integrated vascular surgery residency curriculum.

    Science.gov (United States)

    Smith, Brigitte K; Greenberg, Jacob A; Mitchell, Erica L

    2014-10-01

    PDs voiced concern over the lack of standardization among the differing programs and most of the PDs agree that some degree of programmatic standardization is critical for the continued success of the 0 + 5 training paradigm. Qualitative evaluation of PD experiences with the development of 0 + 5 vascular surgery residency programs reveals the key factors that commonly influence program design. Programs continue to evolve in both structure and content as PDs respond to these influences. Learning from the collective experience of PDs and some standardization of the curricula may help current and future programs avoid common pitfalls in curricular development. Copyright © 2014 Elsevier Inc. All rights reserved.

  18. Mechanics of evolving thin film structures

    Science.gov (United States)

    Liang, Jim

    In the Stranski-Krastanov system, the lattice mismatch between the film and the substrate causes the film to break into islands. During annealing, both the surface energy and the elastic energy drive the islands to coarsen. Motivated by several related studies, we suggest that stable islands should form when a stiff ceiling is placed at a small gap above the film. We show that the role of elasticity is reversed: with the ceiling, the total elastic energy stored in the system increases as the islands coarsen laterally. Consequently, the islands select an equilibrium size to minimize the combined elastic energy and surface energy. In lithographically-induced self-assembly, when a two-phase fluid confined between parallel substrates is subjected to an electric field, one phase can self-assemble into a triangular lattice of islands in another phase. We describe a theory of the stability of the island lattice. The islands select the equilibrium diameter to minimize the combined interface energy and electrostatic energy. Furthermore, we study compressed SiGe thin film islands fabricated on a glass layer, which itself lies on a silicon wafer. Upon annealing, the glass flows, and the islands relax. A small island relaxes by in-plane expansion. A large island, however, wrinkles at the center before the in-plane relaxation arrives. The wrinkles may cause significant tensile stress in the island, leading to fracture. We model the island by the von Karman plate theory and the glass layer by the Reynolds lubrication theory. Numerical simulations evolve the in-plane expansion and the wrinkles simultaneously. We determine the critical island size, below which in-plane expansion prevails over wrinkling. Finally, in devices that integrate dissimilar materials in small dimensions, crack extension in one material often accompanies inelastic deformation in another. We analyze a channel crack advancing in an elastic film under tension, while an underlayer creeps. We use a two

  19. Learning to Detect Traffic Incidents from Data Based on Tree Augmented Naive Bayesian Classifiers

    Directory of Open Access Journals (Sweden)

    Dawei Li

    2017-01-01

    Full Text Available This study develops a tree augmented naive Bayesian (TAN classifier based incident detection algorithm. Compared with the Bayesian networks based detection algorithms developed in the previous studies, this algorithm has less dependency on experts’ knowledge. The structure of TAN classifier for incident detection is learned from data. The discretization of continuous attributes is processed using an entropy-based method automatically. A simulation dataset on the section of the Ayer Rajah Expressway (AYE in Singapore is used to demonstrate the development of proposed algorithm, including wavelet denoising, normalization, entropy-based discretization, and structure learning. The performance of TAN based algorithm is evaluated compared with the previous developed Bayesian network (BN based and multilayer feed forward (MLF neural networks based algorithms with the same AYE data. The experiment results show that the TAN based algorithms perform better than the BN classifiers and have a similar performance to the MLF based algorithm. However, TAN based algorithm would have wider vista of applications because the theory of TAN classifiers is much less complicated than MLF. It should be found from the experiment that the TAN classifier based algorithm has a significant superiority over the speed of model training and calibration compared with MLF.

  20. Obscenity detection using haar-like features and Gentle Adaboost classifier.

    Science.gov (United States)

    Mustafa, Rashed; Min, Yang; Zhu, Dingju

    2014-01-01

    Large exposure of skin area of an image is considered obscene. This only fact may lead to many false images having skin-like objects and may not detect those images which have partially exposed skin area but have exposed erotogenic human body parts. This paper presents a novel method for detecting nipples from pornographic image contents. Nipple is considered as an erotogenic organ to identify pornographic contents from images. In this research Gentle Adaboost (GAB) haar-cascade classifier and haar-like features used for ensuring detection accuracy. Skin filter prior to detection made the system more robust. The experiment showed that, considering accuracy, haar-cascade classifier performs well, but in order to satisfy detection time, train-cascade classifier is suitable. To validate the results, we used 1198 positive samples containing nipple objects and 1995 negative images. The detection rates for haar-cascade and train-cascade classifiers are 0.9875 and 0.8429, respectively. The detection time for haar-cascade is 0.162 seconds and is 0.127 seconds for train-cascade classifier.

  1. Obscenity Detection Using Haar-Like Features and Gentle Adaboost Classifier

    Directory of Open Access Journals (Sweden)

    Rashed Mustafa

    2014-01-01

    Full Text Available Large exposure of skin area of an image is considered obscene. This only fact may lead to many false images having skin-like objects and may not detect those images which have partially exposed skin area but have exposed erotogenic human body parts. This paper presents a novel method for detecting nipples from pornographic image contents. Nipple is considered as an erotogenic organ to identify pornographic contents from images. In this research Gentle Adaboost (GAB haar-cascade classifier and haar-like features used for ensuring detection accuracy. Skin filter prior to detection made the system more robust. The experiment showed that, considering accuracy, haar-cascade classifier performs well, but in order to satisfy detection time, train-cascade classifier is suitable. To validate the results, we used 1198 positive samples containing nipple objects and 1995 negative images. The detection rates for haar-cascade and train-cascade classifiers are 0.9875 and 0.8429, respectively. The detection time for haar-cascade is 0.162 seconds and is 0.127 seconds for train-cascade classifier.

  2. Comparison of Different Features and Classifiers for Driver Fatigue Detection Based on a Single EEG Channel

    Directory of Open Access Journals (Sweden)

    Jianfeng Hu

    2017-01-01

    Full Text Available Driver fatigue has become an important factor to traffic accidents worldwide, and effective detection of driver fatigue has major significance for public health. The purpose method employs entropy measures for feature extraction from a single electroencephalogram (EEG channel. Four types of entropies measures, sample entropy (SE, fuzzy entropy (FE, approximate entropy (AE, and spectral entropy (PE, were deployed for the analysis of original EEG signal and compared by ten state-of-the-art classifiers. Results indicate that optimal performance of single channel is achieved using a combination of channel CP4, feature FE, and classifier Random Forest (RF. The highest accuracy can be up to 96.6%, which has been able to meet the needs of real applications. The best combination of channel + features + classifier is subject-specific. In this work, the accuracy of FE as the feature is far greater than the Acc of other features. The accuracy using classifier RF is the best, while that of classifier SVM with linear kernel is the worst. The impact of channel selection on the Acc is larger. The performance of various channels is very different.

  3. Using Fuzzy Gaussian Inference and Genetic Programming to Classify 3D Human Motions

    Science.gov (United States)

    Khoury, Mehdi; Liu, Honghai

    This research introduces and builds on the concept of Fuzzy Gaussian Inference (FGI) (Khoury and Liu in Proceedings of UKCI, 2008 and IEEE Workshop on Robotic Intelligence in Informationally Structured Space (RiiSS 2009), 2009) as a novel way to build Fuzzy Membership Functions that map to hidden Probability Distributions underlying human motions. This method is now combined with a Genetic Programming Fuzzy rule-based system in order to classify boxing moves from natural human Motion Capture data. In this experiment, FGI alone is able to recognise seven different boxing stances simultaneously with an accuracy superior to a GMM-based classifier. Results seem to indicate that adding an evolutionary Fuzzy Inference Engine on top of FGI improves the accuracy of the classifier in a consistent way.

  4. Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations.

    Science.gov (United States)

    Zhang, Yi; Ren, Jinchang; Jiang, Jianmin

    2015-01-01

    Maximum likelihood classifier (MLC) and support vector machines (SVM) are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions.

  5. Combining MLC and SVM Classifiers for Learning Based Decision Making: Analysis and Evaluations

    Directory of Open Access Journals (Sweden)

    Yi Zhang

    2015-01-01

    Full Text Available Maximum likelihood classifier (MLC and support vector machines (SVM are two commonly used approaches in machine learning. MLC is based on Bayesian theory in estimating parameters of a probabilistic model, whilst SVM is an optimization based nonparametric method in this context. Recently, it is found that SVM in some cases is equivalent to MLC in probabilistically modeling the learning process. In this paper, MLC and SVM are combined in learning and classification, which helps to yield probabilistic output for SVM and facilitate soft decision making. In total four groups of data are used for evaluations, covering sonar, vehicle, breast cancer, and DNA sequences. The data samples are characterized in terms of Gaussian/non-Gaussian distributed and balanced/unbalanced samples which are then further used for performance assessment in comparing the SVM and the combined SVM-MLC classifier. Interesting results are reported to indicate how the combined classifier may work under various conditions.

  6. Balanced sensitivity functions for tuning multi-dimensional Bayesian network classifiers

    NARCIS (Netherlands)

    Bolt, J.H.; van der Gaag, L.C.

    Multi-dimensional Bayesian network classifiers are Bayesian networks of restricted topological structure, which are tailored to classifying data instances into multiple dimensions. Like more traditional classifiers, multi-dimensional classifiers are typically learned from data and may include

  7. Classifying a smoker scale in adult daily and nondaily smokers.

    Science.gov (United States)

    Pulvers, Kim; Scheuermann, Taneisha S; Romero, Devan R; Basora, Brittany; Luo, Xianghua; Ahluwalia, Jasjit S

    2014-05-01

    Smoker identity, or the strength of beliefs about oneself as a smoker, is a robust marker of smoking behavior. However, many nondaily smokers do not identify as smokers, underestimating their risk for tobacco-related disease and resulting in missed intervention opportunities. Assessing underlying beliefs about characteristics used to classify smokers may help explain the discrepancy between smoking behavior and smoker identity. This study examines the factor structure, reliability, and validity of the Classifying a Smoker scale among a racially diverse sample of adult smokers. A cross-sectional survey was administered through an online panel survey service to 2,376 current smokers who were at least 25 years of age. The sample was stratified to obtain equal numbers of 3 racial/ethnic groups (African American, Latino, and White) across smoking level (nondaily and daily smoking). The Classifying a Smoker scale displayed a single factor structure and excellent internal consistency (α = .91). Classifying a Smoker scores significantly increased at each level of smoking, F(3,2375) = 23.68, p smoker identity, stronger dependence on cigarettes, greater health risk perceptions, more smoking friends, and were more likely to carry cigarettes. Classifying a Smoker scores explained unique variance in smoking variables above and beyond that explained by smoker identity. The present study supports the use of the Classifying a Smoker scale among diverse, experienced smokers. Stronger endorsement of characteristics used to classify a smoker (i.e., stricter criteria) was positively associated with heavier smoking and related characteristics. Prospective studies are needed to inform prevention and treatment efforts.

  8. ECLogger: Cross-Project Catch-Block Logging Prediction Using Ensemble of Classifiers

    Directory of Open Access Journals (Sweden)

    Sangeeta Lal

    2017-01-01

    Full Text Available Background: Software developers insert log statements in the source code to record program execution information. However, optimizing the number of log statements in the source code is challenging. Machine learning based within-project logging prediction tools, proposed in previous studies, may not be suitable for new or small software projects. For such software projects, we can use cross-project logging prediction. Aim: The aim of the study presented here is to investigate cross-project logging prediction methods and techniques. Method: The proposed method is ECLogger, which is a novel, ensemble-based, cross-project, catch-block logging prediction model. In the research We use 9 base classifiers were used and combined using ensemble techniques. The performance of ECLogger was evaluated on on three open-source Java projects: Tomcat, CloudStack and Hadoop. Results: ECLogger Bagging, ECLogger AverageVote, and ECLogger MajorityVote show a considerable improvement in the average Logged F-measure (LF on 3, 5, and 4 source -> target project pairs, respectively, compared to the baseline classifiers. ECLogger AverageVote performs best and shows improvements of 3.12% (average LF and 6.08% (average ACC – Accuracy. Conclusion: The classifier based on ensemble techniques, such as bagging, average vote, and majority vote outperforms the baseline classifier. Overall, the ECLogger AverageVote model performs best. The results show that the CloudStack project is more generalizable than the other projects.

  9. Research on classified real-time flood forecasting framework based on K-means cluster and rough set.

    Science.gov (United States)

    Xu, Wei; Peng, Yong

    2015-01-01

    This research presents a new classified real-time flood forecasting framework. In this framework, historical floods are classified by a K-means cluster according to the spatial and temporal distribution of precipitation, the time variance of precipitation intensity and other hydrological factors. Based on the classified results, a rough set is used to extract the identification rules for real-time flood forecasting. Then, the parameters of different categories within the conceptual hydrological model are calibrated using a genetic algorithm. In real-time forecasting, the corresponding category of parameters is selected for flood forecasting according to the obtained flood information. This research tests the new classified framework on Guanyinge Reservoir and compares the framework with the traditional flood forecasting method. It finds that the performance of the new classified framework is significantly better in terms of accuracy. Furthermore, the framework can be considered in a catchment with fewer historical floods.

  10. A support vector machine classifier reduces interscanner variation in the HRCT classification of regional disease pattern in diffuse lung disease: Comparison to a Bayesian classifier

    Energy Technology Data Exchange (ETDEWEB)

    Chang, Yongjun; Lim, Jonghyuck; Kim, Namkug; Seo, Joon Beom [Department of Radiology, University of Ulsan College of Medicine, 388-1 Pungnap2-dong, Songpa-gu, Seoul 138-736 (Korea, Republic of); Lynch, David A. [Department of Radiology, National Jewish Medical and Research Center, Denver, Colorado 80206 (United States)

    2013-05-15

    Purpose: To investigate the effect of using different computed tomography (CT) scanners on the accuracy of high-resolution CT (HRCT) images in classifying regional disease patterns in patients with diffuse lung disease, support vector machine (SVM) and Bayesian classifiers were applied to multicenter data. Methods: Two experienced radiologists marked sets of 600 rectangular 20 Multiplication-Sign 20 pixel regions of interest (ROIs) on HRCT images obtained from two scanners (GE and Siemens), including 100 ROIs for each of local patterns of lungs-normal lung and five of regional pulmonary disease patterns (ground-glass opacity, reticular opacity, honeycombing, emphysema, and consolidation). Each ROI was assessed using 22 quantitative features belonging to one of the following descriptors: histogram, gradient, run-length, gray level co-occurrence matrix, low-attenuation area cluster, and top-hat transform. For automatic classification, a Bayesian classifier and a SVM classifier were compared under three different conditions. First, classification accuracies were estimated using data from each scanner. Next, data from the GE and Siemens scanners were used for training and testing, respectively, and vice versa. Finally, all ROI data were integrated regardless of the scanner type and were then trained and tested together. All experiments were performed based on forward feature selection and fivefold cross-validation with 20 repetitions. Results: For each scanner, better classification accuracies were achieved with the SVM classifier than the Bayesian classifier (92% and 82%, respectively, for the GE scanner; and 92% and 86%, respectively, for the Siemens scanner). The classification accuracies were 82%/72% for training with GE data and testing with Siemens data, and 79%/72% for the reverse. The use of training and test data obtained from the HRCT images of different scanners lowered the classification accuracy compared to the use of HRCT images from the same scanner. For

  11. A support vector machine classifier reduces interscanner variation in the HRCT classification of regional disease pattern in diffuse lung disease: Comparison to a Bayesian classifier

    International Nuclear Information System (INIS)

    Chang, Yongjun; Lim, Jonghyuck; Kim, Namkug; Seo, Joon Beom; Lynch, David A.

    2013-01-01

    Purpose: To investigate the effect of using different computed tomography (CT) scanners on the accuracy of high-resolution CT (HRCT) images in classifying regional disease patterns in patients with diffuse lung disease, support vector machine (SVM) and Bayesian classifiers were applied to multicenter data. Methods: Two experienced radiologists marked sets of 600 rectangular 20 × 20 pixel regions of interest (ROIs) on HRCT images obtained from two scanners (GE and Siemens), including 100 ROIs for each of local patterns of lungs—normal lung and five of regional pulmonary disease patterns (ground-glass opacity, reticular opacity, honeycombing, emphysema, and consolidation). Each ROI was assessed using 22 quantitative features belonging to one of the following descriptors: histogram, gradient, run-length, gray level co-occurrence matrix, low-attenuation area cluster, and top-hat transform. For automatic classification, a Bayesian classifier and a SVM classifier were compared under three different conditions. First, classification accuracies were estimated using data from each scanner. Next, data from the GE and Siemens scanners were used for training and testing, respectively, and vice versa. Finally, all ROI data were integrated regardless of the scanner type and were then trained and tested together. All experiments were performed based on forward feature selection and fivefold cross-validation with 20 repetitions. Results: For each scanner, better classification accuracies were achieved with the SVM classifier than the Bayesian classifier (92% and 82%, respectively, for the GE scanner; and 92% and 86%, respectively, for the Siemens scanner). The classification accuracies were 82%/72% for training with GE data and testing with Siemens data, and 79%/72% for the reverse. The use of training and test data obtained from the HRCT images of different scanners lowered the classification accuracy compared to the use of HRCT images from the same scanner. For integrated ROI

  12. Multi-feature classifiers for burst detection in single EEG channels from preterm infants

    Science.gov (United States)

    Navarro, X.; Porée, F.; Kuchenbuch, M.; Chavez, M.; Beuchée, Alain; Carrault, G.

    2017-08-01

    Objective. The study of electroencephalographic (EEG) bursts in preterm infants provides valuable information about maturation or prognostication after perinatal asphyxia. Over the last two decades, a number of works proposed algorithms to automatically detect EEG bursts in preterm infants, but they were designed for populations under 35 weeks of post menstrual age (PMA). However, as the brain activity evolves rapidly during postnatal life, these solutions might be under-performing with increasing PMA. In this work we focused on preterm infants reaching term ages (PMA  ⩾36 weeks) using multi-feature classification on a single EEG channel. Approach. Five EEG burst detectors relying on different machine learning approaches were compared: logistic regression (LR), linear discriminant analysis (LDA), k-nearest neighbors (kNN), support vector machines (SVM) and thresholding (Th). Classifiers were trained by visually labeled EEG recordings from 14 very preterm infants (born after 28 weeks of gestation) with 36-41 weeks PMA. Main results. The most performing classifiers reached about 95% accuracy (kNN, SVM and LR) whereas Th obtained 84%. Compared to human-automatic agreements, LR provided the highest scores (Cohen’s kappa  =  0.71) using only three EEG features. Applying this classifier in an unlabeled database of 21 infants  ⩾36 weeks PMA, we found that long EEG bursts and short inter-burst periods are characteristic of infants with the highest PMA and weights. Significance. In view of these results, LR-based burst detection could be a suitable tool to study maturation in monitoring or portable devices using a single EEG channel.

  13. A GIS semiautomatic tool for classifying and mapping wetland soils

    Science.gov (United States)

    Moreno-Ramón, Héctor; Marqués-Mateu, Angel; Ibáñez-Asensio, Sara

    2016-04-01

    Wetlands are one of the most productive and biodiverse ecosystems in the world. Water is the main resource and controls the relationships between agents and factors that determine the quality of the wetland. However, vegetation, wildlife and soils are also essential factors to understand these environments. It is possible that soils have been the least studied resource due to their sampling problems. This feature has caused that sometimes wetland soils have been classified broadly. The traditional methodology states that homogeneous soil units should be based on the five soil forming-factors. The problem can appear when the variation of one soil-forming factor is too small to differentiate a change in soil units, or in case that there is another factor, which is not taken into account (e.g. fluctuating water table). This is the case of Albufera of Valencia, a coastal wetland located in the middle east of the Iberian Peninsula (Spain). The saline water table fluctuates throughout the year and it generates differences in soils. To solve this problem, the objectives of this study were to establish a reliable methodology to avoid that problems, and develop a GIS tool that would allow us to define homogeneous soil units in wetlands. This step is essential for the soil scientist, who has to decide the number of soil profiles in a study. The research was conducted with data from 133 soil pits of a previous study in the wetland. In that study, soil parameters of 401 samples (organic carbon, salinity, carbonates, n-value, etc.) were analysed. In a first stage, GIS layers were generated according to depth. The method employed was Bayesian Maxim Entropy. Subsequently, it was designed a program in GIS environment that was based on the decision tree algorithms. The goal of this tool was to create a single layer, for each soil variable, according to the different diagnostic criteria of Soil Taxonomy (properties, horizons and diagnostic epipedons). At the end, the program

  14. Local curvature analysis for classifying breast tumors: Preliminary analysis in dedicated breast CT

    International Nuclear Information System (INIS)

    Lee, Juhun; Nishikawa, Robert M.; Reiser, Ingrid; Boone, John M.; Lindfors, Karen K.

    2015-01-01

    Purpose: The purpose of this study is to measure the effectiveness of local curvature measures as novel image features for classifying breast tumors. Methods: A total of 119 breast lesions from 104 noncontrast dedicated breast computed tomography images of women were used in this study. Volumetric segmentation was done using a seed-based segmentation algorithm and then a triangulated surface was extracted from the resulting segmentation. Total, mean, and Gaussian curvatures were then computed. Normalized curvatures were used as classification features. In addition, traditional image features were also extracted and a forward feature selection scheme was used to select the optimal feature set. Logistic regression was used as a classifier and leave-one-out cross-validation was utilized to evaluate the classification performances of the features. The area under the receiver operating characteristic curve (AUC, area under curve) was used as a figure of merit. Results: Among curvature measures, the normalized total curvature (C_T) showed the best classification performance (AUC of 0.74), while the others showed no classification power individually. Five traditional image features (two shape, two margin, and one texture descriptors) were selected via the feature selection scheme and its resulting classifier achieved an AUC of 0.83. Among those five features, the radial gradient index (RGI), which is a margin descriptor, showed the best classification performance (AUC of 0.73). A classifier combining RGI and C_T yielded an AUC of 0.81, which showed similar performance (i.e., no statistically significant difference) to the classifier with the above five traditional image features. Additional comparisons in AUC values between classifiers using different combinations of traditional image features and C_T were conducted. The results showed that C_T was able to replace the other four image features for the classification task. Conclusions: The normalized curvature measure

  15. Locating and classifying defects using an hybrid data base

    Energy Technology Data Exchange (ETDEWEB)

    Luna-Aviles, A; Diaz Pineda, A [Tecnologico de Estudios Superiores de Coacalco. Av. 16 de Septiembre 54, Col. Cabecera Municipal. C.P. 55700 (Mexico); Hernandez-Gomez, L H; Urriolagoitia-Calderon, G; Urriolagoitia-Sosa, G [Instituto Politecnico Nacional. ESIME-SEPI. Unidad Profesional ' Adolfo Lopez Mateos' Edificio 5, 30 Piso, Colonia Lindavista. Gustavo A. Madero. 07738 Mexico D.F. (Mexico); Durodola, J F [School of Technology, Oxford Brookes University, Headington Campus, Gipsy Lane, Oxford OX3 0BP (United Kingdom); Beltran Fernandez, J A, E-mail: alelunaav@hotmail.com, E-mail: luishector56@hotmail.com, E-mail: jdurodola@brookes.ac.uk

    2011-07-19

    A computational inverse technique was used in the localization and classification of defects. Postulated voids of two different sizes (2 mm and 4 mm diameter) were introduced in PMMA bars with and without a notch. The bar dimensions are 200x20x5 mm. One half of them were plain and the other half has a notch (3 mm x 4 mm) which is close to the defect area (19 mm x 16 mm).This analysis was done with an Artificial Neural Network (ANN) and its optimization was done with an Adaptive Neuro Fuzzy Procedure (ANFIS). A hybrid data base was developed with numerical and experimental results. Synthetic data was generated with the finite element method using SOLID95 element of ANSYS code. A parametric analysis was carried out. Only one defect in such bars was taken into account and the first five natural frequencies were calculated. 460 cases were evaluated. Half of them were plain and the other half has a notch. All the input data was classified in two groups. Each one has 230 cases and corresponds to one of the two sort of voids mentioned above. On the other hand, experimental analysis was carried on with PMMA specimens of the same size. The first two natural frequencies of 40 cases were obtained with one void. The other three frequencies were obtained numerically. 20 of these bars were plain and the others have a notch. These experimental results were introduced in the synthetic data base. 400 cases were taken randomly and, with this information, the ANN was trained with the backpropagation algorithm. The accuracy of the results was tested with the 100 cases that were left. In the next stage of this work, the ANN output was optimized with ANFIS. Previous papers showed that localization and classification of defects was reduced as notches were introduced in such bars. In the case of this paper, improved results were obtained when a hybrid data base was used.

  16. Locating and classifying defects using an hybrid data base

    Science.gov (United States)

    Luna-Avilés, A.; Hernández-Gómez, L. H.; Durodola, J. F.; Urriolagoitia-Calderón, G.; Urriolagoitia-Sosa, G.; Beltrán Fernández, J. A.; Díaz Pineda, A.

    2011-07-01

    A computational inverse technique was used in the localization and classification of defects. Postulated voids of two different sizes (2 mm and 4 mm diameter) were introduced in PMMA bars with and without a notch. The bar dimensions are 200×20×5 mm. One half of them were plain and the other half has a notch (3 mm × 4 mm) which is close to the defect area (19 mm × 16 mm).This analysis was done with an Artificial Neural Network (ANN) and its optimization was done with an Adaptive Neuro Fuzzy Procedure (ANFIS). A hybrid data base was developed with numerical and experimental results. Synthetic data was generated with the finite element method using SOLID95 element of ANSYS code. A parametric analysis was carried out. Only one defect in such bars was taken into account and the first five natural frequencies were calculated. 460 cases were evaluated. Half of them were plain and the other half has a notch. All the input data was classified in two groups. Each one has 230 cases and corresponds to one of the two sort of voids mentioned above. On the other hand, experimental analysis was carried on with PMMA specimens of the same size. The first two natural frequencies of 40 cases were obtained with one void. The other three frequencies were obtained numerically. 20 of these bars were plain and the others have a notch. These experimental results were introduced in the synthetic data base. 400 cases were taken randomly and, with this information, the ANN was trained with the backpropagation algorithm. The accuracy of the results was tested with the 100 cases that were left. In the next stage of this work, the ANN output was optimized with ANFIS. Previous papers showed that localization and classification of defects was reduced as notches were introduced in such bars. In the case of this paper, improved results were obtained when a hybrid data base was used.

  17. Locating and classifying defects using an hybrid data base

    International Nuclear Information System (INIS)

    Luna-Aviles, A; Diaz Pineda, A; Hernandez-Gomez, L H; Urriolagoitia-Calderon, G; Urriolagoitia-Sosa, G; Durodola, J F; Beltran Fernandez, J A

    2011-01-01

    A computational inverse technique was used in the localization and classification of defects. Postulated voids of two different sizes (2 mm and 4 mm diameter) were introduced in PMMA bars with and without a notch. The bar dimensions are 200x20x5 mm. One half of them were plain and the other half has a notch (3 mm x 4 mm) which is close to the defect area (19 mm x 16 mm).This analysis was done with an Artificial Neural Network (ANN) and its optimization was done with an Adaptive Neuro Fuzzy Procedure (ANFIS). A hybrid data base was developed with numerical and experimental results. Synthetic data was generated with the finite element method using SOLID95 element of ANSYS code. A parametric analysis was carried out. Only one defect in such bars was taken into account and the first five natural frequencies were calculated. 460 cases were evaluated. Half of them were plain and the other half has a notch. All the input data was classified in two groups. Each one has 230 cases and corresponds to one of the two sort of voids mentioned above. On the other hand, experimental analysis was carried on with PMMA specimens of the same size. The first two natural frequencies of 40 cases were obtained with one void. The other three frequencies were obtained numerically. 20 of these bars were plain and the others have a notch. These experimental results were introduced in the synthetic data base. 400 cases were taken randomly and, with this information, the ANN was trained with the backpropagation algorithm. The accuracy of the results was tested with the 100 cases that were left. In the next stage of this work, the ANN output was optimized with ANFIS. Previous papers showed that localization and classification of defects was reduced as notches were introduced in such bars. In the case of this paper, improved results were obtained when a hybrid data base was used.

  18. Current Directional Protection of Series Compensated Line Using Intelligent Classifier

    Directory of Open Access Journals (Sweden)

    M. Mollanezhad Heydarabadi

    2016-12-01

    Full Text Available Current inversion condition leads to incorrect operation of current based directional relay in power system with series compensated device. Application of the intelligent system for fault direction classification has been suggested in this paper. A new current directional protection scheme based on intelligent classifier is proposed for the series compensated line. The proposed classifier uses only half cycle of pre-fault and post fault current samples at relay location to feed the classifier. A lot of forward and backward fault simulations under different system conditions upon a transmission line with a fixed series capacitor are carried out using PSCAD/EMTDC software. The applicability of decision tree (DT, probabilistic neural network (PNN and support vector machine (SVM are investigated using simulated data under different system conditions. The performance comparison of the classifiers indicates that the SVM is a best suitable classifier for fault direction discriminating. The backward faults can be accurately distinguished from forward faults even under current inversion without require to detect of the current inversion condition.

  19. Maximum margin classifier working in a set of strings.

    Science.gov (United States)

    Koyano, Hitoshi; Hayashida, Morihiro; Akutsu, Tatsuya

    2016-03-01

    Numbers and numerical vectors account for a large portion of data. However, recently, the amount of string data generated has increased dramatically. Consequently, classifying string data is a common problem in many fields. The most widely used approach to this problem is to convert strings into numerical vectors using string kernels and subsequently apply a support vector machine that works in a numerical vector space. However, this non-one-to-one conversion involves a loss of information and makes it impossible to evaluate, using probability theory, the generalization error of a learning machine, considering that the given data to train and test the machine are strings generated according to probability laws. In this study, we approach this classification problem by constructing a classifier that works in a set of strings. To evaluate the generalization error of such a classifier theoretically, probability theory for strings is required. Therefore, we first extend a limit theorem for a consensus sequence of strings demonstrated by one of the authors and co-workers in a previous study. Using the obtained result, we then demonstrate that our learning machine classifies strings in an asymptotically optimal manner. Furthermore, we demonstrate the usefulness of our machine in practical data analysis by applying it to predicting protein-protein interactions using amino acid sequences and classifying RNAs by the secondary structure using nucleotide sequences.

  20. Use of information barriers to protect classified information

    International Nuclear Information System (INIS)

    MacArthur, D.; Johnson, M.W.; Nicholas, N.J.; Whiteson, R.

    1998-01-01

    This paper discusses the detailed requirements for an information barrier (IB) for use with verification systems that employ intrusive measurement technologies. The IB would protect classified information in a bilateral or multilateral inspection of classified fissile material. Such a barrier must strike a balance between providing the inspecting party the confidence necessary to accept the measurement while protecting the inspected party's classified information. The authors discuss the structure required of an IB as well as the implications of the IB on detector system maintenance. A defense-in-depth approach is proposed which would provide assurance to the inspected party that all sensitive information is protected and to the inspecting party that the measurements are being performed as expected. The barrier could include elements of physical protection (such as locks, surveillance systems, and tamper indicators), hardening of key hardware components, assurance of capabilities and limitations of hardware and software systems, administrative controls, validation and verification of the systems, and error detection and resolution. Finally, an unclassified interface could be used to display and, possibly, record measurement results. The introduction of an IB into an analysis system may result in many otherwise innocuous components (detectors, analyzers, etc.) becoming classified and unavailable for routine maintenance by uncleared personnel. System maintenance and updating will be significantly simplified if the classification status of as many components as possible can be made reversible (i.e. the component can become unclassified following the removal of classified objects)