Dependency Parsing with Transformed Feature

Directory of Open Access Journals (Sweden)

Fuxiang Wu

2017-01-01

Full Text Available Dependency parsing is an important subtask of natural language processing. In this paper, we propose an embedding feature transforming method for graph-based parsing, transform-based parsing, which directly utilizes the inner similarity of the features to extract information from all feature strings including the un-indexed strings and alleviate the feature sparse problem. The model transforms the extracted features to transformed features via applying a feature weight matrix, which consists of similarities between the feature strings. Since the matrix is usually rank-deficient because of similar feature strings, it would influence the strength of constraints. However, it is proven that the duplicate transformed features do not degrade the optimization algorithm: the margin infused relaxed algorithm. Moreover, this problem can be alleviated by reducing the number of the nearest transformed features of a feature. In addition, to further improve the parsing accuracy, a fusion parser is introduced to integrate transformed and original features. Our experiments verify that both transform-based and fusion parser improve the parsing accuracy compared to the corresponding feature-based parser.

The feature-weighted receptive field: an interpretable encoding model for complex feature spaces.

Science.gov (United States)

St-Yves, Ghislain; Naselaris, Thomas

2017-06-20

We introduce the feature-weighted receptive field (fwRF), an encoding model designed to balance expressiveness, interpretability and scalability. The fwRF is organized around the notion of a feature map-a transformation of visual stimuli into visual features that preserves the topology of visual space (but not necessarily the native resolution of the stimulus). The key assumption of the fwRF model is that activity in each voxel encodes variation in a spatially localized region across multiple feature maps. This region is fixed for all feature maps; however, the contribution of each feature map to voxel activity is weighted. Thus, the model has two separable sets of parameters: "where" parameters that characterize the location and extent of pooling over visual features, and "what" parameters that characterize tuning to visual features. The "where" parameters are analogous to classical receptive fields, while "what" parameters are analogous to classical tuning functions. By treating these as separable parameters, the fwRF model complexity is independent of the resolution of the underlying feature maps. This makes it possible to estimate models with thousands of high-resolution feature maps from relatively small amounts of data. Once a fwRF model has been estimated from data, spatial pooling and feature tuning can be read-off directly with no (or very little) additional post-processing or in-silico experimentation. We describe an optimization algorithm for estimating fwRF models from data acquired during standard visual neuroimaging experiments. We then demonstrate the model's application to two distinct sets of features: Gabor wavelets and features supplied by a deep convolutional neural network. We show that when Gabor feature maps are used, the fwRF model recovers receptive fields and spatial frequency tuning functions consistent with known organizational principles of the visual cortex. We also show that a fwRF model can be used to regress entire deep

Language Features and Culture Features on Short Message

Institute of Scientific and Technical Information of China (English)

王佳

2013-01-01

Mobile phone is regarded as“the fifth media”after newspaper,radio,TV and the Internet.The mobile phone short message further highlights the importance of written signs in communication.“The thumb revolution”is eagerly anticipating one kind of trend by the hand replace of mouth,sound substitute for the quiet around us. My paper will analyze the language features and the culture features of mobile phone short messages which are written in Chinese and English.

Feature selection for splice site prediction: A new method using EDA-based feature ranking

Directory of Open Access Journals (Sweden)

Rouzé Pierre

2004-05-01

Full Text Available Abstract Background The identification of relevant biological features in large and complex datasets is an important step towards gaining insight in the processes underlying the data. Other advantages of feature selection include the ability of the classification system to attain good or even better solutions using a restricted subset of features, and a faster classification. Thus, robust methods for fast feature selection are of key importance in extracting knowledge from complex biological data. Results In this paper we present a novel method for feature subset selection applied to splice site prediction, based on estimation of distribution algorithms, a more general framework of genetic algorithms. From the estimated distribution of the algorithm, a feature ranking is derived. Afterwards this ranking is used to iteratively discard features. We apply this technique to the problem of splice site prediction, and show how it can be used to gain insight into the underlying biological process of splicing. Conclusion We show that this technique proves to be more robust than the traditional use of estimation of distribution algorithms for feature selection: instead of returning a single best subset of features (as they normally do this method provides a dynamical view of the feature selection process, like the traditional sequential wrapper methods. However, the method is faster than the traditional techniques, and scales better to datasets described by a large number of features.

Simultaneous Channel and Feature Selection of Fused EEG Features Based on Sparse Group Lasso

Directory of Open Access Journals (Sweden)

Jin-Jia Wang

2015-01-01

Full Text Available Feature extraction and classification of EEG signals are core parts of brain computer interfaces (BCIs. Due to the high dimension of the EEG feature vector, an effective feature selection algorithm has become an integral part of research studies. In this paper, we present a new method based on a wrapped Sparse Group Lasso for channel and feature selection of fused EEG signals. The high-dimensional fused features are firstly obtained, which include the power spectrum, time-domain statistics, AR model, and the wavelet coefficient features extracted from the preprocessed EEG signals. The wrapped channel and feature selection method is then applied, which uses the logistical regression model with Sparse Group Lasso penalized function. The model is fitted on the training data, and parameter estimation is obtained by modified blockwise coordinate descent and coordinate gradient descent method. The best parameters and feature subset are selected by using a 10-fold cross-validation. Finally, the test data is classified using the trained model. Compared with existing channel and feature selection methods, results show that the proposed method is more suitable, more stable, and faster for high-dimensional feature fusion. It can simultaneously achieve channel and feature selection with a lower error rate. The test accuracy on the data used from international BCI Competition IV reached 84.72%.

Coding of visual object features and feature conjunctions in the human brain.

Science.gov (United States)

Martinovic, Jasna; Gruber, Thomas; Müller, Matthias M

2008-01-01

Object recognition is achieved through neural mechanisms reliant on the activity of distributed coordinated neural assemblies. In the initial steps of this process, an object's features are thought to be coded very rapidly in distinct neural assemblies. These features play different functional roles in the recognition process--while colour facilitates recognition, additional contours and edges delay it. Here, we selectively varied the amount and role of object features in an entry-level categorization paradigm and related them to the electrical activity of the human brain. We found that early synchronizations (approx. 100 ms) increased quantitatively when more image features had to be coded, without reflecting their qualitative contribution to the recognition process. Later activity (approx. 200-400 ms) was modulated by the representational role of object features. These findings demonstrate that although early synchronizations may be sufficient for relatively crude discrimination of objects in visual scenes, they cannot support entry-level categorization. This was subserved by later processes of object model selection, which utilized the representational value of object features such as colour or edges to select the appropriate model and achieve identification.

An object-oriented feature-based design system face-based detection of feature interactions

International Nuclear Information System (INIS)

Ariffin Abdul Razak

1999-01-01

This paper presents an object-oriented, feature-based design system which supports the integration of design and manufacture by ensuring that part descriptions fully account for any feature interactions. Manufacturing information is extracted from the feature descriptions in the form of volumes and Tool Access Directions, TADs. When features interact, both volumes and TADs are updated. This methodology has been demonstrated by developing a prototype system in which ACIS attributes are used to record feature information within the data structure of the solid model. The system implemented in the C++ programming language and embedded in a menu-driven X-windows user interface to the ACIS 3D Toolkit. (author)

Feature-Based Retinal Image Registration Using D-Saddle Feature

Directory of Open Access Journals (Sweden)

Roziana Ramli

2017-01-01

Full Text Available Retinal image registration is important to assist diagnosis and monitor retinal diseases, such as diabetic retinopathy and glaucoma. However, registering retinal images for various registration applications requires the detection and distribution of feature points on the low-quality region that consists of vessels of varying contrast and sizes. A recent feature detector known as Saddle detects feature points on vessels that are poorly distributed and densely positioned on strong contrast vessels. Therefore, we propose a multiresolution difference of Gaussian pyramid with Saddle detector (D-Saddle to detect feature points on the low-quality region that consists of vessels with varying contrast and sizes. D-Saddle is tested on Fundus Image Registration (FIRE Dataset that consists of 134 retinal image pairs. Experimental results show that D-Saddle successfully registered 43% of retinal image pairs with average registration accuracy of 2.329 pixels while a lower success rate is observed in other four state-of-the-art retinal image registration methods GDB-ICP (28%, Harris-PIIFD (4%, H-M (16%, and Saddle (16%. Furthermore, the registration accuracy of D-Saddle has the weakest correlation (Spearman with the intensity uniformity metric among all methods. Finally, the paired t-test shows that D-Saddle significantly improved the overall registration accuracy of the original Saddle.

Screening for Plant Features

NARCIS (Netherlands)

Heijden, van der G.W.A.M.; Polder, G.

2015-01-01

In this chapter, an overview of different plant features is given, from (sub)cellular to canopy level. A myriad of methods is available to measure these features using image analysis, and often, multiple methods can be used to measure the same feature. Several criteria are listed for choosing a

Decontaminate feature for tracking: adaptive tracking via evolutionary feature subset

Science.gov (United States)

Liu, Qiaoyuan; Wang, Yuru; Yin, Minghao; Ren, Jinchang; Li, Ruizhi

2017-11-01

Although various visual tracking algorithms have been proposed in the last 2-3 decades, it remains a challenging problem for effective tracking with fast motion, deformation, occlusion, etc. Under complex tracking conditions, most tracking models are not discriminative and adaptive enough. When the combined feature vectors are inputted to the visual models, this may lead to redundancy causing low efficiency and ambiguity causing poor performance. An effective tracking algorithm is proposed to decontaminate features for each video sequence adaptively, where the visual modeling is treated as an optimization problem from the perspective of evolution. Every feature vector is compared to a biological individual and then decontaminated via classical evolutionary algorithms. With the optimized subsets of features, the "curse of dimensionality" has been avoided while the accuracy of the visual model has been improved. The proposed algorithm has been tested on several publicly available datasets with various tracking challenges and benchmarked with a number of state-of-the-art approaches. The comprehensive experiments have demonstrated the efficacy of the proposed methodology.

Dissociation between Features and Feature Relations in Infant Memory: Effects of Memory Load.

Science.gov (United States)

Bhatt, Ramesh S.; Rovee-Collier, Carolyn

1997-01-01

Four experiments examined effects of the number of features and feature relations on learning and long-term memory in 3-month olds. Findings suggested that memory load size selectively constrained infants' long-term memory for relational information, suggesting that in infants, features and relations are psychologically distinct and that memory…

Depth estimation of features in video frames with improved feature matching technique using Kinect sensor

Science.gov (United States)

Sharma, Kajal; Moon, Inkyu; Kim, Sung Gaun

2012-10-01

Estimating depth has long been a major issue in the field of computer vision and robotics. The Kinect sensor's active sensing strategy provides high-frame-rate depth maps and can recognize user gestures and human pose. This paper presents a technique to estimate the depth of features extracted from video frames, along with an improved feature-matching method. In this paper, we used the Kinect camera developed by Microsoft, which captured color and depth images for further processing. Feature detection and selection is an important task for robot navigation. Many feature-matching techniques have been proposed earlier, and this paper proposes an improved feature matching between successive video frames with the use of neural network methodology in order to reduce the computation time of feature matching. The features extracted are invariant to image scale and rotation, and different experiments were conducted to evaluate the performance of feature matching between successive video frames. The extracted features are assigned distance based on the Kinect technology that can be used by the robot in order to determine the path of navigation, along with obstacle detection applications.

Doubly sparse factor models for unifying feature transformation and feature selection

International Nuclear Information System (INIS)

Katahira, Kentaro; Okanoya, Kazuo; Okada, Masato; Matsumoto, Narihisa; Sugase-Miyamoto, Yasuko

2010-01-01

A number of unsupervised learning methods for high-dimensional data are largely divided into two groups based on their procedures, i.e., (1) feature selection, which discards irrelevant dimensions of the data, and (2) feature transformation, which constructs new variables by transforming and mixing over all dimensions. We propose a method that both selects and transforms features in a common Bayesian inference procedure. Our method imposes a doubly automatic relevance determination (ARD) prior on the factor loading matrix. We propose a variational Bayesian inference for our model and demonstrate the performance of our method on both synthetic and real data.

Doubly sparse factor models for unifying feature transformation and feature selection

Energy Technology Data Exchange (ETDEWEB)

Katahira, Kentaro; Okanoya, Kazuo; Okada, Masato [ERATO, Okanoya Emotional Information Project, Japan Science Technology Agency, Saitama (Japan); Matsumoto, Narihisa; Sugase-Miyamoto, Yasuko, E-mail: okada@k.u-tokyo.ac.j [Human Technology Research Institute, National Institute of Advanced Industrial Science and Technology, Ibaraki (Japan)

2010-06-01

A number of unsupervised learning methods for high-dimensional data are largely divided into two groups based on their procedures, i.e., (1) feature selection, which discards irrelevant dimensions of the data, and (2) feature transformation, which constructs new variables by transforming and mixing over all dimensions. We propose a method that both selects and transforms features in a common Bayesian inference procedure. Our method imposes a doubly automatic relevance determination (ARD) prior on the factor loading matrix. We propose a variational Bayesian inference for our model and demonstrate the performance of our method on both synthetic and real data.

Feature Import Vector Machine: A General Classifier with Flexible Feature Selection.

Science.gov (United States)

Ghosh, Samiran; Wang, Yazhen

2015-02-01

The support vector machine (SVM) and other reproducing kernel Hilbert space (RKHS) based classifier systems are drawing much attention recently due to its robustness and generalization capability. General theme here is to construct classifiers based on the training data in a high dimensional space by using all available dimensions. The SVM achieves huge data compression by selecting only few observations which lie close to the boundary of the classifier function. However when the number of observations are not very large (small n ) but the number of dimensions/features are large (large p ), then it is not necessary that all available features are of equal importance in the classification context. Possible selection of an useful fraction of the available features may result in huge data compression. In this paper we propose an algorithmic approach by means of which such an optimal set of features could be selected. In short, we reverse the traditional sequential observation selection strategy of SVM to that of sequential feature selection. To achieve this we have modified the solution proposed by Zhu and Hastie (2005) in the context of import vector machine (IVM), to select an optimal sub-dimensional model to build the final classifier with sufficient accuracy.

Internal versus external features in triggering the brain waveforms for conjunction and feature faces in recognition.

Science.gov (United States)

Nie, Aiqing; Jiang, Jingguo; Fu, Qiao

2014-08-20

Previous research has found that conjunction faces (whose internal features, e.g. eyes, nose, and mouth, and external features, e.g. hairstyle and ears, are from separate studied faces) and feature faces (partial features of these are studied) can produce higher false alarms than both old and new faces (i.e. those that are exactly the same as the studied faces and those that have not been previously presented) in recognition. The event-related potentials (ERPs) that relate to conjunction and feature faces at recognition, however, have not been described as yet; in addition, the contributions of different facial features toward ERPs have not been differentiated. To address these issues, the present study compared the ERPs elicited by old faces, conjunction faces (the internal and the external features were from two studied faces), old internal feature faces (whose internal features were studied), and old external feature faces (whose external features were studied) with those of new faces separately. The results showed that old faces not only elicited an early familiarity-related FN400, but a more anterior distributed late old/new effect that reflected recollection. Conjunction faces evoked similar late brain waveforms as old internal feature faces, but not to old external feature faces. These results suggest that, at recognition, old faces hold higher familiarity than compound faces in the profiles of ERPs and internal facial features are more crucial than external ones in triggering the brain waveforms that are characterized as reflecting the result of familiarity.

Attentional Selection of Feature Conjunctions Is Accomplished by Parallel and Independent Selection of Single Features.

Science.gov (United States)

Andersen, Søren K; Müller, Matthias M; Hillyard, Steven A

2015-07-08

Experiments that study feature-based attention have often examined situations in which selection is based on a single feature (e.g., the color red). However, in more complex situations relevant stimuli may not be set apart from other stimuli by a single defining property but by a specific combination of features. Here, we examined sustained attentional selection of stimuli defined by conjunctions of color and orientation. Human observers attended to one out of four concurrently presented superimposed fields of randomly moving horizontal or vertical bars of red or blue color to detect brief intervals of coherent motion. Selective stimulus processing in early visual cortex was assessed by recordings of steady-state visual evoked potentials (SSVEPs) elicited by each of the flickering fields of stimuli. We directly contrasted attentional selection of single features and feature conjunctions and found that SSVEP amplitudes on conditions in which selection was based on a single feature only (color or orientation) exactly predicted the magnitude of attentional enhancement of SSVEPs when attending to a conjunction of both features. Furthermore, enhanced SSVEP amplitudes elicited by attended stimuli were accompanied by equivalent reductions of SSVEP amplitudes elicited by unattended stimuli in all cases. We conclude that attentional selection of a feature-conjunction stimulus is accomplished by the parallel and independent facilitation of its constituent feature dimensions in early visual cortex. The ability to perceive the world is limited by the brain's processing capacity. Attention affords adaptive behavior by selectively prioritizing processing of relevant stimuli based on their features (location, color, orientation, etc.). We found that attentional mechanisms for selection of different features belonging to the same object operate independently and in parallel: concurrent attentional selection of two stimulus features is simply the sum of attending to each of those

Evaluating the Stability of Feature Selectors that Optimize Feature Subset Cardinality

Czech Academy of Sciences Publication Activity Database

Somol, Petr; Novovičová, Jana

2008-01-01

Roč. 2008, č. 5342 (2008), s. 956-966 ISSN 0302-9743. [Joint IAPR International Workshops SSPR 2008 and SPR 2008. Orlando , 04.12.2008-06.12.2008] R&D Projects: GA AV ČR 1ET400750407; GA MŠk 1M0572; GA ČR GA102/07/1594 Grant - others:GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : Feature selection * stability * relative weighted consistency measure * sequential search * floating search Subject RIV: IN - Informatics, Computer Science http://library.utia.cas.cz/separaty/2008/RO/somol-evaluating the stability of feature selectors that optimize feature subset cardinality.pdf

RESEARCH ON FEATURE POINTS EXTRACTION METHOD FOR BINARY MULTISCALE AND ROTATION INVARIANT LOCAL FEATURE DESCRIPTOR

Directory of Open Access Journals (Sweden)

Hongwei Ying

2014-08-01

Full Text Available An extreme point of scale space extraction method for binary multiscale and rotation invariant local feature descriptor is studied in this paper in order to obtain a robust and fast method for local image feature descriptor. Classic local feature description algorithms often select neighborhood information of feature points which are extremes of image scale space, obtained by constructing the image pyramid using certain signal transform method. But build the image pyramid always consumes a large amount of computing and storage resources, is not conducive to the actual applications development. This paper presents a dual multiscale FAST algorithm, it does not need to build the image pyramid, but can extract feature points of scale extreme quickly. Feature points extracted by proposed method have the characteristic of multiscale and rotation Invariant and are fit to construct the local feature descriptor.

Guilt by Association: The 13 micron Dust Feature in Circumstellar Shells and Related Spectral Features

Science.gov (United States)

Sloan, G. C.; Kraemer, K. E.; Goebel, J. H.; Price, S. D.

A study of spectra from the SWS on ISO of optically thin oxygen-rich dust shells shows that the strength of the 13 micron dust emission feature is correlated with the CO2 bands (13--17 microns) and dust emission features at 19.8 and 28.1 microns. SRb variables tend to show stronger 13 micron features than Mira variables, suggesting that the presence of the 13 micron and related features depends on pulsation mode and mass-loss rate. The absence of any correlation to dust emission features at 16.8 and 32 microns makes spinel an unlikely carrier. The most plausible carrier of the 13 micron feature remains crystalline alumina, and we suggest that the related dust features may be crystalline silicates. When dust forms in regions of low density, it may condense into crystalline grain structures.

Feature displacement interpolation

DEFF Research Database (Denmark)

Nielsen, Mads; Andresen, Per Rønsholt

1998-01-01

Given a sparse set of feature matches, we want to compute an interpolated dense displacement map. The application may be stereo disparity computation, flow computation, or non-rigid medical registration. Also estimation of missing image data, may be phrased in this framework. Since the features...... often are very sparse, the interpolation model becomes crucial. We show that a maximum likelihood estimation based on the covariance properties (Kriging) show properties more expedient than methods such as Gaussian interpolation or Tikhonov regularizations, also including scale......-selection. The computational complexities are identical. We apply the maximum likelihood interpolation to growth analysis of the mandibular bone. Here, the features used are the crest-lines of the object surface....

Mid-Infrared Emission Features in the ISM: Feature-to-Features Flux Ratios

Science.gov (United States)

Lu, N. Y.

1998-01-01

Using a limited, but representative sample of sources in the ISM of our Galaxy with published spectra from the Infrared Space Observatory, we analyze flux ratios between the major mid-IR emission features (EFs) centered around 6.2, 7.7, 8.6 and 11.3 mu, respectively.

FEATUREOUS: AN INTEGRATED ENVIRONMENT FOR FEATURE-CENTRIC ANALYSIS AND MODIFICATION OF OBJECT-ORIENTED SOFTWARE

DEFF Research Database (Denmark)

Olszak, Andrzej; Jørgensen, Bo Nørregaard

2011-01-01

The decentralized nature of collaborations between objects in object-oriented software makes it difficult to understand the implementations of user-observable program features and their respective interdependencies. As feature-centric program understanding and modification are essential during...... software maintenance and evolution, this situation needs to change. In this paper, we present Featureous, an integrated development environment built on top of the NetBeans IDE that facilitates feature-centric analysis of object-oriented software. Our integrated development environment encompasses...... a lightweight feature location mechanism, a number of reusable analytical views, and necessary APIs for supporting future extensions. The base of the integrated development environment is a conceptual framework comprising of three complementary dimensions of comprehension: perspective, abstraction...

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.

Feature confirmation in object perception: Feature integration theory 26 years on from the Treisman Bartlett lecture.

Science.gov (United States)

Humphreys, Glyn W

2016-10-01

The Treisman Bartlett lecture, reported in the Quarterly Journal of Experimental Psychology in 1988, provided a major overview of the feature integration theory of attention. This has continued to be a dominant account of human visual attention to this day. The current paper provides a summary of the work reported in the lecture and an update on critical aspects of the theory as applied to visual object perception. The paper highlights the emergence of findings that pose significant challenges to the theory and which suggest that revisions are required that allow for (a) several rather than a single form of feature integration, (b) some forms of feature integration to operate preattentively, (c) stored knowledge about single objects and interactions between objects to modulate perceptual integration, (d) the application of feature-based inhibition to object files where visual features are specified, which generates feature-based spreading suppression and scene segmentation, and (e) a role for attention in feature confirmation rather than feature integration in visual selection. A feature confirmation account of attention in object perception is outlined.

Complex Topographic Feature Ontology Patterns

Science.gov (United States)

Varanka, Dalia E.; Jerris, Thomas J.

2015-01-01

Semantic ontologies are examined as effective data models for the representation of complex topographic feature types. Complex feature types are viewed as integrated relations between basic features for a basic purpose. In the context of topographic science, such component assemblages are supported by resource systems and found on the local landscape. Ontologies are organized within six thematic modules of a domain ontology called Topography that includes within its sphere basic feature types, resource systems, and landscape types. Context is constructed not only as a spatial and temporal setting, but a setting also based on environmental processes. Types of spatial relations that exist between components include location, generative processes, and description. An example is offered in a complex feature type ‘mine.’ The identification and extraction of complex feature types are an area for future research.

Improving mass candidate detection in mammograms via feature maxima propagation and local feature selection.

Science.gov (United States)

Melendez, Jaime; Sánchez, Clara I; van Ginneken, Bram; Karssemeijer, Nico

2014-08-01

Mass candidate detection is a crucial component of multistep computer-aided detection (CAD) systems. It is usually performed by combining several local features by means of a classifier. When these features are processed on a per-image-location basis (e.g., for each pixel), mismatching problems may arise while constructing feature vectors for classification, which is especially true when the behavior expected from the evaluated features is a peaked response due to the presence of a mass. In this study, two of these problems, consisting of maxima misalignment and differences of maxima spread, are identified and two solutions are proposed. The first proposed method, feature maxima propagation, reproduces feature maxima through their neighboring locations. The second method, local feature selection, combines different subsets of features for different feature vectors associated with image locations. Both methods are applied independently and together. The proposed methods are included in a mammogram-based CAD system intended for mass detection in screening. Experiments are carried out with a database of 382 digital cases. Sensitivity is assessed at two sets of operating points. The first one is the interval of 3.5-15 false positives per image (FPs/image), which is typical for mass candidate detection. The second one is 1 FP/image, which allows to estimate the quality of the mass candidate detector's output for use in subsequent steps of the CAD system. The best results are obtained when the proposed methods are applied together. In that case, the mean sensitivity in the interval of 3.5-15 FPs/image significantly increases from 0.926 to 0.958 (p < 0.0002). At the lower rate of 1 FP/image, the mean sensitivity improves from 0.628 to 0.734 (p < 0.0002). Given the improved detection performance, the authors believe that the strategies proposed in this paper can render mass candidate detection approaches based on image location classification more robust to feature

Opinion mining feature-level using Naive Bayes and feature extraction based analysis dependencies

Science.gov (United States)

Sanda, Regi; Baizal, Z. K. Abdurahman; Nhita, Fhira

2015-12-01

Development of internet and technology, has major impact and providing new business called e-commerce. Many e-commerce sites that provide convenience in transaction, and consumers can also provide reviews or opinions on products that purchased. These opinions can be used by consumers and producers. Consumers to know the advantages and disadvantages of particular feature of the product. Procuders can analyse own strengths and weaknesses as well as it's competitors products. Many opinions need a method that the reader can know the point of whole opinion. The idea emerged from review summarization that summarizes the overall opinion based on sentiment and features contain. In this study, the domain that become the main focus is about the digital camera. This research consisted of four steps 1) giving the knowledge to the system to recognize the semantic orientation of an opinion 2) indentify the features of product 3) indentify whether the opinion gives a positive or negative 4) summarizing the result. In this research discussed the methods such as Naï;ve Bayes for sentiment classification, and feature extraction algorithm based on Dependencies Analysis, which is one of the tools in Natural Language Processing (NLP) and knowledge based dictionary which is useful for handling implicit features. The end result of research is a summary that contains a bunch of reviews from consumers on the features and sentiment. With proposed method, accuration for sentiment classification giving 81.2 % for positive test data, 80.2 % for negative test data, and accuration for feature extraction reach 90.3 %.

Feature Selection by Reordering

Czech Academy of Sciences Publication Activity Database

Jiřina, Marcel; Jiřina jr., M.

2005-01-01

Roč. 2, č. 1 (2005), s. 155-161 ISSN 1738-6438 Institutional research plan: CEZ:AV0Z10300504 Keywords : feature selection * data reduction * ordering of features Subject RIV: BA - General Mathematics

DYNAMIC FEATURE SELECTION FOR WEB USER IDENTIFICATION ON LINGUISTIC AND STYLISTIC FEATURES OF ONLINE TEXTS

Directory of Open Access Journals (Sweden)

A. A. Vorobeva

2017-01-01

Full Text Available The paper deals with identification and authentication of web users participating in the Internet information processes (based on features of online texts.In digital forensics web user identification based on various linguistic features can be used to discover identity of individuals, criminals or terrorists using the Internet to commit cybercrimes. Internet could be used as a tool in different types of cybercrimes (fraud and identity theft, harassment and anonymous threats, terrorist or extremist statements, distribution of illegal content and information warfare. Linguistic identification of web users is a kind of biometric identification, it can be used to narrow down the suspects, identify a criminal and prosecute him. Feature set includes various linguistic and stylistic features extracted from online texts. We propose dynamic feature selection for each web user identification task. Selection is based on calculating Manhattan distance to k-nearest neighbors (Relief-f algorithm. This approach improves the identification accuracy and minimizes the number of features. Experiments were carried out on several datasets with different level of class imbalance. Experiment results showed that features relevance varies in different set of web users (probable authors of some text; features selection for each set of web users improves identification accuracy by 4% at the average that is approximately 1% higher than with the use of static set of features. The proposed approach is most effective for a small number of training samples (messages per user.

Temporal Feature Integration for Music Organisation

DEFF Research Database (Denmark)

Meng, Anders

2006-01-01

This Ph.D. thesis focuses on temporal feature integration for music organisation. Temporal feature integration is the process of combining all the feature vectors of a given time-frame into a single new feature vector in order to capture relevant information in the frame. Several existing methods...... for handling sequences of features are formulated in the temporal feature integration framework. Two datasets for music genre classification have been considered as valid test-beds for music organisation. Human evaluations of these, have been obtained to access the subjectivity on the datasets. Temporal...... ranking' approach is proposed for ranking the short-time features at larger time-scales according to their discriminative power in a music genre classification task. The multivariate AR (MAR) model has been proposed for temporal feature integration. It effectively models local dynamical structure...

Feature Inference Learning and Eyetracking

Science.gov (United States)

Rehder, Bob; Colner, Robert M.; Hoffman, Aaron B.

2009-01-01

Besides traditional supervised classification learning, people can learn categories by inferring the missing features of category members. It has been proposed that feature inference learning promotes learning a category's internal structure (e.g., its typical features and interfeature correlations) whereas classification promotes the learning of…

Hypothesis testing for differentially correlated features.

Science.gov (United States)

Sheng, Elisa; Witten, Daniela; Zhou, Xiao-Hua

2016-10-01

In a multivariate setting, we consider the task of identifying features whose correlations with the other features differ across conditions. Such correlation shifts may occur independently of mean shifts, or differences in the means of the individual features across conditions. Previous approaches for detecting correlation shifts consider features simultaneously, by computing a correlation-based test statistic for each feature. However, since correlations involve two features, such approaches do not lend themselves to identifying which feature is the culprit. In this article, we instead consider a serial testing approach, by comparing columns of the sample correlation matrix across two conditions, and removing one feature at a time. Our method provides a novel perspective and favorable empirical results compared with competing approaches. © The Author 2016. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Emergent interfaces for feature modularization

CERN Document Server

Ribeiro, Márcio; Brabrand, Claus

2014-01-01

Developers frequently introduce errors into software systems when they fail to recognise module dependencies. Using forty-three software families and Software Product Lines (SPLs), where the majority are commonly used in industrial practice, the authors reports on the feature modularization problem and provides a study of how often it may occur in practice. To solve the problem they present the concept of emergent feature modularization which aims to establish contracts between features to prevent developers from breaking other features when performing a maintenance task.

Writer identification using curvature-free features

NARCIS (Netherlands)

He, Sheng; Schomaker, Lambertus

2017-01-01

Feature engineering takes a very important role in writer identification which has been widely studied in the literature. Previous works have shown that the joint feature distribution of two properties can improve the performance. The joint feature distribution makes feature relationships explicit

Patterns of Dysmorphic Features in Schizophrenia

Science.gov (United States)

Scutt, L.E.; Chow, E.W.C.; Weksberg, R.; Honer, W.G.; Bassett, Anne S.

2011-01-01

Congenital dysmorphic features are prevalent in schizophrenia and may reflect underlying neurodevelopmental abnormalities. A cluster analysis approach delineating patterns of dysmorphic features has been used in genetics to classify individuals into more etiologically homogeneous subgroups. In the present study, this approach was applied to schizophrenia, using a sample with a suspected genetic syndrome as a testable model. Subjects (n = 159) with schizophrenia or schizoaffective disorder were ascertained from chronic patient populations (random, n=123) or referred with possible 22q11 deletion syndrome (referred, n = 36). All subjects were evaluated for presence or absence of 70 reliably assessed dysmorphic features, which were used in a three-step cluster analysis. The analysis produced four major clusters with different patterns of dysmorphic features. Significant between-cluster differences were found for rates of 37 dysmorphic features (P dysmorphic features (P = 0.0001), and validating features not used in the cluster analysis: mild mental retardation (P = 0.001) and congenital heart defects (P = 0.002). Two clusters (1 and 4) appeared to represent more developmental subgroups of schizophrenia with elevated rates of dysmorphic features and validating features. Cluster 1 (n = 27) comprised mostly referred subjects. Cluster 4 (n= 18) had a different pattern of dysmorphic features; one subject had a mosaic Turner syndrome variant. Two other clusters had lower rates and patterns of features consistent with those found in previous studies of schizophrenia. Delineating patterns of dysmorphic features may help identify subgroups that could represent neurodevelopmental forms of schizophrenia with more homogeneous origins. PMID:11803519

Object feature extraction and recognition model

International Nuclear Information System (INIS)

Wan Min; Xiang Rujian; Wan Yongxing

2001-01-01

The characteristics of objects, especially flying objects, are analyzed, which include characteristics of spectrum, image and motion. Feature extraction is also achieved. To improve the speed of object recognition, a feature database is used to simplify the data in the source database. The feature vs. object relationship maps are stored in the feature database. An object recognition model based on the feature database is presented, and the way to achieve object recognition is also explained

Solar Features

Data.gov (United States)

National Oceanic and Atmospheric Administration, Department of Commerce — Collection includes a variety of solar feature datasets contributed by a number of national and private solar observatories located worldwide.

Search features of digital libraries

Directory of Open Access Journals (Sweden)

Alastair G. Smith

2000-01-01

Full Text Available Traditional on-line search services such as Dialog, DataStar and Lexis provide a wide range of search features (boolean and proximity operators, truncation, etc. This paper discusses the use of these features for effective searching, and argues that these features are required, regardless of advances in search engine technology. The literature on on-line searching is reviewed, identifying features that searchers find desirable for effective searching. A selective survey of current digital libraries available on the Web was undertaken, identifying which search features are present. The survey indicates that current digital libraries do not implement a wide range of search features. For instance: under half of the examples included controlled vocabulary, under half had proximity searching, only one enabled browsing of term indexes, and none of the digital libraries enable searchers to refine an initial search. Suggestions are made for enhancing the search effectiveness of digital libraries, for instance by: providing a full range of search operators, enabling browsing of search terms, enhancement of records with controlled vocabulary, enabling the refining of initial searches, etc.

[Feature extraction for breast cancer data based on geometric algebra theory and feature selection using differential evolution].

Science.gov (United States)

Li, Jing; Hong, Wenxue

2014-12-01

The feature extraction and feature selection are the important issues in pattern recognition. Based on the geometric algebra representation of vector, a new feature extraction method using blade coefficient of geometric algebra was proposed in this study. At the same time, an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue. The simple linear discriminant analysis was used as the classifier. The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96% and proved superior to that of the original features and traditional feature extraction method.

Tumor recognition in wireless capsule endoscopy images using textural features and SVM-based feature selection.

Science.gov (United States)

Li, Baopu; Meng, Max Q-H

2012-05-01

Tumor in digestive tract is a common disease and wireless capsule endoscopy (WCE) is a relatively new technology to examine diseases for digestive tract especially for small intestine. This paper addresses the problem of automatic recognition of tumor for WCE images. Candidate color texture feature that integrates uniform local binary pattern and wavelet is proposed to characterize WCE images. The proposed features are invariant to illumination change and describe multiresolution characteristics of WCE images. Two feature selection approaches based on support vector machine, sequential forward floating selection and recursive feature elimination, are further employed to refine the proposed features for improving the detection accuracy. Extensive experiments validate that the proposed computer-aided diagnosis system achieves a promising tumor recognition accuracy of 92.4% in WCE images on our collected data.

Volcanic features of Io

International Nuclear Information System (INIS)

Carr, M.H.; Masursky, H.; Strom, R.G.; Terrile, R.J.

1979-01-01

The volcanic features of Io as detected during the Voyager mission are discussed. The volcanic activity is apparently higher than on any other body in the Solar System. Its volcanic landforms are compared with features on Earth to indicate the type of volcanism present on Io. (U.K.)

Evaluating Stability and Comparing Output of Feature Selectors that Optimize Feature Subset Cardinality

Czech Academy of Sciences Publication Activity Database

Somol, Petr; Novovičová, Jana

2010-01-01

Roč. 32, č. 11 (2010), s. 1921-1939 ISSN 0162-8828 R&D Projects: GA MŠk 1M0572; GA ČR GA102/08/0593; GA ČR GA102/07/1594 Grant - others:GA MŠk(CZ) 2C06019 Institutional research plan: CEZ:AV0Z10750506 Keywords : feature selection * feature stability * stability measures * similarity measures * sequential search * individual ranking * feature subset-size optimization * high dimensionality * small sample size Subject RIV: BD - Theory of Information Impact factor: 5.027, year: 2010 http://library.utia.cas.cz/separaty/2010/RO/somol-0348726.pdf

Site Features

Data.gov (United States)

U.S. Environmental Protection Agency — This dataset consists of various site features from multiple Superfund sites in U.S. EPA Region 8. These data were acquired from multiple sources at different times...

New features in MEDM

International Nuclear Information System (INIS)

Evans, K. Jr.

1999-01-01

MEDM, which is derived from Motif Editor and Display Manager, is the primary graphical interface to the EPICS control system. This paper describes new features that have been added to MEDM in the last two years. These features include new editing capabilities, a PV Info dialog box, a means of specifying limits and precision, a new implementation of the Cartesian Plot, new features for several objects, new capability for the Related Display, help, a user-configurable Execute Menu, reconfigured start-up options, and availability for Windows 95/98/NT. Over one hundred bugs have been fixed, and the program is quite stable and in extensive use

Tolerance-Based Feature Transforms

NARCIS (Netherlands)

Reniers, Dennie; Telea, Alexandru

2007-01-01

Tolerance-based feature transforms (TFTs) assign to each pixel in an image not only the nearest feature pixels on the boundary (origins), but all origins from the minimum distance up to a user-defined tolerance. In this paper, we compare four simple-to-implement methods for computing TFTs on binary

Invariant Feature Matching for Image Registration Application Based on New Dissimilarity of Spatial Features

Science.gov (United States)

Mousavi Kahaki, Seyed Mostafa; Nordin, Md Jan; Ashtari, Amir H.; J. Zahra, Sophia

2016-01-01

An invariant feature matching method is proposed as a spatially invariant feature matching approach. Deformation effects, such as affine and homography, change the local information within the image and can result in ambiguous local information pertaining to image points. New method based on dissimilarity values, which measures the dissimilarity of the features through the path based on Eigenvector properties, is proposed. Evidence shows that existing matching techniques using similarity metrics—such as normalized cross-correlation, squared sum of intensity differences and correlation coefficient—are insufficient for achieving adequate results under different image deformations. Thus, new descriptor’s similarity metrics based on normalized Eigenvector correlation and signal directional differences, which are robust under local variation of the image information, are proposed to establish an efficient feature matching technique. The method proposed in this study measures the dissimilarity in the signal frequency along the path between two features. Moreover, these dissimilarity values are accumulated in a 2D dissimilarity space, allowing accurate corresponding features to be extracted based on the cumulative space using a voting strategy. This method can be used in image registration applications, as it overcomes the limitations of the existing approaches. The output results demonstrate that the proposed technique outperforms the other methods when evaluated using a standard dataset, in terms of precision-recall and corner correspondence. PMID:26985996

Invariant Feature Matching for Image Registration Application Based on New Dissimilarity of Spatial Features.

Directory of Open Access Journals (Sweden)

Seyed Mostafa Mousavi Kahaki

Full Text Available An invariant feature matching method is proposed as a spatially invariant feature matching approach. Deformation effects, such as affine and homography, change the local information within the image and can result in ambiguous local information pertaining to image points. New method based on dissimilarity values, which measures the dissimilarity of the features through the path based on Eigenvector properties, is proposed. Evidence shows that existing matching techniques using similarity metrics--such as normalized cross-correlation, squared sum of intensity differences and correlation coefficient--are insufficient for achieving adequate results under different image deformations. Thus, new descriptor's similarity metrics based on normalized Eigenvector correlation and signal directional differences, which are robust under local variation of the image information, are proposed to establish an efficient feature matching technique. The method proposed in this study measures the dissimilarity in the signal frequency along the path between two features. Moreover, these dissimilarity values are accumulated in a 2D dissimilarity space, allowing accurate corresponding features to be extracted based on the cumulative space using a voting strategy. This method can be used in image registration applications, as it overcomes the limitations of the existing approaches. The output results demonstrate that the proposed technique outperforms the other methods when evaluated using a standard dataset, in terms of precision-recall and corner correspondence.

Crowding with conjunctions of simple features.

Science.gov (United States)

Põder, Endel; Wagemans, Johan

2007-11-20

Several recent studies have related crowding with the feature integration stage in visual processing. In order to understand the mechanisms involved in this stage, it is important to use stimuli that have several features to integrate, and these features should be clearly defined and measurable. In this study, Gabor patches were used as target and distractor stimuli. The stimuli differed in three dimensions: spatial frequency, orientation, and color. A group of 3, 5, or 7 objects was presented briefly at 4 deg eccentricity of the visual field. The observers' task was to identify the object located in the center of the group. A strong effect of the number of distractors was observed, consistent with various spatial pooling models. The analysis of incorrect responses revealed that these were a mix of feature errors and mislocalizations of the target object. Feature errors were not purely random, but biased by the features of distractors. We propose a simple feature integration model that predicts most of the observed regularities.

Sensitivity to feature displacement in familiar and unfamiliar faces: beyond the internal/external feature distinction.

Science.gov (United States)

Brooks, Kevin R; Kemp, Richard I

2007-01-01

Previous studies of face recognition and of face matching have shown a general improvement for the processing of internal features as a face becomes more familiar to the participant. In this study, we used a psychophysical two-alternative forced-choice paradigm to investigate thresholds for the detection of a displacement of the eyes, nose, mouth, or ears for familiar and unfamiliar faces. No clear division between internal and external features was observed. Rather, for familiar (compared to unfamiliar) faces participants were more sensitive to displacements of internal features such as the eyes or the nose; yet, for our third internal feature-the mouth no such difference was observed. Despite large displacements, many subjects were unable to perform above chance when stimuli involved shifts in the position of the ears. These results are consistent with the proposal that familiarity effects may be mediated by the construction of a robust representation of a face, although the involvement of attention in the encoding of face stimuli cannot be ruled out. Furthermore, these effects are mediated by information from a spatial configuration of features, rather than by purely feature-based information.

Feature extraction for magnetic domain images of magneto-optical recording films using gradient feature segmentation

International Nuclear Information System (INIS)

Quanqing, Zhu.; Xinsai, Wang; Xuecheng, Zou; Haihua, Li; Xiaofei, Yang

2002-01-01

In this paper, we present a method to realize feature extraction on low contrast magnetic domain images of magneto-optical recording films. The method is based on the following three steps: first, Lee-filtering method is adopted to realize pre-filtering and noise reduction; this is followed by gradient feature segmentation, which separates the object area from the background area; finally the common linking method is adopted and the characteristic parameters of magnetic domain are calculated. We describe these steps with particular emphasis on the gradient feature segmentation. The results show that this method has advantages over other traditional ones for feature extraction of low contrast images

Discrete Feature Model (DFM) User Documentation

Energy Technology Data Exchange (ETDEWEB)

Geier, Joel (Clearwater Hardrock Consulting, Corvallis, OR (United States))

2008-06-15

This manual describes the Discrete-Feature Model (DFM) software package for modelling groundwater flow and solute transport in networks of discrete features. A discrete-feature conceptual model represents fractures and other water-conducting features around a repository as discrete conductors surrounded by a rock matrix which is usually treated as impermeable. This approximation may be valid for crystalline rocks such as granite or basalt, which have very low permeability if macroscopic fractures are excluded. A discrete feature is any entity that can conduct water and permit solute transport through bedrock, and can be reasonably represented as a piecewise-planar conductor. Examples of such entities may include individual natural fractures (joints or faults), fracture zones, and disturbed-zone features around tunnels (e.g. blasting-induced fractures or stress-concentration induced 'onion skin' fractures around underground openings). In a more abstract sense, the effectively discontinuous nature of pathways through fractured crystalline bedrock may be idealized as discrete, equivalent transmissive features that reproduce large-scale observations, even if the details of connective paths (and unconnected domains) are not precisely known. A discrete-feature model explicitly represents the fundamentally discontinuous and irregularly connected nature of systems of such systems, by constraining flow and transport to occur only within such features and their intersections. Pathways for flow and solute transport in this conceptualization are a consequence not just of the boundary conditions and hydrologic properties (as with continuum models), but also the irregularity of connections between conductive/transmissive features. The DFM software package described here is an extensible code for investigating problems of flow and transport in geological (natural or human-altered) systems that can be characterized effectively in terms of discrete features. With this

Discrete Feature Model (DFM) User Documentation

International Nuclear Information System (INIS)

Geier, Joel

2008-06-01

This manual describes the Discrete-Feature Model (DFM) software package for modelling groundwater flow and solute transport in networks of discrete features. A discrete-feature conceptual model represents fractures and other water-conducting features around a repository as discrete conductors surrounded by a rock matrix which is usually treated as impermeable. This approximation may be valid for crystalline rocks such as granite or basalt, which have very low permeability if macroscopic fractures are excluded. A discrete feature is any entity that can conduct water and permit solute transport through bedrock, and can be reasonably represented as a piecewise-planar conductor. Examples of such entities may include individual natural fractures (joints or faults), fracture zones, and disturbed-zone features around tunnels (e.g. blasting-induced fractures or stress-concentration induced 'onion skin' fractures around underground openings). In a more abstract sense, the effectively discontinuous nature of pathways through fractured crystalline bedrock may be idealized as discrete, equivalent transmissive features that reproduce large-scale observations, even if the details of connective paths (and unconnected domains) are not precisely known. A discrete-feature model explicitly represents the fundamentally discontinuous and irregularly connected nature of systems of such systems, by constraining flow and transport to occur only within such features and their intersections. Pathways for flow and solute transport in this conceptualization are a consequence not just of the boundary conditions and hydrologic properties (as with continuum models), but also the irregularity of connections between conductive/transmissive features. The DFM software package described here is an extensible code for investigating problems of flow and transport in geological (natural or human-altered) systems that can be characterized effectively in terms of discrete features. With this software, the

Degree of contribution (DoC) feature selection algorithm for structural brain MRI volumetric features in depression detection.

Science.gov (United States)

Kipli, Kuryati; Kouzani, Abbas Z

2015-07-01

Accurate detection of depression at an individual level using structural magnetic resonance imaging (sMRI) remains a challenge. Brain volumetric changes at a structural level appear to have importance in depression biomarkers studies. An automated algorithm is developed to select brain sMRI volumetric features for the detection of depression. A feature selection (FS) algorithm called degree of contribution (DoC) is developed for selection of sMRI volumetric features. This algorithm uses an ensemble approach to determine the degree of contribution in detection of major depressive disorder. The DoC is the score of feature importance used for feature ranking. The algorithm involves four stages: feature ranking, subset generation, subset evaluation, and DoC analysis. The performance of DoC is evaluated on the Duke University Multi-site Imaging Research in the Analysis of Depression sMRI dataset. The dataset consists of 115 brain sMRI scans of 88 healthy controls and 27 depressed subjects. Forty-four sMRI volumetric features are used in the evaluation. The DoC score of forty-four features was determined as the accuracy threshold (Acc_Thresh) was varied. The DoC performance was compared with that of four existing FS algorithms. At all defined Acc_Threshs, DoC outperformed the four examined FS algorithms for the average classification score and the maximum classification score. DoC has a good ability to generate reduced-size subsets of important features that could yield high classification accuracy. Based on the DoC score, the most discriminant volumetric features are those from the left-brain region.

Flow-like Features On Europa

Science.gov (United States)

1997-01-01

This image shows features on Jupiter's moon Europa that may be 'flows' from ice volcanoes. It was taken by the Galileo spacecraft solid state imaging (CCD) system during its seventh orbit around Jupiter. North is to the top of the image. The sun illuminates the scene from the left, showing features with shapes similar to lava flows on Earth. Two such features can be seen in the northwest corner of the image. The southern feature appears to have flowed over a ridge along its western edge. Scientists use these types of relationships to determine which feature formed first. In this case, the ridge probably formed before the flow-like feature that covers it.The image, centered at 22.6 degrees north latitude and 106.7 degrees west longitude, covers an area of 180 by 215 kilometers (112 by 134 miles). The smallest distinguishable features in the image are about 1.1 kilometers (0.7 miles) across. This image was obtained on April 28, 1997, when Galileo was 27,590 kilometers (16,830 miles) from Europa.The Jet Propulsion Laboratory, Pasadena, CA manages the Galileo mission for NASA's Office of Space Science, Washington, DC. JPL is an operating division of California Institute of Technology (Caltech).This image and other images and data received from Galileo are posted on the World Wide Web, on the Galileo mission home page at URL http://galileo.jpl.nasa.gov. Background information and educational context for the images can be found at URL http://www.jpl.nasa.gov/galileo/sepo

Feature Extraction

CERN Document Server

CERN. Geneva

2015-01-01

Feature selection and reduction are key to robust multivariate analyses. In this talk I will focus on pros and cons of various variable selection methods and focus on those that are most relevant in the context of HEP.

Video genre classification using multimodal features

Science.gov (United States)

Jin, Sung Ho; Bae, Tae Meon; Choo, Jin Ho; Ro, Yong Man

2003-12-01

We propose a video genre classification method using multimodal features. The proposed method is applied for the preprocessing of automatic video summarization or the retrieval and classification of broadcasting video contents. Through a statistical analysis of low-level and middle-level audio-visual features in video, the proposed method can achieve good performance in classifying several broadcasting genres such as cartoon, drama, music video, news, and sports. In this paper, we adopt MPEG-7 audio-visual descriptors as multimodal features of video contents and evaluate the performance of the classification by feeding the features into a decision tree-based classifier which is trained by CART. The experimental results show that the proposed method can recognize several broadcasting video genres with a high accuracy and the classification performance with multimodal features is superior to the one with unimodal features in the genre classification.

Particle swarm optimization based feature enhancement and feature selection for improved emotion recognition in speech and glottal signals.

Science.gov (United States)

Muthusamy, Hariharan; Polat, Kemal; Yaacob, Sazali

2015-01-01

In the recent years, many research works have been published using speech related features for speech emotion recognition, however, recent studies show that there is a strong correlation between emotional states and glottal features. In this work, Mel-frequency cepstralcoefficients (MFCCs), linear predictive cepstral coefficients (LPCCs), perceptual linear predictive (PLP) features, gammatone filter outputs, timbral texture features, stationary wavelet transform based timbral texture features and relative wavelet packet energy and entropy features were extracted from the emotional speech (ES) signals and its glottal waveforms(GW). Particle swarm optimization based clustering (PSOC) and wrapper based particle swarm optimization (WPSO) were proposed to enhance the discerning ability of the features and to select the discriminating features respectively. Three different emotional speech databases were utilized to gauge the proposed method. Extreme learning machine (ELM) was employed to classify the different types of emotions. Different experiments were conducted and the results show that the proposed method significantly improves the speech emotion recognition performance compared to previous works published in the literature.

MRI features associated with acute appendicitis

NARCIS (Netherlands)

Leeuwenburgh, Marjolein M. N.; Jensch, Sebastiaan; Gratama, Jan W. C.; Spilt, Aart; Wiarda, Bart M.; van Es, H. Wouter; Cobben, Lodewijk P. J.; Bossuyt, Patrick M. M.; Boermeester, Marja A.; Stoker, Jaap; Bouma, Wim H.; Houdijk, Alexander P. J.; Richir, Milan C.; Stockmann, Hein B. A. C.; Wiezer, Marinus J.; Verhagen, Thijs

2014-01-01

To identify MRI features associated with appendicitis. Features expected to be associated with appendicitis were recorded in consensus by two expert radiologists on 223 abdominal MRIs in patients with suspected appendicitis. Nine MRI features were studied: appendix diameter >7 mm, appendicolith,

Hong Kong English: phonological features

OpenAIRE

Irina-Ana Drobot

2008-01-01

The aim of the paper is to present phonological features of Hong Kong English, which is a variety of New English. I examine features of the sound system (vowel and consonantal systems), characteristics of stress, rhythm, intonation, and phonological processes of the English spoken by Hongkongers. The way in which the accent and characteristics of the Hong Kong variety of English differs from standard, RP English is pointed out. Influences of Chinese and Cantonese on the phonological features ...

Cascaded face alignment via intimacy definition feature

Science.gov (United States)

Li, Hailiang; Lam, Kin-Man; Chiu, Man-Yau; Wu, Kangheng; Lei, Zhibin

2017-09-01

Recent years have witnessed the emerging popularity of regression-based face aligners, which directly learn mappings between facial appearance and shape-increment manifolds. We propose a random-forest based, cascaded regression model for face alignment by using a locally lightweight feature, namely intimacy definition feature. This feature is more discriminative than the pose-indexed feature, more efficient than the histogram of oriented gradients feature and the scale-invariant feature transform feature, and more compact than the local binary feature (LBF). Experimental validation of our algorithm shows that our approach achieves state-of-the-art performance when testing on some challenging datasets. Compared with the LBF-based algorithm, our method achieves about twice the speed, 20% improvement in terms of alignment accuracy and saves an order of magnitude on memory requirement.

Extract the Relational Information of Static Features and Motion Features for Human Activities Recognition in Videos

Directory of Open Access Journals (Sweden)

Li Yao

2016-01-01

Full Text Available Both static features and motion features have shown promising performance in human activities recognition task. However, the information included in these features is insufficient for complex human activities. In this paper, we propose extracting relational information of static features and motion features for human activities recognition. The videos are represented by a classical Bag-of-Word (BoW model which is useful in many works. To get a compact and discriminative codebook with small dimension, we employ the divisive algorithm based on KL-divergence to reconstruct the codebook. After that, to further capture strong relational information, we construct a bipartite graph to model the relationship between words of different feature set. Then we use a k-way partition to create a new codebook in which similar words are getting together. With this new codebook, videos can be represented by a new BoW vector with strong relational information. Moreover, we propose a method to compute new clusters from the divisive algorithm’s projective function. We test our work on the several datasets and obtain very promising results.

Temporal feature integration for music genre classification

DEFF Research Database (Denmark)

Meng, Anders; Ahrendt, Peter; Larsen, Jan

2007-01-01

, but they capture neither the temporal dynamics nor dependencies among the individual feature dimensions. Here, a multivariate autoregressive feature model is proposed to solve this problem for music genre classification. This model gives two different feature sets, the diagonal autoregressive (DAR......) and multivariate autoregressive (MAR) features which are compared against the baseline mean-variance as well as two other temporal feature integration techniques. Reproducibility in performance ranking of temporal feature integration methods were demonstrated using two data sets with five and eleven music genres...

Inflation and WMAP three year data. Features have a feature.

Energy Technology Data Exchange (ETDEWEB)

Covi, L.; Hamann, J. [Deutsches Elektronen-Synchrotron (DESY), Hamburg (Germany); Melchiorri, A. [INFN, Roma (Italy)]|[Rome-3 Univ. (Italy). Dipt. di Fisica; Slosar, A. [Ljubljana Univ. (Slovenia). Faculty of Mathematics and Physics; Sorbera, I. [Rome-3 Univ. (Italy). Dipt. di Fisica

2006-06-15

The new three year WMAP data seem to confirm the presence of non-standard large scale features in the Cosmic Microwave Anisotropies power spectrum. While these features may hint at uncorrected experimental systematics, it is also possible to generate, in a cosmological way, oscillations on large angular scales by introducing a sharp step in the inflaton potential. Using current cosmological data, we derive constraints on the position, magnitude and gradient of a possible step in the inflaton potential. We show that a step in the potential, while strongly constrained by current data, is still allowed and may provide an interesting explanation to the currently measured deviations from the standard featureless spectrum. (Orig.)

Feature singletons attract spatial attention independently of feature priming.

Science.gov (United States)

Yashar, Amit; White, Alex L; Fang, Wanghaoming; Carrasco, Marisa

2017-08-01

People perform better in visual search when the target feature repeats across trials (intertrial feature priming [IFP]). Here, we investigated whether repetition of a feature singleton's color modulates stimulus-driven shifts of spatial attention by presenting a probe stimulus immediately after each singleton display. The task alternated every two trials between a probe discrimination task and a singleton search task. We measured both stimulus-driven spatial attention (via the distance between the probe and singleton) and IFP (via repetition of the singleton's color). Color repetition facilitated search performance (IFP effect) when the set size was small. When the probe appeared at the singleton's location, performance was better than at the opposite location (stimulus-driven attention effect). The magnitude of this attention effect increased with the singleton's set size (which increases its saliency) but did not depend on whether the singleton's color repeated across trials, even when the previous singleton had been attended as a search target. Thus, our findings show that repetition of a salient singleton's color affects performance when the singleton is task relevant and voluntarily attended (as in search trials). However, color repetition does not affect performance when the singleton becomes irrelevant to the current task, even though the singleton does capture attention (as in probe trials). Therefore, color repetition per se does not make a singleton more salient for stimulus-driven attention. Rather, we suggest that IFP requires voluntary selection of color singletons in each consecutive trial.

MRI features associated with acute appendicitis

Energy Technology Data Exchange (ETDEWEB)

Leeuwenburgh, Marjolein M.N. [University of Amsterdam, Department of Surgery, Academic Medical Center, Amsterdam (Netherlands); University of Amsterdam, Department of Radiology, Academic Medical Center, Amsterdam (Netherlands); Academic Medical Center, Department of Radiology (G1-223.1), Amsterdam (Netherlands); Jensch, Sebastiaan [Sint Lucas Andreas Hospital, Department of Radiology, Amsterdam (Netherlands); Gratama, Jan W.C. [Gelre Hospitals, Department of Radiology, Apeldoorn (Netherlands); Spilt, Aart [Kennemer Gasthuis, Department of Radiology, Haarlem (Netherlands); Wiarda, Bart M. [Alkmaar Medical Center, Department of Radiology, Alkmaar (Netherlands); Es, H.W. van [Sint Antonius Hospital, Department of Radiology, Nieuwegein (Netherlands); Cobben, Lodewijk P.J. [Haaglanden Medical Center, Department of Radiology, Leidschendam (Netherlands); Bossuyt, Patrick M.M. [University of Amsterdam, Department of Clinical Epidemiology, Academic Medical Center, Amsterdam (Netherlands); Boermeester, Marja A. [University of Amsterdam, Department of Surgery, Academic Medical Center, Amsterdam (Netherlands); Stoker, Jaap [University of Amsterdam, Department of Radiology, Academic Medical Center, Amsterdam (Netherlands); Collaboration: on behalf of the OPTIMAP study group

2014-01-15

To identify MRI features associated with appendicitis. Features expected to be associated with appendicitis were recorded in consensus by two expert radiologists on 223 abdominal MRIs in patients with suspected appendicitis. Nine MRI features were studied: appendix diameter >7 mm, appendicolith, peri-appendiceal fat infiltration, peri-appendiceal fluid, absence of gas in the appendix, appendiceal wall destruction, restricted diffusion of the appendiceal wall, lumen or focal fluid collections. Appendicitis was assigned as the final diagnosis in 117/223 patients. Associations between imaging features and appendicitis were evaluated with logistic regression analysis. All investigated features were significantly associated with appendicitis in univariate analysis. Combinations of two and three features were associated with a probability of appendicitis of 88 % and 92 %, respectively. In patients without any of the nine features, appendicitis was present in 2 % of cases. After multivariate analysis, only an appendix diameter >7 mm, peri-appendiceal fat infiltration and restricted diffusion of the appendiceal wall were significantly associated with appendicitis. The probability of appendicitis was 96 % in their presence and 2 % in their absence. An appendix diameter >7 mm, peri-appendiceal fat infiltration and restricted diffusion of the appendiceal wall have the strongest association with appendicitis on MRI. (orig.)

MRI features associated with acute appendicitis

International Nuclear Information System (INIS)

Leeuwenburgh, Marjolein M.N.; Jensch, Sebastiaan; Gratama, Jan W.C.; Spilt, Aart; Wiarda, Bart M.; Es, H.W. van; Cobben, Lodewijk P.J.; Bossuyt, Patrick M.M.; Boermeester, Marja A.; Stoker, Jaap

2014-01-01

To identify MRI features associated with appendicitis. Features expected to be associated with appendicitis were recorded in consensus by two expert radiologists on 223 abdominal MRIs in patients with suspected appendicitis. Nine MRI features were studied: appendix diameter >7 mm, appendicolith, peri-appendiceal fat infiltration, peri-appendiceal fluid, absence of gas in the appendix, appendiceal wall destruction, restricted diffusion of the appendiceal wall, lumen or focal fluid collections. Appendicitis was assigned as the final diagnosis in 117/223 patients. Associations between imaging features and appendicitis were evaluated with logistic regression analysis. All investigated features were significantly associated with appendicitis in univariate analysis. Combinations of two and three features were associated with a probability of appendicitis of 88 % and 92 %, respectively. In patients without any of the nine features, appendicitis was present in 2 % of cases. After multivariate analysis, only an appendix diameter >7 mm, peri-appendiceal fat infiltration and restricted diffusion of the appendiceal wall were significantly associated with appendicitis. The probability of appendicitis was 96 % in their presence and 2 % in their absence. An appendix diameter >7 mm, peri-appendiceal fat infiltration and restricted diffusion of the appendiceal wall have the strongest association with appendicitis on MRI. (orig.)

Textural features for radar image analysis

Science.gov (United States)

Shanmugan, K. S.; Narayanan, V.; Frost, V. S.; Stiles, J. A.; Holtzman, J. C.

1981-01-01

Texture is seen as an important spatial feature useful for identifying objects or regions of interest in an image. While textural features have been widely used in analyzing a variety of photographic images, they have not been used in processing radar images. A procedure for extracting a set of textural features for characterizing small areas in radar images is presented, and it is shown that these features can be used in classifying segments of radar images corresponding to different geological formations.

Conjunctive Coding of Complex Object Features

Science.gov (United States)

Erez, Jonathan; Cusack, Rhodri; Kendall, William; Barense, Morgan D.

2016-01-01

Critical to perceiving an object is the ability to bind its constituent features into a cohesive representation, yet the manner by which the visual system integrates object features to yield a unified percept remains unknown. Here, we present a novel application of multivoxel pattern analysis of neuroimaging data that allows a direct investigation of whether neural representations integrate object features into a whole that is different from the sum of its parts. We found that patterns of activity throughout the ventral visual stream (VVS), extending anteriorly into the perirhinal cortex (PRC), discriminated between the same features combined into different objects. Despite this sensitivity to the unique conjunctions of features comprising objects, activity in regions of the VVS, again extending into the PRC, was invariant to the viewpoints from which the conjunctions were presented. These results suggest that the manner in which our visual system processes complex objects depends on the explicit coding of the conjunctions of features comprising them. PMID:25921583

Hong Kong English: phonological features

Directory of Open Access Journals (Sweden)

Irina-Ana Drobot

2008-01-01

Full Text Available The aim of the paper is to present phonological features of Hong Kong English, which is a variety of New English. I examine features of the sound system (vowel and consonantal systems, characteristics of stress, rhythm, intonation, and phonological processes of the English spoken by Hongkongers. The way in which the accent and characteristics of the Hong Kong variety of English differs from standard, RP English is pointed out. Influences of Chinese and Cantonese on the phonological features of Hong Kong English are noticeable

Personality Features of Motorists

Directory of Open Access Journals (Sweden)

Andrej Justinek

1997-12-01

Full Text Available Justinek tries to answer the question whether or not motorists have specific personality features which predispose them for safe and well-mannered driving. A good driver should have sensory abilities which enable psycho-motor coordiation of a vehicle, intellectual and cognitive features that are important for solving problems in new, unknown situations, and emotional and motivational trails defining a driver's maturity. Justmek advocates the belief that in training future drivers greater attention should be paid to developing these features which are vital for safe driving and appropriate behaviour of drivers in traffic. He also suggests certain learning methods leading to development of the above­ mentioned personality traits. Justinek introduces the notion of the 'philosophy of driving' as an essential educational category in training future drivers.

Features for detecting smoke in laparoscopic videos

Directory of Open Access Journals (Sweden)

Jalal Nour Aldeen

2017-09-01

Full Text Available Video-based smoke detection in laparoscopic surgery has different potential applications, such as the automatic addressing of surgical events associated with the electrocauterization task and the development of automatic smoke removal. In the literature, video-based smoke detection has been studied widely for fire surveillance systems. Nevertheless, the proposed methods are insufficient for smoke detection in laparoscopic videos because they often depend on assumptions which rarely hold in laparoscopic surgery such as static camera. In this paper, ten visual features based on motion, texture and colour of smoke are proposed and evaluated for smoke detection in laparoscopic videos. These features are RGB channels, energy-based feature, texture features based on gray level co-occurrence matrix (GLCM, HSV colour space feature, features based on the detection of moving regions using optical flow and the smoke colour in HSV colour space. These features were tested on four laparoscopic cholecystectomy videos. Experimental observations show that each feature can provide valuable information in performing the smoke detection task. However, each feature has weaknesses to detect the presence of smoke in some cases. By combining all proposed features smoke with high and even low density can be identified robustly and the classification accuracy increases significantly.

Novel Features for Brain-Computer Interfaces

Science.gov (United States)

Woon, W. L.; Cichocki, A.

2007-01-01

While conventional approaches of BCI feature extraction are based on the power spectrum, we have tried using nonlinear features for classifying BCI data. In this paper, we report our test results and findings, which indicate that the proposed method is a potentially useful addition to current feature extraction techniques. PMID:18364991

Feature Binding in Zebrafish

Directory of Open Access Journals (Sweden)

P Neri

2012-07-01

Full Text Available Binding operations are primarily ascribed to cortex or similarly complex avian structures. My experiments show that the zebrafish, a lower vertebrate lacking cortex, supports visual feature binding of form and motion for the purpose of social behavior. These results challenge the notion that feature binding may require highly evolved neural structures and demonstrate that the nervous system of lower vertebrates can afford unexpectedly complex computations.

Ontology patterns for complex topographic feature yypes

Science.gov (United States)

Varanka, Dalia E.

2011-01-01

Complex feature types are defined as integrated relations between basic features for a shared meaning or concept. The shared semantic concept is difficult to define in commonly used geographic information systems (GIS) and remote sensing technologies. The role of spatial relations between complex feature parts was recognized in early GIS literature, but had limited representation in the feature or coverage data models of GIS. Spatial relations are more explicitly specified in semantic technology. In this paper, semantics for topographic feature ontology design patterns (ODP) are developed as data models for the representation of complex features. In the context of topographic processes, component assemblages are supported by resource systems and are found on local landscapes. The topographic ontology is organized across six thematic modules that can account for basic feature types, resource systems, and landscape types. Types of complex feature attributes include location, generative processes and physical description. Node/edge networks model standard spatial relations and relations specific to topographic science to represent complex features. To demonstrate these concepts, data from The National Map of the U. S. Geological Survey was converted and assembled into ODP.

Feature-level domain adaptation

DEFF Research Database (Denmark)

Kouw, Wouter M.; Van Der Maaten, Laurens J P; Krijthe, Jesse H.

2016-01-01

-level domain adaptation (flda), that models the dependence between the two domains by means of a feature-level transfer model that is trained to describe the transfer from source to target domain. Subsequently, we train a domain-adapted classifier by minimizing the expected loss under the resulting transfer...... modeled via a dropout distribution, which allows the classiffier to adapt to differences in the marginal probability of features in the source and the target domain. Our experiments on several real-world problems show that flda performs on par with state-of-the-art domainadaptation techniques.......Domain adaptation is the supervised learning setting in which the training and test data are sampled from different distributions: training data is sampled from a source domain, whilst test data is sampled from a target domain. This paper proposes and studies an approach, called feature...

Addressing scalability while feature requests persist. A look at NASA Worldview's new features and their implementation.

Science.gov (United States)

King, B. A.

2017-12-01

Worldview is a high-traffic web mapping application created using the JavaScript mapping library, OpenLayers. This presentation will primarily focus on three new features: A wrapping component that seamlessly shows satellite imagery over the dateline where most maps either stop or wrap the imagery of the same date. An animation feature that allows users to select date ranges over which they can animate. An A/B comparison feature that gives users the power to compare imagery between dates and layers. In response to an increasingly large codebase caused by ongoing feature requests, Worldview is transitioning to a smaller core codebase comprised of external reusable modules. When creating a module with the intention of having someone else reuse it for a different task, one inherently starts generating code that is easier to read and easier to maintain. This presentation will show demos of these features and cover development techniques used to create them.

Light field morphing using 2D features.

Science.gov (United States)

Wang, Lifeng; Lin, Stephen; Lee, Seungyong; Guo, Baining; Shum, Heung-Yeung

2005-01-01

We present a 2D feature-based technique for morphing 3D objects represented by light fields. Existing light field morphing methods require the user to specify corresponding 3D feature elements to guide morph computation. Since slight errors in 3D specification can lead to significant morphing artifacts, we propose a scheme based on 2D feature elements that is less sensitive to imprecise marking of features. First, 2D features are specified by the user in a number of key views in the source and target light fields. Then the two light fields are warped view by view as guided by the corresponding 2D features. Finally, the two warped light fields are blended together to yield the desired light field morph. Two key issues in light field morphing are feature specification and warping of light field rays. For feature specification, we introduce a user interface for delineating 2D features in key views of a light field, which are automatically interpolated to other views. For ray warping, we describe a 2D technique that accounts for visibility changes and present a comparison to the ideal morphing of light fields. Light field morphing based on 2D features makes it simple to incorporate previous image morphing techniques such as nonuniform blending, as well as to morph between an image and a light field.

Nonmotor Features in Atypical Parkinsonism.

Science.gov (United States)

Bhatia, Kailash P; Stamelou, Maria

2017-01-01

Atypical parkinsonism (AP) comprises mainly multiple system atrophy (MSA), progressive supranuclear palsy (PSP), and corticobasal degeneration (CBD), which are distinct pathological entities, presenting with a wide phenotypic spectrum. The classic syndromes are now called MSA-parkinsonism (MSA-P), MSA-cerebellar type (MSA-C), Richardson's syndrome, and corticobasal syndrome. Nonmotor features in AP have been recognized almost since the initial description of these disorders; however, research has been limited. Autonomic dysfunction is the most prominent nonmotor feature of MSA, but also gastrointestinal symptoms, sleep dysfunction, and pain, can be a feature. In PSP and CBD, the most prominent nonmotor symptoms comprise those deriving from the cognitive/neuropsychiatric domain. Apart from assisting the clinician in the differential diagnosis with Parkinson's disease, nonmotor features in AP have a big impact on quality of life and prognosis of AP and their treatment poses a major challenge for clinicians. © 2017 Elsevier Inc. All rights reserved.

Wilson’s disease: Atypical imaging features

Directory of Open Access Journals (Sweden)

Venugopalan Y Vishnu

2016-10-01

Full Text Available Wilson’s disease is a genetic movement disorder with characteristic clinical and imaging features. We report a 17- year-old boy who presented with sialorrhea, hypophonic speech, paraparesis with repeated falls and recurrent seizures along with cognitive decline. He had bilateral Kayser Flescher rings. Other than the typical features of Wilson’s disease in cranial MRI, there were extensive white matter signal abnormalities (T2 and FLAIR hyperintensities and gyriform contrast enhancement which are rare imaging features in Wilson's disease. A high index of suspicion is required to diagnose Wilson’s disease when atypical imaging features are present.

Multimodal Feature Learning for Video Captioning

Directory of Open Access Journals (Sweden)

Sujin Lee

2018-01-01

Full Text Available Video captioning refers to the task of generating a natural language sentence that explains the content of the input video clips. This study proposes a deep neural network model for effective video captioning. Apart from visual features, the proposed model learns additionally semantic features that describe the video content effectively. In our model, visual features of the input video are extracted using convolutional neural networks such as C3D and ResNet, while semantic features are obtained using recurrent neural networks such as LSTM. In addition, our model includes an attention-based caption generation network to generate the correct natural language captions based on the multimodal video feature sequences. Various experiments, conducted with the two large benchmark datasets, Microsoft Video Description (MSVD and Microsoft Research Video-to-Text (MSR-VTT, demonstrate the performance of the proposed model.

Language identification using excitation source features

CERN Document Server

Rao, K Sreenivasa

2015-01-01

This book discusses the contribution of excitation source information in discriminating language. The authors focus on the excitation source component of speech for enhancement of language identification (LID) performance. Language specific features are extracted using two different modes: (i) Implicit processing of linear prediction (LP) residual and (ii) Explicit parameterization of linear prediction residual. The book discusses how in implicit processing approach, excitation source features are derived from LP residual, Hilbert envelope (magnitude) of LP residual and Phase of LP residual; and in explicit parameterization approach, LP residual signal is processed in spectral domain to extract the relevant language specific features. The authors further extract source features from these modes, which are combined for enhancing the performance of LID systems. The proposed excitation source features are also investigated for LID in background noisy environments. Each chapter of this book provides the motivatio...

Guilt by Association: The 13 Micron Dust Emission Feature and Its Correlation to Other Gas and Dust Features

Science.gov (United States)

Sloan, G. C.; Kraemer, Kathleen E.; Goebel, J. H.; Price, Stephan D.

2003-09-01

A study of all full-scan spectra of optically thin oxygen-rich circumstellar dust shells in the database produced by the Short Wavelength Spectrometer on ISO reveals that the strength of several infrared spectral features correlates with the strength of the 13 μm dust feature. These correlated features include dust features at 19.8 and 28.1 μm and the bands produced by warm carbon dioxide molecules (the strongest of which are at 13.9, 15.0, and 16.2 μm). The database does not provide any evidence for a correlation of the 13 μm feature with a dust feature at 32 μm, and it is more likely that a weak emission feature at 16.8 μm arises from carbon dioxide gas rather than dust. The correlated dust features at 13, 20, and 28 μm tend to be stronger with respect to the total dust emission in semiregular and irregular variables associated with the asymptotic giant branch than in Mira variables or supergiants. This family of dust features also tends to be stronger in systems with lower infrared excesses and thus lower mass-loss rates. We hypothesize that the dust features arise from crystalline forms of alumina (13 μm) and silicates (20 and 28 μm). Based on observations with the ISO, a European Space Agency (ESA) project with instruments funded by ESA member states (especially the Principal Investigator countries: France, Germany, the Netherlands, and the United Kingdom) and with the participation of the Institute of Space and Astronautical Science (ISAS) and the National Aeronautics and Space Administration (NASA).

Comparison of advanced mid-sized reactors regarding passive features, core damage frequencies and core melt retention features

International Nuclear Information System (INIS)

Wider, H.

2005-01-01

New Light Water Reactors, whose regular safety systems are complemented by passive safety systems, are ready for the market. The special aspect of passive safety features is their actuation and functioning independent of the operator. They add significantly to reduce the core damage frequency (CDF) since the operator continues to play its independent role in actuating the regular safety devices based on modern instrumentation and control (I and C). The latter also has passive features regarding the prevention of accidents. Two reactors with significant passive features that are presently offered on the market are the AP1000 PWR and the SWR 1000 BWR. Their passive features are compared and also their core damage frequencies (CDF). The latter are also compared with those of a VVER-1000. A further discussion about the two passive plants concerns their mitigating features for severe accidents. Regarding core-melt retention both rely on in-vessel cooling of the melt. The new VVER-1000 reactor, on the other hand features a validated ex-vessel concept. (author)

Controllable edge feature sharpening for dental applications.

Science.gov (United States)

Fan, Ran; Jin, Xiaogang

2014-01-01

This paper presents a new approach to sharpen blurred edge features in scanned tooth preparation surfaces generated by structured-light scanners. It aims to efficiently enhance the edge features so that the embedded feature lines can be easily identified in dental CAD systems, and to avoid unnatural oversharpening geometry. We first separate the feature regions using graph-cut segmentation, which does not require a user-defined threshold. Then, we filter the face normal vectors to propagate the geometry from the smooth region to the feature region. In order to control the degree of the sharpness, we propose a feature distance measure which is based on normal tensor voting. Finally, the vertex positions are updated according to the modified face normal vectors. We have applied the approach to scanned tooth preparation models. The results show that the blurred edge features are enhanced without unnatural oversharpening geometry.

Controllable Edge Feature Sharpening for Dental Applications

Directory of Open Access Journals (Sweden)

Ran Fan

2014-01-01

Full Text Available This paper presents a new approach to sharpen blurred edge features in scanned tooth preparation surfaces generated by structured-light scanners. It aims to efficiently enhance the edge features so that the embedded feature lines can be easily identified in dental CAD systems, and to avoid unnatural oversharpening geometry. We first separate the feature regions using graph-cut segmentation, which does not require a user-defined threshold. Then, we filter the face normal vectors to propagate the geometry from the smooth region to the feature region. In order to control the degree of the sharpness, we propose a feature distance measure which is based on normal tensor voting. Finally, the vertex positions are updated according to the modified face normal vectors. We have applied the approach to scanned tooth preparation models. The results show that the blurred edge features are enhanced without unnatural oversharpening geometry.

FeatureMap3D - a tool to map protein features and sequence conservation onto homologous structures in the PDB

DEFF Research Database (Denmark)

Wernersson, Rasmus; Rapacki, Krzysztof; Stærfeldt, Hans Henrik

2006-01-01

FeatureMap3D is a web-based tool that maps protein features onto 3D structures. The user provides sequences annotated with any feature of interest, such as post-translational modifications, protease cleavage sites or exonic structure and FeatureMap3D will then search the Protein Data Bank (PDB) f...

Glacial Features (Point) - Quad 168 (EPPING, NH)

Data.gov (United States)

University of New Hampshire — The Glacial Features (Point) layer describes point features associated with surficial geology. These glacial features include, but are not limited to, delta forsets,...

Partial Epilepsy with Auditory Features

Directory of Open Access Journals (Sweden)

J Gordon Millichap

2004-07-01

Full Text Available The clinical characteristics of 53 sporadic (S cases of idiopathic partial epilepsy with auditory features (IPEAF were analyzed and compared to previously reported familial (F cases of autosomal dominant partial epilepsy with auditory features (ADPEAF in a study at the University of Bologna, Italy.

Feature Extraction Using Fractal Codes

NARCIS (Netherlands)

B.A.M. Schouten (Ben); P.M. de Zeeuw (Paul)

1999-01-01

htmlabstractFast and successful searching for an object in a multimedia database is a highly desirable functionality. Several approaches to content based retrieval for multimedia databases can be found in the literature [9,10,12,14,17]. The approach we consider is feature extraction. A feature can

Remodularizing Java programs for comprehension of features

DEFF Research Database (Denmark)

Olszak, Andrzej; Jørgensen, Bo Nørregaard

2009-01-01

. In absence of these mechanisms, feature implementations tend to be scattered and tangled in terms of object-oriented abstractions, making the code implementing features difficult to locate and comprehend. In this paper we present a semi-automatic method for feature-oriented remodularization of Java programs....... Our method uses execution traces to locate implementations of features, and Java packages to establish explicit feature modules. To evaluate usefulness of the approach, we present a case study where we apply our method to two real-world software systems. The obtained results indicate a significant...

Patch layout generation by detecting feature networks

KAUST Repository

Cao, Yuanhao

2015-02-01

The patch layout of 3D surfaces reveals the high-level geometric and topological structures. In this paper, we study the patch layout computation by detecting and enclosing feature loops on surfaces. We present a hybrid framework which combines several key ingredients, including feature detection, feature filtering, feature curve extension, patch subdivision and boundary smoothing. Our framework is able to compute patch layouts through concave features as previous approaches, but also able to generate nice layouts through smoothing regions. We demonstrate the effectiveness of our framework by comparing with the state-of-the-art methods.

Feature coding for image representation and recognition

CERN Document Server

Huang, Yongzhen

2015-01-01

This brief presents a comprehensive introduction to feature coding, which serves as a key module for the typical object recognition pipeline. The text offers a rich blend of theory and practice while reflects the recent developments on feature coding, covering the following five aspects: (1) Review the state-of-the-art, analyzing the motivations and mathematical representations of various feature coding methods; (2) Explore how various feature coding algorithms evolve along years; (3) Summarize the main characteristics of typical feature coding algorithms and categorize them accordingly; (4) D

Currency features for visually impaired people

Science.gov (United States)

Hyland, Sandra L.; Legge, Gordon E.; Shannon, Robert R.; Baer, Norbert S.

1996-03-01

The estimated 3.7 million Americans with low vision experience a uniquely difficult task in identifying the denominations of U.S. banknotes because the notes are remarkably uniform in size, color, and general design. The National Research Council's Committee on Currency Features Usable by the Visually Impaired assessed features that could be used by people who are visually disabled to distinguish currency from other documents and to denominate and authenticate banknotes using available technology. Variation of length and height, introduction of large numerals on a uniform, high-contrast background, use of different colors for each of the six denominations printed, and the introduction of overt denomination codes that could lead to development of effective, low-cost devices for examining banknotes were all deemed features available now. Issues affecting performance, including the science of visual and tactile perception, were addressed for these features, as well as for those features requiring additional research and development. In this group the committee included durable tactile features such as those printed with transparent ink, and the production of currency with holes to indicate denomination. Among long-range approaches considered were the development of technologically advanced devices and smart money.

Fall Detection Using Smartphone Audio Features.

Science.gov (United States)

Cheffena, Michael

2016-07-01

An automated fall detection system based on smartphone audio features is developed. The spectrogram, mel frequency cepstral coefficents (MFCCs), linear predictive coding (LPC), and matching pursuit (MP) features of different fall and no-fall sound events are extracted from experimental data. Based on the extracted audio features, four different machine learning classifiers: k-nearest neighbor classifier (k-NN), support vector machine (SVM), least squares method (LSM), and artificial neural network (ANN) are investigated for distinguishing between fall and no-fall events. For each audio feature, the performance of each classifier in terms of sensitivity, specificity, accuracy, and computational complexity is evaluated. The best performance is achieved using spectrogram features with ANN classifier with sensitivity, specificity, and accuracy all above 98%. The classifier also has acceptable computational requirement for training and testing. The system is applicable in home environments where the phone is placed in the vicinity of the user.

Flexible feature interface for multimedia sources

Science.gov (United States)

Coffland, Douglas R [Livermore, CA

2009-06-09

A flexible feature interface for multimedia sources system that includes a single interface for the addition of features and functions to multimedia sources and for accessing those features and functions from remote hosts. The interface utilizes the export statement: export "C" D11Export void FunctionName(int argc, char ** argv,char * result, SecureSession *ctrl) or the binary equivalent of the export statement.

Prostatic adenocarcinoma with glomeruloid features.

Science.gov (United States)

Pacelli, A; Lopez-Beltran, A; Egan, A J; Bostwick, D G

1998-05-01

A wide variety of architectural patterns of adenocarcinoma may be seen in the prostate. We have recently encountered a hitherto-undescribed pattern of growth characterized by intraluminal ball-like clusters of cancer cells reminiscent of renal glomeruli, which we refer to as prostatic adenocarcinoma with glomeruloid features. To define the architectural features, frequency, and distribution of prostatic adenocarcinoma with glomeruloid features, we reviewed 202 totally embedded radical prostatectomy specimens obtained between October 1992 and April 1994 from the files of the Mayo Clinic. This series was supplemented by 100 consecutive needle biopsies with prostatic cancer from January to February 1996. Prostatic adenocarcinoma with glomeruloid features was characterized by round to oval epithelial tufts growing within malignant acini, often supported by a fibrovascular core. The epithelial cells were sometimes arranged in semicircular concentric rows separated by clefted spaces. In the radical prostatectomy specimens, nine cases (4.5%) had glomeruloid features. The glomeruloid pattern constituted 5% to 20% of each cancer (mean, 8.33%) and was usually located at the apex or in the peripheral zone of the prostate. Seven cases were associated with a high Gleason score (7 or 8), one with a score of 6, and one with a score of 5. All cases were associated with high-grade prostatic intraepithelial neoplasia and extensive perineural invasion. Pathological stages included T2c (three cases), T3b (four cases), and T3c (two cases); one of the T3b cases had lymph node metastases (N1). Three (3%) of 100 consecutive routine needle biopsy specimens with cancer showed glomeruloid features, and this pattern constituted 5% to 10% of each cancer (mean, 6.7%). The Gleason score was 6 for two cases and 8 for one case. Two cases were associated with high-grade prostatic intraepithelial neoplasia, and one case had perineural invasion. Glomeruloid features were not observed in any benign or

Feature extraction using fractal codes

NARCIS (Netherlands)

B.A.M. Ben Schouten; Paul M. de Zeeuw

1999-01-01

Fast and successful searching for an object in a multimedia database is a highly desirable functionality. Several approaches to content based retrieval for multimedia databases can be found in the literature [9,10,12,14,17]. The approach we consider is feature extraction. A feature can be seen as a

Iris recognition based on key image feature extraction.

Science.gov (United States)

Ren, X; Tian, Q; Zhang, J; Wu, S; Zeng, Y

2008-01-01

In iris recognition, feature extraction can be influenced by factors such as illumination and contrast, and thus the features extracted may be unreliable, which can cause a high rate of false results in iris pattern recognition. In order to obtain stable features, an algorithm was proposed in this paper to extract key features of a pattern from multiple images. The proposed algorithm built an iris feature template by extracting key features and performed iris identity enrolment. Simulation results showed that the selected key features have high recognition accuracy on the CASIA Iris Set, where both contrast and illumination variance exist.

Vehicle barriers: emphasis on natural features

International Nuclear Information System (INIS)

Adams, K.G.; Roscoe, B.J.

1985-07-01

The recent increase in the use of car and truck bombs by terrorist organizations has led NRC to evaluate the adequacy of licensee security against such threats. As part of this evaluation, one of the factors is the effectiveness of terrain and vegetation in providing barriers against the vehicle entry. The effectiveness of natural features is presented in two contexts. First, certain natural features are presented. Second, the effectiveness of combinations of features is presented. In addition to the discussion of natural features, this report provides a discussion of methods to slow vehicles. Also included is an overview of man-made barrier systems, with particular attention to ditches. 17 refs., 49 figs

Contextual Multi-armed Bandits under Feature Uncertainty

Energy Technology Data Exchange (ETDEWEB)

Yun, Seyoung [Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Nam, Jun Hyun [Korea Advanced Inst. Science and Technology (KAIST), Daejeon (Korea, Republic of); Mo, Sangwoo [Korea Advanced Inst. Science and Technology (KAIST), Daejeon (Korea, Republic of); Shin, Jinwoo [Korea Advanced Inst. Science and Technology (KAIST), Daejeon (Korea, Republic of)

2017-03-03

We study contextual multi-armed bandit problems under linear realizability on rewards and uncertainty (or noise) on features. For the case of identical noise on features across actions, we propose an algorithm, coined NLinRel, having O(T⁷/₈(log(dT)+K√d)) regret bound for T rounds, K actions, and d-dimensional feature vectors. Next, for the case of non-identical noise, we observe that popular linear hypotheses including NLinRel are impossible to achieve such sub-linear regret. Instead, under assumption of Gaussian feature vectors, we prove that a greedy algorithm has O(T²/₃√log d)regret bound with respect to the optimal linear hypothesis. Utilizing our theoretical understanding on the Gaussian case, we also design a practical variant of NLinRel, coined Universal-NLinRel, for arbitrary feature distributions. It first runs NLinRel for finding the ‘true’ coefficient vector using feature uncertainties and then adjust it to minimize its regret using the statistical feature information. We justify the performance of Universal-NLinRel on both synthetic and real-world datasets.

Unsupervised feature learning for autonomous rock image classification

Science.gov (United States)

Shu, Lei; McIsaac, Kenneth; Osinski, Gordon R.; Francis, Raymond

2017-09-01

Autonomous rock image classification can enhance the capability of robots for geological detection and enlarge the scientific returns, both in investigation on Earth and planetary surface exploration on Mars. Since rock textural images are usually inhomogeneous and manually hand-crafting features is not always reliable, we propose an unsupervised feature learning method to autonomously learn the feature representation for rock images. In our tests, rock image classification using the learned features shows that the learned features can outperform manually selected features. Self-taught learning is also proposed to learn the feature representation from a large database of unlabelled rock images of mixed class. The learned features can then be used repeatedly for classification of any subclass. This takes advantage of the large dataset of unlabelled rock images and learns a general feature representation for many kinds of rocks. We show experimental results supporting the feasibility of self-taught learning on rock images.

Naive Bayes-Guided Bat Algorithm for Feature Selection

Directory of Open Access Journals (Sweden)

Ahmed Majid Taha

2013-01-01

Full Text Available When the amount of data and information is said to double in every 20 months or so, feature selection has become highly important and beneficial. Further improvements in feature selection will positively affect a wide array of applications in fields such as pattern recognition, machine learning, or signal processing. Bio-inspired method called Bat Algorithm hybridized with a Naive Bayes classifier has been presented in this work. The performance of the proposed feature selection algorithm was investigated using twelve benchmark datasets from different domains and was compared to three other well-known feature selection algorithms. Discussion focused on four perspectives: number of features, classification accuracy, stability, and feature generalization. The results showed that BANB significantly outperformed other algorithms in selecting lower number of features, hence removing irrelevant, redundant, or noisy features while maintaining the classification accuracy. BANB is also proven to be more stable than other methods and is capable of producing more general feature subsets.

Naive Bayes-Guided Bat Algorithm for Feature Selection

Science.gov (United States)

Taha, Ahmed Majid; Mustapha, Aida; Chen, Soong-Der

2013-01-01

When the amount of data and information is said to double in every 20 months or so, feature selection has become highly important and beneficial. Further improvements in feature selection will positively affect a wide array of applications in fields such as pattern recognition, machine learning, or signal processing. Bio-inspired method called Bat Algorithm hybridized with a Naive Bayes classifier has been presented in this work. The performance of the proposed feature selection algorithm was investigated using twelve benchmark datasets from different domains and was compared to three other well-known feature selection algorithms. Discussion focused on four perspectives: number of features, classification accuracy, stability, and feature generalization. The results showed that BANB significantly outperformed other algorithms in selecting lower number of features, hence removing irrelevant, redundant, or noisy features while maintaining the classification accuracy. BANB is also proven to be more stable than other methods and is capable of producing more general feature subsets. PMID:24396295

Less common CT features of medulloblastoma

International Nuclear Information System (INIS)

Zee, C.S; Segall, H.D.; Miller, C.; Ahmad, J.; McComb, J.G.; Han, J.S.; Park, S.H.

1982-01-01

While many medulloblastomas have characteristic features on computed tomography (CT), a significant number have atypical features, including a cystic or necrotic component, calcification, hemorrhage, lack of contrast enhancement, and eccentric location, and/or direct supratentorial extension. Of 30 consecutive untreated cases reviewed by the authors, 14 (47%) had such findings. Failure to make the proper diagnosis will result in some cases if these features are not recognized as possible signs of medulloblastoma

Improving scale invariant feature transform-based descriptors with shape-color alliance robust feature

Science.gov (United States)

Wang, Rui; Zhu, Zhengdan; Zhang, Liang

2015-05-01

Constructing appropriate descriptors for interest points in image matching is a critical aspect task in computer vision and pattern recognition. A method as an extension of the scale invariant feature transform (SIFT) descriptor called shape-color alliance robust feature (SCARF) descriptor is presented. To address the problem that SIFT is designed mainly for gray images and lack of global information for feature points, the proposed approach improves the SIFT descriptor by means of a concentric-rings model, as well as integrating the color invariant space and shape context with SIFT to construct the SCARF descriptor. The SCARF method developed is more robust than the conventional SIFT with respect to not only the color and photometrical variations but also the measuring similarity as a global variation between two shapes. A comparative evaluation of different descriptors is carried out showing that the SCARF approach provides better results than the other four state-of-the-art related methods.

Discriminative semi-supervised feature selection via manifold regularization.

Science.gov (United States)

Xu, Zenglin; King, Irwin; Lyu, Michael Rung-Tsong; Jin, Rong

2010-07-01

Feature selection has attracted a huge amount of interest in both research and application communities of data mining. We consider the problem of semi-supervised feature selection, where we are given a small amount of labeled examples and a large amount of unlabeled examples. Since a small number of labeled samples are usually insufficient for identifying the relevant features, the critical problem arising from semi-supervised feature selection is how to take advantage of the information underneath the unlabeled data. To address this problem, we propose a novel discriminative semi-supervised feature selection method based on the idea of manifold regularization. The proposed approach selects features through maximizing the classification margin between different classes and simultaneously exploiting the geometry of the probability distribution that generates both labeled and unlabeled data. In comparison with previous semi-supervised feature selection algorithms, our proposed semi-supervised feature selection method is an embedded feature selection method and is able to find more discriminative features. We formulate the proposed feature selection method into a convex-concave optimization problem, where the saddle point corresponds to the optimal solution. To find the optimal solution, the level method, a fairly recent optimization method, is employed. We also present a theoretic proof of the convergence rate for the application of the level method to our problem. Empirical evaluation on several benchmark data sets demonstrates the effectiveness of the proposed semi-supervised feature selection method.

Feature Evaluation for Building Facade Images - AN Empirical Study

Science.gov (United States)

Yang, M. Y.; Förstner, W.; Chai, D.

2012-08-01

The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.

Schizophrenia classification using functional network features

Science.gov (United States)

Rish, Irina; Cecchi, Guillermo A.; Heuton, Kyle

2012-03-01

This paper focuses on discovering statistical biomarkers (features) that are predictive of schizophrenia, with a particular focus on topological properties of fMRI functional networks. We consider several network properties, such as node (voxel) strength, clustering coefficients, local efficiency, as well as just a subset of pairwise correlations. While all types of features demonstrate highly significant statistical differences in several brain areas, and close to 80% classification accuracy, the most remarkable results of 93% accuracy are achieved by using a small subset of only a dozen of most-informative (lowest p-value) correlation features. Our results suggest that voxel-level correlations and functional network features derived from them are highly informative about schizophrenia and can be used as statistical biomarkers for the disease.

Classification Using Markov Blanket for Feature Selection

DEFF Research Database (Denmark)

Zeng, Yifeng; Luo, Jian

2009-01-01

Selecting relevant features is in demand when a large data set is of interest in a classification task. It produces a tractable number of features that are sufficient and possibly improve the classification performance. This paper studies a statistical method of Markov blanket induction algorithm...... for filtering features and then applies a classifier using the Markov blanket predictors. The Markov blanket contains a minimal subset of relevant features that yields optimal classification performance. We experimentally demonstrate the improved performance of several classifiers using a Markov blanket...... induction as a feature selection method. In addition, we point out an important assumption behind the Markov blanket induction algorithm and show its effect on the classification performance....

Hierarchical feature selection for erythema severity estimation

Science.gov (United States)

Wang, Li; Shi, Chenbo; Shu, Chang

2014-10-01

At present PASI system of scoring is used for evaluating erythema severity, which can help doctors to diagnose psoriasis [1-3]. The system relies on the subjective judge of doctors, where the accuracy and stability cannot be guaranteed [4]. This paper proposes a stable and precise algorithm for erythema severity estimation. Our contributions are twofold. On one hand, in order to extract the multi-scale redness of erythema, we design the hierarchical feature. Different from traditional methods, we not only utilize the color statistical features, but also divide the detect window into small window and extract hierarchical features. Further, a feature re-ranking step is introduced, which can guarantee that extracted features are irrelevant to each other. On the other hand, an adaptive boosting classifier is applied for further feature selection. During the step of training, the classifier will seek out the most valuable feature for evaluating erythema severity, due to its strong learning ability. Experimental results demonstrate the high precision and robustness of our algorithm. The accuracy is 80.1% on the dataset which comprise 116 patients' images with various kinds of erythema. Now our system has been applied for erythema medical efficacy evaluation in Union Hosp, China.

Discriminating Induced-Microearthquakes Using New Seismic Features

Science.gov (United States)

Mousavi, S. M.; Horton, S.

2016-12-01

We studied characteristics of induced-microearthquakes on the basis of the waveforms recorded on a limited number of surface receivers using machine-learning techniques. Forty features in the time, frequency, and time-frequency domains were measured on each waveform, and several techniques such as correlation-based feature selection, Artificial Neural Networks (ANNs), Logistic Regression (LR) and X-mean were used as research tools to explore the relationship between these seismic features and source parameters. The results show that spectral features have the highest correlation to source depth. Two new measurements developed as seismic features for this study, spectral centroids and 2D cross-correlations in the time-frequency domain, performed better than the common seismic measurements. These features can be used by machine learning techniques for efficient automatic classification of low energy signals recorded at one or more seismic stations. We applied the technique to 440 microearthquakes-1.7Reference: Mousavi, S.M., S.P. Horton, C. A. Langston, B. Samei, (2016) Seismic features and automatic discrimination of deep and shallow induced-microearthquakes using neural network and logistic regression, Geophys. J. Int. doi: 10.1093/gji/ggw258.

Effective Feature Preprocessing for Time Series Forecasting

DEFF Research Database (Denmark)

Zhao, Junhua; Dong, Zhaoyang; Xu, Zhao

2006-01-01

Time series forecasting is an important area in data mining research. Feature preprocessing techniques have significant influence on forecasting accuracy, therefore are essential in a forecasting model. Although several feature preprocessing techniques have been applied in time series forecasting...... performance in time series forecasting. It is demonstrated in our experiment that, effective feature preprocessing can significantly enhance forecasting accuracy. This research can be a useful guidance for researchers on effectively selecting feature preprocessing techniques and integrating them with time...... series forecasting models....

Feature-specific encoding flexibility in visual working memory.

Directory of Open Access Journals (Sweden)

Aki Kondo

Full Text Available The current study examined selective encoding in visual working memory by systematically investigating interference from task-irrelevant features. The stimuli were objects defined by three features (color, shape, and location, and during a delay period, any of the features could switch between two objects. Additionally, single- and whole-probe trials were randomized within experimental blocks to investigate effects of memory retrieval. A series of relevant-feature switch detection tasks, where one feature was task-irrelevant, showed that interference from the task-irrelevant feature was only observed in the color-shape task, suggesting that color and shape information could be successfully filtered out, but location information could not, even when location was a task-irrelevant feature. Therefore, although location information is added to object representations independent of task demands in a relatively automatic manner, other features (e.g., color, shape can be flexibly added to object representations.

Feature-specific encoding flexibility in visual working memory.

Science.gov (United States)

Kondo, Aki; Saiki, Jun

2012-01-01

The current study examined selective encoding in visual working memory by systematically investigating interference from task-irrelevant features. The stimuli were objects defined by three features (color, shape, and location), and during a delay period, any of the features could switch between two objects. Additionally, single- and whole-probe trials were randomized within experimental blocks to investigate effects of memory retrieval. A series of relevant-feature switch detection tasks, where one feature was task-irrelevant, showed that interference from the task-irrelevant feature was only observed in the color-shape task, suggesting that color and shape information could be successfully filtered out, but location information could not, even when location was a task-irrelevant feature. Therefore, although location information is added to object representations independent of task demands in a relatively automatic manner, other features (e.g., color, shape) can be flexibly added to object representations.

EEG feature selection method based on decision tree.

Science.gov (United States)

Duan, Lijuan; Ge, Hui; Ma, Wei; Miao, Jun

2015-01-01

This paper aims to solve automated feature selection problem in brain computer interface (BCI). In order to automate feature selection process, we proposed a novel EEG feature selection method based on decision tree (DT). During the electroencephalogram (EEG) signal processing, a feature extraction method based on principle component analysis (PCA) was used, and the selection process based on decision tree was performed by searching the feature space and automatically selecting optimal features. Considering that EEG signals are a series of non-linear signals, a generalized linear classifier named support vector machine (SVM) was chosen. In order to test the validity of the proposed method, we applied the EEG feature selection method based on decision tree to BCI Competition II datasets Ia, and the experiment showed encouraging results.

Text feature extraction based on deep learning: a review.

Science.gov (United States)

Liang, Hong; Sun, Xiao; Sun, Yunlei; Gao, Yuan

2017-01-01

Selection of text feature item is a basic and important matter for text mining and information retrieval. Traditional methods of feature extraction require handcrafted features. To hand-design, an effective feature is a lengthy process, but aiming at new applications, deep learning enables to acquire new effective feature representation from training data. As a new feature extraction method, deep learning has made achievements in text mining. The major difference between deep learning and conventional methods is that deep learning automatically learns features from big data, instead of adopting handcrafted features, which mainly depends on priori knowledge of designers and is highly impossible to take the advantage of big data. Deep learning can automatically learn feature representation from big data, including millions of parameters. This thesis outlines the common methods used in text feature extraction first, and then expands frequently used deep learning methods in text feature extraction and its applications, and forecasts the application of deep learning in feature extraction.

The Non-motor Features of Essential Tremor: A Primary Disease Feature or Just a Secondary Phenomenon?

Directory of Open Access Journals (Sweden)

Ketan Jhunjhunwala

2014-08-01

Full Text Available Essential tremor (ET is a pathologically heterogeneous neurodegenerative disorder with both motor and increasingly recognized non-motor features. It is debated whether the non-motor manifestations in ET result from widespread neurodegeneration or are merely secondary to impaired motor functions and decreased quality of life due to tremor. It is important to review these features to determine how to best treat the non-motor symptoms of patients and to understand the basic pathophysiology of the disease and develop appropriate pharmacotherapies. In this review, retrospective and prospective clinical studies were critically analyzed to identify possible correlations between the severities of non-motor features and tremor. We speculated that if such a correlation existed, the non-motor features were likely to be secondary to tremor. According to the current literature, the deficits in executive function, attention, concentration, and memory often observed in ET are likely to be a primary manifestation of the disease. It has also been documented that patients with ET often exhibit characteristic personality traits. However, it remains to be determined whether the other non-motor features often seen in ET, such as anxiety, depression, and sleep disturbances are primary or secondary to motor manifestations of ET and subsequent poor quality of life. Finally, there is evidence that patients with ET can also have impaired color vision, disturbances of olfaction, and hearing impairments, though there are few studies in these areas. Further investigations of large cohorts of patients with ET are required to understand the prevalence, nature, and true significance of the non-motor features in ET.

CT features of renal epithelioid angiomyolipomas

International Nuclear Information System (INIS)

Hu Xiaoyun; Fang Xiangming; Hu Chunhong; Chen Hongwei; Cui Lei; Bao Jian; Yao Xuanjun

2010-01-01

Objective: To explore the CT and pathological features of renal epithelioid angiomyolipoma (EAML). Methods: Clinical data and CT images from ten cases with EAML proved by surgery and pathology were retrospectively analyzed. All cases were performed with plain and contrast enhanced CT scans. Results: CT features: higher pre-contrasted density than kidney, bulging from kidney, absent of fat, markedly heterogeneous enhancement (quick wash-in and slow wash-out), big size without lobular sign, complete capsule with clear margin and mild necrostic area. Pathological features: diffuse sheets of epithelioid cells were found under microscopy with immunohistochemistrical findings including positivity for HMB-45 and negativity for EMA. Conclusion: Some specific CT features, which is correlated well with the pathological findings, provide helpful information in the primary diagnosis of EAML. (authors)

Feature Extraction in Radar Target Classification

Directory of Open Access Journals (Sweden)

Z. Kus

1999-09-01

Full Text Available This paper presents experimental results of extracting features in the Radar Target Classification process using the J frequency band pulse radar. The feature extraction is based on frequency analysis methods, the discrete-time Fourier Transform (DFT and Multiple Signal Characterisation (MUSIC, based on the detection of Doppler effect. The analysis has turned to the preference of DFT with implemented Hanning windowing function. We assumed to classify targets-vehicles into two classes, the wheeled vehicle and tracked vehicle. The results show that it is possible to classify them only while moving. The feature of the class results from a movement of moving parts of the vehicle. However, we have not found any feature to classify the wheeled and tracked vehicles while non-moving, although their engines are on.

Review of research in feature based design

NARCIS (Netherlands)

Salomons, O.W.; van Houten, Frederikus J.A.M.; Kals, H.J.J.

1993-01-01

Research in feature-based design is reviewed. Feature-based design is regarded as a key factor towards CAD/CAPP integration from a process planning point of view. From a design point of view, feature-based design offers possibilities for supporting the design process better than current CAD systems

Genetic search feature selection for affective modeling

DEFF Research Database (Denmark)

Martínez, Héctor P.; Yannakakis, Georgios N.

2010-01-01

Automatic feature selection is a critical step towards the generation of successful computational models of affect. This paper presents a genetic search-based feature selection method which is developed as a global-search algorithm for improving the accuracy of the affective models built....... The method is tested and compared against sequential forward feature selection and random search in a dataset derived from a game survey experiment which contains bimodal input features (physiological and gameplay) and expressed pairwise preferences of affect. Results suggest that the proposed method...

Feature Scaling via Second-Order Cone Programming

Directory of Open Access Journals (Sweden)

Zhizheng Liang

2016-01-01

Full Text Available Feature scaling has attracted considerable attention during the past several decades because of its important role in feature selection. In this paper, a novel algorithm for learning scaling factors of features is proposed. It first assigns a nonnegative scaling factor to each feature of data and then adopts a generalized performance measure to learn the optimal scaling factors. It is of interest to note that the proposed model can be transformed into a convex optimization problem: second-order cone programming (SOCP. Thus the scaling factors of features in our method are globally optimal in some sense. Several experiments on simulated data, UCI data sets, and the gene data set are conducted to demonstrate that the proposed method is more effective than previous methods.

Shielding voices: The modulation of binding processes between voice features and response features by task representations.

Science.gov (United States)

Bogon, Johanna; Eisenbarth, Hedwig; Landgraf, Steffen; Dreisbach, Gesine

2017-09-01

Vocal events offer not only semantic-linguistic content but also information about the identity and the emotional-motivational state of the speaker. Furthermore, most vocal events have implications for our actions and therefore include action-related features. But the relevance and irrelevance of vocal features varies from task to task. The present study investigates binding processes for perceptual and action-related features of spoken words and their modulation by the task representation of the listener. Participants reacted with two response keys to eight different words spoken by a male or a female voice (Experiment 1) or spoken by an angry or neutral male voice (Experiment 2). There were two instruction conditions: half of participants learned eight stimulus-response mappings by rote (SR), and half of participants applied a binary task rule (TR). In both experiments, SR instructed participants showed clear evidence for binding processes between voice and response features indicated by an interaction between the irrelevant voice feature and the response. By contrast, as indicated by a three-way interaction with instruction, no such binding was found in the TR instructed group. These results are suggestive of binding and shielding as two adaptive mechanisms that ensure successful communication and action in a dynamic social environment.

Integrated Phoneme Subspace Method for Speech Feature Extraction

Directory of Open Access Journals (Sweden)

Park Hyunsin

2009-01-01

Full Text Available Speech feature extraction has been a key focus in robust speech recognition research. In this work, we discuss data-driven linear feature transformations applied to feature vectors in the logarithmic mel-frequency filter bank domain. Transformations are based on principal component analysis (PCA, independent component analysis (ICA, and linear discriminant analysis (LDA. Furthermore, this paper introduces a new feature extraction technique that collects the correlation information among phoneme subspaces and reconstructs feature space for representing phonemic information efficiently. The proposed speech feature vector is generated by projecting an observed vector onto an integrated phoneme subspace (IPS based on PCA or ICA. The performance of the new feature was evaluated for isolated word speech recognition. The proposed method provided higher recognition accuracy than conventional methods in clean and reverberant environments.

Does Attention Serve to Integrate Features?

Science.gov (United States)

Navon, David; Treisman, Anne

1990-01-01

An article and two commentaries consider the attentional feature-integration theory proposed by A. Treisman and colleagues. Hypotheses about the encoding of conjunctions are reviewed. Whether or not data support perceptual feature-integration is argued. (SLD)

14 CFR 35.7 - Features and characteristics.

Science.gov (United States)

2010-01-01

... 14 Aeronautics and Space 1 2010-01-01 2010-01-01 false Features and characteristics. 35.7 Section... AIRWORTHINESS STANDARDS: PROPELLERS General § 35.7 Features and characteristics. (a) The propeller may not have features or characteristics, revealed by any test or analysis or known to the applicant, that make it...

Finger vein recognition based on the hyperinformation feature

Science.gov (United States)

Xi, Xiaoming; Yang, Gongping; Yin, Yilong; Yang, Lu

2014-01-01

The finger vein is a promising biometric pattern for personal identification due to its advantages over other existing biometrics. In finger vein recognition, feature extraction is a critical step, and many feature extraction methods have been proposed to extract the gray, texture, or shape of the finger vein. We treat them as low-level features and present a high-level feature extraction framework. Under this framework, base attribute is first defined to represent the characteristics of a certain subcategory of a subject. Then, for an image, the correlation coefficient is used for constructing the high-level feature, which reflects the correlation between this image and all base attributes. Since the high-level feature can reveal characteristics of more subcategories and contain more discriminative information, we call it hyperinformation feature (HIF). Compared with low-level features, which only represent the characteristics of one subcategory, HIF is more powerful and robust. In order to demonstrate the potential of the proposed framework, we provide a case study to extract HIF. We conduct comprehensive experiments to show the generality of the proposed framework and the efficiency of HIF on our databases, respectively. Experimental results show that HIF significantly outperforms the low-level features.

Multi-scale salient feature extraction on mesh models

KAUST Repository

Yang, Yongliang; Shen, ChaoHui

2012-01-01

We present a new method of extracting multi-scale salient features on meshes. It is based on robust estimation of curvature on multiple scales. The coincidence between salient feature and the scale of interest can be established straightforwardly, where detailed feature appears on small scale and feature with more global shape information shows up on large scale. We demonstrate this multi-scale description of features accords with human perception and can be further used for several applications as feature classification and viewpoint selection. Experiments exhibit that our method as a multi-scale analysis tool is very helpful for studying 3D shapes. © 2012 Springer-Verlag.

Passive Safety Features for Small Modular Reactors

International Nuclear Information System (INIS)

Ingersoll, Daniel T.

2010-01-01

The rapid growth in the size and complexity of commercial nuclear power plants in the 1970s spawned an interest in smaller, simpler designs that are inherently or intrinsically safe through the use of passive design features. Several designs were developed, but none were ever built, although some of their passive safety features were incorporated into large commercial plant designs that are being planned or built today. In recent years, several reactor vendors are actively redeveloping small modular reactor (SMR) designs with even greater use of passive features. Several designs incorporate the ultimate in passive safety they completely eliminate specific accident initiators from the design. Other design features help to reduce the likelihood of an accident or help to mitigate the accidents consequences, should one occur. While some passive safety features are common to most SMR designs, irrespective of the coolant technology, other features are specific to water, gas, or liquid-metal cooled SMR designs. The extensive use of passive safety features in SMRs promise to make these plants highly robust, protecting both the general public and the owner/investor. Once demonstrated, these plants should allow nuclear power to be used confidently for a broader range of customers and applications than will be possible with large plants alone.

Effective traffic features selection algorithm for cyber-attacks samples

Science.gov (United States)

Li, Yihong; Liu, Fangzheng; Du, Zhenyu

2018-05-01

By studying the defense scheme of Network attacks, this paper propose an effective traffic features selection algorithm based on k-means++ clustering to deal with the problem of high dimensionality of traffic features which extracted from cyber-attacks samples. Firstly, this algorithm divide the original feature set into attack traffic feature set and background traffic feature set by the clustering. Then, we calculates the variation of clustering performance after removing a certain feature. Finally, evaluating the degree of distinctiveness of the feature vector according to the result. Among them, the effective feature vector is whose degree of distinctiveness exceeds the set threshold. The purpose of this paper is to select out the effective features from the extracted original feature set. In this way, it can reduce the dimensionality of the features so as to reduce the space-time overhead of subsequent detection. The experimental results show that the proposed algorithm is feasible and it has some advantages over other selection algorithms.

Prominent feature extraction for review analysis: an empirical study

Science.gov (United States)

Agarwal, Basant; Mittal, Namita

2016-05-01

Sentiment analysis (SA) research has increased tremendously in recent times. SA aims to determine the sentiment orientation of a given text into positive or negative polarity. Motivation for SA research is the need for the industry to know the opinion of the users about their product from online portals, blogs, discussion boards and reviews and so on. Efficient features need to be extracted for machine-learning algorithm for better sentiment classification. In this paper, initially various features are extracted such as unigrams, bi-grams and dependency features from the text. In addition, new bi-tagged features are also extracted that conform to predefined part-of-speech patterns. Furthermore, various composite features are created using these features. Information gain (IG) and minimum redundancy maximum relevancy (mRMR) feature selection methods are used to eliminate the noisy and irrelevant features from the feature vector. Finally, machine-learning algorithms are used for classifying the review document into positive or negative class. Effects of different categories of features are investigated on four standard data-sets, namely, movie review and product (book, DVD and electronics) review data-sets. Experimental results show that composite features created from prominent features of unigram and bi-tagged features perform better than other features for sentiment classification. mRMR is a better feature selection method as compared with IG for sentiment classification. Boolean Multinomial Naïve Bayes) algorithm performs better than support vector machine classifier for SA in terms of accuracy and execution time.

MCNP4A: Features and philosophy

International Nuclear Information System (INIS)

Hendricks, J.S.

1993-01-01

This paper describes MCNP, states its philosophy, introduces a number of new features becoming available with version MCNP4A, and answers a number of questions asked by participants in the workshop. MCNP is a general-purpose three-dimensional neutron, photon and electron transport code. Its philosophy is ''Quality, Value and New Features.'' Quality is exemplified by new software quality assurance practices and a program of benchmarking against experiments. Value includes a strong emphasis on documentation and code portability. New features are the third priority. MCNP4A is now available at Los Alamos. New features in MCNP4A include enhanced statistical analysis, distributed processor multitasking, new photon libraries, ENDF/B-VI capabilities, X-Windows graphics, dynamic memory allocation, expanded criticality output, periodic boundaries, plotting of particle tracks via SABRINA, and many other improvements. 23 refs

Interplay of a multiplicity of security features

Science.gov (United States)

Moser, Jean-Frederic

2000-04-01

The great variety of existing security features can cause difficulty in choosing the adequate set for a particular security document. Considering the cost/benefit aspects with respect to the overall protection performance requested, a choice has to be made, for example, between either few features of high-security value or numerous many, less- resistant features. Another choice is the high versus low complexity of one particular features. A study aimed at providing a decision basis is a challenging matter because it involves human factors. Attention, perception, physiology of seeing and habits - to name some of the factors - are intangibles and are subject to evaluations involving normally a great number of experiments, if they are to be representative. The opportunity was given for a case study with the introduction of new Swiss banknotes between 1995 and 1998, because the new banknotes represent a novelty in the sense of the multiplicity and interplay of its optical security features. We have analyzed 652 articles which appeared in the press media concerning the new banknotes, seeking especially for peoples' reaction towards the security features.

Feature Vector Construction Method for IRIS Recognition

Science.gov (United States)

Odinokikh, G.; Fartukov, A.; Korobkin, M.; Yoo, J.

2017-05-01

One of the basic stages of iris recognition pipeline is iris feature vector construction procedure. The procedure represents the extraction of iris texture information relevant to its subsequent comparison. Thorough investigation of feature vectors obtained from iris showed that not all the vector elements are equally relevant. There are two characteristics which determine the vector element utility: fragility and discriminability. Conventional iris feature extraction methods consider the concept of fragility as the feature vector instability without respect to the nature of such instability appearance. This work separates sources of the instability into natural and encodinginduced which helps deeply investigate each source of instability independently. According to the separation concept, a novel approach of iris feature vector construction is proposed. The approach consists of two steps: iris feature extraction using Gabor filtering with optimal parameters and quantization with separated preliminary optimized fragility thresholds. The proposed method has been tested on two different datasets of iris images captured under changing environmental conditions. The testing results show that the proposed method surpasses all the methods considered as a prior art by recognition accuracy on both datasets.

Disruption of visual feature binding in working memory.

Science.gov (United States)

Ueno, Taiji; Allen, Richard J; Baddeley, Alan D; Hitch, Graham J; Saito, Satoru

2011-01-01

In a series of five experiments, we studied the effect of a visual suffix on the retention in short-term visual memory of both individual visual features and objects involving the binding of two features. Experiments 1A, 1B, and 2 involved suffixes consisting of features external to the to-be-remembered set and revealed a modest but equivalent disruption on individual and bound feature conditions. Experiments 3A and 3B involved suffixes comprising features that could potentially have formed part of the to-be-remembered set (but did not on that trial). Both experiments showed greater disruption of retention for objects comprising bound features than for their individual features. The results are interpreted as differentiating two components of suffix interference, one affecting memory for features and bindings equally, the other affecting memory for bindings. The general component is tentatively identified with the attentional cost of operating a filter to prevent the suffix from entering visual working memory, whereas the specific component is attributed to the particular fragility of bound representations when the filter fails.

Feature-based Alignment of Volumetric Multi-modal Images

Science.gov (United States)

Toews, Matthew; Zöllei, Lilla; Wells, William M.

2014-01-01

This paper proposes a method for aligning image volumes acquired from different imaging modalities (e.g. MR, CT) based on 3D scale-invariant image features. A novel method for encoding invariant feature geometry and appearance is developed, based on the assumption of locally linear intensity relationships, providing a solution to poor repeatability of feature detection in different image modalities. The encoding method is incorporated into a probabilistic feature-based model for multi-modal image alignment. The model parameters are estimated via a group-wise alignment algorithm, that iteratively alternates between estimating a feature-based model from feature data, then realigning feature data to the model, converging to a stable alignment solution with few pre-processing or pre-alignment requirements. The resulting model can be used to align multi-modal image data with the benefits of invariant feature correspondence: globally optimal solutions, high efficiency and low memory usage. The method is tested on the difficult RIRE data set of CT, T1, T2, PD and MP-RAGE brain images of subjects exhibiting significant inter-subject variability due to pathology. PMID:24683955

Feature-Oriented Programming with Object Algebras

NARCIS (Netherlands)

B.C.d.S. Oliveira (Bruno); T. van der Storm (Tijs); A. Loh; W.R. Cook

2013-01-01

htmlabstractObject algebras are a new programming technique that enables a simple solution to basic extensibility and modularity issues in programming languages. While object algebras excel at defining modular features, the composition mechanisms for object algebras (and features) are still

Biometric feature extraction using local fractal auto-correlation

International Nuclear Information System (INIS)

Chen Xi; Zhang Jia-Shu

2014-01-01

Image texture feature extraction is a classical means for biometric recognition. To extract effective texture feature for matching, we utilize local fractal auto-correlation to construct an effective image texture descriptor. Three main steps are involved in the proposed scheme: (i) using two-dimensional Gabor filter to extract the texture features of biometric images; (ii) calculating the local fractal dimension of Gabor feature under different orientations and scales using fractal auto-correlation algorithm; and (iii) linking the local fractal dimension of Gabor feature under different orientations and scales into a big vector for matching. Experiments and analyses show our proposed scheme is an efficient biometric feature extraction approach. (condensed matter: structural, mechanical, and thermal properties)

Image feature detectors and descriptors foundations and applications

CERN Document Server

Hassaballah, Mahmoud

2016-01-01

This book provides readers with a selection of high-quality chapters that cover both theoretical concepts and practical applications of image feature detectors and descriptors. It serves as reference for researchers and practitioners by featuring survey chapters and research contributions on image feature detectors and descriptors. Additionally, it emphasizes several keywords in both theoretical and practical aspects of image feature extraction. The keywords include acceleration of feature detection and extraction, hardware implantations, image segmentation, evolutionary algorithm, ordinal measures, as well as visual speech recognition. .

Organization Features and School Performance

OpenAIRE

Atkins, Lois Major

2005-01-01

The purpose of this study was to determine the odds of school organization features predicting schools meeting district or state performance goals. The school organization features were organizational complexity, shared decision making, and leadership behavior. The dependent variable was school performance, operationally defined as a principalâ s yes response or no response to the question, â did your school meet district or state performance goals.â The independent variables representing...

Designing attractive gamification features for collaborative storytelling websites.

Science.gov (United States)

Hsu, Shang Hwa; Chang, Jen-Wei; Lee, Chun-Chia

2013-06-01

Gamification design is considered as the predictor of collaborative storytelling websites' success. Although aforementioned studies have mentioned a broad range of factors that may influence gamification, they neither depicted the actual design features nor relative attractiveness among them. This study aims to identify attractive gamification features for collaborative storytelling websites. We first constructed a hierarchical system structure of gamification design of collaborative storytelling websites and conducted a focus group interview with eighteen frequent users to identify 35gamification features. After that, this study determined the relative attractiveness of these gamification features by administrating an online survey to 6333 collaborative storytelling websites users. The results indicated that the top 10 most attractive gamification features could account for more than 50% of attractiveness among these 35 gamification features. The feature of unpredictable time pressure is important to website users, yet not revealed in previous relevant studies. Implications of the findings were discussed.

Discovering highly informative feature set over high dimensions

KAUST Repository

Zhang, Chongsheng; Masseglia, Florent; Zhang, Xiangliang

2012-01-01

For many textual collections, the number of features is often overly large. These features can be very redundant, it is therefore desirable to have a small, succinct, yet highly informative collection of features that describes the key characteristics of a dataset. Information theory is one such tool for us to obtain this feature collection. With this paper, we mainly contribute to the improvement of efficiency for the process of selecting the most informative feature set over high-dimensional unlabeled data. We propose a heuristic theory for informative feature set selection from high dimensional data. Moreover, we design data structures that enable us to compute the entropies of the candidate feature sets efficiently. We also develop a simple pruning strategy that eliminates the hopeless candidates at each forward selection step. We test our method through experiments on real-world data sets, showing that our proposal is very efficient. © 2012 IEEE.

Discovering highly informative feature set over high dimensions

KAUST Repository

Zhang, Chongsheng

2012-11-01

For many textual collections, the number of features is often overly large. These features can be very redundant, it is therefore desirable to have a small, succinct, yet highly informative collection of features that describes the key characteristics of a dataset. Information theory is one such tool for us to obtain this feature collection. With this paper, we mainly contribute to the improvement of efficiency for the process of selecting the most informative feature set over high-dimensional unlabeled data. We propose a heuristic theory for informative feature set selection from high dimensional data. Moreover, we design data structures that enable us to compute the entropies of the candidate feature sets efficiently. We also develop a simple pruning strategy that eliminates the hopeless candidates at each forward selection step. We test our method through experiments on real-world data sets, showing that our proposal is very efficient. © 2012 IEEE.

Feature Selection for Chemical Sensor Arrays Using Mutual Information

Science.gov (United States)

Wang, X. Rosalind; Lizier, Joseph T.; Nowotny, Thomas; Berna, Amalia Z.; Prokopenko, Mikhail; Trowell, Stephen C.

2014-01-01

We address the problem of feature selection for classifying a diverse set of chemicals using an array of metal oxide sensors. Our aim is to evaluate a filter approach to feature selection with reference to previous work, which used a wrapper approach on the same data set, and established best features and upper bounds on classification performance. We selected feature sets that exhibit the maximal mutual information with the identity of the chemicals. The selected features closely match those found to perform well in the previous study using a wrapper approach to conduct an exhaustive search of all permitted feature combinations. By comparing the classification performance of support vector machines (using features selected by mutual information) with the performance observed in the previous study, we found that while our approach does not always give the maximum possible classification performance, it always selects features that achieve classification performance approaching the optimum obtained by exhaustive search. We performed further classification using the selected feature set with some common classifiers and found that, for the selected features, Bayesian Networks gave the best performance. Finally, we compared the observed classification performances with the performance of classifiers using randomly selected features. We found that the selected features consistently outperformed randomly selected features for all tested classifiers. The mutual information filter approach is therefore a computationally efficient method for selecting near optimal features for chemical sensor arrays. PMID:24595058

The radiographic features of familial expansile osteolysis

International Nuclear Information System (INIS)

Crone, M.D.; Wallace, R.G.H.

1990-01-01

The radiographic features of a unique autosomal dominant bone dysplasia are presented. The features are classified as generalised and/or focal. Generalised features are either altered trabecular pattern or modelling abnormalities. Focal features comprise lytic areas which progressively enlarge, producing expansion of the bone and eventual disintegration due to fibrous and finally fatty replacement of the normal medulla. Almost 90% of these lesions occur in the appendicular skeleton. Clinically, hearing loss is the earliest manifestation of the disease, presenting sometimes as early as 4 years of age. Apical and cervical resorption of teeth is extremely common, resulting in premature loss of teeth. Radiologically, the differential diagnosis refers to Paget's disease, polyostotic fibrous dysplasia, and osteofibrous dysplasia. The progressive destruction of the bone is similar to massive osteolysis (Gorham's disease). The radiographic features in combination with the histopathology render the condition unique. (orig.)

Probabilistic Slow Features for Behavior Analysis

NARCIS (Netherlands)

Zafeiriou, Lazaros; Nicolaou, Mihalis A.; Zafeiriou, Stefanos; Nikitidis, Symeon; Pantic, Maja

A recently introduced latent feature learning technique for time-varying dynamic phenomena analysis is the so-called slow feature analysis (SFA). SFA is a deterministic component analysis technique for multidimensional sequences that, by minimizing the variance of the first-order time derivative

Learning slow features for behavior analysis

NARCIS (Netherlands)

Zafeiriou, Lazaros; Nicolaou, Mihalis A.; Zafeiriou, Stefanos; Nikitids, Symeon; Pantic, Maja

2013-01-01

A recently introduced latent feature learning technique for time varying dynamic phenomena analysis is the socalled Slow Feature Analysis (SFA). SFA is a deterministic component analysis technique for multi-dimensional sequences that by minimizing the variance of the first order time derivative

Aging, selective attention, and feature integration.

Science.gov (United States)

Plude, D J; Doussard-Roosevelt, J A

1989-03-01

This study used feature-integration theory as a means of determining the point in processing at which selective attention deficits originate. The theory posits an initial stage of processing in which features are registered in parallel and then a serial process in which features are conjoined to form complex stimuli. Performance of young and older adults on feature versus conjunction search is compared. Analyses of reaction times and error rates suggest that elderly adults in addition to young adults, can capitalize on the early parallel processing stage of visual information processing, and that age decrements in visual search arise as a result of the later, serial stage of processing. Analyses of a third, unconfounded, conjunction search condition reveal qualitatively similar modes of conjunction search in young and older adults. The contribution of age-related data limitations is found to be secondary to the contribution of age decrements in selective attention.

Behind every innovative solution lies an obscure feature

Directory of Open Access Journals (Sweden)

Lee Spector (Fellow ISGEC

2012-06-01

Full Text Available The Obscure Features Hypothesis (OFH for innovation states that a two-step process undergirds almost all innovative solutions: (1 notice an infrequently observed or new (i.e., obscure feature of the problem and (2 construct an interaction involving the obscure feature that produces the desired effects to solve the problem. The OFH leads to a systematic derivation of innovation-enhancing techniques by engaging in two tasks. First, we developed a 32-category system of the types of features possessable by a physical object or material. This Feature Type Taxonomy (FTT provides a panoramic view of the space of features and assists in searches for the obscure ones. Second, we are articulating the many cognitive reasons that obscure features are overlooked and are developing countering techniques for each known reason. We present the implications and techniques of the OFH, as well as indicate how software can assist innovators in the effective use of these innovation-enhancing techniques.

Mammographic feature enhancement by multiscale analysis

International Nuclear Information System (INIS)

Laine, A.F.; Schuler, S.; Fan, J.; Huda, W.

1994-01-01

This paper introduces a novel approach for accomplishing mammographic feature analysis by overcomplete multiresolution representations. The authors show that efficient representations may be identified within a continuum of scale-space and used to enhance features of importance to mammography. Methods of contrast enhancement are described based on three overcomplete multiscale representations: (1) the dyadic wavelet transform (separable), (2) the var-phi-transform (nonseparable, nonorthogonal), and (3) the hexagonal wavelet transform (nonseparable). Multiscale edges identified within distinct levels of transform space provide local support for image enhancement. Mammograms are reconstructed from wavelet coefficients modified at one or more levels by local and global nonlinear operators. In each case, edges and gain parameters are identified adaptively by a measure of energy within each level of scale-space. The authors show quantitatively that transform coefficients, modified by adaptive nonlinear operators, can make more obvious unseen or barely seen features of mammography without requiring additional radiation. The results are compared with traditional image enhancement techniques by measuring the local contrast of known mammographic features. The authors demonstrate that features extracted from multiresolution representations can provide an adaptive mechanism for accomplishing local contrast enhancement. By improving the visualization of breast pathology, they can improve chances of early detection while requiring less time to evaluate mammograms for most patients

Laboratory simulation of infrared astrophysical features

International Nuclear Information System (INIS)

Rose, L.A.

1979-01-01

Laboratory infrared emission and absorption spectra have been taken of terrestrial silicates, meteorites and lunar soils in the form of micrometer and sub-micrometer grains. The emission spectra were taken in a way that imitates telescopic observations. The purpose was to see which materials best simulate the 10 μm astrophysical feature. The emission spectra of dunite, fayalite and Allende give a good fit to the 10 μm broadband emission feature of comets Bennett and Kohoutek. A study of the effect of grain size on the presence of the 10 μm emission features of dunite shows that for particles larger than 37 μm no feature is seen. The emission spectrum of the Murray meteorite, a Type 2 carbonaceous chondrite, is quite similar to the intermediate resolution spectrum of comet Kohoutek in the 10 μm region. Hydrous silicates or amorphous magnesium silicates in combination with high-temperature condensates, such as olivine or anorthite, would yield spectra that match the intermediate resolution spectrum of comet Kohoutek in the 10 μm region. Glassy olivine and glassy anorthite in approximately equal proportions would also give a spectrum that is a good fit to the cometary 10 μm feature. (Auth.)

Joint Feature Selection and Classification for Multilabel Learning.

Science.gov (United States)

Huang, Jun; Li, Guorong; Huang, Qingming; Wu, Xindong

2018-03-01

Multilabel learning deals with examples having multiple class labels simultaneously. It has been applied to a variety of applications, such as text categorization and image annotation. A large number of algorithms have been proposed for multilabel learning, most of which concentrate on multilabel classification problems and only a few of them are feature selection algorithms. Current multilabel classification models are mainly built on a single data representation composed of all the features which are shared by all the class labels. Since each class label might be decided by some specific features of its own, and the problems of classification and feature selection are often addressed independently, in this paper, we propose a novel method which can perform joint feature selection and classification for multilabel learning, named JFSC. Different from many existing methods, JFSC learns both shared features and label-specific features by considering pairwise label correlations, and builds the multilabel classifier on the learned low-dimensional data representations simultaneously. A comparative study with state-of-the-art approaches manifests a competitive performance of our proposed method both in classification and feature selection for multilabel learning.

Automatic feature-based grouping during multiple object tracking.

Science.gov (United States)

Erlikhman, Gennady; Keane, Brian P; Mettler, Everett; Horowitz, Todd S; Kellman, Philip J

2013-12-01

Contour interpolation automatically binds targets with distractors to impair multiple object tracking (Keane, Mettler, Tsoi, & Kellman, 2011). Is interpolation special in this regard or can other features produce the same effect? To address this question, we examined the influence of eight features on tracking: color, contrast polarity, orientation, size, shape, depth, interpolation, and a combination (shape, color, size). In each case, subjects tracked 4 of 8 objects that began as undifferentiated shapes, changed features as motion began (to enable grouping), and returned to their undifferentiated states before halting. We found that intertarget grouping improved performance for all feature types except orientation and interpolation (Experiment 1 and Experiment 2). Most importantly, target-distractor grouping impaired performance for color, size, shape, combination, and interpolation. The impairments were, at times, large (>15% decrement in accuracy) and occurred relative to a homogeneous condition in which all objects had the same features at each moment of a trial (Experiment 2), and relative to a "diversity" condition in which targets and distractors had different features at each moment (Experiment 3). We conclude that feature-based grouping occurs for a variety of features besides interpolation, even when irrelevant to task instructions and contrary to the task demands, suggesting that interpolation is not unique in promoting automatic grouping in tracking tasks. Our results also imply that various kinds of features are encoded automatically and in parallel during tracking.

Superpixel-Based Feature for Aerial Image Scene Recognition

Directory of Open Access Journals (Sweden)

Hongguang Li

2018-01-01

Full Text Available Image scene recognition is a core technology for many aerial remote sensing applications. Different landforms are inputted as different scenes in aerial imaging, and all landform information is regarded as valuable for aerial image scene recognition. However, the conventional features of the Bag-of-Words model are designed using local points or other related information and thus are unable to fully describe landform areas. This limitation cannot be ignored when the aim is to ensure accurate aerial scene recognition. A novel superpixel-based feature is proposed in this study to characterize aerial image scenes. Then, based on the proposed feature, a scene recognition method of the Bag-of-Words model for aerial imaging is designed. The proposed superpixel-based feature that utilizes landform information establishes top-task superpixel extraction of landforms to bottom-task expression of feature vectors. This characterization technique comprises the following steps: simple linear iterative clustering based superpixel segmentation, adaptive filter bank construction, Lie group-based feature quantification, and visual saliency model-based feature weighting. Experiments of image scene recognition are carried out using real image data captured by an unmanned aerial vehicle (UAV. The recognition accuracy of the proposed superpixel-based feature is 95.1%, which is higher than those of scene recognition algorithms based on other local features.

Spatiotemporal Features for Asynchronous Event-based Data

Directory of Open Access Journals (Sweden)

Xavier eLagorce

2015-02-01

Full Text Available Bio-inspired asynchronous event-based vision sensors are currently introducing a paradigm shift in visual information processing. These new sensors rely on a stimulus-driven principle of light acquisition similar to biological retinas. They are event-driven and fully asynchronous, thereby reducing redundancy and encoding exact times of input signal changes, leading to a very precise temporal resolution. Approaches for higher-level computer vision often rely on the realiable detection of features in visual frames, but similar definitions of features for the novel dynamic and event-based visual input representation of silicon retinas have so far been lacking. This article addresses the problem of learning and recognizing features for event-based vision sensors, which capture properties of truly spatiotemporal volumes of sparse visual event information. A novel computational architecture for learning and encoding spatiotemporal features is introduced based on a set of predictive recurrent reservoir networks, competing via winner-take-all selection. Features are learned in an unsupervised manner from real-world input recorded with event-based vision sensors. It is shown that the networks in the architecture learn distinct and task-specific dynamic visual features, and can predict their trajectories over time.

Selective Audiovisual Semantic Integration Enabled by Feature-Selective Attention.

Science.gov (United States)

Li, Yuanqing; Long, Jinyi; Huang, Biao; Yu, Tianyou; Wu, Wei; Li, Peijun; Fang, Fang; Sun, Pei

2016-01-13

An audiovisual object may contain multiple semantic features, such as the gender and emotional features of the speaker. Feature-selective attention and audiovisual semantic integration are two brain functions involved in the recognition of audiovisual objects. Humans often selectively attend to one or several features while ignoring the other features of an audiovisual object. Meanwhile, the human brain integrates semantic information from the visual and auditory modalities. However, how these two brain functions correlate with each other remains to be elucidated. In this functional magnetic resonance imaging (fMRI) study, we explored the neural mechanism by which feature-selective attention modulates audiovisual semantic integration. During the fMRI experiment, the subjects were presented with visual-only, auditory-only, or audiovisual dynamical facial stimuli and performed several feature-selective attention tasks. Our results revealed that a distribution of areas, including heteromodal areas and brain areas encoding attended features, may be involved in audiovisual semantic integration. Through feature-selective attention, the human brain may selectively integrate audiovisual semantic information from attended features by enhancing functional connectivity and thus regulating information flows from heteromodal areas to brain areas encoding the attended features.

Critical feature analysis of a radiotherapy machine

International Nuclear Information System (INIS)

Rae, Andrew; Jackson, Daniel; Ramanan, Prasad; Flanz, Jay; Leyman, Didier

2005-01-01

The software implementation of the emergency shutdown feature in a major radiotherapy system was analyzed, using a directed form of code review based on module dependences. Dependences between modules are labelled by particular assumptions; this allows one to trace through the code, and identify those fragments responsible for critical features. An 'assumption tree' is constructed in parallel, showing the assumptions which each module makes about others. The root of the assumption tree is the critical feature of interest, and its leaves represent assumptions which, if not valid, might cause the critical feature to fail. The analysis revealed some unexpected assumptions that motivated improvements to the code

Analysing Feature Model Changes using FMDiff

NARCIS (Netherlands)

Dintzner, N.J.R.; Van Deursen, A.; Pinzger, M.

2015-01-01

Evolving a large scale, highly variable sys- tems is a challenging task. For such a system, evolution operations often require to update consistently both their implementation and its feature model. In this con- text, the evolution of the feature model closely follows the evolution of the system.

Graphical matching rules for cardinality based service feature diagrams

Directory of Open Access Journals (Sweden)

Faiza Kanwal

2017-03-01

Full Text Available To provide efficient services to end-users, variability and commonality among the features of the product line is a challenge for industrialist and researchers. Feature modeling provides great services to deal with variability and commonality among the features of product line. Cardinality based service feature diagrams changed the basic framework of service feature diagrams by putting constraints to them, which make service specifications more flexible, but apart from their variation in selection third party services may have to be customizable. Although to control variability, cardinality based service feature diagrams provide high level visual notations. For specifying variability, the use of cardinality based service feature diagrams raises the problem of matching a required feature diagram against the set of provided diagrams.

Robust emotion recognition using spectral and prosodic features

CERN Document Server

Rao, K Sreenivasa

2013-01-01

In this brief, the authors discuss recently explored spectral (sub-segmental and pitch synchronous) and prosodic (global and local features at word and syllable levels in different parts of the utterance) features for discerning emotions in a robust manner. The authors also delve into the complementary evidences obtained from excitation source, vocal tract system and prosodic features for the purpose of enhancing emotion recognition performance. Features based on speaking rate characteristics are explored with the help of multi-stage and hybrid models for further improving emotion recognition performance. Proposed spectral and prosodic features are evaluated on real life emotional speech corpus.

Video Scene Parsing with Predictive Feature Learning

OpenAIRE

Jin, Xiaojie; Li, Xin; Xiao, Huaxin; Shen, Xiaohui; Lin, Zhe; Yang, Jimei; Chen, Yunpeng; Dong, Jian; Liu, Luoqi; Jie, Zequn; Feng, Jiashi; Yan, Shuicheng

2016-01-01

In this work, we address the challenging video scene parsing problem by developing effective representation learning methods given limited parsing annotations. In particular, we contribute two novel methods that constitute a unified parsing framework. (1) \\textbf{Predictive feature learning}} from nearly unlimited unlabeled video data. Different from existing methods learning features from single frame parsing, we learn spatiotemporal discriminative features by enforcing a parsing network to ...

Characters Feature Extraction Based on Neat Oracle Bone Rubbings

OpenAIRE

Lei Guo

2013-01-01

In order to recognize characters on the neat oracle bone rubbings, a new mesh point feature extraction algorithm was put forward in this paper by researching and improving of the existing coarse mesh feature extraction algorithm and the point feature extraction algorithm. Some improvements of this algorithm were as followings: point feature was introduced into the coarse mesh feature, the absolute address was converted to relative address, and point features have been changed grid and positio...

Speech recognition using articulatory and excitation source features

CERN Document Server

Rao, K Sreenivasa

2017-01-01

This book discusses the contribution of articulatory and excitation source information in discriminating sound units. The authors focus on excitation source component of speech -- and the dynamics of various articulators during speech production -- for enhancement of speech recognition (SR) performance. Speech recognition is analyzed for read, extempore, and conversation modes of speech. Five groups of articulatory features (AFs) are explored for speech recognition, in addition to conventional spectral features. Each chapter provides the motivation for exploring the specific feature for SR task, discusses the methods to extract those features, and finally suggests appropriate models to capture the sound unit specific knowledge from the proposed features. The authors close by discussing various combinations of spectral, articulatory and source features, and the desired models to enhance the performance of SR systems.

MRI features of placenta accreta

International Nuclear Information System (INIS)

Cao Manrui; Du Mu; Huang Yi; Liu Bingguang; Zhang Fangjing; Guo Jimin; Zhu Zhijun

2012-01-01

Objective: To investigate the MRI features of placenta accreta. Methods: From Apr 2009 to Jun 2011, 15 patients with placenta accrete received MRI examination. In them, placenta accreta was diagnosed based on clinical manifestations or postoperative histopathology. The MR features of placenta accreta in them (study group) were retrospectively analyzed and compared with those in 15 pregnant women without placenta accreta (control group) with Fisher exact test. Results: In the 15 patients with placenta accreta,uterine bulging and (or) a focal outward contour bulge was detected in 14 patients; heterogeneous signal intensity in the placenta was detected in 15 patients; dark intraplacental bands on T 2 -weighted images was detected in 15 patients; and increased subplacental vascularity was detected in 11 patients on T 1 - weighted images. In the study group, 14 patients showed at least three of the above four features, and in all of them uterine bulging and (or) a focal outward contour bulge, heterogeneous signal intensity in the placenta and dark intraplacental bands on T 2 -weighted images were detected; one patient showed heterogeneous signal intensity in the placenta, dark intraplacental bands on T 2 -weighted images and increased subplacental vascularity. In the control group,none patient had three of the above features.Uterine bulging and (or) a focal outward contour bulge, heterogeneous signal intensity in the placenta, dark intraplacental bands on T 2 -weighted images and increased subplacental vascularity were detected in 3, 6, 3 and 4 patients (P=0.000, 0.001, 0.000 and 0.027), respectively. Conclusions: The main MRI features of placenta accreta are uterine bulging and (or) a focal outward contour bulge, heterogeneous signal intensity in the placenta and dark intraplacental bands on T 2 -weighted images Besides, increased subplacental vascularity also could provide useful information for the diagnosis of placenta accreta. (authors)

A study on feature analysis for musical instrument classification.

Science.gov (United States)

Deng, Jeremiah D; Simmermacher, Christian; Cranefield, Stephen

2008-04-01

In tackling data mining and pattern recognition tasks, finding a compact but effective set of features has often been found to be a crucial step in the overall problem-solving process. In this paper, we present an empirical study on feature analysis for recognition of classical instrument, using machine learning techniques to select and evaluate features extracted from a number of different feature schemes. It is revealed that there is significant redundancy between and within feature schemes commonly used in practice. Our results suggest that further feature analysis research is necessary in order to optimize feature selection and achieve better results for the instrument recognition problem.

Audio feature extraction using probability distribution function

Science.gov (United States)

Suhaib, A.; Wan, Khairunizam; Aziz, Azri A.; Hazry, D.; Razlan, Zuradzman M.; Shahriman A., B.

2015-05-01

Voice recognition has been one of the popular applications in robotic field. It is also known to be recently used for biometric and multimedia information retrieval system. This technology is attained from successive research on audio feature extraction analysis. Probability Distribution Function (PDF) is a statistical method which is usually used as one of the processes in complex feature extraction methods such as GMM and PCA. In this paper, a new method for audio feature extraction is proposed which is by using only PDF as a feature extraction method itself for speech analysis purpose. Certain pre-processing techniques are performed in prior to the proposed feature extraction method. Subsequently, the PDF result values for each frame of sampled voice signals obtained from certain numbers of individuals are plotted. From the experimental results obtained, it can be seen visually from the plotted data that each individuals' voice has comparable PDF values and shapes.

Temporality of Features in Near-Death Experience Narratives

Directory of Open Access Journals (Sweden)

Charlotte Martial

2017-06-01

Full Text Available Background: After an occurrence of a Near-Death Experience (NDE, Near-Death Experiencers (NDErs usually report extremely rich and detailed narratives. Phenomenologically, a NDE can be described as a set of distinguishable features. Some authors have proposed regular patterns of NDEs, however, the actual temporality sequence of NDE core features remains a little explored area.Objectives: The aim of the present study was to investigate the frequency distribution of these features (globally and according to the position of features in narratives as well as the most frequently reported temporality sequences of features.Methods: We collected 154 French freely expressed written NDE narratives (i.e., Greyson NDE scale total score ≥ 7/32. A text analysis was conducted on all narratives in order to infer temporal ordering and frequency distribution of NDE features.Results: Our analyses highlighted the following most frequently reported sequence of consecutive NDE features: Out-of-Body Experience, Experiencing a tunnel, Seeing a bright light, Feeling of peace. Yet, this sequence was encountered in a very limited number of NDErs.Conclusion: These findings may suggest that NDEs temporality sequences can vary across NDErs. Exploring associations and relationships among features encountered during NDEs may complete the rigorous definition and scientific comprehension of the phenomenon.

Feature Optimization for Long-Range Visual Homing in Changing Environments

Directory of Open Access Journals (Sweden)

Qidan Zhu

2014-02-01

Full Text Available This paper introduces a feature optimization method for robot long-range feature-based visual homing in changing environments. To cope with the changing environmental appearance, the optimization procedure is introduced to distinguish the most relevant features for feature-based visual homing, including the spatial distribution, selection and updating. In the previous research on feature-based visual homing, less effort has been spent on the way to improve the feature distribution to get uniformly distributed features, which are closely related to homing performance. This paper presents a modified feature extraction algorithm to decrease the influence of anisotropic feature distribution. In addition, the feature selection and updating mechanisms, which have hardly drawn any attention in the domain of feature-based visual homing, are crucial in improving homing accuracy and in maintaining the representation of changing environments. To verify the feasibility of the proposal, several comprehensive evaluations are conducted. The results indicate that the feature optimization method can find optimal feature sets for feature-based visual homing, and adapt the appearance representation to the changing environments as well.

Acoustic Features Influence Musical Choices Across Multiple Genres.

Science.gov (United States)

Barone, Michael D; Bansal, Jotthi; Woolhouse, Matthew H

2017-01-01

Based on a large behavioral dataset of music downloads, two analyses investigate whether the acoustic features of listeners' preferred musical genres influence their choice of tracks within non-preferred, secondary musical styles. Analysis 1 identifies feature distributions for pairs of genre-defined subgroups that are distinct. Using correlation analysis, these distributions are used to test the degree of similarity between subgroups' main genres and the other music within their download collections. Analysis 2 explores the issue of main-to-secondary genre influence through the production of 10 feature-influence matrices, one per acoustic feature, in which cell values indicate the percentage change in features for genres and subgroups compared to overall population averages. In total, 10 acoustic features and 10 genre-defined subgroups are explored within the two analyses. Results strongly indicate that the acoustic features of people's main genres influence the tracks they download within non-preferred, secondary musical styles. The nature of this influence and its possible actuating mechanisms are discussed with respect to research on musical preference, personality, and statistical learning.

Imaging features of kaposiform lymphangiomatosis

International Nuclear Information System (INIS)

Goyal, Pradeep; Alomari, Ahmad I.; Shaikh, Raja; Chaudry, Gulraiz; Kozakewich, Harry P.; Perez-Atayde, Antonio R.; Trenor, Cameron C.; Fishman, Steven J.; Greene, Arin K.

2016-01-01

Kaposiform lymphangiomatosis is a rare, aggressive lymphatic disorder. The imaging and presenting features of kaposiform lymphangiomatosis can overlap with those of central conducting lymphatic anomaly and generalized lymphatic anomaly. To analyze the imaging findings of kaposiform lymphangiomatosis disorder and highlight features most suggestive of this diagnosis. We retrospectively identified and characterized 20 children and young adults with histopathological diagnosis of kaposiform lymphangiomatosis and radiologic imaging referred to the vascular anomalies center between 1995 and 2015. The median age at onset was 6.5 years (range 3 months to 27 years). The most common presenting features were respiratory compromise (dyspnea, cough, chest pain; 55.5%), swelling/mass (25%), bleeding (15%) and fracture (5%). The thoracic cavity was involved in all patients; all patients had mediastinal involvement followed by lung parenchymal disease (90%) and pleural (85%) and pericardial (50%) effusions. The most common extra-thoracic sites of disease were the retroperitoneum (80%), bone (60%), abdominal viscera (55%) and muscles (45%). There was characteristic enhancing and infiltrative soft-tissue thickening in the mediastinum and retroperitoneum extending along the lymphatic distribution. Kaposiform lymphangiomatosis has overlapping imaging features with central conducting lymphatic anomaly and generalized lymphatic anomaly. Presence of mediastinal or retroperitoneal enhancing and infiltrative soft-tissue disease along the lymphatic distribution, hemorrhagic effusions and moderate thrombocytopenia (50-100,000/μl) should favor diagnosis of kaposiform lymphangiomatosis. (orig.)

Spectral features in the cosmic ray fluxes

Science.gov (United States)

Lipari, Paolo

2018-01-01

The cosmic ray energy distributions contain spectral features, that is narrow energy regions where the slope of the spectrum changes rapidly. The identification and study of these features is of great importance to understand the astrophysical mechanisms of acceleration and propagation that form the spectra. In first approximation a spectral feature is often described as a discontinuous change in slope, however very valuable information is also contained in its width, that is the length of the energy interval where the change in spectral index develops. In this work we discuss the best way to define and parameterize the width a spectral feature, and for illustration discuss some of the most prominent known structures.

A Novel Real-Time Feature Matching Scheme

Directory of Open Access Journals (Sweden)

Ying Liu

2014-02-01

Full Text Available Affine Scale Invariant Feature Transform (ASIFT can obtain fully affine invariance, however, its time cost reaches about twice that in Scale Invariant Feature Transform (SIFT. We propose an improved ASIFT algorithm based on feature points in scale space for real-time application. In order to detect the affine invariant feature point, we establish a second-order difference of Gaussian (DOG pyramid and replace the extreme detection in the DOG pyramid by zero detection in the proposed second-order DOG pyramid, which decreases the complexity of the scheme. Experimental results show that the proposed method has a big progress in the real-time performance compared to the traditional one, while preserving the fully affine invariance and precision.

Single-labelled music genre classification using content-based features

CSIR Research Space (South Africa)

Ajoodha, R

2015-11-01

Full Text Available In this paper we use content-based features to perform automatic classification of music pieces into genres. We categorise these features into four groups: features extracted from the Fourier transform’s magnitude spectrum, features designed...

SIP-FS: a novel feature selection for data representation

Directory of Open Access Journals (Sweden)

Yiyou Guo

2018-02-01

Full Text Available Abstract Multiple features are widely used to characterize real-world datasets. It is desirable to select leading features with stability and interpretability from a set of distinct features for a comprehensive data description. However, most of existing feature selection methods focus on the predictability (e.g., prediction accuracy of selected results yet neglect stability. To obtain compact data representation, a novel feature selection method is proposed to improve stability, and interpretability without sacrificing predictability (SIP-FS. Instead of mutual information, generalized correlation is adopted in minimal redundancy maximal relevance to measure the relation between different feature types. Several feature types (each contains a certain number of features can then be selected and evaluated quantitatively to determine what types contribute to a specific class, thereby enhancing the so-called interpretability of features. Moreover, stability is introduced in the criterion of SIP-FS to obtain consistent results of ranking. We conduct experiments on three publicly available datasets using one-versus-all strategy to select class-specific features. The experiments illustrate that SIP-FS achieves significant performance improvements in terms of stability and interpretability with desirable prediction accuracy and indicates advantages over several state-of-the-art approaches.

Integration of heterogeneous features for remote sensing scene classification

Science.gov (United States)

Wang, Xin; Xiong, Xingnan; Ning, Chen; Shi, Aiye; Lv, Guofang

2018-01-01

Scene classification is one of the most important issues in remote sensing (RS) image processing. We find that features from different channels (shape, spectral, texture, etc.), levels (low-level and middle-level), or perspectives (local and global) could provide various properties for RS images, and then propose a heterogeneous feature framework to extract and integrate heterogeneous features with different types for RS scene classification. The proposed method is composed of three modules (1) heterogeneous features extraction, where three heterogeneous feature types, called DS-SURF-LLC, mean-Std-LLC, and MS-CLBP, are calculated, (2) heterogeneous features fusion, where the multiple kernel learning (MKL) is utilized to integrate the heterogeneous features, and (3) an MKL support vector machine classifier for RS scene classification. The proposed method is extensively evaluated on three challenging benchmark datasets (a 6-class dataset, a 12-class dataset, and a 21-class dataset), and the experimental results show that the proposed method leads to good classification performance. It produces good informative features to describe the RS image scenes. Moreover, the integration of heterogeneous features outperforms some state-of-the-art features on RS scene classification tasks.

EOG feature relevance determination for microsleep detection

Directory of Open Access Journals (Sweden)

Golz Martin

2017-09-01

Full Text Available Automatic relevance determination (ARD was applied to two-channel EOG recordings for microsleep event (MSE recognition. 10 s immediately before MSE and also before counterexamples of fatigued, but attentive driving were analysed. Two type of signal features were extracted: the maximum cross correlation (MaxCC and logarithmic power spectral densities (PSD averaged in spectral bands of 0.5 Hz width ranging between 0 and 8 Hz. Generalised learn-ing vector quantisation (GRLVQ was used as ARD method to show the potential of feature reduction. This is compared to support-vector machines (SVM, in which the feature reduction plays a much smaller role. Cross validation yielded mean normalised relevancies of PSD features in the range of 1.6 – 4.9 % and 1.9 – 10.4 % for horizontal and vertical EOG, respectively. MaxCC relevancies were 0.002 – 0.006 % and 0.002 – 0.06 %, respectively. This shows that PSD features of vertical EOG are indispensable, whereas MaxCC can be neglected. Mean classification accuracies were estimated at 86.6±b 1.3 % and 92.3±b 0.2 % for GRLVQ and SVM, respectively. GRLVQ permits objective feature reduction by inclusion of all processing stages, but is not as accurate as SVM.

EOG feature relevance determination for microsleep detection

Directory of Open Access Journals (Sweden)

Golz Martin

2017-09-01

Full Text Available Automatic relevance determination (ARD was applied to two-channel EOG recordings for microsleep event (MSE recognition. 10 s immediately before MSE and also before counterexamples of fatigued, but attentive driving were analysed. Two type of signal features were extracted: the maximum cross correlation (MaxCC and logarithmic power spectral densities (PSD averaged in spectral bands of 0.5 Hz width ranging between 0 and 8 Hz. Generalised learn-ing vector quantisation (GRLVQ was used as ARD method to show the potential of feature reduction. This is compared to support-vector machines (SVM, in which the feature reduction plays a much smaller role. Cross validation yielded mean normalised relevancies of PSD features in the range of 1.6 - 4.9 % and 1.9 - 10.4 % for horizontal and vertical EOG, respectively. MaxCC relevancies were 0.002 - 0.006 % and 0.002 - 0.06 %, respectively. This shows that PSD features of vertical EOG are indispensable, whereas MaxCC can be neglected. Mean classification accuracies were estimated at 86.6±b 1.3 % and 92.3±b 0.2 % for GRLVQ and SVM, respec-tively. GRLVQ permits objective feature reduction by inclu-sion of all processing stages, but is not as accurate as SVM.

Tunable features of magnetoelectric transformers.

Science.gov (United States)

Dong, Shuxiang; Zhai, Junyi; Priya, Shashank; Li, Jie-Fang; Viehland, Dwight

2009-06-01

We have found that magnetostrictive FeBSiC alloy ribbons laminated with piezoelectric Pb(Zr,Ti)O(3) fiber can act as a tunable transformer when driven under resonant conditions. These composites were also found to exhibit the strongest resonant magnetoelectric voltage coefficient of 750 V/cm-Oe. The tunable features were achieved by applying small dc magnetic biases of -5 transformer features can be attributed to large changes in the piezomagnetic coefficient and permeability of the magnetostrictive phase under H(dc).

Enhanced feature integration in musicians

DEFF Research Database (Denmark)

Hansen, Niels Christian; Højlund, Andreas; Møller, Cecilie

the classical oddball control paradigm which used identical sounds. This novel finding supports the dependent processing hypothesis suggesting that musicians recruit overlapping neural resources facilitating more holistic representations of domain-relevant stimuli. These specialised refinements in predictive......Distinguishing and integrating features of sensory input is essential to human survival and no less paramount in music perception and cognition. Yet, little is known about training-induced plasticity of neural mechanisms for auditory feature integration. This study aimed to contrast the two...

Solving jigsaw puzzles using image features

DEFF Research Database (Denmark)

Nielsen, Ture R.; Drewsen, Peter; Hansen, Klaus

2008-01-01

In this article, we describe a method for automatic solving of the jigsaw puzzle problem based on using image features instead of the shape of the pieces. The image features are used for obtaining an accurate measure for edge similarity to be used in a new edge matching algorithm. The algorithm i...

FEATURE EVALUATION FOR BUILDING FACADE IMAGES – AN EMPIRICAL STUDY

Directory of Open Access Journals (Sweden)

M. Y. Yang

2012-08-01

Full Text Available The classification of building facade images is a challenging problem that receives a great deal of attention in the photogrammetry community. Image classification is critically dependent on the features. In this paper, we perform an empirical feature evaluation task for building facade images. Feature sets we choose are basic features, color features, histogram features, Peucker features, texture features, and SIFT features. We present an approach for region-wise labeling using an efficient randomized decision forest classifier and local features. We conduct our experiments with building facade image classification on the eTRIMS dataset, where our focus is the object classes building, car, door, pavement, road, sky, vegetation, and window.

Learning Transferable Features with Deep Adaptation Networks

OpenAIRE

Long, Mingsheng; Cao, Yue; Wang, Jianmin; Jordan, Michael I.

2015-01-01

Recent studies reveal that a deep neural network can learn transferable features which generalize well to novel tasks for domain adaptation. However, as deep features eventually transition from general to specific along the network, the feature transferability drops significantly in higher layers with increasing domain discrepancy. Hence, it is important to formally reduce the dataset bias and enhance the transferability in task-specific layers. In this paper, we propose a new Deep Adaptation...

SIFT based algorithm for point feature tracking

Directory of Open Access Journals (Sweden)

Adrian BURLACU

2007-12-01

Full Text Available In this paper a tracking algorithm for SIFT features in image sequences is developed. For each point feature extracted using SIFT algorithm a descriptor is computed using information from its neighborhood. Using an algorithm based on minimizing the distance between two descriptors tracking point features throughout image sequences is engaged. Experimental results, obtained from image sequences that capture scaling of different geometrical type object, reveal the performances of the tracking algorithm.

Mining Videos for Features that Drive Attention

Science.gov (United States)

2015-04-01

that can be added or removed from the final saliency computation. Examples of these features include intensity contrast, motion energy , color opponent...corresponding to the image. Each pixel in the feature map indicates the energy that the feature in question contributes at that location. In the standard...eye and head animation using a neurobio - logical model of visual attention. In: Bosacchi B, Fogel DB, Bezdek JC (eds) Proceedings of SPIE 48th annual

Radiographic features of periapical cysts and granulomas

OpenAIRE

Zain, R. B.; Roswati, N.; Ismail, K.

1989-01-01

Many studies have been reported on radiographic lesion sizes of periapical lesions. However no studies have been reported on prevalences of subjective radiographic features in these lesions except for the early assumption that a periapical cyst usually exhibit a radiopaque cortex. This study is conducted to evaluate the prevalences of several subjective radiographic features of periapical cysts and granulomas in the hope to identify features that maybe suggestive of either diagnosis. The resu...

PROBLEMATIC FEATURES OF THE POLITICAL DECISION MAKERS

OpenAIRE

Aleksey Sergeevih Voynov

2014-01-01

Purpose: identify the most important features in the process of making political decisions that affect the effectiveness of problem-solving situationsScientific novelty: as a result of the analysis identified the problematic features of major importance for the efficiency of the development and adoption of the most rational solution to a problem situation.Results: the analysis of the most significant features affecting the quality of decisions among them the interest of the person making deci...

Recognition of handwritten characters using local gradient feature descriptors

NARCIS (Netherlands)

Surinta, Olarik; Karaaba, Mahir F.; Schomaker, Lambert R.B.; Wiering, Marco A.

2015-01-01

Abstract In this paper we propose to use local gradient feature descriptors, namely the scale invariant feature transform keypoint descriptor and the histogram of oriented gradients, for handwritten character recognition. The local gradient feature descriptors are used to extract feature vectors

MetaFIND: A feature analysis tool for metabolomics data

Directory of Open Access Journals (Sweden)

Cunningham Pádraig

2008-11-01

Full Text Available Abstract Background Metabolomics, or metabonomics, refers to the quantitative analysis of all metabolites present within a biological sample and is generally carried out using NMR spectroscopy or Mass Spectrometry. Such analysis produces a set of peaks, or features, indicative of the metabolic composition of the sample and may be used as a basis for sample classification. Feature selection may be employed to improve classification accuracy or aid model explanation by establishing a subset of class discriminating features. Factors such as experimental noise, choice of technique and threshold selection may adversely affect the set of selected features retrieved. Furthermore, the high dimensionality and multi-collinearity inherent within metabolomics data may exacerbate discrepancies between the set of features retrieved and those required to provide a complete explanation of metabolite signatures. Given these issues, the latter in particular, we present the MetaFIND application for 'post-feature selection' correlation analysis of metabolomics data. Results In our evaluation we show how MetaFIND may be used to elucidate metabolite signatures from the set of features selected by diverse techniques over two metabolomics datasets. Importantly, we also show how MetaFIND may augment standard feature selection and aid the discovery of additional significant features, including those which represent novel class discriminating metabolites. MetaFIND also supports the discovery of higher level metabolite correlations. Conclusion Standard feature selection techniques may fail to capture the full set of relevant features in the case of high dimensional, multi-collinear metabolomics data. We show that the MetaFIND 'post-feature selection' analysis tool may aid metabolite signature elucidation, feature discovery and inference of metabolic correlations.

Interactive music composition driven by feature evolution.

Science.gov (United States)

Kaliakatsos-Papakostas, Maximos A; Floros, Andreas; Vrahatis, Michael N

2016-01-01

Evolutionary music composition is a prominent technique for automatic music generation. The immense adaptation potential of evolutionary algorithms has allowed the realisation of systems that automatically produce music through feature and interactive-based composition approaches. Feature-based composition employs qualitatively descriptive music features as fitness landmarks. Interactive composition systems on the other hand, derive fitness directly from human ratings and/or selection. The paper at hand introduces a methodological framework that combines the merits of both evolutionary composition methodologies. To this end, a system is presented that is organised in two levels: the higher level of interaction and the lower level of composition. The higher level incorporates the particle swarm optimisation algorithm, along with a proposed variant and evolves musical features according to user ratings. The lower level realizes feature-based music composition with a genetic algorithm, according to the top level features. The aim of this work is not to validate the efficiency of the currently utilised setup in each level, but to examine the convergence behaviour of such a two-level technique in an objective manner. Therefore, an additional novelty in this work concerns the utilisation of artificial raters that guide the system through the space of musical features, allowing the exploration of its convergence characteristics: does the system converge to optimal melodies, is this convergence fast enough for potential human listeners and is the trajectory to convergence "interesting' and "creative" enough? The experimental results reveal that the proposed methodological framework represents a fruitful and robust, novel approach to interactive music composition.

Feature-aware natural texture synthesis

KAUST Repository

Wu, Fuzhang

2014-12-04

This article presents a framework for natural texture synthesis and processing. This framework is motivated by the observation that given examples captured in natural scene, texture synthesis addresses a critical problem, namely, that synthesis quality can be affected adversely if the texture elements in an example display spatially varied patterns, such as perspective distortion, the composition of different sub-textures, and variations in global color pattern as a result of complex illumination. This issue is common in natural textures and is a fundamental challenge for previously developed methods. Thus, we address it from a feature point of view and propose a feature-aware approach to synthesize natural textures. The synthesis process is guided by a feature map that represents the visual characteristics of the input texture. Moreover, we present a novel adaptive initialization algorithm that can effectively avoid the repeat and verbatim copying artifacts. Our approach improves texture synthesis in many images that cannot be handled effectively with traditional technologies.

Histological image classification using biologically interpretable shape-based features

International Nuclear Information System (INIS)

Kothari, Sonal; Phan, John H; Young, Andrew N; Wang, May D

2013-01-01

Automatic cancer diagnostic systems based on histological image classification are important for improving therapeutic decisions. Previous studies propose textural and morphological features for such systems. These features capture patterns in histological images that are useful for both cancer grading and subtyping. However, because many of these features lack a clear biological interpretation, pathologists may be reluctant to adopt these features for clinical diagnosis. We examine the utility of biologically interpretable shape-based features for classification of histological renal tumor images. Using Fourier shape descriptors, we extract shape-based features that capture the distribution of stain-enhanced cellular and tissue structures in each image and evaluate these features using a multi-class prediction model. We compare the predictive performance of the shape-based diagnostic model to that of traditional models, i.e., using textural, morphological and topological features. The shape-based model, with an average accuracy of 77%, outperforms or complements traditional models. We identify the most informative shapes for each renal tumor subtype from the top-selected features. Results suggest that these shapes are not only accurate diagnostic features, but also correlate with known biological characteristics of renal tumors. Shape-based analysis of histological renal tumor images accurately classifies disease subtypes and reveals biologically insightful discriminatory features. This method for shape-based analysis can be extended to other histological datasets to aid pathologists in diagnostic and therapeutic decisions

Grammar-based feature generation for time-series prediction

CERN Document Server

De Silva, Anthony Mihirana

2015-01-01

This book proposes a novel approach for time-series prediction using machine learning techniques with automatic feature generation. Application of machine learning techniques to predict time-series continues to attract considerable attention due to the difficulty of the prediction problems compounded by the non-linear and non-stationary nature of the real world time-series. The performance of machine learning techniques, among other things, depends on suitable engineering of features. This book proposes a systematic way for generating suitable features using context-free grammar. A number of feature selection criteria are investigated and a hybrid feature generation and selection algorithm using grammatical evolution is proposed. The book contains graphical illustrations to explain the feature generation process. The proposed approaches are demonstrated by predicting the closing price of major stock market indices, peak electricity load and net hourly foreign exchange client trade volume. The proposed method ...

Treatment recommendations for DSM-5-defined mixed features.

Science.gov (United States)

Rosenblat, Joshua D; McIntyre, Roger S

2017-04-01

The Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5) mixed features specifier provides a less restrictive definition of mixed mood states, compared to the Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition, Text Revision (DSM-IV-TR), including mood episodes that manifest with subthreshold symptoms of the opposite mood state. A limited number of studies have assessed the efficacy of treatments specifically for DSM-5-defined mixed features in mood disorders. As such, there is currently an inadequate amount of data to appropriately inform evidence-based treatment guidelines of DSM-5 defined mixed features. However, given the high prevalence and morbidity of mixed features, treatment recommendations based on the currently available evidence along with expert opinion may be of benefit. This article serves to provide these interim treatment recommendations while humbly acknowledging the limited amount of evidence currently available. Second-generation antipsychotics (SGAs) appear to have the greatest promise in the treatment of bipolar disorder (BD) with mixed features. Conventional mood stabilizing agents (ie, lithium and divalproex) may also be of benefit; however, they have been inadequately studied. In the treatment of major depressive disorder (MDD) with mixed features, the comparable efficacy of antidepressants versus other treatments, such as SGAs, remains unknown. As such, antidepressants remain first-line treatment of MDD with or without mixed features; however, there are significant safety concerns associated with antidepressant monotherapy when mixed features are present, which merits increased monitoring. Lurasidone is the only SGA monotherapy that has been shown to be efficacious specifically in the treatment of MDD with mixed features. Further research is needed to accurately determine the efficacy, safety, and tolerability of treatments specifically for mood episodes with mixed features to adequately inform

A feature dictionary supporting a multi-domain medical knowledge base.

Science.gov (United States)

Naeymi-Rad, F

1989-01-01

Because different terminology is used by physicians of different specialties in different locations to refer to the same feature (signs, symptoms, test results), it is essential that our knowledge development tools provide a means to access a common pool of terms. This paper discusses the design of an online medical dictionary that provides a solution to this problem for developers of multi-domain knowledge bases for MEDAS (Medical Emergency Decision Assistance System). Our Feature Dictionary supports phrase equivalents for features, feature interactions, feature classifications, and translations to the binary features generated by the expert during knowledge creation. It is also used in the conversion of a domain knowledge to the database used by the MEDAS inference diagnostic sessions. The Feature Dictionary also provides capabilities for complex queries across multiple domains using the supported relations. The Feature Dictionary supports three methods for feature representation: (1) for binary features, (2) for continuous valued features, and (3) for derived features.

Online Feature Selection for Classifying Emphysema in HRCT Images

Directory of Open Access Journals (Sweden)

M. Prasad

2008-06-01

Full Text Available Feature subset selection, applied as a pre- processing step to machine learning, is valuable in dimensionality reduction, eliminating irrelevant data and improving classifier performance. In the classic formulation of the feature selection problem, it is assumed that all the features are available at the beginning. However, in many real world problems, there are scenarios where not all features are present initially and must be integrated as they become available. In such scenarios, online feature selection provides an efficient way to sort through a large space of features. It is in this context that we introduce online feature selection for the classification of emphysema, a smoking related disease that appears as low attenuation regions in High Resolution Computer Tomography (HRCT images. The technique was successfully evaluated on 61 HRCT scans and compared with different online feature selection approaches, including hill climbing, best first search, grafting, and correlation-based feature selection. The results were also compared against ldensity maskr, a standard approach used for emphysema detection in medical image analysis.

Feature Selection via Chaotic Antlion Optimization.

Directory of Open Access Journals (Sweden)

Hossam M Zawbaa

Full Text Available Selecting a subset of relevant properties from a large set of features that describe a dataset is a challenging machine learning task. In biology, for instance, the advances in the available technologies enable the generation of a very large number of biomarkers that describe the data. Choosing the more informative markers along with performing a high-accuracy classification over the data can be a daunting task, particularly if the data are high dimensional. An often adopted approach is to formulate the feature selection problem as a biobjective optimization problem, with the aim of maximizing the performance of the data analysis model (the quality of the data training fitting while minimizing the number of features used.We propose an optimization approach for the feature selection problem that considers a "chaotic" version of the antlion optimizer method, a nature-inspired algorithm that mimics the hunting mechanism of antlions in nature. The balance between exploration of the search space and exploitation of the best solutions is a challenge in multi-objective optimization. The exploration/exploitation rate is controlled by the parameter I that limits the random walk range of the ants/prey. This variable is increased iteratively in a quasi-linear manner to decrease the exploration rate as the optimization progresses. The quasi-linear decrease in the variable I may lead to immature convergence in some cases and trapping in local minima in other cases. The chaotic system proposed here attempts to improve the tradeoff between exploration and exploitation. The methodology is evaluated using different chaotic maps on a number of feature selection datasets. To ensure generality, we used ten biological datasets, but we also used other types of data from various sources. The results are compared with the particle swarm optimizer and with genetic algorithm variants for feature selection using a set of quality metrics.

Features Selection for Skin Micro-Image Symptomatic Recognition

Institute of Scientific and Technical Information of China (English)

HUYue-li; CAOJia-lin; ZHAOQian; FENGXu

2004-01-01

Automatic recognition of skin micro-image symptom is important in skin diagnosis and treatment. Feature selection is to improve the classification performance of skin micro-image symptom.This paper proposes a hybrid approach based on the support vector machine (SVM) technique and genetic algorithm (GA) to select an optimum feature subset from the feature group extracted from the skin micro-images. An adaptive GA is introduced for maintaining the convergence rate. With the proposed method, the average cross validation accuracy is increased from 88.25% using all features to 96.92% using only selected features provided by a classifier for classification of 5 classes of skin symptoms. The experimental results are satisfactory.

Features Selection for Skin Micro-Image Symptomatic Recognition

Institute of Scientific and Technical Information of China (English)

HU Yue-li; CAO Jia-lin; ZHAO Qian; FENG Xu

2004-01-01

Automatic recognition of skin micro-image symptom is important in skin diagnosis and treatment. Feature selection is to improve the classification performance of skin micro-image symptom.This paper proposes a hybrid approach based on the support vector machine (SVM) technique and genetic algorithm (GA) to select an optimum feature subset from the feature group extracted from the skin micro-images. An adaptive GA is introduced for maintaining the convergence rate. With the proposed method, the average cross validation accuracy is increased from 88.25% using all features to 96.92 % using only selected features provided by a classifier for classification of 5 classes of skin symptoms. The experimental results are satisfactory.

Teaching World Music through Feature Films

Science.gov (United States)

Lum, Chee-Hoo

2009-01-01

When used effectively, feature films can bring a plethora of visual and aural stimulation to students and enhance their learning about world cultures. Feature films can take students to places, sights, and sounds that they have yet to experience. After watching these films, students might become new admirers or even keen followers of the subject…

Recent Development of the Two-Stroke Engine. II - Design Features. 2; Design Features

Science.gov (United States)

Zeman, J.

1945-01-01

Completing the first paper dealing with charging methods and arrangements, the present paper discusses the design forms of two-stroke engines. Features which largely influence piston running are: (a) The shape and surface condition of the sliding parts. (b) The cylinder and piston materials. (c) Heat conditions in the piston, and lubrication. There is little essential difference between four-stroke and two-stroke engines with ordinary pistons. In large engines, for example, are always found separately cast or welded frames in which the stresses are taken up by tie rods. Twin piston and timing piston engines often differ from this design. Examples can be found in many engines of German or foreign make. Their methods of operation will be dealt with in the third part of the present paper, which also includes the bibliography. The development of two-stroke engine design is, of course, mainly concerned with such features as are inherently difficult to master; that is, the piston barrel and the design of the gudgeon pin bearing. Designers of four-stroke engines now-a-days experience approximately the same difficulties, since heat stresses have increased to the point of influencing conditions in the piston barrel. Features which notably affect this are: (a) The material. (b) Prevailing heat conditions.

New features of the Helioviewer Project

Science.gov (United States)

Ireland, J.; Zahniy, S.; Nicula, B.; Mueller, D.; Felix, S.; Verstringe, F.; Bourgoignie, B.

2016-12-01

This year saw the release of major new upgrades to the capabilities of helioviewer.org and JHelioviewer. The helioviewer.org interface was completely re-designed, and now provides image and feature/event time-lines and data download capabilities. JHelioviewer introduced interactive time-series, the ability to query different servers for different data, and image reprojection. We introduce the new features of these software releases and give use cases. We will summarize our latest usage statistics, and discuss what's coming up next for the Helioviewer Project. We will also be soliciting bug reports, requests for new features and comments on the effectiveness of helioviewer.org and JHelioviewer. What would you like to see next from the Helioviewer Project?

Temporal resolution for the perception of features and conjunctions.

Science.gov (United States)

Bodelón, Clara; Fallah, Mazyar; Reynolds, John H

2007-01-24

The visual system decomposes stimuli into their constituent features, represented by neurons with different feature selectivities. How the signals carried by these feature-selective neurons are integrated into coherent object representations is unknown. To constrain the set of possible integrative mechanisms, we quantified the temporal resolution of perception for color, orientation, and conjunctions of these two features. We find that temporal resolution is measurably higher for each feature than for their conjunction, indicating that time is required to integrate features into a perceptual whole. This finding places temporal limits on the mechanisms that could mediate this form of perceptual integration.

Feature Binding and the Hebb Repetition Effect

OpenAIRE

Barrett, Maeve

2008-01-01

Previous studies have found no evidence that long-term learning of integrated objects and individual features benefit visual short term memory tasks (Logie, Brockmole, & Vandenbroucke, in press; Olson & Jiang, 2004; Treisman, 2006). These findings may have been due to stimulus interference as a restricted number of features were utilised in these studies to form objects in the stimulus arrays. In these studies, participants would have needed to break apart the features of several objects in a...

Optimized feature subsets for epileptic seizure prediction studies.

Science.gov (United States)

Direito, Bruno; Ventura, Francisco; Teixeira, César; Dourado, António

2011-01-01

The reduction of the number of EEG features to give as inputs to epilepsy seizure predictors is a needed step towards the development of a transportable device for real-time warning. This paper presents a comparative study of three feature selection methods, based on Support Vector Machines. Minimum-Redundancy Maximum-Relevance, Recursive Feature Elimination, Genetic Algorithms, show that, for three patients of the European Database on Epilepsy, the most important univariate features are related to spectral information and statistical moments.

Imaging features of thalassemia

Energy Technology Data Exchange (ETDEWEB)

Tunaci, M.; Tunaci, A.; Engin, G.; Oezkorkmaz, B.; Acunas, G.; Acunas, B. [Dept. of Radiology, Istanbul Univ. (Turkey); Dincol, G. [Dept. of Internal Medicine, Istanbul Univ. (Turkey)

1999-07-01

Thalassemia is a kind of chronic, inherited, microcytic anemia characterized by defective hemoglobin synthesis and ineffective erythropoiesis. In all thalassemias clinical features that result from anemia, transfusional, and absorptive iron overload are similar but vary in severity. The radiographic features of {beta}-thalassemia are due in large part to marrow hyperplasia. Markedly expanded marrow space lead to various skeletal manifestations including spine, skull, facial bones, and ribs. Extramedullary hematopoiesis (ExmH), hemosiderosis, and cholelithiasis are among the non-skeletal manifestations of thalassemia. The skeletal X-ray findings show characteristics of chronic overactivity of the marrow. In this article both skeletal and non-skeletal manifestations of thalassemia are discussed with an overview of X-ray findings, including MRI and CT findings. (orig.)

Imaging features of thalassemia

International Nuclear Information System (INIS)

Tunaci, M.; Tunaci, A.; Engin, G.; Oezkorkmaz, B.; Acunas, G.; Acunas, B.; Dincol, G.

1999-01-01

Thalassemia is a kind of chronic, inherited, microcytic anemia characterized by defective hemoglobin synthesis and ineffective erythropoiesis. In all thalassemias clinical features that result from anemia, transfusional, and absorptive iron overload are similar but vary in severity. The radiographic features of β-thalassemia are due in large part to marrow hyperplasia. Markedly expanded marrow space lead to various skeletal manifestations including spine, skull, facial bones, and ribs. Extramedullary hematopoiesis (ExmH), hemosiderosis, and cholelithiasis are among the non-skeletal manifestations of thalassemia. The skeletal X-ray findings show characteristics of chronic overactivity of the marrow. In this article both skeletal and non-skeletal manifestations of thalassemia are discussed with an overview of X-ray findings, including MRI and CT findings. (orig.)

Identification of DNA-Binding Proteins Using Mixed Feature Representation Methods.

Science.gov (United States)

Qu, Kaiyang; Han, Ke; Wu, Song; Wang, Guohua; Wei, Leyi

2017-09-22

DNA-binding proteins play vital roles in cellular processes, such as DNA packaging, replication, transcription, regulation, and other DNA-associated activities. The current main prediction method is based on machine learning, and its accuracy mainly depends on the features extraction method. Therefore, using an efficient feature representation method is important to enhance the classification accuracy. However, existing feature representation methods cannot efficiently distinguish DNA-binding proteins from non-DNA-binding proteins. In this paper, a multi-feature representation method, which combines three feature representation methods, namely, K-Skip-N-Grams, Information theory, and Sequential and structural features (SSF), is used to represent the protein sequences and improve feature representation ability. In addition, the classifier is a support vector machine. The mixed-feature representation method is evaluated using 10-fold cross-validation and a test set. Feature vectors, which are obtained from a combination of three feature extractions, show the best performance in 10-fold cross-validation both under non-dimensional reduction and dimensional reduction by max-relevance-max-distance. Moreover, the reduced mixed feature method performs better than the non-reduced mixed feature technique. The feature vectors, which are a combination of SSF and K-Skip-N-Grams, show the best performance in the test set. Among these methods, mixed features exhibit superiority over the single features.

Identification of DNA-Binding Proteins Using Mixed Feature Representation Methods

Directory of Open Access Journals (Sweden)

Kaiyang Qu

2017-09-01

Full Text Available DNA-binding proteins play vital roles in cellular processes, such as DNA packaging, replication, transcription, regulation, and other DNA-associated activities. The current main prediction method is based on machine learning, and its accuracy mainly depends on the features extraction method. Therefore, using an efficient feature representation method is important to enhance the classification accuracy. However, existing feature representation methods cannot efficiently distinguish DNA-binding proteins from non-DNA-binding proteins. In this paper, a multi-feature representation method, which combines three feature representation methods, namely, K-Skip-N-Grams, Information theory, and Sequential and structural features (SSF, is used to represent the protein sequences and improve feature representation ability. In addition, the classifier is a support vector machine. The mixed-feature representation method is evaluated using 10-fold cross-validation and a test set. Feature vectors, which are obtained from a combination of three feature extractions, show the best performance in 10-fold cross-validation both under non-dimensional reduction and dimensional reduction by max-relevance-max-distance. Moreover, the reduced mixed feature method performs better than the non-reduced mixed feature technique. The feature vectors, which are a combination of SSF and K-Skip-N-Grams, show the best performance in the test set. Among these methods, mixed features exhibit superiority over the single features.

Low-Dimensional Feature Representation for Instrument Identification

Science.gov (United States)

Ihara, Mizuki; Maeda, Shin-Ichi; Ikeda, Kazushi; Ishii, Shin

For monophonic music instrument identification, various feature extraction and selection methods have been proposed. One of the issues toward instrument identification is that the same spectrum is not always observed even in the same instrument due to the difference of the recording condition. Therefore, it is important to find non-redundant instrument-specific features that maintain information essential for high-quality instrument identification to apply them to various instrumental music analyses. For such a dimensionality reduction method, the authors propose the utilization of linear projection methods: local Fisher discriminant analysis (LFDA) and LFDA combined with principal component analysis (PCA). After experimentally clarifying that raw power spectra are actually good for instrument classification, the authors reduced the feature dimensionality by LFDA or by PCA followed by LFDA (PCA-LFDA). The reduced features achieved reasonably high identification performance that was comparable or higher than those by the power spectra and those achieved by other existing studies. These results demonstrated that our LFDA and PCA-LFDA can successfully extract low-dimensional instrument features that maintain the characteristic information of the instruments.

Hindi vowel classification using QCN-MFCC features

Directory of Open Access Journals (Sweden)

Shipra Mishra

2016-09-01

Full Text Available In presence of environmental noise, speakers tend to emphasize their vocal effort to improve the audibility of voice. This involuntary adjustment is known as Lombard effect (LE. Due to LE the signal to noise ratio of speech increases, but at the same time the loudness, pitch and duration of phonemes changes. Hence, accuracy of automatic speech recognition systems degrades. In this paper, the effect of unsupervised equalization of Lombard effect is investigated for Hindi vowel classification task using Hindi database designed at TIFR Mumbai, India. Proposed Quantile-based Dynamic Cepstral Normalization MFCC (QCN-MFCC along with baseline MFCC features have been used for vowel classification. Hidden Markov Model (HMM is used as classifier. It is observed that QCN-MFCC features have given a maximum improvement of 5.97% and 5% over MFCC features for context-dependent and context-independent cases respectively. It is also observed that QCN-MFCC features have given improvement of 13% and 11.5% over MFCC features for context-dependent and context-independent classification of mid vowels.

Breast Cancer Detection with Reduced Feature Set

Directory of Open Access Journals (Sweden)

Ahmet Mert

2015-01-01

Full Text Available This paper explores feature reduction properties of independent component analysis (ICA on breast cancer decision support system. Wisconsin diagnostic breast cancer (WDBC dataset is reduced to one-dimensional feature vector computing an independent component (IC. The original data with 30 features and reduced one feature (IC are used to evaluate diagnostic accuracy of the classifiers such as k-nearest neighbor (k-NN, artificial neural network (ANN, radial basis function neural network (RBFNN, and support vector machine (SVM. The comparison of the proposed classification using the IC with original feature set is also tested on different validation (5/10-fold cross-validations and partitioning (20%–40% methods. These classifiers are evaluated how to effectively categorize tumors as benign and malignant in terms of specificity, sensitivity, accuracy, F-score, Youden’s index, discriminant power, and the receiver operating characteristic (ROC curve with its criterion values including area under curve (AUC and 95% confidential interval (CI. This represents an improvement in diagnostic decision support system, while reducing computational complexity.

Feature-based tolerancing for intelligent inspection process definition

International Nuclear Information System (INIS)

Brown, C.W.

1993-07-01

This paper describes a feature-based tolerancing capability that complements a geometric solid model with an explicit representation of conventional and geometric tolerances. This capability is focused on supporting an intelligent inspection process definition system. The feature-based tolerance model's benefits include advancing complete product definition initiatives (e.g., STEP -- Standard for Exchange of Product model dam), suppling computer-integrated manufacturing applications (e.g., generative process planning and automated part programming) with product definition information, and assisting in the solution of measurement performance issues. A feature-based tolerance information model was developed based upon the notion of a feature's toleranceable aspects and describes an object-oriented scheme for representing and relating tolerance features, tolerances, and datum reference frames. For easy incorporation, the tolerance feature entities are interconnected with STEP solid model entities. This schema will explicitly represent the tolerance specification for mechanical products, support advanced dimensional measurement applications, and assist in tolerance-related methods divergence issues

Dynamic Features for Iris Recognition.

Science.gov (United States)

da Costa, R M; Gonzaga, A

2012-08-01

The human eye is sensitive to visible light. Increasing illumination on the eye causes the pupil of the eye to contract, while decreasing illumination causes the pupil to dilate. Visible light causes specular reflections inside the iris ring. On the other hand, the human retina is less sensitive to near infra-red (NIR) radiation in the wavelength range from 800 nm to 1400 nm, but iris detail can still be imaged with NIR illumination. In order to measure the dynamic movement of the human pupil and iris while keeping the light-induced reflexes from affecting the quality of the digitalized image, this paper describes a device based on the consensual reflex. This biological phenomenon contracts and dilates the two pupils synchronously when illuminating one of the eyes by visible light. In this paper, we propose to capture images of the pupil of one eye using NIR illumination while illuminating the other eye using a visible-light pulse. This new approach extracts iris features called "dynamic features (DFs)." This innovative methodology proposes the extraction of information about the way the human eye reacts to light, and to use such information for biometric recognition purposes. The results demonstrate that these features are discriminating features, and, even using the Euclidean distance measure, an average accuracy of recognition of 99.1% was obtained. The proposed methodology has the potential to be "fraud-proof," because these DFs can only be extracted from living irises.

Performance Evaluation of Feature Sets of Minutiae Quadruplets ...

African Journals Online (AJOL)

The features proposed in this paper are derived from minutiae quadruplets and are applicable in matching and indexing ngerprint images. In this work nineteen different possibilities of features were explored for indexing and the performances of some of the feature sets were mixed: some giving good performances on ...

Feature Selection for Audio Surveillance in Urban Environment

Directory of Open Access Journals (Sweden)

KIKTOVA Eva

2014-05-01

Full Text Available This paper presents the work leading to the acoustic event detection system, which is designed to recognize two types of acoustic events (shot and breaking glass in urban environment. For this purpose, a huge front-end processing was performed for the effective parametric representation of an input sound. MFCC features and features computed during their extraction (MELSPEC and FBANK, then MPEG-7 audio descriptors and other temporal and spectral characteristics were extracted. High dimensional feature sets were created and in the next phase reduced by the mutual information based selection algorithms. Hidden Markov Model based classifier was applied and evaluated by the Viterbi decoding algorithm. Thus very effective feature sets were identified and also the less important features were found.

Research on oral test modeling based on multi-feature fusion

Science.gov (United States)

Shi, Yuliang; Tao, Yiyue; Lei, Jun

2018-04-01

In this paper, the spectrum of speech signal is taken as an input of feature extraction. The advantage of PCNN in image segmentation and other processing is used to process the speech spectrum and extract features. And a new method combining speech signal processing and image processing is explored. At the same time of using the features of the speech map, adding the MFCC to establish the spectral features and integrating them with the features of the spectrogram to further improve the accuracy of the spoken language recognition. Considering that the input features are more complicated and distinguishable, we use Support Vector Machine (SVM) to construct the classifier, and then compare the extracted test voice features with the standard voice features to achieve the spoken standard detection. Experiments show that the method of extracting features from spectrograms using PCNN is feasible, and the fusion of image features and spectral features can improve the detection accuracy.

Efficient Multi-Label Feature Selection Using Entropy-Based Label Selection

Directory of Open Access Journals (Sweden)

Jaesung Lee

2016-11-01

Full Text Available Multi-label feature selection is designed to select a subset of features according to their importance to multiple labels. This task can be achieved by ranking the dependencies of features and selecting the features with the highest rankings. In a multi-label feature selection problem, the algorithm may be faced with a dataset containing a large number of labels. Because the computational cost of multi-label feature selection increases according to the number of labels, the algorithm may suffer from a degradation in performance when processing very large datasets. In this study, we propose an efficient multi-label feature selection method based on an information-theoretic label selection strategy. By identifying a subset of labels that significantly influence the importance of features, the proposed method efficiently outputs a feature subset. Experimental results demonstrate that the proposed method can identify a feature subset much faster than conventional multi-label feature selection methods for large multi-label datasets.

Features of upbringing children in civil law

OpenAIRE

Лобжанідзе, Давид

2014-01-01

The paper analyzes the features of upbringing children in civil law, in particular under the Civil Code of Georgia. The author examines the concept of the family as a social phenomenon and its underlying principles. Attention is paid also to the court practice of upbringing children and determining the place of their residence. English abstract D. Lobzhanidze Features of upbringing children in civil law. The paper analyzes the features of upbringing children in civil law, in particular u...

Clinical features of radiation retinopathy

International Nuclear Information System (INIS)

Tabuchi, Shoko; Oda, Itsuo; Okawa, Tomohiko

1977-01-01

The clinical features of 25 cases with radiation retinopathy are described. Retinopathy was induced following therapeutic irradiation of paraobital malignancies with megavoltage Linac x-ray of 3,000 rads or more. Retinal vessels, particularly the proximal portion of retinal arteries, seemed to be the primary site of damage due to radiation. According to the type of lesion and dosage, fundus features simulated papillitis, retinal angiosclerosis, or hard exudates due to capillary obliteration. Acute obstruction of the central retinal artery and ischemic optic neuropathy could result from heavy irradiation of over 5,000 rads. (Evans, J.)

News and Features Updates from USA.gov

Data.gov (United States)

General Services Administration — Stay on top of important government news and information with the USA.gov Updates: News and Features RSS feed. We'll update this feed when we add news and featured...

Realistic Free-Spins Features Increase Preference for Slot Machines.

Science.gov (United States)

Taylor, Lorance F; Macaskill, Anne C; Hunt, Maree J

2017-06-01

Despite increasing research into how the structural characteristics of slot machines influence gambling behaviour there have been no experimental investigations into the effect of free-spins bonus features-a structural characteristic that is commonly central to the design of slot machines. This series of three experiments investigated the free-spins feature using slot machine simulations to determine whether participants allocate more wagers to a machine with free spins, and, which components of free-spins features drive this preference. In each experiment, participants were exposed to two computer-simulated slot machines-one with a free-spins feature or similar bonus feature and one without. Participants then completed a testing phase where they could freely switch between the two machines. In Experiment 1, participants did not prefer the machine with a simple free-spins feature. In Experiment 2 the free-spins feature incorporated additional elements such as sounds, animations, and an increased win frequency; participants preferred to gamble on this machine. The Experiment 3 "bonus feature" machine resembled the free spins machine in Experiment 2 except spins were not free; participants showed a clear preference for this machine also. These findings indicate that (1) free-spins features have a major influence over machine choice and (2) the "freeness" of the free-spins bonus features is not an important driver of preference, contrary to self-report and interview research with gamblers.

Abdominal cocoon: sonographic features.

Science.gov (United States)

Vijayaraghavan, S Boopathy; Palanivelu, Chinnusamy; Sendhilkumar, Karuppusamy; Parthasarathi, Ramakrishnan

2003-07-01

An abdominal cocoon is a rare condition in which the small bowel is encased in a membrane. The diagnosis is usually established at surgery. Here we describe the sonographic features of this condition.

Are Haar-like Rectangular Features for Biometric Recognition Reducible?

DEFF Research Database (Denmark)

Nasrollahi, Kamal; Moeslund, Thomas B.

2013-01-01

Biometric recognition is still a very difficult task in real-world scenarios wherein unforeseen changes in degradations factors like noise, occlusion, blurriness and illumination can drastically affect the extracted features from the biometric signals. Very recently Haar-like rectangular features...... which have usually been used for object detection were introduced for biometric recognition resulting in systems that are robust against most of the mentioned degradations [9]. The problem with these features is that one can define many different such features for a given biometric signal...... and it is not clear whether all of these features are required for the actual recognition or not. This is exactly what we are dealing with in this paper: How can an initial set of Haar-like rectangular features, that have been used for biometric recognition, be reduced to a set of most influential features...

Automatic processing of unattended object features by functional connectivity

Directory of Open Access Journals (Sweden)

Katja Martina Mayer

2013-05-01

Full Text Available Observers can selectively attend to object features that are relevant for a task. However, unattended task-irrelevant features may still be processed and possibly integrated with the attended features. This study investigated the neural mechanisms for processing both task-relevant (attended and task-irrelevant (unattended object features. The Garner paradigm was adapted for functional magnetic resonance imaging (fMRI to test whether specific brain areas process the conjunction of features or whether multiple interacting areas are involved in this form of feature integration. Observers attended to shape, colour, or non-rigid motion of novel objects while unattended features changed from trial to trial (change blocks or remained constant (no-change blocks during a given block. This block manipulation allowed us to measure the extent to which unattended features affected neural responses which would reflect the extent to which multiple object features are automatically processed. We did not find Garner interference at the behavioural level. However, we designed the experiment to equate performance across block types so that any fMRI results could not be due solely to differences in task difficulty between change and no-change blocks. Attention to specific features localised several areas known to be involved in object processing. No area showed larger responses on change blocks compared to no-change blocks. However, psychophysiological interaction analyses revealed that several functionally-localised areas showed significant positive interactions with areas in occipito-temporal and frontal areas that depended on block type. Overall, these findings suggest that both regional responses and functional connectivity are crucial for processing multi-featured objects.

TreeBASIS Feature Descriptor and Its Hardware Implementation

Directory of Open Access Journals (Sweden)

Spencer Fowers

2014-01-01

Full Text Available This paper presents a novel feature descriptor called TreeBASIS that provides improvements in descriptor size, computation time, matching speed, and accuracy. This new descriptor uses a binary vocabulary tree that is computed using basis dictionary images and a test set of feature region images. To facilitate real-time implementation, a feature region image is binary quantized and the resulting quantized vector is passed into the BASIS vocabulary tree. A Hamming distance is then computed between the feature region image and the effectively descriptive basis dictionary image at a node to determine the branch taken and the path the feature region image takes is saved as a descriptor. The TreeBASIS feature descriptor is an excellent candidate for hardware implementation because of its reduced descriptor size and the fact that descriptors can be created and features matched without the use of floating point operations. The TreeBASIS descriptor is more computationally and space efficient than other descriptors such as BASIS, SIFT, and SURF. Moreover, it can be computed entirely in hardware without the support of a CPU for additional software-based computations. Experimental results and a hardware implementation show that the TreeBASIS descriptor compares well with other descriptors for frame-to-frame homography computation while requiring fewer hardware resources.

High Dimensional Classification Using Features Annealed Independence Rules.

Science.gov (United States)

Fan, Jianqing; Fan, Yingying

2008-01-01

Classification using high-dimensional features arises frequently in many contemporary statistical studies such as tumor classification using microarray or other high-throughput data. The impact of dimensionality on classifications is largely poorly understood. In a seminal paper, Bickel and Levina (2004) show that the Fisher discriminant performs poorly due to diverging spectra and they propose to use the independence rule to overcome the problem. We first demonstrate that even for the independence classification rule, classification using all the features can be as bad as the random guessing due to noise accumulation in estimating population centroids in high-dimensional feature space. In fact, we demonstrate further that almost all linear discriminants can perform as bad as the random guessing. Thus, it is paramountly important to select a subset of important features for high-dimensional classification, resulting in Features Annealed Independence Rules (FAIR). The conditions under which all the important features can be selected by the two-sample t-statistic are established. The choice of the optimal number of features, or equivalently, the threshold value of the test statistics are proposed based on an upper bound of the classification error. Simulation studies and real data analysis support our theoretical results and demonstrate convincingly the advantage of our new classification procedure.

3-D FEATURE-BASED MATCHING BY RSTG APPROACH

Directory of Open Access Journals (Sweden)

J.-J. Jaw

2012-07-01

Full Text Available 3-D feature matching is the essential kernel in a fully automated feature-based LiDAR point cloud registration. After feasible procedures of feature acquisition, connecting corresponding features in different data frames is imperative to be solved. The objective addressed in this paper is developing an approach coined RSTG to retrieve corresponding counterparts of unsorted multiple 3-D features extracted from sets of LiDAR point clouds. RSTG stands for the four major processes, "Rotation alignment"; "Scale estimation"; "Translation alignment" and "Geometric check," strategically formulated towards finding out matching solution with high efficiency and leading to accomplishing the 3-D similarity transformation among all sets. The workable types of features to RSTG comprise points, lines, planes and clustered point groups. Each type of features can be employed exclusively or combined with others, if sufficiently supplied, throughout the matching scheme. The paper gives a detailed description of the matching methodology and discusses on the matching effects based on the statistical assessment which revealed that the RSTG approach reached an average matching rate of success up to 93% with around 6.6% of statistical type 1 error. Notably, statistical type 2 error, the critical indicator of matching reliability, was kept 0% throughout all the experiments.

Parabolic features and the erosion rate on Venus

Science.gov (United States)

Strom, Robert G.

1993-01-01

The impact cratering record on Venus consists of 919 craters covering 98 percent of the surface. These craters are remarkably well preserved, and most show pristine structures including fresh ejecta blankets. Only 35 craters (3.8 percent) have had their ejecta blankets embayed by lava and most of these occur in the Atla-Beta Regio region; an area thought to be recently active. parabolic features are associated with 66 of the 919 craters. These craters range in size from 6 to 105 km diameter. The parabolic features are thought to be the result of the deposition of fine-grained ejecta by winds in the dense venusian atmosphere. The deposits cover about 9 percent of the surface and none appear to be embayed by younger volcanic materials. However, there appears to be a paucity of these deposits in the Atla-Beta Regio region, and this may be due to the more recent volcanism in this area of Venus. Since parabolic features are probably fine-grain, wind-deposited ejecta, then all impact craters on Venus probably had these deposits at some time in the past. The older deposits have probably been either eroded or buried by eolian processes. Therefore, the present population of these features is probably associated with the most recent impact craters on the planet. Furthermore, the size/frequency distribution of craters with parabolic features is virtually identical to that of the total crater population. This suggests that there has been little loss of small parabolic features compared to large ones, otherwise there should be a significant and systematic paucity of craters with parabolic features with decreasing size compared to the total crater population. Whatever is erasing the parabolic features apparently does so uniformly regardless of the areal extent of the deposit. The lifetime of parabolic features and the eolian erosion rate on Venus can be estimated from the average age of the surface and the present population of parabolic features.

Real-time hypothesis driven feature extraction on parallel processing architectures

DEFF Research Database (Denmark)

Granmo, O.-C.; Jensen, Finn Verner

2002-01-01

the problem of higher-order feature-content/feature-feature correlation, causally complexly interacting features are identified through Bayesian network d-separation analysis and combined into joint features. When used on a moderately complex object-tracking case, the technique is able to select...... extraction, which selectively extract relevant features one-by-one, have in some cases achieved real-time performance on single processing element architectures. In this paperwe propose a novel technique which combines the above two approaches. Features are selectively extracted in parallelizable sets...

Feature representation of RGB-D images using joint spatial-depth feature pooling

DEFF Research Database (Denmark)

Pan, Hong; Olsen, Søren Ingvor; Zhu, Yaping

2016-01-01

Recent development in depth imaging technology makes acquisition of depth information easier. With the additional depth cue, RGB-D cameras can provide effective support for many RGB-D perception tasks beyond traditional RGB information. However, current feature representation based on RGB-D image...

Dynamic binding of visual features by neuronal/stimulus synchrony.

Science.gov (United States)

Iwabuchi, A

1998-05-01

When people see a visual scene, certain parts of the visual scene are treated as belonging together and we regard them as a perceptual unit, which is called a "figure". People focus on figures, and the remaining parts of the scene are disregarded as "ground". In Gestalt psychology this process is called "figure-ground segregation". According to current perceptual psychology, a figure is formed by binding various visual features in a scene, and developments in neuroscience have revealed that there are many feature-encoding neurons, which respond to such features specifically. It is not known, however, how the brain binds different features of an object into a coherent visual object representation. Recently, the theory of binding by neuronal synchrony, which argues that feature binding is dynamically mediated by neuronal synchrony of feature-encoding neurons, has been proposed. This review article portrays the problem of figure-ground segregation and features binding, summarizes neurophysiological and psychophysical experiments and theory relevant to feature binding by neuronal/stimulus synchrony, and suggests possible directions for future research on this topic.

Effective Feature Selection for Classification of Promoter Sequences.

Directory of Open Access Journals (Sweden)

Kouser K

Full Text Available Exploring novel computational methods in making sense of biological data has not only been a necessity, but also productive. A part of this trend is the search for more efficient in silico methods/tools for analysis of promoters, which are parts of DNA sequences that are involved in regulation of expression of genes into other functional molecules. Promoter regions vary greatly in their function based on the sequence of nucleotides and the arrangement of protein-binding short-regions called motifs. In fact, the regulatory nature of the promoters seems to be largely driven by the selective presence and/or the arrangement of these motifs. Here, we explore computational classification of promoter sequences based on the pattern of motif distributions, as such classification can pave a new way of functional analysis of promoters and to discover the functionally crucial motifs. We make use of Position Specific Motif Matrix (PSMM features for exploring the possibility of accurately classifying promoter sequences using some of the popular classification techniques. The classification results on the complete feature set are low, perhaps due to the huge number of features. We propose two ways of reducing features. Our test results show improvement in the classification output after the reduction of features. The results also show that decision trees outperform SVM (Support Vector Machine, KNN (K Nearest Neighbor and ensemble classifier LibD3C, particularly with reduced features. The proposed feature selection methods outperform some of the popular feature transformation methods such as PCA and SVD. Also, the methods proposed are as accurate as MRMR (feature selection method but much faster than MRMR. Such methods could be useful to categorize new promoters and explore regulatory mechanisms of gene expressions in complex eukaryotic species.

Feature-based RNN target recognition

Science.gov (United States)

Bakircioglu, Hakan; Gelenbe, Erol

1998-09-01

Detection and recognition of target signatures in sensory data obtained by synthetic aperture radar (SAR), forward- looking infrared, or laser radar, have received considerable attention in the literature. In this paper, we propose a feature based target classification methodology to detect and classify targets in cluttered SAR images, that makes use of selective signature data from sensory data, together with a neural network technique which uses a set of trained networks based on the Random Neural Network (RNN) model (Gelenbe 89, 90, 91, 93) which is trained to act as a matched filter. We propose and investigate radial features of target shapes that are invariant to rotation, translation, and scale, to characterize target and clutter signatures. These features are then used to train a set of learning RNNs which can be used to detect targets within clutter with high accuracy, and to classify the targets or man-made objects from natural clutter. Experimental data from SAR imagery is used to illustrate and validate the proposed method, and to calculate Receiver Operating Characteristics which illustrate the performance of the proposed algorithm.

Adversarial Feature Selection Against Evasion Attacks.

Science.gov (United States)

Zhang, Fei; Chan, Patrick P K; Biggio, Battista; Yeung, Daniel S; Roli, Fabio

2016-03-01

Pattern recognition and machine learning techniques have been increasingly adopted in adversarial settings such as spam, intrusion, and malware detection, although their security against well-crafted attacks that aim to evade detection by manipulating data at test time has not yet been thoroughly assessed. While previous work has been mainly focused on devising adversary-aware classification algorithms to counter evasion attempts, only few authors have considered the impact of using reduced feature sets on classifier security against the same attacks. An interesting, preliminary result is that classifier security to evasion may be even worsened by the application of feature selection. In this paper, we provide a more detailed investigation of this aspect, shedding some light on the security properties of feature selection against evasion attacks. Inspired by previous work on adversary-aware classifiers, we propose a novel adversary-aware feature selection model that can improve classifier security against evasion attacks, by incorporating specific assumptions on the adversary's data manipulation strategy. We focus on an efficient, wrapper-based implementation of our approach, and experimentally validate its soundness on different application examples, including spam and malware detection.

Neural Architecture for Feature Binding in Visual Working Memory.

Science.gov (United States)

Schneegans, Sebastian; Bays, Paul M

2017-04-05

Binding refers to the operation that groups different features together into objects. We propose a neural architecture for feature binding in visual working memory that employs populations of neurons with conjunction responses. We tested this model using cued recall tasks, in which subjects had to memorize object arrays composed of simple visual features (color, orientation, and location). After a brief delay, one feature of one item was given as a cue, and the observer had to report, on a continuous scale, one or two other features of the cued item. Binding failure in this task is associated with swap errors, in which observers report an item other than the one indicated by the cue. We observed that the probability of swapping two items strongly correlated with the items' similarity in the cue feature dimension, and found a strong correlation between swap errors occurring in spatial and nonspatial report. The neural model explains both swap errors and response variability as results of decoding noisy neural activity, and can account for the behavioral results in quantitative detail. We then used the model to compare alternative mechanisms for binding nonspatial features. We found the behavioral results fully consistent with a model in which nonspatial features are bound exclusively via their shared location, with no indication of direct binding between color and orientation. These results provide evidence for a special role of location in feature binding, and the model explains how this special role could be realized in the neural system. SIGNIFICANCE STATEMENT The problem of feature binding is of central importance in understanding the mechanisms of working memory. How do we remember not only that we saw a red and a round object, but that these features belong together to a single object rather than to different objects in our environment? Here we present evidence for a neural mechanism for feature binding in working memory, based on encoding of visual

Efficient Generation and Selection of Combined Features for Improved Classification

KAUST Repository

Shono, Ahmad N.

2014-05-01

This study contributes a methodology and associated toolkit developed to allow users to experiment with the use of combined features in classification problems. Methods are provided for efficiently generating combined features from an original feature set, for efficiently selecting the most discriminating of these generated combined features, and for efficiently performing a preliminary comparison of the classification results when using the original features exclusively against the results when using the selected combined features. The potential benefit of considering combined features in classification problems is demonstrated by applying the developed methodology and toolkit to three sample data sets where the discovery of combined features containing new discriminating information led to improved classification results.

Cherubism: Clinicoradiographic Features and Treatment

Directory of Open Access Journals (Sweden)

Luiz Antonio Guimarães Cabral

2010-04-01

Full Text Available Objectives: Cherubism is a congenital childhood disease of autosomal dominant inheritance. This disease is characterized by painless bilateral enlargement of the jaws, in which bone is replaced with fibrous tissue. The condition has sui generis clinical, radiographic and histological features, of which the clinician should be aware for a better differential diagnosis in the presence of a fibro-osseous lesion affecting the bones of the maxillomandibular complex. The purpose of present paper was to review the literature and to report the most important aspects of cherubism in order to facilitate the study of this disease.Material and Methods: Literature was reviewed about cherubism, emphasizing the relevant clinicoradiographic features and treatment. Literature was selected through a search of PubMed and Scielo electronic databases. The keywords used for search were adolescent, cherubism, cherubism/physiopathology, cherubism/treatment, cherubism/radiography. A manual search of the reference lists of the identified articles and the authors’ article files and recent reviews was conducted to identify additional publications. Those studies that described new features about cherubism were included in this review.Results: In total 44 literature sources were obtained and reviewed. Studies that described new features about cherubism physiopathology, diagnostics and treatment were reviewed.Conclusions: Despite the exceptions, cherubism is a clinically well-characterized disease. In cases of a suspicion of cherubism, radiographic examination is essential since the clinical presentation, the location and distribution of the lesions may define the diagnosis. Histopathological examination is complementary. Nowadays, genetic tests should be used for final diagnosis of cherubism.

Improving Music Genre Classification by Short-Time Feature Integration

DEFF Research Database (Denmark)

Meng, Anders; Ahrendt, Peter; Larsen, Jan

2005-01-01

Many different short-time features, using time windows in the size of 10-30 ms, have been proposed for music segmentation, retrieval and genre classification. However, often the available time frame of the music to make the actual decision or comparison (the decision time horizon) is in the range...... of seconds instead of milliseconds. The problem of making new features on the larger time scale from the short-time features (feature integration) has only received little attention. This paper investigates different methods for feature integration and late information fusion for music genre classification...

Classification of Textures Using Filter Based Local Feature Extraction

Directory of Open Access Journals (Sweden)

Bocekci Veysel Gokhan

2016-01-01

Full Text Available In this work local features are used in feature extraction process in image processing for textures. The local binary pattern feature extraction method from textures are introduced. Filtering is also used during the feature extraction process for getting discriminative features. To show the effectiveness of the algorithm before the extraction process, three different noise are added to both train and test images. Wiener filter and median filter are used to remove the noise from images. We evaluate the performance of the method with Naïve Bayesian classifier. We conduct the comparative analysis on benchmark dataset with different filtering and size. Our experiments demonstrate that feature extraction process combine with filtering give promising results on noisy images.

Face recognition algorithm using extended vector quantization histogram features.

Science.gov (United States)

Yan, Yan; Lee, Feifei; Wu, Xueqian; Chen, Qiu

2018-01-01

In this paper, we propose a face recognition algorithm based on a combination of vector quantization (VQ) and Markov stationary features (MSF). The VQ algorithm has been shown to be an effective method for generating features; it extracts a codevector histogram as a facial feature representation for face recognition. Still, the VQ histogram features are unable to convey spatial structural information, which to some extent limits their usefulness in discrimination. To alleviate this limitation of VQ histograms, we utilize Markov stationary features (MSF) to extend the VQ histogram-based features so as to add spatial structural information. We demonstrate the effectiveness of our proposed algorithm by achieving recognition results superior to those of several state-of-the-art methods on publicly available face databases.

Uniform competency-based local feature extraction for remote sensing images

Science.gov (United States)

Sedaghat, Amin; Mohammadi, Nazila

2018-01-01

Local feature detectors are widely used in many photogrammetry and remote sensing applications. The quantity and distribution of the local features play a critical role in the quality of the image matching process, particularly for multi-sensor high resolution remote sensing image registration. However, conventional local feature detectors cannot extract desirable matched features either in terms of the number of correct matches or the spatial and scale distribution in multi-sensor remote sensing images. To address this problem, this paper proposes a novel method for uniform and robust local feature extraction for remote sensing images, which is based on a novel competency criterion and scale and location distribution constraints. The proposed method, called uniform competency (UC) local feature extraction, can be easily applied to any local feature detector for various kinds of applications. The proposed competency criterion is based on a weighted ranking process using three quality measures, including robustness, spatial saliency and scale parameters, which is performed in a multi-layer gridding schema. For evaluation, five state-of-the-art local feature detector approaches, namely, scale-invariant feature transform (SIFT), speeded up robust features (SURF), scale-invariant feature operator (SFOP), maximally stable extremal region (MSER) and hessian-affine, are used. The proposed UC-based feature extraction algorithms were successfully applied to match various synthetic and real satellite image pairs, and the results demonstrate its capability to increase matching performance and to improve the spatial distribution. The code to carry out the UC feature extraction is available from href="https://www.researchgate.net/publication/317956777_UC-Feature_Extraction.

Prostate cancer multi-feature analysis using trans-rectal ultrasound images

International Nuclear Information System (INIS)

Mohamed, S S; Salama, M M A; Kamel, M; El-Saadany, E F; Rizkalla, K; Chin, J

2005-01-01

This note focuses on extracting and analysing prostate texture features from trans-rectal ultrasound (TRUS) images for tissue characterization. One of the principal contributions of this investigation is the use of the information of the images' frequency domain features and spatial domain features to attain a more accurate diagnosis. Each image is divided into regions of interest (ROIs) by the Gabor multi-resolution analysis, a crucial stage, in which segmentation is achieved according to the frequency response of the image pixels. The pixels with a similar response to the same filter are grouped to form one ROI. Next, from each ROI two different statistical feature sets are constructed; the first set includes four grey level dependence matrix (GLDM) features and the second set consists of five grey level difference vector (GLDV) features. These constructed feature sets are then ranked by the mutual information feature selection (MIFS) algorithm. Here, the features that provide the maximum mutual information of each feature and class (cancerous and non-cancerous) and the minimum mutual information of the selected features are chosen, yeilding a reduced feature subset. The two constructed feature sets, GLDM and GLDV, as well as the reduced feature subset, are examined in terms of three different classifiers: the condensed k-nearest neighbour (CNN), the decision tree (DT) and the support vector machine (SVM). The accuracy classification results range from 87.5% to 93.75%, where the performance of the SVM and that of the DT are significantly better than the performance of the CNN. (note)

Including product features in process redesign

DEFF Research Database (Denmark)

Hvam, Lars; Hauksdóttir, Dagný; Mortensen, Niels Henrik

2017-01-01

do not take into account how the product features are applied throughout the process, which makes it difficult to obtain a comprehensive understanding of the activities in the processes and to generate significant improvements. The suggested approach models the product family using the so......This article suggests a visual modelling method for integrating models of product features with business process models for redesigning the business processes involving specifications of customer-tailored products and services. The current methods for redesigning these types of business processes......-called product variant master and the business process modelling notation for modelling the process flow. The product model is combined with the process map by identifying features used in each step of the process flow. Additionally, based on the information absorbed from the integrated model, the value stream...

Detection of fraudulent emails by employing advanced feature abundance

Directory of Open Access Journals (Sweden)

Sarwat Nizamani

2014-11-01

Full Text Available In this paper, we present a fraudulent email detection model using advanced feature choice. We extracted various kinds of features and compared the performance of each category of features with the others in terms of the fraudulent email detection rate. The different types of features are incorporated step by step. The detection of fraudulent email has been considered as a classification problem and it is evaluated using various state-of-the art algorithms and on CCM (Nizamani et al., 2011 [1] which is authors’ previous cluster based classification model. The experiments have been performed on diverse feature sets and the different classification methods. The comparison of the results is also presented and the evaluation show that for the fraudulent email detection tasks, the feature set is more important regardless of classification method. The results of the study suggest that the task of fraudulent emails detection requires the better choice of feature set; while the choice of classification method is of less importance.

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.

Influence of Familiar Features on Diagnosis: Instantiated Features in an Applied Setting

Science.gov (United States)

Dore, Kelly L.; Brooks, Lee R.; Weaver, Bruce; Norman, Geoffrey R.

2012-01-01

Medical diagnosis can be viewed as a categorization task. There are two mechanisms whereby humans make categorical judgments: "analytical reasoning," based on explicit consideration of features and "nonanalytical reasoning," an unconscious holistic process of matching against prior exemplars. However, there is evidence that prior experience can…

Mesoblastic nephroma: Pathological features

African Journals Online (AJOL)

N.M. El-Badawy

determined mainly by its histologic type, we found it worthwhile to elaborate more on the gross and microscopic features of ... behavior of mesoblastic nephroma is determined mainly by its his- .... However, it exhibits a nodular growth pattern at.

Genome-wide analyses of borderline personality features

NARCIS (Netherlands)

Lubke, G.H.; Laurin, C.; Amin, N.; Hottenga, J.J.; Willemsen, G.; Grootheest, G.; Abdellaoui, A.; Karssen, L.C.; Oostra, B.A.; van Duijn, C.M.; Penninx, B.W.J.H.; Boomsma, D.I.

2014-01-01

The heritability of borderline personality (BP) features has been established in multiple twin and family studies. Using data from the borderline subscale of the Personality Assessment Inventory Borderline Features Scale (PAI-BOR) collected in two Dutch cohorts (N=7125), the Netherlands Twin

Shapes and features of the primordial bispectrum

Energy Technology Data Exchange (ETDEWEB)

Gong, Jinn-Ouk [Asia Pacific Center for Theoretical Physics, Cheongam-ro 67, Pohang, 37673 (Korea, Republic of); Palma, Gonzalo A.; Sypsas, Spyros, E-mail: jinn-ouk.gong@apctp.org, E-mail: gpalmaquilod@ing.uchile.cl, E-mail: s.sypsas@gmail.com [Departamento de Física, FCFM, Universidad de Chile, Blanco Encalada 2008, Santiago, 837.0415 Chile (Chile)

2017-05-01

If time-dependent disruptions from slow-roll occur during inflation, the correlation functions of the primordial curvature perturbation should have scale-dependent features, a case which is marginally supported from the cosmic microwave background (CMB) data. We offer a new approach to analyze the appearance of such features in the primordial bispectrum that yields new consistency relations and justifies the search of oscillating patterns modulated by orthogonal and local templates. Under the assumption of sharp features, we find that the cubic couplings of the curvature perturbation can be expressed in terms of the bispectrum in two specific momentum configurations, for example local and equilateral. This allows us to derive consistency relations among different bispectrum shapes, which in principle could be tested in future CMB surveys. Furthermore, based on the form of the consistency relations, we construct new two-parameter templates for features that include all the known shapes.

An Effective Combined Feature For Web Based Image Retrieval

Directory of Open Access Journals (Sweden)

H.M.R.B Herath

2015-08-01

Full Text Available Abstract Technology advances as well as the emergence of large scale multimedia applications and the revolution of the World Wide Web has changed the world into a digital age. Anybody can use their mobile phone to take a photo at any time anywhere and upload that image to ever growing image databases. Development of effective techniques for visual and multimedia retrieval systems is one of the most challenging and important directions of the future research. This paper proposes an effective combined feature for web based image retrieval. Frequently used colour and texture features are explored in order to develop a combined feature for this purpose. Widely used three colour features Colour moments Colour coherence vector and Colour Correlogram and three texture features Grey Level Co-occurrence matrix Tamura features and Gabor filter were analyzed for their performance. Precision and Recall were used to evaluate the performance of each of these techniques. By comparing precision and recall values the methods that performed best were taken and combined to form a hybrid feature. The developed combined feature was evaluated by developing a web based CBIR system. A web crawler was used to first crawl through Web sites and images found in those sites are downloaded and the combined feature representation technique was used to extract image features. The test results indicated that this web system can be used to index web images with the combined feature representation schema and to find similar images. Random image retrievals using the web system shows that the combined feature can be used to retrieve images belonging to the general image domain. Accuracy of the retrieval can be noted high for natural images like outdoor scenes images of flowers etc. Also images which have a similar colour and texture distribution were retrieved as similar even though the images were belonging to deferent semantic categories. This can be ideal for an artist who wants

Adaptive feature selection using v-shaped binary particle swarm optimization.

Science.gov (United States)

Teng, Xuyang; Dong, Hongbin; Zhou, Xiurong

2017-01-01

Feature selection is an important preprocessing method in machine learning and data mining. This process can be used not only to reduce the amount of data to be analyzed but also to build models with stronger interpretability based on fewer features. Traditional feature selection methods evaluate the dependency and redundancy of features separately, which leads to a lack of measurement of their combined effect. Moreover, a greedy search considers only the optimization of the current round and thus cannot be a global search. To evaluate the combined effect of different subsets in the entire feature space, an adaptive feature selection method based on V-shaped binary particle swarm optimization is proposed. In this method, the fitness function is constructed using the correlation information entropy. Feature subsets are regarded as individuals in a population, and the feature space is searched using V-shaped binary particle swarm optimization. The above procedure overcomes the hard constraint on the number of features, enables the combined evaluation of each subset as a whole, and improves the search ability of conventional binary particle swarm optimization. The proposed algorithm is an adaptive method with respect to the number of feature subsets. The experimental results show the advantages of optimizing the feature subsets using the V-shaped transfer function and confirm the effectiveness and efficiency of the feature subsets obtained under different classifiers.

Feature-based morphometry: discovering group-related anatomical patterns.

Science.gov (United States)

Toews, Matthew; Wells, William; Collins, D Louis; Arbel, Tal

2010-02-01

This paper presents feature-based morphometry (FBM), a new fully data-driven technique for discovering patterns of group-related anatomical structure in volumetric imagery. In contrast to most morphometry methods which assume one-to-one correspondence between subjects, FBM explicitly aims to identify distinctive anatomical patterns that may only be present in subsets of subjects, due to disease or anatomical variability. The image is modeled as a collage of generic, localized image features that need not be present in all subjects. Scale-space theory is applied to analyze image features at the characteristic scale of underlying anatomical structures, instead of at arbitrary scales such as global or voxel-level. A probabilistic model describes features in terms of their appearance, geometry, and relationship to subject groups, and is automatically learned from a set of subject images and group labels. Features resulting from learning correspond to group-related anatomical structures that can potentially be used as image biomarkers of disease or as a basis for computer-aided diagnosis. The relationship between features and groups is quantified by the likelihood of feature occurrence within a specific group vs. the rest of the population, and feature significance is quantified in terms of the false discovery rate. Experiments validate FBM clinically in the analysis of normal (NC) and Alzheimer's (AD) brain images using the freely available OASIS database. FBM automatically identifies known structural differences between NC and AD subjects in a fully data-driven fashion, and an equal error classification rate of 0.80 is achieved for subjects aged 60-80 years exhibiting mild AD (CDR=1). Copyright (c) 2009 Elsevier Inc. All rights reserved.

Physical model for the 2175 A interstellar extinction feature

International Nuclear Information System (INIS)

Hecht, J.H.

1986-01-01

Recent IUE observations have shown that the 2175 A interstellar extinction feature is constant in wavelength but varies in width. A model has been constructed to explain these results. It is proposed that the 2175 A feature will only be seen when there is extinction due to carbon grains which have lost their hydrogen. In particular, the feature is caused by a separate population of small (less than 50 A radius), hydrogen-free carbon grains. The variations in width would be due to differences in either their temperature, size distribution, or impurity content. All other carbon grains retain hydrogen, which causes the feature to be suppressed. If this model is correct, then it implies that the grains responsible for the unidentified IR emission features would not generally cause the 2175 A feature. 53 references

Consistency relations for sharp inflationary non-Gaussian features

Energy Technology Data Exchange (ETDEWEB)

Mooij, Sander; Palma, Gonzalo A.; Panotopoulos, Grigoris [Departamento de Física, Facultad de Ciencias Físicas y Matemáticas, Universidad de Chile, Blanco Encalada 2008, Santiago (Chile); Soto, Alex, E-mail: sander.mooij@ing.uchile.cl, E-mail: gpalmaquilod@ing.uchile.cl, E-mail: gpanotop@ing.uchile.cl, E-mail: gatogeno@gmail.com [Departamento de Física, Facultad de Ciencias, Universidad de Chile, Las Palmeras 3425, Ñuñoa, Santiago (Chile)

2016-09-01

If cosmic inflation suffered tiny time-dependent deviations from the slow-roll regime, these would induce the existence of small scale-dependent features imprinted in the primordial spectra, with their shapes and sizes revealing information about the physics that produced them. Small sharp features could be suppressed at the level of the two-point correlation function, making them undetectable in the power spectrum, but could be amplified at the level of the three-point correlation function, offering us a window of opportunity to uncover them in the non-Gaussian bispectrum. In this article, we show that sharp features may be analyzed using only data coming from the three point correlation function parametrizing primordial non-Gaussianity. More precisely, we show that if features appear in a particular non-Gaussian triangle configuration (e.g. equilateral, folded, squeezed), these must reappear in every other configuration according to a specific relation allowing us to correlate features across the non-Gaussian bispectrum. As a result, we offer a method to study scale-dependent features generated during inflation that depends only on data coming from measurements of non-Gaussianity, allowing us to omit data from the power spectrum.

Consistency relations for sharp inflationary non-Gaussian features

International Nuclear Information System (INIS)

Mooij, Sander; Palma, Gonzalo A.; Panotopoulos, Grigoris; Soto, Alex

2016-01-01

If cosmic inflation suffered tiny time-dependent deviations from the slow-roll regime, these would induce the existence of small scale-dependent features imprinted in the primordial spectra, with their shapes and sizes revealing information about the physics that produced them. Small sharp features could be suppressed at the level of the two-point correlation function, making them undetectable in the power spectrum, but could be amplified at the level of the three-point correlation function, offering us a window of opportunity to uncover them in the non-Gaussian bispectrum. In this article, we show that sharp features may be analyzed using only data coming from the three point correlation function parametrizing primordial non-Gaussianity. More precisely, we show that if features appear in a particular non-Gaussian triangle configuration (e.g. equilateral, folded, squeezed), these must reappear in every other configuration according to a specific relation allowing us to correlate features across the non-Gaussian bispectrum. As a result, we offer a method to study scale-dependent features generated during inflation that depends only on data coming from measurements of non-Gaussianity, allowing us to omit data from the power spectrum.

Character feature integration of Chinese calligraphy and font

Science.gov (United States)

Shi, Cao; Xiao, Jianguo; Jia, Wenhua; Xu, Canhui

2013-01-01

A framework is proposed in this paper to effectively generate a new hybrid character type by means of integrating local contour feature of Chinese calligraphy with structural feature of font in computer system. To explore traditional art manifestation of calligraphy, multi-directional spatial filter is applied for local contour feature extraction. Then the contour of character image is divided into sub-images. The sub-images in the identical position from various characters are estimated by Gaussian distribution. According to its probability distribution, the dilation operator and erosion operator are designed to adjust the boundary of font image. And then new Chinese character images are generated which possess both contour feature of artistical calligraphy and elaborate structural feature of font. Experimental results demonstrate the new characters are visually acceptable, and the proposed framework is an effective and efficient strategy to automatically generate the new hybrid character of calligraphy and font.

Multistage feature extraction for accurate face alignment

NARCIS (Netherlands)

Zuo, F.; With, de P.H.N.

2004-01-01

We propose a novel multistage facial feature extraction approach using a combination of 'global' and 'local' techniques. At the first stage, we use template matching, based on an Edge-Orientation-Map for fast feature position estimation. Using this result, a statistical framework applying the Active

Second feature of the matter two-point function

Science.gov (United States)

Tansella, Vittorio

2018-05-01

We point out the existence of a second feature in the matter two-point function, besides the acoustic peak, due to the baryon-baryon correlation in the early Universe and positioned at twice the distance of the peak. We discuss how the existence of this feature is implied by the well-known heuristic argument that explains the baryon bump in the correlation function. A standard χ2 analysis to estimate the detection significance of the second feature is mimicked. We conclude that, for realistic values of the baryon density, a SKA-like galaxy survey will not be able to detect this feature with standard correlation function analysis.

Image fusion using sparse overcomplete feature dictionaries

Science.gov (United States)

Brumby, Steven P.; Bettencourt, Luis; Kenyon, Garrett T.; Chartrand, Rick; Wohlberg, Brendt

2015-10-06

Approaches for deciding what individuals in a population of visual system "neurons" are looking for using sparse overcomplete feature dictionaries are provided. A sparse overcomplete feature dictionary may be learned for an image dataset and a local sparse representation of the image dataset may be built using the learned feature dictionary. A local maximum pooling operation may be applied on the local sparse representation to produce a translation-tolerant representation of the image dataset. An object may then be classified and/or clustered within the translation-tolerant representation of the image dataset using a supervised classification algorithm and/or an unsupervised clustering algorithm.

Feature Importance for Human Epithelial (HEp-2 Cell Image Classification

Directory of Open Access Journals (Sweden)

Vibha Gupta

2018-02-01

Full Text Available Indirect Immuno-Fluorescence (IIF microscopy imaging of human epithelial (HEp-2 cells is a popular method for diagnosing autoimmune diseases. Considering large data volumes, computer-aided diagnosis (CAD systems, based on image-based classification, can help in terms of time, effort, and reliability of diagnosis. Such approaches are based on extracting some representative features from the images. This work explores the selection of the most distinctive features for HEp-2 cell images using various feature selection (FS methods. Considering that there is no single universally optimal feature selection technique, we also propose hybridization of one class of FS methods (filter methods. Furthermore, the notion of variable importance for ranking features, provided by another type of approaches (embedded methods such as Random forest, Random uniform forest is exploited to select a good subset of features from a large set, such that addition of new features does not increase classification accuracy. In this work, we have also, with great consideration, designed class-specific features to capture morphological visual traits of the cell patterns. We perform various experiments and discussions to demonstrate the effectiveness of FS methods along with proposed and a standard feature set. We achieve state-of-the-art performance even with small number of features, obtained after the feature selection.

Slow feature analysis: unsupervised learning of invariances.

Science.gov (United States)

Wiskott, Laurenz; Sejnowski, Terrence J

2002-04-01

Invariant features of temporally varying signals are useful for analysis and classification. Slow feature analysis (SFA) is a new method for learning invariant or slowly varying features from a vectorial input signal. It is based on a nonlinear expansion of the input signal and application of principal component analysis to this expanded signal and its time derivative. It is guaranteed to find the optimal solution within a family of functions directly and can learn to extract a large number of decorrelated features, which are ordered by their degree of invariance. SFA can be applied hierarchically to process high-dimensional input signals and extract complex features. SFA is applied first to complex cell tuning properties based on simple cell output, including disparity and motion. Then more complicated input-output functions are learned by repeated application of SFA. Finally, a hierarchical network of SFA modules is presented as a simple model of the visual system. The same unstructured network can learn translation, size, rotation, contrast, or, to a lesser degree, illumination invariance for one-dimensional objects, depending on only the training stimulus. Surprisingly, only a few training objects suffice to achieve good generalization to new objects. The generated representation is suitable for object recognition. Performance degrades if the network is trained to learn multiple invariances simultaneously.

Rotation invariant fast features for large-scale recognition

Science.gov (United States)

Takacs, Gabriel; Chandrasekhar, Vijay; Tsai, Sam; Chen, David; Grzeszczuk, Radek; Girod, Bernd

2012-10-01

We present an end-to-end feature description pipeline which uses a novel interest point detector and Rotation- Invariant Fast Feature (RIFF) descriptors. The proposed RIFF algorithm is 15× faster than SURF1 while producing large-scale retrieval results that are comparable to SIFT.2 Such high-speed features benefit a range of applications from Mobile Augmented Reality (MAR) to web-scale image retrieval and analysis.

Features of MCNP6

International Nuclear Information System (INIS)

Goorley, T.; James, M.; Booth, T.; Brown, F.; Bull, J.; Cox, L.J.; Durkee, J.; Elson, J.; Fensin, M.; Forster, R.A.; Hendricks, J.; Hughes, H.G.; Johns, R.; Kiedrowski, B.; Martz, R.; Mashnik, S.; McKinney, G.; Pelowitz, D.; Prael, R.; Sweezy, J.

2016-01-01

Highlights: • MCNP6 is simply and accurately described as the merger of MCNP5 and MCNPX capabilities, but it is much more than the sum of these two computer codes. • MCNP6 is the result of six years of effort by the MCNP5 and MCNPX code development teams. • These groups of people, residing in Los Alamos National Laboratory’s X Computational Physics Division, Monte Carlo Codes Group (XCP-3) and Nuclear Engineering and Nonproliferation Division, Radiation Transport Modeling Team (NEN-5) respectively, have combined their code development efforts to produce the next evolution of MCNP. • While maintenance and major bug fixes will continue for MCNP5 1.60 and MCNPX 2.7.0 for upcoming years, new code development capabilities only will be developed and released in MCNP6. • In fact, the initial release of MCNP6 contains numerous new features not previously found in either code. • These new features are summarized in this document. • Packaged with MCNP6 is also the new production release of the ENDF/B-VII.1 nuclear data files usable by MCNP. • The high quality of the overall merged code, usefulness of these new features, along with the desire in the user community to start using the merged code, have led us to make the first MCNP6 production release: MCNP6 version 1. • High confidence in the MCNP6 code is based on its performance with the verification and validation test suites, comparisons to its predecessor codes, our automated nightly software debugger tests, the underlying high quality nuclear and atomic databases, and significant testing by many beta testers. - Abstract: MCNP6 can be described as the merger of MCNP5 and MCNPX capabilities, but it is much more than the sum of these two computer codes. MCNP6 is the result of six years of effort by the MCNP5 and MCNPX code development teams. These groups of people, residing in Los Alamos National Laboratory’s X Computational Physics Division, Monte Carlo Codes Group (XCP-3) and Nuclear Engineering and

A performance evaluation of point pair features

DEFF Research Database (Denmark)

Kiforenko, Lilita; Drost, Bertram; Tombari, Federico

2018-01-01

have low resolution data, where local histogram features show a higher performance than PPFs. We also found that PPFs compared to most local histogram features degrade faster under disturbances such as occlusion and clutter, however, PPFs still remain more descriptive on an absolute scale. The main...

Feature Selection with the Boruta Package

OpenAIRE

Kursa, Miron B.; Rudnicki, Witold R.

2010-01-01

This article describes a R package Boruta, implementing a novel feature selection algorithm for finding emph{all relevant variables}. The algorithm is designed as a wrapper around a Random Forest classification algorithm. It iteratively removes the features which are proved by a statistical test to be less relevant than random probes. The Boruta package provides a convenient interface to the algorithm. The short description of the algorithm and examples of its application are presented.

Turkish Music Genre Classification using Audio and Lyrics Features

Directory of Open Access Journals (Sweden)

Önder ÇOBAN

2017-05-01

Full Text Available Music Information Retrieval (MIR has become a popular research area in recent years. In this context, researchers have developed music information systems to find solutions for such major problems as automatic playlist creation, hit song detection, and music genre or mood classification. Meta-data information, lyrics, or melodic content of music are used as feature resource in previous works. However, lyrics do not often used in MIR systems and the number of works in this field is not enough especially for Turkish. In this paper, firstly, we have extended our previously created Turkish MIR (TMIR dataset, which comprises of Turkish lyrics, by including the audio file of each song. Secondly, we have investigated the effect of using audio and textual features together or separately on automatic Music Genre Classification (MGC. We have extracted textual features from lyrics using different feature extraction models such as word2vec and traditional Bag of Words. We have conducted our experiments on Support Vector Machine (SVM algorithm and analysed the impact of feature selection and different feature groups on MGC. We have considered lyrics based MGC as a text classification task and also investigated the effect of term weighting method. Experimental results show that textual features can also be effective as well as audio features for Turkish MGC, especially when a supervised term weighting method is employed. We have achieved the highest success rate as 99,12\\% by using both audio and textual features together.

Feature selection gait-based gender classification under different circumstances

Science.gov (United States)

Sabir, Azhin; Al-Jawad, Naseer; Jassim, Sabah

2014-05-01

This paper proposes a gender classification based on human gait features and investigates the problem of two variations: clothing (wearing coats) and carrying bag condition as addition to the normal gait sequence. The feature vectors in the proposed system are constructed after applying wavelet transform. Three different sets of feature are proposed in this method. First, Spatio-temporal distance that is dealing with the distance of different parts of the human body (like feet, knees, hand, Human Height and shoulder) during one gait cycle. The second and third feature sets are constructed from approximation and non-approximation coefficient of human body respectively. To extract these two sets of feature we divided the human body into two parts, upper and lower body part, based on the golden ratio proportion. In this paper, we have adopted a statistical method for constructing the feature vector from the above sets. The dimension of the constructed feature vector is reduced based on the Fisher score as a feature selection method to optimize their discriminating significance. Finally k-Nearest Neighbor is applied as a classification method. Experimental results demonstrate that our approach is providing more realistic scenario and relatively better performance compared with the existing approaches.

Online Feature Transformation Learning for Cross-Domain Object Category Recognition.

Science.gov (United States)

Zhang, Xuesong; Zhuang, Yan; Wang, Wei; Pedrycz, Witold

2017-06-09

In this paper, we introduce a new research problem termed online feature transformation learning in the context of multiclass object category recognition. The learning of a feature transformation is viewed as learning a global similarity metric function in an online manner. We first consider the problem of online learning a feature transformation matrix expressed in the original feature space and propose an online passive aggressive feature transformation algorithm. Then these original features are mapped to kernel space and an online single kernel feature transformation (OSKFT) algorithm is developed to learn a nonlinear feature transformation. Based on the OSKFT and the existing Hedge algorithm, a novel online multiple kernel feature transformation algorithm is also proposed, which can further improve the performance of online feature transformation learning in large-scale application. The classifier is trained with k nearest neighbor algorithm together with the learned similarity metric function. Finally, we experimentally examined the effect of setting different parameter values in the proposed algorithms and evaluate the model performance on several multiclass object recognition data sets. The experimental results demonstrate the validity and good performance of our methods on cross-domain and multiclass object recognition application.

Classification of radiolarian images with hand-crafted and deep features

Science.gov (United States)

Keçeli, Ali Seydi; Kaya, Aydın; Keçeli, Seda Uzunçimen

2017-12-01

Radiolarians are planktonic protozoa and are important biostratigraphic and paleoenvironmental indicators for paleogeographic reconstructions. Radiolarian paleontology still remains as a low cost and the one of the most convenient way to obtain dating of deep ocean sediments. Traditional methods for identifying radiolarians are time-consuming and cannot scale to the granularity or scope necessary for large-scale studies. Automated image classification will allow making these analyses promptly. In this study, a method for automatic radiolarian image classification is proposed on Scanning Electron Microscope (SEM) images of radiolarians to ease species identification of fossilized radiolarians. The proposed method uses both hand-crafted features like invariant moments, wavelet moments, Gabor features, basic morphological features and deep features obtained from a pre-trained Convolutional Neural Network (CNN). Feature selection is applied over deep features to reduce high dimensionality. Classification outcomes are analyzed to compare hand-crafted features, deep features, and their combinations. Results show that the deep features obtained from a pre-trained CNN are more discriminative comparing to hand-crafted ones. Additionally, feature selection utilizes to the computational cost of classification algorithms and have no negative effect on classification accuracy.

Hybrid feature selection for supporting lightweight intrusion detection systems

Science.gov (United States)

Song, Jianglong; Zhao, Wentao; Liu, Qiang; Wang, Xin

2017-08-01

Redundant and irrelevant features not only cause high resource consumption but also degrade the performance of Intrusion Detection Systems (IDS), especially when coping with big data. These features slow down the process of training and testing in network traffic classification. Therefore, a hybrid feature selection approach in combination with wrapper and filter selection is designed in this paper to build a lightweight intrusion detection system. Two main phases are involved in this method. The first phase conducts a preliminary search for an optimal subset of features, in which the chi-square feature selection is utilized. The selected set of features from the previous phase is further refined in the second phase in a wrapper manner, in which the Random Forest(RF) is used to guide the selection process and retain an optimized set of features. After that, we build an RF-based detection model and make a fair comparison with other approaches. The experimental results on NSL-KDD datasets show that our approach results are in higher detection accuracy as well as faster training and testing processes.

FEATURE EXTRACTION FOR EMG BASED PROSTHESES CONTROL

Directory of Open Access Journals (Sweden)

R. Aishwarya

2013-01-01

Full Text Available The control of prosthetic limb would be more effective if it is based on Surface Electromyogram (SEMG signals from remnant muscles. The analysis of SEMG signals depend on a number of factors, such as amplitude as well as time- and frequency-domain properties. Time series analysis using Auto Regressive (AR model and Mean frequency which is tolerant to white Gaussian noise are used as feature extraction techniques. EMG Histogram is used as another feature vector that was seen to give more distinct classification. The work was done with SEMG dataset obtained from the NINAPRO DATABASE, a resource for bio robotics community. Eight classes of hand movements hand open, hand close, Wrist extension, Wrist flexion, Pointing index, Ulnar deviation, Thumbs up, Thumb opposite to little finger are taken into consideration and feature vectors are extracted. The feature vectors can be given to an artificial neural network for further classification in controlling the prosthetic arm which is not dealt in this paper.

Reductio ad discrimen: Where features come from

Directory of Open Access Journals (Sweden)

Elizabeth Cowper

2015-04-01

Full Text Available This paper addresses two fundamental questions about the nature of formal features in phonology and morphosyntax: what is their expressive power, and where do they come from? To answer these questions, we begin with the most restrictive possible hypothesis (all features are privative, and are wholly dictated by Universal Grammar, with no room for cross-linguistic variation, and examine the extent to which empirical evidence from a variety of languages compels a retreat from this position. We argue that there is little to be gained by positing a universal set of specific features, and propose instead that the crucial contribution of UG is the language learner's ability to construct features by identifying correlations between contrasts at different levels of linguistic structure. This view resonates with current research on how the interaction between UG and external 'third factors' shapes the structure of language, while at the same time harking back to the Saussurean notion that contrast is the central function of linguistic representations.

Individual discriminative face recognition models based on subsets of features

DEFF Research Database (Denmark)

Clemmensen, Line Katrine Harder; Gomez, David Delgado; Ersbøll, Bjarne Kjær

2007-01-01

The accuracy of data classification methods depends considerably on the data representation and on the selected features. In this work, the elastic net model selection is used to identify meaningful and important features in face recognition. Modelling the characteristics which distinguish one...... person from another using only subsets of features will both decrease the computational cost and increase the generalization capacity of the face recognition algorithm. Moreover, identifying which are the features that better discriminate between persons will also provide a deeper understanding...... of the face recognition problem. The elastic net model is able to select a subset of features with low computational effort compared to other state-of-the-art feature selection methods. Furthermore, the fact that the number of features usually is larger than the number of images in the data base makes feature...

Saliency image of feature building for image quality assessment

Science.gov (United States)

Ju, Xinuo; Sun, Jiyin; Wang, Peng

2011-11-01

The purpose and method of image quality assessment are quite different for automatic target recognition (ATR) and traditional application. Local invariant feature detectors, mainly including corner detectors, blob detectors and region detectors etc., are widely applied for ATR. A saliency model of feature was proposed to evaluate feasibility of ATR in this paper. The first step consisted of computing the first-order derivatives on horizontal orientation and vertical orientation, and computing DoG maps in different scales respectively. Next, saliency images of feature were built based auto-correlation matrix in different scale. Then, saliency images of feature of different scales amalgamated. Experiment were performed on a large test set, including infrared images and optical images, and the result showed that the salient regions computed by this model were consistent with real feature regions computed by mostly local invariant feature extraction algorithms.

Boosting Discriminant Learners for Gait Recognition Using MPCA Features

Directory of Open Access Journals (Sweden)

Haiping Lu

2009-01-01

Full Text Available This paper proposes a boosted linear discriminant analysis (LDA solution on features extracted by the multilinear principal component analysis (MPCA to enhance gait recognition performance. Three-dimensional gait objects are projected in the MPCA space first to obtain low-dimensional tensorial features. Then, lower-dimensional vectorial features are obtained through discriminative feature selection. These feature vectors are then fed into an LDA-style booster, where several regularized and weakened LDA learners work together to produce a strong learner through a novel feature weighting and sampling process. The LDA learner employs a simple nearest-neighbor classifier with a weighted angle distance measure for classification. The experimental results on the NIST/USF “Gait Challenge” data-sets show that the proposed solution has successfully improved the gait recognition performance and outperformed several state-of-the-art gait recognition algorithms.

Detection of Fraudulent Emails by Employing Advanced Feature Abundance

DEFF Research Database (Denmark)

Nizamani, Sarwat; Memon, Nasrullah; Glasdam, Mathies

2014-01-01

In this paper, we present a fraudulent email detection model using advanced feature choice. We extracted various kinds of features and compared the performance of each category of features with the others in terms of the fraudulent email detection rate. The different types of features...... are incorporated step by step. The detection of fraudulent email has been considered as a classification problem and it is evaluated using various state-of-the art algorithms and on CCM [1] which is authors' previous cluster based classification model. The experiments have been performed on diverse feature sets...... and the different classification methods. The comparison of the results is also presented and the evaluations shows that for the fraudulent email detection tasks, the feature set is more important regardless of classification method. The results of the study suggest that the task of fraudulent emails detection...

Cloud field classification based on textural features

Science.gov (United States)

Sengupta, Sailes Kumar

1989-01-01

An essential component in global climate research is accurate cloud cover and type determination. Of the two approaches to texture-based classification (statistical and textural), only the former is effective in the classification of natural scenes such as land, ocean, and atmosphere. In the statistical approach that was adopted, parameters characterizing the stochastic properties of the spatial distribution of grey levels in an image are estimated and then used as features for cloud classification. Two types of textural measures were used. One is based on the distribution of the grey level difference vector (GLDV), and the other on a set of textural features derived from the MaxMin cooccurrence matrix (MMCM). The GLDV method looks at the difference D of grey levels at pixels separated by a horizontal distance d and computes several statistics based on this distribution. These are then used as features in subsequent classification. The MaxMin tectural features on the other hand are based on the MMCM, a matrix whose (I,J)th entry give the relative frequency of occurrences of the grey level pair (I,J) that are consecutive and thresholded local extremes separated by a given pixel distance d. Textural measures are then computed based on this matrix in much the same manner as is done in texture computation using the grey level cooccurrence matrix. The database consists of 37 cloud field scenes from LANDSAT imagery using a near IR visible channel. The classification algorithm used is the well known Stepwise Discriminant Analysis. The overall accuracy was estimated by the percentage or correct classifications in each case. It turns out that both types of classifiers, at their best combination of features, and at any given spatial resolution give approximately the same classification accuracy. A neural network based classifier with a feed forward architecture and a back propagation training algorithm is used to increase the classification accuracy, using these two classes

A TALE OF THREE MYSTERIOUS SPECTRAL FEATURES IN CARBON-RICH EVOLVED STARS: THE 21 μm, 30 μm, AND “UNIDENTIFIED INFRARED” EMISSION FEATURES

Energy Technology Data Exchange (ETDEWEB)

Mishra, Ajay; Li, Aigen [Department of Physics and Astronomy, University of Missouri, Columbia, MO 65211 (United States); Jiang, B. W., E-mail: amishra@mail.missouri.edu, E-mail: lia@missouri.edu, E-mail: bjiang@bnu.edu.cn [Department of Astronomy, Beijing Normal University, Beijing 100875 (China)

2015-03-20

The mysterious “21 μm” emission feature seen almost exclusively in the short-lived protoplanetary nebula (PPN) phase of stellar evolution remains unidentified since its discovery two decades ago. This feature is always accompanied by the equally mysterious, unidentified “30 μm” feature and the so-called “unidentified infrared” (UIR) features at 3.3, 6.2, 7.7, 8.6, and 11.3 μm which are generally attributed to polycyclic aromatic hydrocarbon (PAH) molecules. The 30 μm feature is commonly observed in all stages of stellar evolution from the asymptotic giant branch through PPN to the planetary nebula phase. We explore the interrelations among the mysterious 21, 30 μm, and UIR features of the 21 μm sources. We derive the fluxes emitted in the observed UIR, 21, and 30 μm features from published Infrared Space Observatory or Spitzer/IRS spectra. We find that none of these spectral features correlate with each other. This argues against a common carrier (e.g., thiourea) for both the 21 μm feature and the 30 μm feature. This also does not support large PAH clusters as a possible carrier for the 21 μm feature.

Multithreaded hybrid feature tracking for markerless augmented reality.

Science.gov (United States)

Lee, Taehee; Höllerer, Tobias

2009-01-01

We describe a novel markerless camera tracking approach and user interaction methodology for augmented reality (AR) on unprepared tabletop environments. We propose a real-time system architecture that combines two types of feature tracking. Distinctive image features of the scene are detected and tracked frame-to-frame by computing optical flow. In order to achieve real-time performance, multiple operations are processed in a synchronized multi-threaded manner: capturing a video frame, tracking features using optical flow, detecting distinctive invariant features, and rendering an output frame. We also introduce user interaction methodology for establishing a global coordinate system and for placing virtual objects in the AR environment by tracking a user's outstretched hand and estimating a camera pose relative to it. We evaluate the speed and accuracy of our hybrid feature tracking approach, and demonstrate a proof-of-concept application for enabling AR in unprepared tabletop environments, using bare hands for interaction.

Image Recommendation Algorithm Using Feature-Based Collaborative Filtering

Science.gov (United States)

Kim, Deok-Hwan

As the multimedia contents market continues its rapid expansion, the amount of image contents used in mobile phone services, digital libraries, and catalog service is increasing remarkably. In spite of this rapid growth, users experience high levels of frustration when searching for the desired image. Even though new images are profitable to the service providers, traditional collaborative filtering methods cannot recommend them. To solve this problem, in this paper, we propose feature-based collaborative filtering (FBCF) method to reflect the user's most recent preference by representing his purchase sequence in the visual feature space. The proposed approach represents the images that have been purchased in the past as the feature clusters in the multi-dimensional feature space and then selects neighbors by using an inter-cluster distance function between their feature clusters. Various experiments using real image data demonstrate that the proposed approach provides a higher quality recommendation and better performance than do typical collaborative filtering and content-based filtering techniques.

Infants' Developing Sensitivity to Object Function: Attention to Features and Feature Correlations

Science.gov (United States)

Baumgartner, Heidi A.; Oakes, Lisa M.

2011-01-01

When learning object function, infants must detect relations among features--for example, that squeezing is associated with squeaking or that objects with wheels roll. Previously, Perone and Oakes (2006) found 10-month-old infants were sensitive to relations between object appearances and actions, but not to relations between appearances and…

A Study of Feature Extraction Using Divergence Analysis of Texture Features

Science.gov (United States)

Hallada, W. A.; Bly, B. G.; Boyd, R. K.; Cox, S.

1982-01-01

An empirical study of texture analysis for feature extraction and classification of high spatial resolution remotely sensed imagery (10 meters) is presented in terms of specific land cover types. The principal method examined is the use of spatial gray tone dependence (SGTD). The SGTD method reduces the gray levels within a moving window into a two-dimensional spatial gray tone dependence matrix which can be interpreted as a probability matrix of gray tone pairs. Haralick et al (1973) used a number of information theory measures to extract texture features from these matrices, including angular second moment (inertia), correlation, entropy, homogeneity, and energy. The derivation of the SGTD matrix is a function of: (1) the number of gray tones in an image; (2) the angle along which the frequency of SGTD is calculated; (3) the size of the moving window; and (4) the distance between gray tone pairs. The first three parameters were varied and tested on a 10 meter resolution panchromatic image of Maryville, Tennessee using the five SGTD measures. A transformed divergence measure was used to determine the statistical separability between four land cover categories forest, new residential, old residential, and industrial for each variation in texture parameters.

Creating fair lineups for suspects with distinctive features

OpenAIRE

Zarkadi, Theodora; Wade, Kimberley A.; Stewart, Neil

2009-01-01

In their descriptions, eyewitnesses often refer to a culprit's distinctive facial features. However, in a police lineup, selecting the only member with the described distinctive feature is unfair to the suspect and provides the police with little further information. For fair and informative lineups, the distinctive feature should be either replicated across foils or concealed on the target. In the present experiments, replication produced more correct identifications in target-present lineup...

Bread crumb classification using fractal and multifractal features

OpenAIRE

Baravalle, Rodrigo Guillermo; Delrieux, Claudio Augusto; Gómez, Juan Carlos

2017-01-01

Adequate image descriptors are fundamental in image classification and object recognition. Main requirements for image features are robustness and low dimensionality which would lead to low classification errors in a variety of situations and with a reasonable computational cost. In this context, the identification of materials poses a significant challenge, since typical (geometric and/or differential) feature extraction methods are not robust enough. Texture features based on Fourier or wav...

Sequence-based classification using discriminatory motif feature selection.

Directory of Open Access Journals (Sweden)

Hao Xiong

Full Text Available Most existing methods for sequence-based classification use exhaustive feature generation, employing, for example, all k-mer patterns. The motivation behind such (enumerative approaches is to minimize the potential for overlooking important features. However, there are shortcomings to this strategy. First, practical constraints limit the scope of exhaustive feature generation to patterns of length ≤ k, such that potentially important, longer (> k predictors are not considered. Second, features so generated exhibit strong dependencies, which can complicate understanding of derived classification rules. Third, and most importantly, numerous irrelevant features are created. These concerns can compromise prediction and interpretation. While remedies have been proposed, they tend to be problem-specific and not broadly applicable. Here, we develop a generally applicable methodology, and an attendant software pipeline, that is predicated on discriminatory motif finding. In addition to the traditional training and validation partitions, our framework entails a third level of data partitioning, a discovery partition. A discriminatory motif finder is used on sequences and associated class labels in the discovery partition to yield a (small set of features. These features are then used as inputs to a classifier in the training partition. Finally, performance assessment occurs on the validation partition. Important attributes of our approach are its modularity (any discriminatory motif finder and any classifier can be deployed and its universality (all data, including sequences that are unaligned and/or of unequal length, can be accommodated. We illustrate our approach on two nucleosome occupancy datasets and a protein solubility dataset, previously analyzed using enumerative feature generation. Our method achieves excellent performance results, with and without optimization of classifier tuning parameters. A Python pipeline implementing the approach is

Feature-Based Statistical Analysis of Combustion Simulation Data

Energy Technology Data Exchange (ETDEWEB)

Bennett, J; Krishnamoorthy, V; Liu, S; Grout, R; Hawkes, E; Chen, J; Pascucci, V; Bremer, P T

2011-11-18

We present a new framework for feature-based statistical analysis of large-scale scientific data and demonstrate its effectiveness by analyzing features from Direct Numerical Simulations (DNS) of turbulent combustion. Turbulent flows are ubiquitous and account for transport and mixing processes in combustion, astrophysics, fusion, and climate modeling among other disciplines. They are also characterized by coherent structure or organized motion, i.e. nonlocal entities whose geometrical features can directly impact molecular mixing and reactive processes. While traditional multi-point statistics provide correlative information, they lack nonlocal structural information, and hence, fail to provide mechanistic causality information between organized fluid motion and mixing and reactive processes. Hence, it is of great interest to capture and track flow features and their statistics together with their correlation with relevant scalar quantities, e.g. temperature or species concentrations. In our approach we encode the set of all possible flow features by pre-computing merge trees augmented with attributes, such as statistical moments of various scalar fields, e.g. temperature, as well as length-scales computed via spectral analysis. The computation is performed in an efficient streaming manner in a pre-processing step and results in a collection of meta-data that is orders of magnitude smaller than the original simulation data. This meta-data is sufficient to support a fully flexible and interactive analysis of the features, allowing for arbitrary thresholds, providing per-feature statistics, and creating various global diagnostics such as Cumulative Density Functions (CDFs), histograms, or time-series. We combine the analysis with a rendering of the features in a linked-view browser that enables scientists to interactively explore, visualize, and analyze the equivalent of one terabyte of simulation data. We highlight the utility of this new framework for combustion

Discrete-Feature Model Implementation of SDM-Site Forsmark

Energy Technology Data Exchange (ETDEWEB)

Geier, Joel (Clearwater Hardrock Consulting, Corvallis, OR (United States))

2010-03-15

A discrete-feature model (DFM) was implemented for the Forsmark repository site based on the final site descriptive model from surface based investigations. The discrete-feature conceptual model represents deformation zones, individual fractures, and other water-conducting features around a repository as discrete conductors surrounded by a rock matrix which, in the present study, is treated as impermeable. This approximation is reasonable for sites in crystalline rock which has very low permeability, apart from that which results from macroscopic fracturing. Models are constructed based on the geological and hydrogeological description of the sites and engineering designs. Hydraulic heads and flows through the network of water-conducting features are calculated by the finite-element method, and are used in turn to simulate migration of non-reacting solute by a particle-tracking method, in order to estimate the properties of pathways by which radionuclides could be released to the biosphere. Stochastic simulation is used to evaluate portions of the model that can only be characterized in statistical terms, since many water-conducting features within the model volume cannot be characterized deterministically. Chapter 2 describes the methodology by which discrete features are derived to represent water-conducting features around the hypothetical repository at Forsmark (including both natural features and features that result from the disturbance of excavation), and then assembled to produce a discrete-feature network model for numerical simulation of flow and transport. Chapter 3 describes how site-specific data and repository design are adapted to produce the discrete-feature model. Chapter 4 presents results of the calculations. These include utilization factors for deposition tunnels based on the emplacement criteria that have been set forth by the implementers, flow distributions to the deposition holes, and calculated properties of discharge paths as well as

Discrete-Feature Model Implementation of SDM-Site Forsmark

International Nuclear Information System (INIS)

Geier, Joel

2010-03-01

A discrete-feature model (DFM) was implemented for the Forsmark repository site based on the final site descriptive model from surface based investigations. The discrete-feature conceptual model represents deformation zones, individual fractures, and other water-conducting features around a repository as discrete conductors surrounded by a rock matrix which, in the present study, is treated as impermeable. This approximation is reasonable for sites in crystalline rock which has very low permeability, apart from that which results from macroscopic fracturing. Models are constructed based on the geological and hydrogeological description of the sites and engineering designs. Hydraulic heads and flows through the network of water-conducting features are calculated by the finite-element method, and are used in turn to simulate migration of non-reacting solute by a particle-tracking method, in order to estimate the properties of pathways by which radionuclides could be released to the biosphere. Stochastic simulation is used to evaluate portions of the model that can only be characterized in statistical terms, since many water-conducting features within the model volume cannot be characterized deterministically. Chapter 2 describes the methodology by which discrete features are derived to represent water-conducting features around the hypothetical repository at Forsmark (including both natural features and features that result from the disturbance of excavation), and then assembled to produce a discrete-feature network model for numerical simulation of flow and transport. Chapter 3 describes how site-specific data and repository design are adapted to produce the discrete-feature model. Chapter 4 presents results of the calculations. These include utilization factors for deposition tunnels based on the emplacement criteria that have been set forth by the implementers, flow distributions to the deposition holes, and calculated properties of discharge paths as well as

A new approach for detecting local features

DEFF Research Database (Denmark)

Nguyen, Phuong Giang; Andersen, Hans Jørgen

2010-01-01

Local features up to now are often mentioned in the meaning of interest points. A patch around each point is formed to compute descriptors or feature vectors. Therefore, in order to satisfy different invariant imaging conditions such as scales and viewpoints, an input image is often represented i...

Meta-Level Runtime Feature Awareness for Java

DEFF Research Database (Denmark)

Olszak, Andrzej; Jensen, Martin Lykke Rytter; Jørgensen, Bo Nørregaard

2011-01-01

introduce the concept of runtime feature awareness that enables a running program to establish and make use of its own feature-code traceability links. We present an implementation of this idea, a dynamic-analysis Java library called JAwareness. JAwareness provides a meta-level architecture that can be non...

Constraint solving for direct manipulation of features

NARCIS (Netherlands)

Lourenco, D.; Oliveira, P.; Noort, A.; Bidarra, R.

2006-01-01

In current commercial feature modeling systems, support for direct manipulation of features is not commonly available. This is partly due to the strong reliance of such systems on constraints, but also to the lack of speed of current constraint solvers. In this paper, an approach to the optimization

Feature-Fusion Guidelines for Image-Based Multi-Modal Biometric Fusion

Directory of Open Access Journals (Sweden)

Dane Brown

2017-07-01

Full Text Available The feature level, unlike the match score level, lacks multi-modal fusion guidelines. This work demonstrates a new approach for improved image-based biometric feature-fusion. The approach extracts and combines the face, fingerprint and palmprint at the feature level for improved human identification accuracy. Feature-fusion guidelines, proposed in our recent work, are extended by adding a new face segmentation method and the support vector machine classifier. The new face segmentation method improves the face identification equal error rate (EER by 10%. The support vector machine classifier combined with the new feature selection approach, proposed in our recent work, outperforms other classifiers when using a single training sample. Feature-fusion guidelines take the form of strengths and weaknesses as observed in the applied feature processing modules during preliminary experiments. The guidelines are used to implement an effective biometric fusion system at the feature level, using a novel feature-fusion methodology, reducing the EER of two groups of three datasets namely: SDUMLA face, SDUMLA fingerprint and IITD palmprint; MUCT Face, MCYT Fingerprint and CASIA Palmprint.

Alexnet Feature Extraction and Multi-Kernel Learning for Objectoriented Classification

Science.gov (United States)

Ding, L.; Li, H.; Hu, C.; Zhang, W.; Wang, S.

2018-04-01

In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

ALEXNET FEATURE EXTRACTION AND MULTI-KERNEL LEARNING FOR OBJECTORIENTED CLASSIFICATION

Directory of Open Access Journals (Sweden)

L. Ding

2018-04-01

Full Text Available In view of the fact that the deep convolutional neural network has stronger ability of feature learning and feature expression, an exploratory research is done on feature extraction and classification for high resolution remote sensing images. Taking the Google image with 0.3 meter spatial resolution in Ludian area of Yunnan Province as an example, the image segmentation object was taken as the basic unit, and the pre-trained AlexNet deep convolution neural network model was used for feature extraction. And the spectral features, AlexNet features and GLCM texture features are combined with multi-kernel learning and SVM classifier, finally the classification results were compared and analyzed. The results show that the deep convolution neural network can extract more accurate remote sensing image features, and significantly improve the overall accuracy of classification, and provide a reference value for earthquake disaster investigation and remote sensing disaster evaluation.

Stylistic Features of the Legal Discourse | Alabi | UJAH: Unizik ...

African Journals Online (AJOL)

Every profession, every occupation, for example architecture, journalism, medicine, sports, has its specialised language features. These features may be viewed at the phonological, semantic, syntactic, lexical and graphological levels, among others. The language features identified with certain professions are most of the ...

A keyword spotting model using perceptually significant energy features

Science.gov (United States)

Umakanthan, Padmalochini

The task of a keyword recognition system is to detect the presence of certain words in a conversation based on the linguistic information present in human speech. Such keyword spotting systems have applications in homeland security, telephone surveillance and human-computer interfacing. General procedure of a keyword spotting system involves feature generation and matching. In this work, new set of features that are based on the psycho-acoustic masking nature of human speech are proposed. After developing these features a time aligned pattern matching process was implemented to locate the words in a set of unknown words. A word boundary detection technique based on frame classification using the nonlinear characteristics of speech is also addressed in this work. Validation of this keyword spotting model was done using widely acclaimed Cepstral features. The experimental results indicate the viability of using these perceptually significant features as an augmented feature set in keyword spotting.

Feature Selection Criteria for Real Time EKF-SLAM Algorithm

Directory of Open Access Journals (Sweden)

Fernando Auat Cheein

2010-02-01

Full Text Available This paper presents a seletion procedure for environmet features for the correction stage of a SLAM (Simultaneous Localization and Mapping algorithm based on an Extended Kalman Filter (EKF. This approach decreases the computational time of the correction stage which allows for real and constant-time implementations of the SLAM. The selection procedure consists in chosing the features the SLAM system state covariance is more sensible to. The entire system is implemented on a mobile robot equipped with a range sensor laser. The features extracted from the environment correspond to lines and corners. Experimental results of the real time SLAM algorithm and an analysis of the processing-time consumed by the SLAM with the feature selection procedure proposed are shown. A comparison between the feature selection approach proposed and the classical sequential EKF-SLAM along with an entropy feature selection approach is also performed.

Feature Selection with the Boruta Package

Directory of Open Access Journals (Sweden)

Miron B. Kursa

2010-10-01

Full Text Available This article describes a R package Boruta, implementing a novel feature selection algorithm for finding emph{all relevant variables}. The algorithm is designed as a wrapper around a Random Forest classification algorithm. It iteratively removes the features which are proved by a statistical test to be less relevant than random probes. The Boruta package provides a convenient interface to the algorithm. The short description of the algorithm and examples of its application are presented.

Quantitative Comparison of Tolerance-Based Feature Transforms

NARCIS (Netherlands)

Reniers, Dennie; Telea, Alexandru

2006-01-01

Tolerance-based feature transforms (TFTs) assign to each pixel in an image not only the nearest feature pixels on the boundary (origins), but all origins from the minimum distance up to a user-defined tolerance. In this paper, we compare four simple-to-implement methods for computing TFTs for binary

W-transform method for feature-oriented multiresolution image retrieval

Energy Technology Data Exchange (ETDEWEB)

Kwong, M.K.; Lin, B. [Argonne National Lab., IL (United States). Mathematics and Computer Science Div.

1995-07-01

Image database management is important in the development of multimedia technology. Since an enormous amount of digital images is likely to be generated within the next few decades in order to integrate computers, television, VCR, cables, telephone and various imaging devices. Effective image indexing and retrieval systems are urgently needed so that images can be easily organized, searched, transmitted, and presented. Here, the authors present a local-feature-oriented image indexing and retrieval method based on Kwong, and Tang`s W-transform. Multiresolution histogram comparison is an effective method for content-based image indexing and retrieval. However, most recent approaches perform multiresolution analysis for whole images but do not exploit the local features present in the images. Since W-transform is featured by its ability to handle images of arbitrary size, with no periodicity assumptions, it provides a natural tool for analyzing local image features and building indexing systems based on such features. In this approach, the histograms of the local features of images are used in the indexing, system. The system not only can retrieve images that are similar or identical to the query images but also can retrieve images that contain features specified in the query images, even if the retrieved images as a whole might be very different from the query images. The local-feature-oriented method also provides a speed advantage over the global multiresolution histogram comparison method. The feature-oriented approach is expected to be applicable in managing large-scale image systems such as video databases and medical image databases.

Diffusion tensor image registration using hybrid connectivity and tensor features.

Science.gov (United States)

Wang, Qian; Yap, Pew-Thian; Wu, Guorong; Shen, Dinggang

2014-07-01

Most existing diffusion tensor imaging (DTI) registration methods estimate structural correspondences based on voxelwise matching of tensors. The rich connectivity information that is given by DTI, however, is often neglected. In this article, we propose to integrate complementary information given by connectivity features and tensor features for improved registration accuracy. To utilize connectivity information, we place multiple anchors representing different brain anatomies in the image space, and define the connectivity features for each voxel as the geodesic distances from all anchors to the voxel under consideration. The geodesic distance, which is computed in relation to the tensor field, encapsulates information of brain connectivity. We also extract tensor features for every voxel to reflect the local statistics of tensors in its neighborhood. We then combine both connectivity features and tensor features for registration of tensor images. From the images, landmarks are selected automatically and their correspondences are determined based on their connectivity and tensor feature vectors. The deformation field that deforms one tensor image to the other is iteratively estimated and optimized according to the landmarks and their associated correspondences. Experimental results show that, by using connectivity features and tensor features simultaneously, registration accuracy is increased substantially compared with the cases using either type of features alone. Copyright © 2013 Wiley Periodicals, Inc.

Acoustic features of objects matched by an echolocating bottlenose dolphin.

Science.gov (United States)

Delong, Caroline M; Au, Whitlow W L; Lemonds, David W; Harley, Heidi E; Roitblat, Herbert L

2006-03-01

The focus of this study was to investigate how dolphins use acoustic features in returning echolocation signals to discriminate among objects. An echolocating dolphin performed a match-to-sample task with objects that varied in size, shape, material, and texture. After the task was completed, the features of the object echoes were measured (e.g., target strength, peak frequency). The dolphin's error patterns were examined in conjunction with the between-object variation in acoustic features to identify the acoustic features that the dolphin used to discriminate among the objects. The present study explored two hypotheses regarding the way dolphins use acoustic information in echoes: (1) use of a single feature, or (2) use of a linear combination of multiple features. The results suggested that dolphins do not use a single feature across all object sets or a linear combination of six echo features. Five features appeared to be important to the dolphin on four or more sets: the echo spectrum shape, the pattern of changes in target strength and number of highlights as a function of object orientation, and peak and center frequency. These data suggest that dolphins use multiple features and integrate information across echoes from a range of object orientations.

Intuitiveness of Symbol Features for Air Traffic Management

Science.gov (United States)

Ngo, Mary Kim; Vu, Kim-Phuong L.; Thorpe, Elaine; Battiste, Vernol; Strybel, Thomas Z.

2012-01-01

We present the results of two online surveys asking participants to indicate what type of air traffic information might be conveyed by a number of symbols and symbol features (color, fill, text, and shape). The results of this initial study suggest that the well-developed concepts of ownership, altitude, and trajectory are readily associated with certain symbol features, while the relatively novel concept of equipage was not clearly associated with any specific symbol feature.

Classification of line features from remote sensing data

OpenAIRE

Kolankiewiczová, Soňa

2009-01-01

This work deals with object-based classification of high resolution data. The aim of the thesis (paper, work) is to develope an acceptable classification process of linear features (roads and railways) from high-resolution satellite images. The first part shows different approaches of the linear feature classification and compares theoretic differences between an object-oriented and a pixel-based classification. Linear feature classification was created in the second part. The high-resolution...

Characteristic features of the exotic superconductors: A summary

International Nuclear Information System (INIS)

Brandow, B.

1997-09-01

The authors summarize the results of a comprehensive examination of the characteristic features of the exotic superconductors, the superconductors so-labelled by Uemura and co-workers. In both the electronic and the crystal-chemistry properties, they find anomalous features which appear to be universal for these materials, as well as other features which are clearly not universal but common enough to be considered typical for these materials. Some implications of these anomalies are discussed

Pedestrian count estimation using texture feature with spatial distribution

Directory of Open Access Journals (Sweden)

Hongyu Hu

2016-12-01

Full Text Available We present a novel pedestrian count estimation approach based on global image descriptors formed from multi-scale texture features that considers spatial distribution. For regions of interest, local texture features are represented based on histograms of multi-scale block local binary pattern, which jointly constitute the feature vector of the whole image. Therefore, to achieve an effective estimation of pedestrian count, principal component analysis is used to reduce the dimension of the global representation features, and a fitting model between image global features and pedestrian count is constructed via support vector regression. The experimental result shows that the proposed method exhibits high accuracy on pedestrian count estimation and can be applied well in the real world.

Breast image feature learning with adaptive deconvolutional networks

Science.gov (United States)

Jamieson, Andrew R.; Drukker, Karen; Giger, Maryellen L.

2012-03-01

Feature extraction is a critical component of medical image analysis. Many computer-aided diagnosis approaches employ hand-designed, heuristic lesion extracted features. An alternative approach is to learn features directly from images. In this preliminary study, we explored the use of Adaptive Deconvolutional Networks (ADN) for learning high-level features in diagnostic breast mass lesion images with potential application to computer-aided diagnosis (CADx) and content-based image retrieval (CBIR). ADNs (Zeiler, et. al., 2011), are recently-proposed unsupervised, generative hierarchical models that decompose images via convolution sparse coding and max pooling. We trained the ADNs to learn multiple layers of representation for two breast image data sets on two different modalities (739 full field digital mammography (FFDM) and 2393 ultrasound images). Feature map calculations were accelerated by use of GPUs. Following Zeiler et. al., we applied the Spatial Pyramid Matching (SPM) kernel (Lazebnik, et. al., 2006) on the inferred feature maps and combined this with a linear support vector machine (SVM) classifier for the task of binary classification between cancer and non-cancer breast mass lesions. Non-linear, local structure preserving dimension reduction, Elastic Embedding (Carreira-Perpiñán, 2010), was then used to visualize the SPM kernel output in 2D and qualitatively inspect image relationships learned. Performance was found to be competitive with current CADx schemes that use human-designed features, e.g., achieving a 0.632+ bootstrap AUC (by case) of 0.83 [0.78, 0.89] for an ultrasound image set (1125 cases).

Divided spatial attention and feature-mixing errors.

Science.gov (United States)

Golomb, Julie D

2015-11-01

Spatial attention is thought to play a critical role in feature binding. However, often multiple objects or locations are of interest in our environment, and we need to shift or split attention between them. Recent evidence has demonstrated that shifting and splitting spatial attention results in different types of feature-binding errors. In particular, when two locations are simultaneously sharing attentional resources, subjects are susceptible to feature-mixing errors; that is, they tend to report a color that is a subtle blend of the target color and the color at the other attended location. The present study was designed to test whether these feature-mixing errors are influenced by target-distractor similarity. Subjects were cued to split attention across two different spatial locations, and were subsequently presented with an array of colored stimuli, followed by a postcue indicating which color to report. Target-distractor similarity was manipulated by varying the distance in color space between the two attended stimuli. Probabilistic modeling in all cases revealed shifts in the response distribution consistent with feature-mixing errors; however, the patterns differed considerably across target-distractor color distances. With large differences in color, the findings replicated the mixing result, but with small color differences, repulsion was instead observed, with the reported target color shifted away from the other attended color.

Face Alignment via Regressing Local Binary Features.

Science.gov (United States)

Ren, Shaoqing; Cao, Xudong; Wei, Yichen; Sun, Jian

2016-03-01

This paper presents a highly efficient and accurate regression approach for face alignment. Our approach has two novel components: 1) a set of local binary features and 2) a locality principle for learning those features. The locality principle guides us to learn a set of highly discriminative local binary features for each facial landmark independently. The obtained local binary features are used to jointly learn a linear regression for the final output. This approach achieves the state-of-the-art results when tested on the most challenging benchmarks to date. Furthermore, because extracting and regressing local binary features are computationally very cheap, our system is much faster than previous methods. It achieves over 3000 frames per second (FPS) on a desktop or 300 FPS on a mobile phone for locating a few dozens of landmarks. We also study a key issue that is important but has received little attention in the previous research, which is the face detector used to initialize alignment. We investigate several face detectors and perform quantitative evaluation on how they affect alignment accuracy. We find that an alignment friendly detector can further greatly boost the accuracy of our alignment method, reducing the error up to 16% relatively. To facilitate practical usage of face detection/alignment methods, we also propose a convenient metric to measure how good a detector is for alignment initialization.

Face-iris multimodal biometric scheme based on feature level fusion

Science.gov (United States)

Huo, Guang; Liu, Yuanning; Zhu, Xiaodong; Dong, Hongxing; He, Fei

2015-11-01

Unlike score level fusion, feature level fusion demands all the features extracted from unimodal traits with high distinguishability, as well as homogeneity and compatibility, which is difficult to achieve. Therefore, most multimodal biometric research focuses on score level fusion, whereas few investigate feature level fusion. We propose a face-iris recognition method based on feature level fusion. We build a special two-dimensional-Gabor filter bank to extract local texture features from face and iris images, and then transform them by histogram statistics into an energy-orientation variance histogram feature with lower dimensions and higher distinguishability. Finally, through a fusion-recognition strategy based on principal components analysis and support vector machine (FRSPS), feature level fusion and one-to-n identification are accomplished. The experimental results demonstrate that this method can not only effectively extract face and iris features but also provide higher recognition accuracy. Compared with some state-of-the-art fusion methods, the proposed method has a significant performance advantage.

A comparative analysis of DNA barcode microarray feature size

Directory of Open Access Journals (Sweden)

Smith Andrew M

2009-10-01

Full Text Available Abstract Background Microarrays are an invaluable tool in many modern genomic studies. It is generally perceived that decreasing the size of microarray features leads to arrays with higher resolution (due to greater feature density, but this increase in resolution can compromise sensitivity. Results We demonstrate that barcode microarrays with smaller features are equally capable of detecting variation in DNA barcode intensity when compared to larger feature sizes within a specific microarray platform. The barcodes used in this study are the well-characterized set derived from the Yeast KnockOut (YKO collection used for screens of pooled yeast (Saccharomyces cerevisiae deletion mutants. We treated these pools with the glycosylation inhibitor tunicamycin as a test compound. Three generations of barcode microarrays at 30, 8 and 5 μm features sizes independently identified the primary target of tunicamycin to be ALG7. Conclusion We show that the data obtained with 5 μm feature size is of comparable quality to the 30 μm size and propose that further shrinking of features could yield barcode microarrays with equal or greater resolving power and, more importantly, higher density.

Cuticular features as indicators of environmental pollution

Science.gov (United States)

G. K. Sharma

1976-01-01

Several leaf cuticular features such as stomatal frequency, stomatal size, trichome length, type, and frequency, and subsidiary cell complex respond to environmental pollution in different ways and hence can be used as indicators of environmental pollution in an area. Several modifications in cuticular features under polluted environments seem to indicate ecotypic or...

A Meta-Heuristic Regression-Based Feature Selection for Predictive Analytics

Directory of Open Access Journals (Sweden)

Bharat Singh

2014-11-01

Full Text Available A high-dimensional feature selection having a very large number of features with an optimal feature subset is an NP-complete problem. Because conventional optimization techniques are unable to tackle large-scale feature selection problems, meta-heuristic algorithms are widely used. In this paper, we propose a particle swarm optimization technique while utilizing regression techniques for feature selection. We then use the selected features to classify the data. Classification accuracy is used as a criterion to evaluate classifier performance, and classification is accomplished through the use of k-nearest neighbour (KNN and Bayesian techniques. Various high dimensional data sets are used to evaluate the usefulness of the proposed approach. Results show that our approach gives better results when compared with other conventional feature selection algorithms.

The importance of internal facial features in learning new faces.

Science.gov (United States)

Longmore, Christopher A; Liu, Chang Hong; Young, Andrew W

2015-01-01

For familiar faces, the internal features (eyes, nose, and mouth) are known to be differentially salient for recognition compared to external features such as hairstyle. Two experiments are reported that investigate how this internal feature advantage accrues as a face becomes familiar. In Experiment 1, we tested the contribution of internal and external features to the ability to generalize from a single studied photograph to different views of the same face. A recognition advantage for the internal features over the external features was found after a change of viewpoint, whereas there was no internal feature advantage when the same image was used at study and test. In Experiment 2, we removed the most salient external feature (hairstyle) from studied photographs and looked at how this affected generalization to a novel viewpoint. Removing the hair from images of the face assisted generalization to novel viewpoints, and this was especially the case when photographs showing more than one viewpoint were studied. The results suggest that the internal features play an important role in the generalization between different images of an individual's face by enabling the viewer to detect the common identity-diagnostic elements across non-identical instances of the face.

Component Composition Using Feature Models

DEFF Research Database (Denmark)

Eichberg, Michael; Klose, Karl; Mitschke, Ralf

2010-01-01

interface description languages. If this variability is relevant when selecting a matching component then human interaction is required to decide which components can be bound. We propose to use feature models for making this variability explicit and (re-)enabling automatic component binding. In our...... approach, feature models are one part of service specifications. This enables to declaratively specify which service variant is provided by a component. By referring to a service's variation points, a component that requires a specific service can list the requirements on the desired variant. Using...... these specifications, a component environment can then determine if a binding of the components exists that satisfies all requirements. The prototypical environment Columbus demonstrates the feasibility of the approach....

Multimodal Discrimination of Schizophrenia Using Hybrid Weighted Feature Concatenation of Brain Functional Connectivity and Anatomical Features with an Extreme Learning Machine

Directory of Open Access Journals (Sweden)

Muhammad Naveed Iqbal Qureshi

2017-09-01

Full Text Available Multimodal features of structural and functional magnetic resonance imaging (MRI of the human brain can assist in the diagnosis of schizophrenia. We performed a classification study on age, sex, and handedness-matched subjects. The dataset we used is publicly available from the Center for Biomedical Research Excellence (COBRE and it consists of two groups: patients with schizophrenia and healthy controls. We performed an independent component analysis and calculated global averaged functional connectivity-based features from the resting-state functional MRI data for all the cortical and subcortical anatomical parcellation. Cortical thickness along with standard deviation, surface area, volume, curvature, white matter volume, and intensity measures from the cortical parcellation, as well as volume and intensity from sub-cortical parcellation and overall volume of cortex features were extracted from the structural MRI data. A novel hybrid weighted feature concatenation method was used to acquire maximal 99.29% (P < 0.0001 accuracy which preserves high discriminatory power through the weight of the individual feature type. The classification was performed by an extreme learning machine, and its efficiency was compared to linear and non-linear (radial basis function support vector machines, linear discriminant analysis, and random forest bagged tree ensemble algorithms. This article reports the predictive accuracy of both unimodal and multimodal features after 10-by-10-fold nested cross-validation. A permutation test followed the classification experiment to assess the statistical significance of the classification results. It was concluded that, from a clinical perspective, this feature concatenation approach may assist the clinicians in schizophrenia diagnosis.

MRI features of chondroblastoma

International Nuclear Information System (INIS)

Cheng Xiaoguang; Liu Xia; Cheng Kebin; Liu Wei

2009-01-01

Objective: To evaluate the MR imaging features of chondroblastoma. Methods: MRI examinations of 20 patients with histological proven chondmblastoma were reviewed retrospectively. The MRI findings of chondroblastoma including the signal intensity, the shape, the growth patterns, and the surrounding bone marrow edema and the adjacent soft tissue edema, the periosteal reaction, the adjacent joint effusion were analyzed. Results: All 20 cases demonstrated heterogeneous MR signal intensity on T 1 WI and T 2 WI images and showed lobular margins. Sixteen cases demonstrated expansive growth patterns. Surrounding bone marrow edema was found in 18 cases and adjacent soft tissue edema in 14 cases. Periosteal reaction was identified in 6 cases. In 7 cases the tumor extended to adjacent soft tissue. Adjacent joint effusion was visible on MRI in 6 cases. Conclusion: Heterogeneous signal intensity, lobular margins and expansive growth pattern, adjacent bone marrow and soft tissue edema were the common features of chondroblastoma on MRI. (authors)

Extracting Feature Model Changes from the Linux Kernel Using FMDiff

NARCIS (Netherlands)

Dintzner, N.J.R.; Van Deursen, A.; Pinzger, M.

2014-01-01

The Linux kernel feature model has been studied as an example of large scale evolving feature model and yet details of its evolution are not known. We present here a classification of feature changes occurring on the Linux kernel feature model, as well as a tool, FMDiff, designed to automatically

Embedded Incremental Feature Selection for Reinforcement Learning

Science.gov (United States)

2012-05-01

Prior to this work, feature selection for reinforce- ment learning has focused on linear value function ap- proximation ( Kolter and Ng, 2009; Parr et al...InProceed- ings of the the 23rd International Conference on Ma- chine Learning, pages 449–456. Kolter , J. Z. and Ng, A. Y. (2009). Regularization and feature

Individual Identification Using Linear Projection of Heartbeat Features

Directory of Open Access Journals (Sweden)

Yogendra Narain Singh

2014-01-01

Full Text Available This paper presents a novel method to use the electrocardiogram (ECG signal as biometrics for individual identification. The ECG characterization is performed using an automated approach consisting of analytical and appearance methods. The analytical method extracts the fiducial features from heartbeats while the appearance method extracts the morphological features from the ECG trace. We linearly project the extracted features into a subspace of lower dimension using an orthogonal basis that represent the most significant features for distinguishing heartbeats among the subjects. Result demonstrates that the proposed characterization of the ECG signal and subsequently derived eigenbeat features are insensitive to signal variations and nonsignal artifacts. The proposed system utilizing ECG biometric method achieves the best identification rates of 85.7% for the subjects of MIT-BIH arrhythmia database and 92.49% for the healthy subjects of our IIT (BHU database. These results are significantly better than the classification accuracies of 79.55% and 84.9%, reported using support vector machine on the tested subjects of MIT-BIH arrhythmia database and our IIT (BHU database, respectively.

Joint Tensor Feature Analysis For Visual Object Recognition.

Science.gov (United States)

Wong, Wai Keung; Lai, Zhihui; Xu, Yong; Wen, Jiajun; Ho, Chu Po

2015-11-01

Tensor-based object recognition has been widely studied in the past several years. This paper focuses on the issue of joint feature selection from the tensor data and proposes a novel method called joint tensor feature analysis (JTFA) for tensor feature extraction and recognition. In order to obtain a set of jointly sparse projections for tensor feature extraction, we define the modified within-class tensor scatter value and the modified between-class tensor scatter value for regression. The k-mode optimization technique and the L(2,1)-norm jointly sparse regression are combined together to compute the optimal solutions. The convergent analysis, computational complexity analysis and the essence of the proposed method/model are also presented. It is interesting to show that the proposed method is very similar to singular value decomposition on the scatter matrix but with sparsity constraint on the right singular value matrix or eigen-decomposition on the scatter matrix with sparse manner. Experimental results on some tensor datasets indicate that JTFA outperforms some well-known tensor feature extraction and selection algorithms.

Face recognition using slow feature analysis and contourlet transform

Science.gov (United States)

Wang, Yuehao; Peng, Lingling; Zhe, Fuchuan

2018-04-01

In this paper we propose a novel face recognition approach based on slow feature analysis (SFA) in contourlet transform domain. This method firstly use contourlet transform to decompose the face image into low frequency and high frequency part, and then takes technological advantages of slow feature analysis for facial feature extraction. We named the new method combining the slow feature analysis and contourlet transform as CT-SFA. The experimental results on international standard face database demonstrate that the new face recognition method is effective and competitive.

Unique features in the ARIES glovebox line

International Nuclear Information System (INIS)

Martinez, H.E.; Brown, W.G.; Flamm, B.; James, C.A.; Laskie, R.; Nelson, T.O.; Wedman, D.E.

1998-01-01

A series of unique features have been incorporated into the Advanced Recovery and Integrated Extraction System (ARIES) at the Los Alamos National Laboratory, TA-55 Plutonium Facility. The features enhance the material handling in the process of the dismantlement of nuclear weapon primaries in the glovebox line. Incorporated into these features are the various plutonium process module's different ventilation zone requirements that the material handling systems must meet. These features include a conveyor system that consists of a remotely controlled cart that transverses the length of the conveyor glovebox, can be operated from a remote location and can deliver process components to the entrance of any selected module glovebox. Within the modules there exists linear motion material handling systems with lifting hoist, which are controlled via an Allen Bradley control panel or local control panels. To remove the packaged products from the hot process line, the package is processed through an air lock/electrolytic decontamination process that removes the radioactive contamination from the outside of the package container and allows the package to be removed from the process line

Mobility as a feature: Evidence from Zulu

Directory of Open Access Journals (Sweden)

Jochen Zeller

2016-01-01

Full Text Available This paper provides evidence for the view that syntactic movement of an element Y to a position X is not driven by features of the target X, but by features of the moving element Y. The data that constitute evidence for this type of analysis come from A-bar movement constructions (object left and right dislocation; object relativisation in the Bantu language Zulu. As I show, only object-DPs that move out of the VP in Zulu are active Goals for Agree-relations and can trigger object agreement with the verb. The fact that the functional head responsible for object agreement must be able to identify a DP in its c-command domain as an active Goal entails that the “mobility” of this DP must be encoded as a property of the DP. Based on this conclusion, I also discuss two proposals about the nature of the feature that activates a DP for movement in Zulu and examine the conditions that determine how this feature is checked and deleted through movement.

Feature Selection Methods for Zero-Shot Learning of Neural Activity

Directory of Open Access Journals (Sweden)

Carlos A. Caceres

2017-06-01

Full Text Available Dimensionality poses a serious challenge when making predictions from human neuroimaging data. Across imaging modalities, large pools of potential neural features (e.g., responses from particular voxels, electrodes, and temporal windows have to be related to typically limited sets of stimuli and samples. In recent years, zero-shot prediction models have been introduced for mapping between neural signals and semantic attributes, which allows for classification of stimulus classes not explicitly included in the training set. While choices about feature selection can have a substantial impact when closed-set accuracy, open-set robustness, and runtime are competing design objectives, no systematic study of feature selection for these models has been reported. Instead, a relatively straightforward feature stability approach has been adopted and successfully applied across models and imaging modalities. To characterize the tradeoffs in feature selection for zero-shot learning, we compared correlation-based stability to several other feature selection techniques on comparable data sets from two distinct imaging modalities: functional Magnetic Resonance Imaging and Electrocorticography. While most of the feature selection methods resulted in similar zero-shot prediction accuracies and spatial/spectral patterns of selected features, there was one exception; A novel feature/attribute correlation approach was able to achieve those accuracies with far fewer features, suggesting the potential for simpler prediction models that yield high zero-shot classification accuracy.

Imaging features of aggressive angiomyxoma

International Nuclear Information System (INIS)

Jeyadevan, N.N.; Sohaib, S.A.A.; Thomas, J.M.; Jeyarajah, A.; Shepherd, J.H.; Fisher, C.

2003-01-01

AIM: To describe the imaging features of aggressive angiomyxoma in a rare benign mesenchymal tumour most frequently arising from the perineum in young female patients. MATERIALS AND METHODS: We reviewed the computed tomography (CT) and magnetic resonance (MR) imaging features of patients with aggressive angiomyxoma who were referred to our hospital. The imaging features were correlated with clinical information and pathology in all patients. RESULTS: Four CT and five MR studies were available for five patients (all women, mean age 39, range 24-55). Three patients had recurrent tumour at follow-up. CT and MR imaging demonstrated a well-defined mass-displacing adjacent structures. The tumour was of low attenuation relative to muscle on CT. On MR, the tumour was isointense relative to muscle on T1-weighted image, hyperintense on T2-weighted image and enhanced avidly after gadolinium contrast with a characteristic 'swirled' internal pattern. MR imaging demonstrates the extent of the tumour and its relation to the pelvic floor. Recurrent tumour has a similar appearance to the primary lesion. CONCLUSION: The MR appearances of aggressive angiomyxomas are characteristic, and the diagnosis should be considered in any young woman presenting with a well-defined mass arising from the perineum. Jeyadevan, N. N. etal. (2003). Clinical Radiology58, 157--162

Sexual dimorphism in medulloblastoma features.

Science.gov (United States)

Zannoni, Gian Franco; Ciucci, Alessandra; Marucci, Gianluca; Travaglia, Daniele; Stigliano, Egidio; Foschini, Maria Pia; Scambia, Giovanni; Gallo, Daniela

2016-03-01

Male sex is a risk factor for medulloblastoma (MB), and is also a negative predictor for clinical outcome. The aim of this study was to assess sex differences in tumour biological features and hormone receptor profiles in a cohort of MB patients. Sixty-four MBs and five normal cerebella were included in the study. Cell proliferation (Ki67), apoptosis (cleaved caspase-3) and microvessel density (CD31) were evaluated in tumours by immunohistochemistry. Tissues were analysed for oestrogen receptor (ER)α, ERβ1, ERβ2, ERβ5 and androgen receptor (AR) expression. The results demonstrated sex-specific features in MBs, with tumours from females showing a higher apoptosis/proliferation ratio and less tumour vascularization than tumours from males. MBs were negative for ERα and AR, but expressed ERβ isoforms at similar levels between the sexes. Altogether, these findings indicate that signalling mechanisms that control cell turnover and angiogenesis operate more efficiently in females than in males. The lack of sex differences in the hormone receptor profiles suggests that circulating oestrogens could be the major determinants of the sexual dimorphism observed in MB features. Here, we provide molecular support for epidemiological data showing sex differences in MB incidence and outcome, completely defining the hormone receptor profile of the tumours. © 2015 John Wiley & Sons Ltd.

Feature hashing for fast image retrieval

Science.gov (United States)

Yan, Lingyu; Fu, Jiarun; Zhang, Hongxin; Yuan, Lu; Xu, Hui

2018-03-01

Currently, researches on content based image retrieval mainly focus on robust feature extraction. However, due to the exponential growth of online images, it is necessary to consider searching among large scale images, which is very timeconsuming and unscalable. Hence, we need to pay much attention to the efficiency of image retrieval. In this paper, we propose a feature hashing method for image retrieval which not only generates compact fingerprint for image representation, but also prevents huge semantic loss during the process of hashing. To generate the fingerprint, an objective function of semantic loss is constructed and minimized, which combine the influence of both the neighborhood structure of feature data and mapping error. Since the machine learning based hashing effectively preserves neighborhood structure of data, it yields visual words with strong discriminability. Furthermore, the generated binary codes leads image representation building to be of low-complexity, making it efficient and scalable to large scale databases. Experimental results show good performance of our approach.

MRI features of tuberculosis of peripheral joints

Energy Technology Data Exchange (ETDEWEB)

Sawlani, V.; Chandra, T.; Mishra, R.N.; Aggarwal, A.; Jain, U.K.; Gujral, R.B. E-mail: gujralrb@sgpgi.ac.in

2003-10-01

The aim of this article is to present the magnetic resonance imaging (MRI) features of peripheral tubercular arthritis. The clinical presentation of peripheral tubercular arthritis is variable and simulates other chronic inflammatory arthritic disorders. MRI is a highly sensitive technique which demonstrates fine anatomical details and identifies the early changes of arthritis, which are not visible on radiographs. The MRI features of tubercular arthritis include synovitis, effusion, central and peripheral erosions, active and chronic pannus, abscess, bone chips and hypo-intense synovium. These imaging features in an appropriate clinical setting may help in the diagnosis of tubercular arthritis. Early diagnosis and treatment can effectively eliminate the long-term morbidity of joints affected by tuberculosis.

MRI features of tuberculosis of peripheral joints

International Nuclear Information System (INIS)

Sawlani, V.; Chandra, T.; Mishra, R.N.; Aggarwal, A.; Jain, U.K.; Gujral, R.B.

2003-01-01

The aim of this article is to present the magnetic resonance imaging (MRI) features of peripheral tubercular arthritis. The clinical presentation of peripheral tubercular arthritis is variable and simulates other chronic inflammatory arthritic disorders. MRI is a highly sensitive technique which demonstrates fine anatomical details and identifies the early changes of arthritis, which are not visible on radiographs. The MRI features of tubercular arthritis include synovitis, effusion, central and peripheral erosions, active and chronic pannus, abscess, bone chips and hypo-intense synovium. These imaging features in an appropriate clinical setting may help in the diagnosis of tubercular arthritis. Early diagnosis and treatment can effectively eliminate the long-term morbidity of joints affected by tuberculosis

Feature selection for high-dimensional integrated data

KAUST Repository

Zheng, Charles

2012-04-26

Motivated by the problem of identifying correlations between genes or features of two related biological systems, we propose a model of feature selection in which only a subset of the predictors Xt are dependent on the multidimensional variate Y, and the remainder of the predictors constitute a “noise set” Xu independent of Y. Using Monte Carlo simulations, we investigated the relative performance of two methods: thresholding and singular-value decomposition, in combination with stochastic optimization to determine “empirical bounds” on the small-sample accuracy of an asymptotic approximation. We demonstrate utility of the thresholding and SVD feature selection methods to with respect to a recent infant intestinal gene expression and metagenomics dataset.

Feature selection for high-dimensional integrated data

KAUST Repository

Zheng, Charles; Schwartz, Scott; Chapkin, Robert S.; Carroll, Raymond J.; Ivanov, Ivan

2012-01-01

Motivated by the problem of identifying correlations between genes or features of two related biological systems, we propose a model of feature selection in which only a subset of the predictors Xt are dependent on the multidimensional variate Y, and the remainder of the predictors constitute a “noise set” Xu independent of Y. Using Monte Carlo simulations, we investigated the relative performance of two methods: thresholding and singular-value decomposition, in combination with stochastic optimization to determine “empirical bounds” on the small-sample accuracy of an asymptotic approximation. We demonstrate utility of the thresholding and SVD feature selection methods to with respect to a recent infant intestinal gene expression and metagenomics dataset.

Palmprint Based Verification System Using SURF Features

Science.gov (United States)

Srinivas, Badrinath G.; Gupta, Phalguni

This paper describes the design and development of a prototype of robust biometric system for verification. The system uses features extracted using Speeded Up Robust Features (SURF) operator of human hand. The hand image for features is acquired using a low cost scanner. The palmprint region extracted is robust to hand translation and rotation on the scanner. The system is tested on IITK database of 200 images and PolyU database of 7751 images. The system is found to be robust with respect to translation and rotation. It has FAR 0.02%, FRR 0.01% and accuracy of 99.98% and can be a suitable system for civilian applications and high-security environments.

The analysis of image feature robustness using cometcloud

Directory of Open Access Journals (Sweden)

Xin Qi

2012-01-01

Full Text Available The robustness of image features is a very important consideration in quantitative image analysis. The objective of this paper is to investigate the robustness of a range of image texture features using hematoxylin stained breast tissue microarray slides which are assessed while simulating different imaging challenges including out of focus, changes in magnification and variations in illumination, noise, compression, distortion, and rotation. We employed five texture analysis methods and tested them while introducing all of the challenges listed above. The texture features that were evaluated include co-occurrence matrix, center-symmetric auto-correlation, texture feature coding method, local binary pattern, and texton. Due to the independence of each transformation and texture descriptor, a network structured combination was proposed and deployed on the Rutgers private cloud. The experiments utilized 20 randomly selected tissue microarray cores. All the combinations of the image transformations and deformations are calculated, and the whole feature extraction procedure was completed in 70 minutes using a cloud equipped with 20 nodes. Center-symmetric auto-correlation outperforms all the other four texture descriptors but also requires the longest computational time. It is roughly 10 times slower than local binary pattern and texton. From a speed perspective, both the local binary pattern and texton features provided excellent performance for classification and content-based image retrieval.

Feature learning and change feature classification based on deep learning for ternary change detection in SAR images

Science.gov (United States)

Gong, Maoguo; Yang, Hailun; Zhang, Puzhao

2017-07-01

Ternary change detection aims to detect changes and group the changes into positive change and negative change. It is of great significance in the joint interpretation of spatial-temporal synthetic aperture radar images. In this study, sparse autoencoder, convolutional neural networks (CNN) and unsupervised clustering are combined to solve ternary change detection problem without any supervison. Firstly, sparse autoencoder is used to transform log-ratio difference image into a suitable feature space for extracting key changes and suppressing outliers and noise. And then the learned features are clustered into three classes, which are taken as the pseudo labels for training a CNN model as change feature classifier. The reliable training samples for CNN are selected from the feature maps learned by sparse autoencoder with certain selection rules. Having training samples and the corresponding pseudo labels, the CNN model can be trained by using back propagation with stochastic gradient descent. During its training procedure, CNN is driven to learn the concept of change, and more powerful model is established to distinguish different types of changes. Unlike the traditional methods, the proposed framework integrates the merits of sparse autoencoder and CNN to learn more robust difference representations and the concept of change for ternary change detection. Experimental results on real datasets validate the effectiveness and superiority of the proposed framework.

Topographic features over the continental shelf off Visakhapatnam

Digital Repository Service at National Institute of Oceanography (India)

Rao, T.C.S.; Machado, T.; Murthy, K.S.R.

water depth and the continental shelfedge several interesting topographic features such as Terraces, Karstic structures associated with pinnacles and troughs and smooth dome shaped reef structures are recorded. The nature of these features...

Arabic Feature-Based Level Sentiment Analysis Using Lexicon ...

African Journals Online (AJOL)

pc

2018-03-05

Mar 5, 2018 ... structured reviews being prior knowledge for mining unstructured reviews. ... FDSO has been introduced, which defines a space of product features ... polarity of a review using feature ontology and sentiment lexicons.

An Integrated Account of Generalization across Objects and Features

Science.gov (United States)

Kemp, Charles; Shafto, Patrick; Tenenbaum, Joshua B.

2012-01-01

Humans routinely make inductive generalizations about unobserved features of objects. Previous accounts of inductive reasoning often focus on inferences about a single object or feature: accounts of causal reasoning often focus on a single object with one or more unobserved features, and accounts of property induction often focus on a single…

CT features of intussusception through an Ileostomy

Energy Technology Data Exchange (ETDEWEB)

Jung, Mi Ran; Park, Mi Hyun; Jee, Keum Nahn; Namgung, Hwan [Dankook University School of Medicine, Cheonan (Korea, Republic of)

2017-08-15

Intussusception of the small bowel through an ileostomy is very rare; when it causes necrosis of the bowel, immediate surgery is required. Computed tomography (CT) features of intussusception through an ileostomy have not been reported in the literature. Herein, we report the typical CT features of intussusception through an ileostomy, followed by a brief literature review.

Improved pulmonary nodule classification utilizing quantitative lung parenchyma features.

Science.gov (United States)

Dilger, Samantha K N; Uthoff, Johanna; Judisch, Alexandra; Hammond, Emily; Mott, Sarah L; Smith, Brian J; Newell, John D; Hoffman, Eric A; Sieren, Jessica C

2015-10-01

Current computer-aided diagnosis (CAD) models for determining pulmonary nodule malignancy characterize nodule shape, density, and border in computed tomography (CT) data. Analyzing the lung parenchyma surrounding the nodule has been minimally explored. We hypothesize that improved nodule classification is achievable by including features quantified from the surrounding lung tissue. To explore this hypothesis, we have developed expanded quantitative CT feature extraction techniques, including volumetric Laws texture energy measures for the parenchyma and nodule, border descriptors using ray-casting and rubber-band straightening, histogram features characterizing densities, and global lung measurements. Using stepwise forward selection and leave-one-case-out cross-validation, a neural network was used for classification. When applied to 50 nodules (22 malignant and 28 benign) from high-resolution CT scans, 52 features (8 nodule, 39 parenchymal, and 5 global) were statistically significant. Nodule-only features yielded an area under the ROC curve of 0.918 (including nodule size) and 0.872 (excluding nodule size). Performance was improved through inclusion of parenchymal (0.938) and global features (0.932). These results show a trend toward increased performance when the parenchyma is included, coupled with the large number of significant parenchymal features that support our hypothesis: the pulmonary parenchyma is influenced differentially by malignant versus benign nodules, assisting CAD-based nodule characterizations.

Feature Detector and Descriptor for Medical Images

Science.gov (United States)

Sargent, Dusty; Chen, Chao-I.; Tsai, Chang-Ming; Wang, Yuan-Fang; Koppel, Daniel

2009-02-01

The ability to detect and match features across multiple views of a scene is a crucial first step in many computer vision algorithms for dynamic scene analysis. State-of-the-art methods such as SIFT and SURF perform successfully when applied to typical images taken by a digital camera or camcorder. However, these methods often fail to generate an acceptable number of features when applied to medical images, because such images usually contain large homogeneous regions with little color and intensity variation. As a result, tasks like image registration and 3D structure recovery become difficult or impossible in the medical domain. This paper presents a scale, rotation and color/illumination invariant feature detector and descriptor for medical applications. The method incorporates elements of SIFT and SURF while optimizing their performance on medical data. Based on experiments with various types of medical images, we combined, adjusted, and built on methods and parameter settings employed in both algorithms. An approximate Hessian based detector is used to locate scale invariant keypoints and a dominant orientation is assigned to each keypoint using a gradient orientation histogram, providing rotation invariance. Finally, keypoints are described with an orientation-normalized distribution of gradient responses at the assigned scale, and the feature vector is normalized for contrast invariance. Experiments show that the algorithm detects and matches far more features than SIFT and SURF on medical images, with similar error levels.

Feature and Region Selection for Visual Learning.

Science.gov (United States)

Zhao, Ji; Wang, Liantao; Cabral, Ricardo; De la Torre, Fernando

2016-03-01

Visual learning problems, such as object classification and action recognition, are typically approached using extensions of the popular bag-of-words (BoWs) model. Despite its great success, it is unclear what visual features the BoW model is learning. Which regions in the image or video are used to discriminate among classes? Which are the most discriminative visual words? Answering these questions is fundamental for understanding existing BoW models and inspiring better models for visual recognition. To answer these questions, this paper presents a method for feature selection and region selection in the visual BoW model. This allows for an intermediate visualization of the features and regions that are important for visual learning. The main idea is to assign latent weights to the features or regions, and jointly optimize these latent variables with the parameters of a classifier (e.g., support vector machine). There are four main benefits of our approach: 1) our approach accommodates non-linear additive kernels, such as the popular χ(2) and intersection kernel; 2) our approach is able to handle both regions in images and spatio-temporal regions in videos in a unified way; 3) the feature selection problem is convex, and both problems can be solved using a scalable reduced gradient method; and 4) we point out strong connections with multiple kernel learning and multiple instance learning approaches. Experimental results in the PASCAL VOC 2007, MSR Action Dataset II and YouTube illustrate the benefits of our approach.

Novel acoustic features for speech emotion recognition

Institute of Scientific and Technical Information of China (English)

ROH; Yong-Wan; KIM; Dong-Ju; LEE; Woo-Seok; HONG; Kwang-Seok

2009-01-01

This paper focuses on acoustic features that effectively improve the recognition of emotion in human speech.The novel features in this paper are based on spectral-based entropy parameters such as fast Fourier transform(FFT) spectral entropy,delta FFT spectral entropy,Mel-frequency filter bank(MFB) spectral entropy,and Delta MFB spectral entropy.Spectral-based entropy features are simple.They reflect frequency characteristic and changing characteristic in frequency of speech.We implement an emotion rejection module using the probability distribution of recognized-scores and rejected-scores.This reduces the false recognition rate to improve overall performance.Recognized-scores and rejected-scores refer to probabilities of recognized and rejected emotion recognition results,respectively.These scores are first obtained from a pattern recognition procedure.The pattern recognition phase uses the Gaussian mixture model(GMM).We classify the four emotional states as anger,sadness,happiness and neutrality.The proposed method is evaluated using 45 sentences in each emotion for 30 subjects,15 males and 15 females.Experimental results show that the proposed method is superior to the existing emotion recognition methods based on GMM using energy,Zero Crossing Rate(ZCR),linear prediction coefficient(LPC),and pitch parameters.We demonstrate the effectiveness of the proposed approach.One of the proposed features,combined MFB and delta MFB spectral entropy improves performance approximately 10% compared to the existing feature parameters for speech emotion recognition methods.We demonstrate a 4% performance improvement in the applied emotion rejection with low confidence score.

Novel acoustic features for speech emotion recognition

Institute of Scientific and Technical Information of China (English)

ROH Yong-Wan; KIM Dong-Ju; LEE Woo-Seok; HONG Kwang-Seok

2009-01-01

This paper focuses on acoustic features that effectively improve the recognition of emotion in human speech. The novel features in this paper are based on spectral-based entropy parameters such as fast Fourier transform (FFT) spectral entropy, delta FFT spectral entropy, Mel-frequency filter bank (MFB)spectral entropy, and Delta MFB spectral entropy. Spectral-based entropy features are simple. They reflect frequency characteristic and changing characteristic in frequency of speech. We implement an emotion rejection module using the probability distribution of recognized-scores and rejected-scores.This reduces the false recognition rate to improve overall performance. Recognized-scores and rejected-scores refer to probabilities of recognized and rejected emotion recognition results, respectively.These scores are first obtained from a pattern recognition procedure. The pattern recognition phase uses the Gaussian mixture model (GMM). We classify the four emotional states as anger, sadness,happiness and neutrality. The proposed method is evaluated using 45 sentences in each emotion for 30 subjects, 15 males and 15 females. Experimental results show that the proposed method is superior to the existing emotion recognition methods based on GMM using energy, Zero Crossing Rate (ZCR),linear prediction coefficient (LPC), and pitch parameters. We demonstrate the effectiveness of the proposed approach. One of the proposed features, combined MFB and delta MFB spectral entropy improves performance approximately 10% compared to the existing feature parameters for speech emotion recognition methods. We demonstrate a 4% performance improvement in the applied emotion rejection with low confidence score.

Associations Between PET Textural Features and GLUT1 Expression, and the Prognostic Significance of Textural Features in Lung Adenocarcinoma.

Science.gov (United States)

Koh, Young Wha; Park, Seong Yong; Hyun, Seung Hyup; Lee, Su Jin

2018-02-01

We evaluated the association between positron emission tomography (PET) textural features and glucose transporter 1 (GLUT1) expression level and further investigated the prognostic significance of textural features in lung adenocarcinoma. We evaluated 105 adenocarcinoma patients. We extracted texture-based PET parameters of primary tumors. Conventional PET parameters were also measured. The relationships between PET parameters and GLUT1 expression levels were evaluated. The association between PET parameters and overall survival (OS) was assessed using Cox's proportional hazard regression models. In terms of PET textural features, tumors expressing high levels of GLUT1 exhibited significantly lower coarseness, contrast, complexity, and strength, but significantly higher busyness. On univariate analysis, the metabolic tumor volume, total lesion glycolysis, contrast, busyness, complexity, and strength were significant predictors of OS. Multivariate analysis showed that lower complexity (HR=2.017, 95%CI=1.032-3.942, p=0.040) was independently associated with poorer survival. PET textural features may aid risk stratification in lung adenocarcinoma patients. Copyright© 2018, International Institute of Anticancer Research (Dr. George J. Delinasios), All rights reserved.

Search asymmetry: a diagnostic for preattentive processing of separable features.

Science.gov (United States)

Treisman, A; Souther, J

1985-09-01

The search rate for a target among distractors may vary dramatically depending on which stimulus plays the role of target and which that of distractors. For example, the time required to find a circle distinguished by an intersecting line is independent of the number of regular circles in the display, whereas the time to find a regular circle among circles with lines increases linearly with the number of distractors. The pattern of performance suggests parallel processing when the target has a unique distinguishing feature and serial self-terminating search when the target is distinguished only by the absence of a feature that is present in all the distractors. The results are consistent with feature-integration theory (Treisman & Gelade, 1980), which predicts that a single feature should be detected by the mere presence of activity in the relevant feature map, whereas tasks that require subjects to locate multiple instances of a feature demand focused attention. Search asymmetries may therefore offer a new diagnostic to identify the primitive features of early vision. Several candidate features are examined in this article: Colors, line ends or terminators, and closure (in the sense of a partly or wholly enclosed area) appear to be functional features; connectedness, intactness (absence of an intersecting line), and acute angles do not.

Feature-Learning-Based Printed Circuit Board Inspection via Speeded-Up Robust Features and Random Forest

Directory of Open Access Journals (Sweden)

Eun Hye Yuk

2018-06-01

Full Text Available With the coming of the 4th industrial revolution era, manufacturers produce high-tech products. As the production process is refined, inspection technologies become more important. Specifically, the inspection of a printed circuit board (PCB, which is an indispensable part of electronic products, is an essential step to improve the quality of the process and yield. Image processing techniques are utilized for inspection, but there are limitations because the backgrounds of images are different and the kinds of defects increase. In order to overcome these limitations, methods based on machine learning have been used recently. These methods can inspect without a normal image by learning fault patterns. Therefore, this paper proposes a method can detect various types of defects using machine learning. The proposed method first extracts features through speeded-up robust features (SURF, then learns the fault pattern and calculates probabilities. After that, we generate a weighted kernel density estimation (WKDE map weighted by the probabilities to consider the density of the features. Because the probability of the WKDE map can detect an area where the defects are concentrated, it improves the performance of the inspection. To verify the proposed method, we apply the method to PCB images and confirm the performance of the method.

Storage of features, conjunctions and objects in visual working memory.

Science.gov (United States)

Vogel, E K; Woodman, G F; Luck, S J

2001-02-01

Working memory can be divided into separate subsystems for verbal and visual information. Although the verbal system has been well characterized, the storage capacity of visual working memory has not yet been established for simple features or for conjunctions of features. The authors demonstrate that it is possible to retain information about only 3-4 colors or orientations in visual working memory at one time. Observers are also able to retain both the color and the orientation of 3-4 objects, indicating that visual working memory stores integrated objects rather than individual features. Indeed, objects defined by a conjunction of four features can be retained in working memory just as well as single-feature objects, allowing many individual features to be retained when distributed across a small number of objects. Thus, the capacity of visual working memory must be understood in terms of integrated objects rather than individual features.

Adapting Local Features for Face Detection in Thermal Image

Directory of Open Access Journals (Sweden)

Chao Ma

2017-11-01

Full Text Available A thermal camera captures the temperature distribution of a scene as a thermal image. In thermal images, facial appearances of different people under different lighting conditions are similar. This is because facial temperature distribution is generally constant and not affected by lighting condition. This similarity in face appearances is advantageous for face detection. To detect faces in thermal images, cascade classifiers with Haar-like features are generally used. However, there are few studies exploring the local features for face detection in thermal images. In this paper, we introduce two approaches relying on local features for face detection in thermal images. First, we create new feature types by extending Multi-Block LBP. We consider a margin around the reference and the generally constant distribution of facial temperature. In this way, we make the features more robust to image noise and more effective for face detection in thermal images. Second, we propose an AdaBoost-based training method to get cascade classifiers with multiple types of local features. These feature types have different advantages. In this way we enhance the description power of local features. We did a hold-out validation experiment and a field experiment. In the hold-out validation experiment, we captured a dataset from 20 participants, comprising 14 males and 6 females. For each participant, we captured 420 images with 10 variations in camera distance, 21 poses, and 2 appearances (participant with/without glasses. We compared the performance of cascade classifiers trained by different sets of the features. The experiment results showed that the proposed approaches effectively improve the performance of face detection in thermal images. In the field experiment, we compared the face detection performance in realistic scenes using thermal and RGB images, and gave discussion based on the results.

IDENTIFICATION OF BURSTING WATER MASER FEATURES IN ORION KL

International Nuclear Information System (INIS)

Hirota, Tomoya; Honma, Mareki; Kim, Mi Kyoung; Kobayashi, Hideyuki; Shibata, Katsunori M.; Tsuboi, Masato; Fujisawa, Kenta; Kawaguchi, Noriyuki; Imai, Hiroshi; Omodaka, Toshihiro; Shimoikura, Tomomi; Yonekura, Yoshinori

2011-01-01

In 2011 February, a burst event of the H 2 O maser in Orion KL (Kleinmann-Low object) has started after a 13 year silence. This is the third time such phenomena has been detected in Orion KL, followed by the events in 1979-1985 and 1998. We have carried out astrometric observations of the bursting H 2 O maser features in Orion KL with the VLBI Exploration of Radio Astrometry (VERA), a Japanese very long baseline interferometry network dedicated for astrometry. The total flux of the bursting feature at the local standard of rest (LSR) velocity of 7.58 km s -1 reaches 4.4 x 10 4 Jy in 2011 March. The intensity of the bursting feature is three orders of magnitude larger than that of the same velocity feature in the quiescent phase in 2006. Two months later, another new feature appears at the LSR velocity of 6.95 km s -1 in 2011 May, separated by 12 mas north of the 7.58 km s -1 feature. Thus, the current burst occurs at two spatially different features. The bursting masers are elongated along the northwest-southeast direction as reported in the previous burst in 1998. We determine the absolute positions of the bursting features for the first time ever with a submilliarcsecond (mas) accuracy. Their positions are coincident with the shocked molecular gas called the Orion Compact Ridge. We tentatively detect the absolute proper motions of the bursting features toward the southwest direction. It is most likely that the outflow from the radio source I or another young stellar object interacting with the Compact Ridge is a possible origin of the H 2 O maser burst.

On the use of INS to improve Feature Matching

Science.gov (United States)

Masiero, A.; Guarnieri, A.; Vettore, A.; Pirotti, F.

2014-11-01

The continuous technological improvement of mobile devices opens the frontiers of Mobile Mapping systems to very compact systems, i.e. a smartphone or a tablet. This motivates the development of efficient 3D reconstruction techniques based on the sensors typically embedded in such devices, i.e. imaging sensors, GPS and Inertial Navigation System (INS). Such methods usually exploits photogrammetry techniques (structure from motion) to provide an estimation of the geometry of the scene. Actually, 3D reconstruction techniques (e.g. structure from motion) rely on use of features properly matched in different images to compute the 3D positions of objects by means of triangulation. Hence, correct feature matching is of fundamental importance to ensure good quality 3D reconstructions. Matching methods are based on the appearance of features, that can change as a consequence of variations of camera position and orientation, and environment illumination. For this reason, several methods have been developed in recent years in order to provide feature descriptors robust (ideally invariant) to such variations, e.g. Scale-Invariant Feature Transform (SIFT), Affine SIFT, Hessian affine and Harris affine detectors, Maximally Stable Extremal Regions (MSER). This work deals with the integration of information provided by the INS in the feature matching procedure: a previously developed navigation algorithm is used to constantly estimate the device position and orientation. Then, such information is exploited to estimate the transformation of feature regions between two camera views. This allows to compare regions from different images but associated to the same feature as seen by the same point of view, hence significantly easing the comparison of feature characteristics and, consequently, improving matching. SIFT-like descriptors are used in order to ensure good matching results in presence of illumination variations and to compensate the approximations related to the estimation

Engineering features of ISX

International Nuclear Information System (INIS)

Lousteau, D.C.; Jernigan, T.C.; Schaffer, M.J.; Hussung, R.O.

1975-01-01

ISX, an Impurity Study Experiment, is presently being designed at Oak Ridge National Laboratory as a joint scientific effort between ORNL and General Atomic Company. ISX is a moderate size tokamak dedicated to the study of impurity production, diffusion, and control. The significant engineering features of this device are discussed

Cutaneous features seen in primary liver cell (Hepatocellular ...

African Journals Online (AJOL)

kemrilib

features associated with the entity as a possible aid to diagnosis cutaneous features being considered a cheap tool that can help ... liver cell cancer (PLCC) and cancer of the breast and ... laboratory based -abdominal ultrasonography, liver.

Color and neighbor edge directional difference feature for image retrieval

Institute of Scientific and Technical Information of China (English)

Chaobing Huang; Shengsheng Yu; Jingli Zhou; Hongwei Lu

2005-01-01

@@ A novel image feature termed neighbor edge directional difference unit histogram is proposed, in which the neighbor edge directional difference unit is defined and computed for every pixel in the image, and is used to generate the neighbor edge directional difference unit histogram. This histogram and color histogram are used as feature indexes to retrieve color image. The feature is invariant to image scaling and translation and has more powerful descriptive for the natural color images. Experimental results show that the feature can achieve better retrieval performance than other color-spatial features.

Novel Automatic Filter-Class Feature Selection for Machine Learning Regression

DEFF Research Database (Denmark)

Wollsen, Morten Gill; Hallam, John; Jørgensen, Bo Nørregaard

2017-01-01

With the increased focus on application of Big Data in all sectors of society, the performance of machine learning becomes essential. Efficient machine learning depends on efficient feature selection algorithms. Filter feature selection algorithms are model-free and therefore very fast, but require...... model in the feature selection process. PCA is often used in machine learning litterature and can be considered the default feature selection method. RDESF outperformed PCA in both experiments in both prediction error and computational speed. RDESF is a new step into filter-based automatic feature...

Clinical features of movement disorders.

Science.gov (United States)

Yung, C Y

1983-08-01

The descriptive aspects of all types of movement disorders and their related syndromes and terminologies used in the literature are reviewed and described. This comprises the features of (a) movement disorders secondary to neurological diseases affecting the extrapyramidal motor system, such as: athetosis, chorea, dystonia, hemiballismus, myoclonus, tremor, tics and spasm, (b) drug induced movement disorders, such as: akathisia, akinesia, hyperkinesia, dyskinesias, extrapyramidal syndrome, and tardive dyskinesia, and (c) abnormal movements in psychiatric disorders, such as: mannerism, stereotyped behaviour and psychomotor retardation. It is intended to bring about a more comprehensive overview of these movement disorders from a phenomenological perspective, so that clinicians can familiarize with these features for diagnosis. Some general statements are made in regard to some of the characteristics of movement disorders.

Optics in computing: introduction to the feature issue.

Science.gov (United States)

Drabik, T; Thienpont, H; Ishikawa, M

2000-02-10

This issue of Applied Optics features 21 papers that describe the implementation of optics in computer systems and applications. This feature is the eighth in a series on the application of optics in the field of computing.

Feature Selection Based on Mutual Correlation

Czech Academy of Sciences Publication Activity Database

Haindl, Michal; Somol, Petr; Ververidis, D.; Kotropoulos, C.

2006-01-01

Roč. 19, č. 4225 (2006), s. 569-577 ISSN 0302-9743. [Iberoamerican Congress on Pattern Recognition. CIARP 2006 /11./. Cancun, 14.11.2006-17.11.2006] R&D Projects: GA AV ČR 1ET400750407; GA MŠk 1M0572; GA AV ČR IAA2075302 EU Projects: European Commission(XE) 507752 - MUSCLE Institutional research plan: CEZ:AV0Z10750506 Keywords : feature selection Subject RIV: BD - Theory of Information Impact factor: 0.402, year: 2005 http://library.utia.cas.cz/separaty/historie/haindl-feature selection based on mutual correlation.pdf

Improved features of MARS 1.4 and verification

Energy Technology Data Exchange (ETDEWEB)

Lee, Won Jae; Chung, Bub Don; Jeong, Jae Jun; Ha, Kwi Seok [Korea Atomic Energy Research Institute, Taejon (Korea)

1999-09-01

MARS 1.4 code has been developed as a basic code frame for multi-dimensional thermal-hydraulic analysis of light water reactor transients. This report describes the newly improved features of MARS 1.4 and their verification results. The new features of MARS 1.4 include the implementation of point kinetics model in the 3D module, the coupled heat structure model, the extension of control functions and input check functions in the 3D module, the implementation of new features of RELAP5/MOD3.2.2 -version, the addition of automatic initialization function for fuel 3-D analysis and the unification of material properties and forcing functions, etc. These features have been implemented in the code in order to extend the code modeling capability and to enhance the user friendliness. Among these features, this report describes the implementation of new features of RELAP5/MOD3.3.3-version such as reflood model and critical heat flux models, etc., the automatic initialization function, the unification of material properties and forcing functions and the other code improvements and error corrections, which were not reported in the previous report. Through the verification calculations, the new features of MARS 1.4 have been verified well implemented in the code. In conclusion, MARS 1.4 code has been developed and verified as implemented in the code. In conclusion, MARS 1.4 code has been developed and verified as a multi-dimensional system thermal-hydraulic analysis tool. And, it can play its role as a basic code frame for the future development of a multi-purpose consolidated code, MARS 2.x, for coupled analysis of multi-dimensional system thermal hydraulics, 3D core kinetics, core CHF and containment as well as for further improvement of thermal-hydraulic and numerical models. 4 refs., 10 figs. (Author)

Structural health monitoring feature design by genetic programming

International Nuclear Information System (INIS)

Harvey, Dustin Y; Todd, Michael D

2014-01-01

Structural health monitoring (SHM) systems provide real-time damage and performance information for civil, aerospace, and other high-capital or life-safety critical structures. Conventional data processing involves pre-processing and extraction of low-dimensional features from in situ time series measurements. The features are then input to a statistical pattern recognition algorithm to perform the relevant classification or regression task necessary to facilitate decisions by the SHM system. Traditional design of signal processing and feature extraction algorithms can be an expensive and time-consuming process requiring extensive system knowledge and domain expertise. Genetic programming, a heuristic program search method from evolutionary computation, was recently adapted by the authors to perform automated, data-driven design of signal processing and feature extraction algorithms for statistical pattern recognition applications. The proposed method, called Autofead, is particularly suitable to handle the challenges inherent in algorithm design for SHM problems where the manifestation of damage in structural response measurements is often unclear or unknown. Autofead mines a training database of response measurements to discover information-rich features specific to the problem at hand. This study provides experimental validation on three SHM applications including ultrasonic damage detection, bearing damage classification for rotating machinery, and vibration-based structural health monitoring. Performance comparisons with common feature choices for each problem area are provided demonstrating the versatility of Autofead to produce significant algorithm improvements on a wide range of problems. (paper)

Optimized Feature Extraction for Temperature-Modulated Gas Sensors

Directory of Open Access Journals (Sweden)

Alexander Vergara

2009-01-01

Full Text Available One of the most serious limitations to the practical utilization of solid-state gas sensors is the drift of their signal. Even if drift is rooted in the chemical and physical processes occurring in the sensor, improved signal processing is generally considered as a methodology to increase sensors stability. Several studies evidenced the augmented stability of time variable signals elicited by the modulation of either the gas concentration or the operating temperature. Furthermore, when time-variable signals are used, the extraction of features can be accomplished in shorter time with respect to the time necessary to calculate the usual features defined in steady-state conditions. In this paper, we discuss the stability properties of distinct dynamic features using an array of metal oxide semiconductors gas sensors whose working temperature is modulated with optimized multisinusoidal signals. Experiments were aimed at measuring the dispersion of sensors features in repeated sequences of a limited number of experimental conditions. Results evidenced that the features extracted during the temperature modulation reduce the multidimensional data dispersion among repeated measurements. In particular, the Energy Signal Vector provided an almost constant classification rate along the time with respect to the temperature modulation.

Oversampling the Minority Class in the Feature Space.

Science.gov (United States)

Perez-Ortiz, Maria; Gutierrez, Pedro Antonio; Tino, Peter; Hervas-Martinez, Cesar

2016-09-01

The imbalanced nature of some real-world data is one of the current challenges for machine learning researchers. One common approach oversamples the minority class through convex combination of its patterns. We explore the general idea of synthetic oversampling in the feature space induced by a kernel function (as opposed to input space). If the kernel function matches the underlying problem, the classes will be linearly separable and synthetically generated patterns will lie on the minority class region. Since the feature space is not directly accessible, we use the empirical feature space (EFS) (a Euclidean space isomorphic to the feature space) for oversampling purposes. The proposed method is framed in the context of support vector machines, where the imbalanced data sets can pose a serious hindrance. The idea is investigated in three scenarios: 1) oversampling in the full and reduced-rank EFSs; 2) a kernel learning technique maximizing the data class separation to study the influence of the feature space structure (implicitly defined by the kernel function); and 3) a unified framework for preferential oversampling that spans some of the previous approaches in the literature. We support our investigation with extensive experiments over 50 imbalanced data sets.

FEATURES BASED ON NEIGHBORHOOD PIXELS DENSITY - A STUDY AND COMPARISON

Directory of Open Access Journals (Sweden)

Satish Kumar

2016-02-01

Full Text Available In optical character recognition applications, the feature extraction method(s used to recognize document images play an important role. The features are the properties of the pattern that can be statistical, structural and/or transforms or series expansion. The structural features are difficult to compute particularly from hand-printed images. The structure of the strokes present inside the hand-printed images can be estimated using statistical means. In this paper three features have been purposed, those are based on the distribution of B/W pixels on the neighborhood of a pixel in an image. We name these features as Spiral Neighbor Density, Layer Pixel Density and Ray Density. The recognition performance of these features has been compared with two more features Neighborhood Pixels Weight and Total Distances in Four Directions already studied in our work. We have used more than 20000 Devanagari handwritten character images for conducting experiments. The experiments are conducted with two classifiers i.e. PNN and k-NN.

Robust Features Of Surface Electromyography Signal

Science.gov (United States)

Sabri, M. I.; Miskon, M. F.; Yaacob, M. R.

2013-12-01

Nowadays, application of robotics in human life has been explored widely. Robotics exoskeleton system are one of drastically areas in recent robotic research that shows mimic impact in human life. These system have been developed significantly to be used for human power augmentation, robotics rehabilitation, human power assist, and haptic interaction in virtual reality. This paper focus on solving challenges in problem using neural signals and extracting human intent. Commonly, surface electromyography signal (sEMG) are used in order to control human intent for application exoskeleton robot. But the problem lies on difficulty of pattern recognition of the sEMG features due to high noises which are electrode and cable motion artifact, electrode noise, dermic noise, alternating current power line interface, and other noise came from electronic instrument. The main objective in this paper is to study the best features of electromyography in term of time domain (statistical analysis) and frequency domain (Fast Fourier Transform).The secondary objectives is to map the relationship between torque and best features of muscle unit activation potential (MaxPS and RMS) of biceps brachii. This project scope use primary data of 2 male sample subject which using same dominant hand (right handed), age between 20-27 years old, muscle diameter 32cm to 35cm and using single channel muscle (biceps brachii muscle). The experiment conduct 2 times repeated task of contraction and relaxation of biceps brachii when lifting different load from no load to 3kg with ascending 1kg The result shows that Fast Fourier Transform maximum power spectrum (MaxPS) has less error than mean value of reading compare to root mean square (RMS) value. Thus, Fast Fourier Transform maximum power spectrum (MaxPS) show the linear relationship against torque experience by elbow joint to lift different load. As the conclusion, the best features is MaxPS because it has the lowest error than other features and show

Robust Features Of Surface Electromyography Signal

International Nuclear Information System (INIS)

Sabri, M I; Miskon, M F; Yaacob, M R

2013-01-01

Nowadays, application of robotics in human life has been explored widely. Robotics exoskeleton system are one of drastically areas in recent robotic research that shows mimic impact in human life. These system have been developed significantly to be used for human power augmentation, robotics rehabilitation, human power assist, and haptic interaction in virtual reality. This paper focus on solving challenges in problem using neural signals and extracting human intent. Commonly, surface electromyography signal (sEMG) are used in order to control human intent for application exoskeleton robot. But the problem lies on difficulty of pattern recognition of the sEMG features due to high noises which are electrode and cable motion artifact, electrode noise, dermic noise, alternating current power line interface, and other noise came from electronic instrument. The main objective in this paper is to study the best features of electromyography in term of time domain (statistical analysis) and frequency domain (Fast Fourier Transform).The secondary objectives is to map the relationship between torque and best features of muscle unit activation potential (MaxPS and RMS) of biceps brachii. This project scope use primary data of 2 male sample subject which using same dominant hand (right handed), age between 20–27 years old, muscle diameter 32cm to 35cm and using single channel muscle (biceps brachii muscle). The experiment conduct 2 times repeated task of contraction and relaxation of biceps brachii when lifting different load from no load to 3kg with ascending 1kg The result shows that Fast Fourier Transform maximum power spectrum (MaxPS) has less error than mean value of reading compare to root mean square (RMS) value. Thus, Fast Fourier Transform maximum power spectrum (MaxPS) show the linear relationship against torque experience by elbow joint to lift different load. As the conclusion, the best features is MaxPS because it has the lowest error than other features and

Storage of feature conjunctions in transient auditory memory.

Science.gov (United States)

Gomes, H; Bernstein, R; Ritter, W; Vaughan, H G; Miller, J

1997-11-01

The purpose of this study was to determine whether feature conjunctions are stored in transient auditory memory. The mismatch negativity (MMN), an event-related potential that is elicited by stimuli that differ from a series of preceding stimuli, was used in this endeavour. A tone that differed from the preceding series of stimuli in the conjunction of two of its features, both present in preceding stimuli but in different combinations, was found to elicit the MMN. The data are interpreted to indicate that information about the conjunction of features is stored in the memory.

Analysing co-articulation using frame-based feature trajectories

CSIR Research Space (South Africa)

Badenhorst, J

2010-11-01

Full Text Available The authors investigate several approaches aimed at a more detailed understanding of co-articulation in spoken utterances. They find that the Euclidean difference between instantaneous frame-based feature values and the mean values of these features...

Solar Features - Prominences and Filaments

Data.gov (United States)

National Oceanic and Atmospheric Administration, Department of Commerce — Prominences and filaments are two manifestations of the same phenomenon. Both prominences and filaments are features formed above the chromosphere by cool dense...

Feature selection using genetic algorithms for fetal heart rate analysis

International Nuclear Information System (INIS)

Xu, Liang; Redman, Christopher W G; Georgieva, Antoniya; Payne, Stephen J

2014-01-01

The fetal heart rate (FHR) is monitored on a paper strip (cardiotocogram) during labour to assess fetal health. If necessary, clinicians can intervene and assist with a prompt delivery of the baby. Data-driven computerized FHR analysis could help clinicians in the decision-making process. However, selecting the best computerized FHR features that relate to labour outcome is a pressing research problem. The objective of this study is to apply genetic algorithms (GA) as a feature selection method to select the best feature subset from 64 FHR features and to integrate these best features to recognize unfavourable FHR patterns. The GA was trained on 404 cases and tested on 106 cases (both balanced datasets) using three classifiers, respectively. Regularization methods and backward selection were used to optimize the GA. Reasonable classification performance is shown on the testing set for the best feature subset (Cohen's kappa values of 0.45 to 0.49 using different classifiers). This is, to our knowledge, the first time that a feature selection method for FHR analysis has been developed on a database of this size. This study indicates that different FHR features, when integrated, can show good performance in predicting labour outcome. It also gives the importance of each feature, which will be a valuable reference point for further studies. (paper)

Deep-learning derived features for lung nodule classification with limited datasets

Science.gov (United States)

Thammasorn, P.; Wu, W.; Pierce, L. A.; Pipavath, S. N.; Lampe, P. D.; Houghton, A. M.; Haynor, D. R.; Chaovalitwongse, W. A.; Kinahan, P. E.

2018-02-01

Only a few percent of indeterminate nodules found in lung CT images are cancer. However, enabling earlier diagnosis is important to avoid invasive procedures or long-time surveillance to those benign nodules. We are evaluating a classification framework using radiomics features derived with a machine learning approach from a small data set of indeterminate CT lung nodule images. We used a retrospective analysis of 194 cases with pulmonary nodules in the CT images with or without contrast enhancement from lung cancer screening clinics. The nodules were contoured by a radiologist and texture features of the lesion were calculated. In addition, sematic features describing shape were categorized. We also explored a Multiband network, a feature derivation path that uses a modified convolutional neural network (CNN) with a Triplet Network. This was trained to create discriminative feature representations useful for variable-sized nodule classification. The diagnostic accuracy was evaluated for multiple machine learning algorithms using texture, shape, and CNN features. In the CT contrast-enhanced group, the texture or semantic shape features yielded an overall diagnostic accuracy of 80%. Use of a standard deep learning network in the framework for feature derivation yielded features that substantially underperformed compared to texture and/or semantic features. However, the proposed Multiband approach of feature derivation produced results similar in diagnostic accuracy to the texture and semantic features. While the Multiband feature derivation approach did not outperform the texture and/or semantic features, its equivalent performance indicates promise for future improvements to increase diagnostic accuracy. Importantly, the Multiband approach adapts readily to different size lesions without interpolation, and performed well with relatively small amount of training data.

Breast cancer molecular subtype classifier that incorporates MRI features.

Science.gov (United States)

Sutton, Elizabeth J; Dashevsky, Brittany Z; Oh, Jung Hun; Veeraraghavan, Harini; Apte, Aditya P; Thakur, Sunitha B; Morris, Elizabeth A; Deasy, Joseph O

2016-07-01

To use features extracted from magnetic resonance (MR) images and a machine-learning method to assist in differentiating breast cancer molecular subtypes. This retrospective Health Insurance Portability and Accountability Act (HIPAA)-compliant study received Institutional Review Board (IRB) approval. We identified 178 breast cancer patients between 2006-2011 with: 1) ERPR + (n = 95, 53.4%), ERPR-/HER2 + (n = 35, 19.6%), or triple negative (TN, n = 48, 27.0%) invasive ductal carcinoma (IDC), and 2) preoperative breast MRI at 1.5T or 3.0T. Shape, texture, and histogram-based features were extracted from each tumor contoured on pre- and three postcontrast MR images using in-house software. Clinical and pathologic features were also collected. Machine-learning-based (support vector machines) models were used to identify significant imaging features and to build models that predict IDC subtype. Leave-one-out cross-validation (LOOCV) was used to avoid model overfitting. Statistical significance was determined using the Kruskal-Wallis test. Each support vector machine fit in the LOOCV process generated a model with varying features. Eleven out of the top 20 ranked features were significantly different between IDC subtypes with P machine-learning-based predictive model using features extracted from MRI that can distinguish IDC subtypes with significant predictive power. J. Magn. Reson. Imaging 2016;44:122-129. © 2016 Wiley Periodicals, Inc.

Mid-Infrared Silicate Dust Features in Seyfert 1 Spectra

Science.gov (United States)

Thompson, Grant D.; Levenson, N. A.; Sirocky, M. M.; Uddin, S.

2007-12-01

Silicate dust emission dominates the mid-infrared spectra of galaxies, and the dust produces two spectral features, at 10 and 18 μm. These features' strengths (in emission or absorption) and peak wavelengths reveal the geometry of the dust distribution, and they are sensitive to the dust composition. We examine mid-infrared spectra of 32 Seyfert 1 active galactic nuclei (AGN), observed with the Infrared Spectrograph aboard the Spitzer Space Telescope. In the spectra, we typically find the shorter-wavelength feature in emission, at an average peak wavelength of 10.0 μm, although it is known historically as the "9.7 μm" feature. In addition, peak wavelength increases with feature strength. The 10 and 18 μm feature strengths together are sensitive to the dust geometry surrounding the central heating engine. Numerical calculations of radiative transfer distinguish between clumpy and smooth distributions, and we find that the surroundings of these AGN (the obscuring "tori" of unified AGN schemes) are clumpy. Polycyclic aromatic hydrocarbon (PAH) features are associated with star formation, and we find strong PAH emission (luminosity ≥ 1042 erg/s) in only four sources, three of which show independent evidence for starbursts. We will explore the effects of luminosity on dust geometry and chemistry in a comparison sample of quasars. We acknowledge work supported by the NSF under grant number 0237291.

Obligatory encoding of task-irrelevant features depletes working memory resources.

Science.gov (United States)

Marshall, Louise; Bays, Paul M

2013-02-18

Selective attention is often considered the "gateway" to visual working memory (VWM). However, the extent to which we can voluntarily control which of an object's features enter memory remains subject to debate. Recent research has converged on the concept of VWM as a limited commodity distributed between elements of a visual scene. Consequently, as memory load increases, the fidelity with which each visual feature is stored decreases. Here we used changes in recall precision to probe whether task-irrelevant features were encoded into VWM when individuals were asked to store specific feature dimensions. Recall precision for both color and orientation was significantly enhanced when task-irrelevant features were removed, but knowledge of which features would be probed provided no advantage over having to memorize both features of all items. Next, we assessed the effect an interpolated orientation-or color-matching task had on the resolution with which orientations in a memory array were stored. We found that the presence of orientation information in the second array disrupted memory of the first array. The cost to recall precision was identical whether the interfering features had to be remembered, attended to, or could be ignored. Therefore, it appears that storing, or merely attending to, one feature of an object is sufficient to promote automatic encoding of all its features, depleting VWM resources. However, the precision cost was abolished when the match task preceded the memory array. So, while encoding is automatic, maintenance is voluntary, allowing resources to be reallocated to store new visual information.

Feature-space transformation improves supervised segmentation across scanners

DEFF Research Database (Denmark)

van Opbroek, Annegreet; Achterberg, Hakim C.; de Bruijne, Marleen

2015-01-01

Image-segmentation techniques based on supervised classification generally perform well on the condition that training and test samples have the same feature distribution. However, if training and test images are acquired with different scanners or scanning parameters, their feature distributions...

Human Activity Recognition Using Hierarchically-Mined Feature Constellations

NARCIS (Netherlands)

Oikonomopoulos, A.; Pantic, Maja

In this paper we address the problem of human activity modelling and recognition by means of a hierarchical representation of mined dense spatiotemporal features. At each level of the hierarchy, the proposed method selects feature constellations that are increasingly discriminative and

Technical Evaluation Report 51: Text-based Conferencing: Features vs. functionality

Directory of Open Access Journals (Sweden)

Lynn Anderson

2005-11-01

Full Text Available This report examines three text-based conferencing products: WowBB, Invision Power Board, and vBulletin. Their selection was prompted by a feature-by-feature comparison of the same products on the WowBB website. The comparison chart painted a misleading impression of WowBB’s features in relation to the other two products; so the evaluation team undertook a more comprehensive and impartial comparison using the categories and criteria for online software evaluation developed by the American Society for Training and Development (ASTD. The findings are summarised in terms of the softwares’ pricing, common features/ functions, and differentiating features.

A New Feature Selection Algorithm Based on the Mean Impact Variance

Directory of Open Access Journals (Sweden)

Weidong Cheng

2014-01-01

Full Text Available The selection of fewer or more representative features from multidimensional features is important when the artificial neural network (ANN algorithm is used as a classifier. In this paper, a new feature selection method called the mean impact variance (MIVAR method is proposed to determine the feature that is more suitable for classification. Moreover, this method is constructed on the basis of the training process of the ANN algorithm. To verify the effectiveness of the proposed method, the MIVAR value is used to rank the multidimensional features of the bearing fault diagnosis. In detail, (1 70-dimensional all waveform features are extracted from a rolling bearing vibration signal with four different operating states, (2 the corresponding MIVAR values of all 70-dimensional features are calculated to rank all features, (3 14 groups of 10-dimensional features are separately generated according to the ranking results and the principal component analysis (PCA algorithm and a back propagation (BP network is constructed, and (4 the validity of the ranking result is proven by training this BP network with these seven groups of 10-dimensional features and by comparing the corresponding recognition rates. The results prove that the features with larger MIVAR value can lead to higher recognition rates.

CT appearance and features of tubal pregnancy

Energy Technology Data Exchange (ETDEWEB)

Xiaohong, Wang; Hong, Shan; Zaibo, Jiang; Xinghe, Deng; Xiaochun, Meng; Bingbing, Ye; Mingyue, Luo; Yunya, Lin [Sun Yat-sen Univ., Guangzhou (China). The Third Univ. Hospital, Dept. of Radiology

2004-06-01

Objective: To investigate the CT appearance and features of tubal pregnancy. Methods: Precontrast and postcontrast CT scans were employed in 38 patients who were clinically and ultrasonographically suspected of tubal pregnancy. 34 of them were verified as tubal pregnancy through operative pathology. Results: 1. The direct CT imaging feature was the whole pregnancies sac (4/34, 11.8%) or half-baked pregnancies sac (14/34, 41.2%); 2. The indirect CT imaging features were: (1) abnormal density image, which could be enhanced, in a cystic mass around adnexal area (8/34, 23.5%); (2) mix density mass around adnexal area, which was mainly solid and had mild to moderate inhomogeneous enhancement (19/34, 55.9%); (3) large area irregular shadow with high density were found beside the uterus, with no enhancement (3/34, 8.8%). (4) bloody density in uterus-rectum-fossa (23/34, 67.6%). 3. The CT imaging features of tubal pregnancy was classified as: (1) Pregnant sac type (4/34, 11.8%); (2) Cystic (8/34, 23.5%); (3) Massive type (17/34, 50%); (4) Chronic mass type (2/34, 5.9%); (5) Bleeding type (3/34, 8.8%). 4. The CT imaging appearance of tubal pregnancy related with the pregnancy location; 5. The CT imaging appearance of tubal pregnancy related with the clinical significant. Conclusion: The CT imaging appearance of tubal pregnancy has some features, which can help in the diagnosis or differential diagnosis of the pelvis masses. CT scan is an effective supplementary attempt to the clinically and ultrasonographically suspected tubal pregnancy patients.

Coding visual features extracted from video sequences.

Science.gov (United States)

Baroffio, Luca; Cesana, Matteo; Redondi, Alessandro; Tagliasacchi, Marco; Tubaro, Stefano

2014-05-01

Visual features are successfully exploited in several applications (e.g., visual search, object recognition and tracking, etc.) due to their ability to efficiently represent image content. Several visual analysis tasks require features to be transmitted over a bandwidth-limited network, thus calling for coding techniques to reduce the required bit budget, while attaining a target level of efficiency. In this paper, we propose, for the first time, a coding architecture designed for local features (e.g., SIFT, SURF) extracted from video sequences. To achieve high coding efficiency, we exploit both spatial and temporal redundancy by means of intraframe and interframe coding modes. In addition, we propose a coding mode decision based on rate-distortion optimization. The proposed coding scheme can be conveniently adopted to implement the analyze-then-compress (ATC) paradigm in the context of visual sensor networks. That is, sets of visual features are extracted from video frames, encoded at remote nodes, and finally transmitted to a central controller that performs visual analysis. This is in contrast to the traditional compress-then-analyze (CTA) paradigm, in which video sequences acquired at a node are compressed and then sent to a central unit for further processing. In this paper, we compare these coding paradigms using metrics that are routinely adopted to evaluate the suitability of visual features in the context of content-based retrieval, object recognition, and tracking. Experimental results demonstrate that, thanks to the significant coding gains achieved by the proposed coding scheme, ATC outperforms CTA with respect to all evaluation metrics.

CT appearance and features of tubal pregnancy

International Nuclear Information System (INIS)

Wang Xiaohong; Shan Hong; Jiang Zaibo; Deng Xinghe; Meng Xiaochun; Ye Bingbing; Luo Mingyue; Lin Yunya

2004-01-01

Objective: To investigate the CT appearance and features of tubal pregnancy. Methods: Precontrast and postcontrast CT scans were employed in 38 patients who were clinically and ultrasonographically suspected of tubal pregnancy. 34 of them were verified as tubal pregnancy through operative pathology. Results: 1. The direct CT imaging feature was the whole pregnancies sac (4/34, 11.8%) or half-baked pregnancies sac (14/34, 41.2%); 2. The indirect CT imaging features were: (1) abnormal density image, which could be enhanced, in a cystic mass around adnexal area (8/34, 23.5%); (2) mix density mass around adnexal area, which was mainly solid and had mild to moderate inhomogeneous enhancement (19/34, 55.9%); (3) large area irregular shadow with high density were found beside the uterus, with no enhancement (3/34, 8.8%). (4) bloody density in uterus-rectum-fossa (23/34, 67.6%). 3. The CT imaging features of tubal pregnancy was classified as: (1) Pregnant sac type (4/34, 11.8%); (2) Cystic (8/34, 23.5%); (3) Massive type (17/34, 50%); (4) Chronic mass type (2/34, 5.9%); (5) Bleeding type (3/34, 8.8%). 4. The CT imaging appearance of tubal pregnancy related with the pregnancy location; 5. The CT imaging appearance of tubal pregnancy related with the clinical significant. Conclusion: The CT imaging appearance of tubal pregnancy has some features, which can help in the diagnosis or differential diagnosis of the pelvis masses. CT scan is an effective supplementary attempt to the clinically and ultrasonographically suspected tubal pregnancy patients

Penalized feature selection and classification in bioinformatics

OpenAIRE

Ma, Shuangge; Huang, Jian

2008-01-01

In bioinformatics studies, supervised classification with high-dimensional input variables is frequently encountered. Examples routinely arise in genomic, epigenetic and proteomic studies. Feature selection can be employed along with classifier construction to avoid over-fitting, to generate more reliable classifier and to provide more insights into the underlying causal relationships. In this article, we provide a review of several recently developed penalized feature selection and classific...

Enhanced Performance by Time-Frequency-Phase Feature for EEG-Based BCI Systems

Directory of Open Access Journals (Sweden)

Baolei Xu

2014-01-01

Full Text Available We introduce a new motor parameter imagery paradigm using clench speed and clench force motor imagery. The time-frequency-phase features are extracted from mu rhythm and beta rhythms, and the features are optimized using three process methods: no-scaled feature using “MIFS” feature selection criterion, scaled feature using “MIFS” feature selection criterion, and scaled feature using “mRMR” feature selection criterion. Support vector machines (SVMs and extreme learning machines (ELMs are compared for classification between clench speed and clench force motor imagery using the optimized feature. Our results show that no significant difference in the classification rate between SVMs and ELMs is found. The scaled feature combinations can get higher classification accuracy than the no-scaled feature combinations at significant level of 0.01, and the “mRMR” feature selection criterion can get higher classification rate than the “MIFS” feature selection criterion at significant level of 0.01. The time-frequency-phase feature can improve the classification rate by about 20% more than the time-frequency feature, and the best classification rate between clench speed motor imagery and clench force motor imagery is 92%. In conclusion, the motor parameter imagery paradigm has the potential to increase the direct control commands for BCI control and the time-frequency-phase feature has the ability to improve BCI classification accuracy.

Action recognition using mined hierarchical compound features.

Science.gov (United States)

Gilbert, Andrew; Illingworth, John; Bowden, Richard

2011-05-01

The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single-frame object recognition and adapting them for temporal-based action recognition. Inspired by the success of interest points in the 2D spatial domain, their 3D (space-time) counterparts typically form the basic components used to describe actions, and in action recognition the features used are often engineered to fire sparsely. This is to ensure that the problem is tractable; however, this can sacrifice recognition accuracy as it cannot be assumed that the optimum features in terms of class discrimination are obtained from this approach. In contrast, we propose to initially use an overcomplete set of simple 2D corners in both space and time. These are grouped spatially and temporally using a hierarchical process, with an increasing search area. At each stage of the hierarchy, the most distinctive and descriptive features are learned efficiently through data mining. This allows large amounts of data to be searched for frequently reoccurring patterns of features. At each level of the hierarchy, the mined compound features become more complex, discriminative, and sparse. This results in fast, accurate recognition with real-time performance on high-resolution video. As the compound features are constructed and selected based upon their ability to discriminate, their speed and accuracy increase at each level of the hierarchy. The approach is tested on four state-of-the-art data sets, the popular KTH data set to provide a comparison with other state-of-the-art approaches, the Multi-KTH data set to illustrate performance at simultaneous multiaction classification, despite no explicit localization information provided during training. Finally, the recent Hollywood and Hollywood2 data sets provide challenging complex actions taken from commercial movie sequences. For all four data sets, the proposed hierarchical

Task-induced frequency modulation features for brain-computer interfacing.

Science.gov (United States)

Jayaram, Vinay; Hohmann, Matthias; Just, Jennifer; Schölkopf, Bernhard; Grosse-Wentrup, Moritz

2017-10-01

Task-induced amplitude modulation of neural oscillations is routinely used in brain-computer interfaces (BCIs) for decoding subjects' intents, and underlies some of the most robust and common methods in the field, such as common spatial patterns and Riemannian geometry. While there has been some interest in phase-related features for classification, both techniques usually presuppose that the frequencies of neural oscillations remain stable across various tasks. We investigate here whether features based on task-induced modulation of the frequency of neural oscillations enable decoding of subjects' intents with an accuracy comparable to task-induced amplitude modulation. We compare cross-validated classification accuracies using the amplitude and frequency modulated features, as well as a joint feature space, across subjects in various paradigms and pre-processing conditions. We show results with a motor imagery task, a cognitive task, and also preliminary results in patients with amyotrophic lateral sclerosis (ALS), as well as using common spatial patterns and Laplacian filtering. The frequency features alone do not significantly out-perform traditional amplitude modulation features, and in some cases perform significantly worse. However, across both tasks and pre-processing in healthy subjects the joint space significantly out-performs either the frequency or amplitude features alone. This result only does not hold for ALS patients, for whom the dataset is of insufficient size to draw any statistically significant conclusions. Task-induced frequency modulation is robust and straight forward to compute, and increases performance when added to standard amplitude modulation features across paradigms. This allows more information to be extracted from the EEG signal cheaply and can be used throughout the field of BCIs.

Task-induced frequency modulation features for brain-computer interfacing

Science.gov (United States)

Jayaram, Vinay; Hohmann, Matthias; Just, Jennifer; Schölkopf, Bernhard; Grosse-Wentrup, Moritz

2017-10-01

Objective. Task-induced amplitude modulation of neural oscillations is routinely used in brain-computer interfaces (BCIs) for decoding subjects’ intents, and underlies some of the most robust and common methods in the field, such as common spatial patterns and Riemannian geometry. While there has been some interest in phase-related features for classification, both techniques usually presuppose that the frequencies of neural oscillations remain stable across various tasks. We investigate here whether features based on task-induced modulation of the frequency of neural oscillations enable decoding of subjects’ intents with an accuracy comparable to task-induced amplitude modulation. Approach. We compare cross-validated classification accuracies using the amplitude and frequency modulated features, as well as a joint feature space, across subjects in various paradigms and pre-processing conditions. We show results with a motor imagery task, a cognitive task, and also preliminary results in patients with amyotrophic lateral sclerosis (ALS), as well as using common spatial patterns and Laplacian filtering. Main results. The frequency features alone do not significantly out-perform traditional amplitude modulation features, and in some cases perform significantly worse. However, across both tasks and pre-processing in healthy subjects the joint space significantly out-performs either the frequency or amplitude features alone. This result only does not hold for ALS patients, for whom the dataset is of insufficient size to draw any statistically significant conclusions. Significance. Task-induced frequency modulation is robust and straight forward to compute, and increases performance when added to standard amplitude modulation features across paradigms. This allows more information to be extracted from the EEG signal cheaply and can be used throughout the field of BCIs.

Feature-based component model for design of embedded systems

Science.gov (United States)

Zha, Xuan Fang; Sriram, Ram D.

2004-11-01

An embedded system is a hybrid of hardware and software, which combines software's flexibility and hardware real-time performance. Embedded systems can be considered as assemblies of hardware and software components. An Open Embedded System Model (OESM) is currently being developed at NIST to provide a standard representation and exchange protocol for embedded systems and system-level design, simulation, and testing information. This paper proposes an approach to representing an embedded system feature-based model in OESM, i.e., Open Embedded System Feature Model (OESFM), addressing models of embedded system artifacts, embedded system components, embedded system features, and embedded system configuration/assembly. The approach provides an object-oriented UML (Unified Modeling Language) representation for the embedded system feature model and defines an extension to the NIST Core Product Model. The model provides a feature-based component framework allowing the designer to develop a virtual embedded system prototype through assembling virtual components. The framework not only provides a formal precise model of the embedded system prototype but also offers the possibility of designing variation of prototypes whose members are derived by changing certain virtual components with different features. A case study example is discussed to illustrate the embedded system model.

Volume Decomposition and Feature Recognition for Hexahedral Mesh Generation

Energy Technology Data Exchange (ETDEWEB)

GADH,RAJIT; LU,YONG; TAUTGES,TIMOTHY J.

1999-09-27

Considerable progress has been made on automatic hexahedral mesh generation in recent years. Several automatic meshing algorithms have proven to be very reliable on certain classes of geometry. While it is always worth pursuing general algorithms viable on more general geometry, a combination of the well-established algorithms is ready to take on classes of complicated geometry. By partitioning the entire geometry into meshable pieces matched with appropriate meshing algorithm the original geometry becomes meshable and may achieve better mesh quality. Each meshable portion is recognized as a meshing feature. This paper, which is a part of the feature based meshing methodology, presents the work on shape recognition and volume decomposition to automatically decompose a CAD model into meshable volumes. There are four phases in this approach: (1) Feature Determination to extinct decomposition features, (2) Cutting Surfaces Generation to form the ''tailored'' cutting surfaces, (3) Body Decomposition to get the imprinted volumes; and (4) Meshing Algorithm Assignment to match volumes decomposed with appropriate meshing algorithms. The feature determination procedure is based on the CLoop feature recognition algorithm that is extended to be more general. Results are demonstrated over several parts with complicated topology and geometry.

Generic Physiological Features as Predictors of Player Experience

DEFF Research Database (Denmark)

Martínez, Héctor Pérez; Garbarino, Maurizio; Yannakakis, Georgios N.

2011-01-01

This paper examines the generality of features extracted from heart rate (HR) and skin conductance (SC) signals as predictors of self-reported player affect expressed as pairwise preferences. Artificial neural networks are trained to accurately map physiological features to expressed affect in two...

Hierarchical Fuzzy Feature Similarity Combination for Presentation Slide Retrieval

Directory of Open Access Journals (Sweden)

A. Kushki

2009-02-01

Full Text Available This paper proposes a novel XML-based system for retrieval of presentation slides to address the growing data mining needs in presentation archives for educational and scholarly settings. In particular, contextual information, such as structural and formatting features, is extracted from the open format XML representation of presentation slides. In response to a textual user query, each extracted feature is used to compute a fuzzy relevance score for each slide in the database. The fuzzy scores from the various features are then combined through a hierarchical scheme to generate a single relevance score per slide. Various fusion operators and their properties are examined with respect to their effect on retrieval performance. Experimental results indicate a significant increase in retrieval performance measured in terms of precision-recall. The improvements are attributed to both the incorporation of the contextual features and the hierarchical feature combination scheme.

A Mean-Shift-Based Feature Descriptor for Wide Baseline Stereo Matching

Directory of Open Access Journals (Sweden)

Yiwen Dou

2015-01-01

Full Text Available We propose a novel Mean-Shift-based building approach in wide baseline. Initially, scale-invariance feature transform (SIFT approach is used to extract relatively stable feature points. As to each matching SIFT feature point, it needs a reasonable neighborhood range so as to choose feature points set. Subsequently, in view of selecting repeatable and high robust feature points, Mean-Shift controls corresponding feature scale. At last, our approach is employed to depth image acquirement in wide baseline and Graph Cut algorithm optimizes disparity information. Compared with the existing methods such as SIFT, speeded up robust feature (SURF, and normalized cross-correlation (NCC, the presented approach has the advantages of higher robustness and accuracy rate. Experimental results on low resolution image and weak feature description in wide baseline confirm the validity of our approach.

Eye movement identification based on accumulated time feature

Science.gov (United States)

Guo, Baobao; Wu, Qiang; Sun, Jiande; Yan, Hua

2017-06-01

Eye movement is a new kind of feature for biometrical recognition, it has many advantages compared with other features such as fingerprint, face, and iris. It is not only a sort of static characteristics, but also a combination of brain activity and muscle behavior, which makes it effective to prevent spoofing attack. In addition, eye movements can be incorporated with faces, iris and other features recorded from the face region into multimode systems. In this paper, we do an exploring study on eye movement identification based on the eye movement datasets provided by Komogortsev et al. in 2011 with different classification methods. The time of saccade and fixation are extracted from the eye movement data as the eye movement features. Furthermore, the performance analysis was conducted on different classification methods such as the BP, RBF, ELMAN and SVM in order to provide a reference to the future research in this field.

Psychological features of attention in archery

Directory of Open Access Journals (Sweden)

Ekaterina Yu. Korobeynikova

2017-06-01

Full Text Available The issue of attention is one of the leading in sports psychology. Quite often, athletes’ failures in competitions are ultimately connected with the attention processes, i.e. distraction, switching or loss of concentration. Simultaneously, each particular kind of sport is distinguished by a specific competitive situation and accordingly presents a number of requirements to athletes, including attention features. Archery is no exception. Thus, in shooting sports, concentration and stability of attention are often deemed as the most significant features of attention. The paper is devoted to the study of the attention dynamic properties in archers. Attention features of athletes were assessed depending on the sports major, gender, age, experience and level of competence. 65 archers from different regions of Russia took part in the study, including 34 males and 31 females, the average age being 16.29 ± 1.74. Experience ranges from 1 year to 8 years, average experience is 4.46 ± 1.93. The research results showed that archers are characterized by high indicators of stability of attention, and also high efficiency of solving attention problems. The professional success of archery was associated with the ability to distribute attention when necessary. At the same time, there were no significant differences in the features of attention for recurved and compound archers, which indicates the uniformity of tasks related to attention in the sporting practice of archers. Summing up, it is necessary to include skills in the distribution of attention in the program of psychological training of archers.

Discrimination of single features and conjunctions by children.

Science.gov (United States)

Taylor, M J; Chevalier, H; Lobaugh, N J

2003-12-01

Stimuli that are discriminated by a conjunction of features can show more rapid early processing in adults. To determine how this facilitation effect develops, the processing of visual features and their conjunction was examined in 7-12-year-old children. The children completed a series of tasks in which they made a target-non-target judgement as a function of shape only, colour only or shape and colour features, while event-related potentials were recorded. To assess early stages of feature processing the posteriorly distributed P1 and N1 were analysed. Attentional effects were seen for both components. P1 had a shorter latency and P1 and N1 had larger amplitudes to targets than non-targets. Task effects were driven by the conjunction task. P1 amplitude was largest, while N1 amplitude was smallest for the conjunction targets. In contrast to larger left-sided N1 in adults, N1 had a symmetrical distribution in the children. N1 latency was shortest for the conjunction targets in the 9-10-year olds and 11-12-year olds, demonstrating facilitation in children, but which continued to develop over the pre-teen years. These data underline the sensitivity of early stages of processing to both top-down modulations and the parallel binding of non-spatial features in young children. Furthermore, facilitation effects, increased speed of processing when features need to be conjoined, mature in mid-childhood, arguing against a hierarchical model of visual processing, and supporting a rapid, integrated facilitative model.

Convolutional neural network features based change detection in satellite images

Science.gov (United States)

Mohammed El Amin, Arabi; Liu, Qingjie; Wang, Yunhong

2016-07-01

With the popular use of high resolution remote sensing (HRRS) satellite images, a huge research efforts have been placed on change detection (CD) problem. An effective feature selection method can significantly boost the final result. While hand-designed features have proven difficulties to design features that effectively capture high and mid-level representations, the recent developments in machine learning (Deep Learning) omit this problem by learning hierarchical representation in an unsupervised manner directly from data without human intervention. In this letter, we propose approaching the change detection problem from a feature learning perspective. A novel deep Convolutional Neural Networks (CNN) features based HR satellite images change detection method is proposed. The main guideline is to produce a change detection map directly from two images using a pretrained CNN. This method can omit the limited performance of hand-crafted features. Firstly, CNN features are extracted through different convolutional layers. Then, a concatenation step is evaluated after an normalization step, resulting in a unique higher dimensional feature map. Finally, a change map was computed using pixel-wise Euclidean distance. Our method has been validated on real bitemporal HRRS satellite images according to qualitative and quantitative analyses. The results obtained confirm the interest of the proposed method.

A visual perceptual descriptor with depth feature for image retrieval

Science.gov (United States)

Wang, Tianyang; Qin, Zhengrui

2017-07-01

This paper proposes a visual perceptual descriptor (VPD) and a new approach to extract perceptual depth feature for 2D image retrieval. VPD mimics human visual system, which can easily distinguish regions that have different textures, whereas for regions which have similar textures, color features are needed for further differentiation. We apply VPD on the gradient direction map of an image, capture texture-similar regions to generate a VPD map. We then impose the VPD map on a quantized color map and extract color features only from the overlapped regions. To reflect the nature of perceptual distance in single 2D image, we propose and extract the perceptual depth feature by computing the nuclear norm of the sparse depth map of an image. Extracted color features and the perceptual depth feature are both incorporated to a feature vector, we utilize this vector to represent an image and measure similarity. We observe that the proposed VPD + depth method achieves a promising result, and extensive experiments prove that it outperforms other typical methods on 2D image retrieval.

High-level intuitive features (HLIFs) for intuitive skin lesion description.

Science.gov (United States)

Amelard, Robert; Glaister, Jeffrey; Wong, Alexander; Clausi, David A

2015-03-01

A set of high-level intuitive features (HLIFs) is proposed to quantitatively describe melanoma in standard camera images. Melanoma is the deadliest form of skin cancer. With rising incidence rates and subjectivity in current clinical detection methods, there is a need for melanoma decision support systems. Feature extraction is a critical step in melanoma decision support systems. Existing feature sets for analyzing standard camera images are comprised of low-level features, which exist in high-dimensional feature spaces and limit the system's ability to convey intuitive diagnostic rationale. The proposed HLIFs were designed to model the ABCD criteria commonly used by dermatologists such that each HLIF represents a human-observable characteristic. As such, intuitive diagnostic rationale can be conveyed to the user. Experimental results show that concatenating the proposed HLIFs with a full low-level feature set increased classification accuracy, and that HLIFs were able to separate the data better than low-level features with statistical significance. An example of a graphical interface for providing intuitive rationale is given.

AVC: Selecting discriminative features on basis of AUC by maximizing variable complementarity.

Science.gov (United States)

Sun, Lei; Wang, Jun; Wei, Jinmao

2017-03-14

The Receiver Operator Characteristic (ROC) curve is well-known in evaluating classification performance in biomedical field. Owing to its superiority in dealing with imbalanced and cost-sensitive data, the ROC curve has been exploited as a popular metric to evaluate and find out disease-related genes (features). The existing ROC-based feature selection approaches are simple and effective in evaluating individual features. However, these approaches may fail to find real target feature subset due to their lack of effective means to reduce the redundancy between features, which is essential in machine learning. In this paper, we propose to assess feature complementarity by a trick of measuring the distances between the misclassified instances and their nearest misses on the dimensions of pairwise features. If a misclassified instance and its nearest miss on one feature dimension are far apart on another feature dimension, the two features are regarded as complementary to each other. Subsequently, we propose a novel filter feature selection approach on the basis of the ROC analysis. The new approach employs an efficient heuristic search strategy to select optimal features with highest complementarities. The experimental results on a broad range of microarray data sets validate that the classifiers built on the feature subset selected by our approach can get the minimal balanced error rate with a small amount of significant features. Compared with other ROC-based feature selection approaches, our new approach can select fewer features and effectively improve the classification performance.

Feature-based motion control for near-repetitive structures

NARCIS (Netherlands)

Best, de J.J.T.H.

2011-01-01

In many manufacturing processes, production steps are carried out on repetitive structures which consist of identical features placed in a repetitive pattern. In the production of these repetitive structures one or more consecutive steps are carried out on the features to create the final product.

A bank-fund projection framework with CGE features

DEFF Research Database (Denmark)

Jensen, Henning Tarp; Tarp, Finn

2006-01-01

In this paper, we present a SAM-based methodology for integrating standard CGE features with a macroeconomic World Bank–International Monetary Fund (IMF) modelling framework. The resulting macro–micro framework is based on optimising agents, but it retains key features from the macroeconomic model...

Deep Complementary Bottleneck Features for Visual Speech Recognition

NARCIS (Netherlands)

Petridis, Stavros; Pantic, Maja

Deep bottleneck features (DBNFs) have been used successfully in the past for acoustic speech recognition from audio. However, research on extracting DBNFs for visual speech recognition is very limited. In this work, we present an approach to extract deep bottleneck visual features based on deep

Magnetic mirror fusion systems: Characteristics and distinctive features

International Nuclear Information System (INIS)

Post, R.F.

1987-01-01

A tutorial account is given of the main characteristics and distinctive features of conceptual magnetic fusion systems employing the magnetic mirror principle. These features are related to the potential advantages that mirror-based fusion systems may exhibit for the generation of economic fusion power

Predictive Feature Selection for Genetic Policy Search

Science.gov (United States)

2014-05-22

limited manual intervention are becoming increasingly desirable as more complex tasks in dynamic and high- tempo environments are explored. Reinforcement...states in many domains causes features relevant to the reward variations to be overlooked, which hinders the policy search. 3.4 Parameter Selection PFS...the current feature subset. This local minimum may be “deceptive,” meaning that it does not clearly lead to the global optimal policy ( Goldberg and

Efficient Divide-And-Conquer Classification Based on Feature-Space Decomposition

OpenAIRE

Guo, Qi; Chen, Bo-Wei; Jiang, Feng; Ji, Xiangyang; Kung, Sun-Yuan

2015-01-01

This study presents a divide-and-conquer (DC) approach based on feature space decomposition for classification. When large-scale datasets are present, typical approaches usually employed truncated kernel methods on the feature space or DC approaches on the sample space. However, this did not guarantee separability between classes, owing to overfitting. To overcome such problems, this work proposes a novel DC approach on feature spaces consisting of three steps. Firstly, we divide the feature ...

Creating fair lineups for suspects with distinctive features.

Science.gov (United States)

Zarkadi, Theodora; Wade, Kimberley A; Stewart, Neil

2009-12-01

In their descriptions, eyewitnesses often refer to a culprit's distinctive facial features. However, in a police lineup, selecting the only member with the described distinctive feature is unfair to the suspect and provides the police with little further information. For fair and informative lineups, the distinctive feature should be either replicated across foils or concealed on the target. In the present experiments, replication produced more correct identifications in target-present lineups--without increasing the incorrect identification of foils in target-absent lineups--than did concealment. This pattern, and only this pattern, is predicted by the hybrid-similarity model of recognition.

Proscene: A feature-rich framework for interactive environments

Directory of Open Access Journals (Sweden)

Jean Pierre Charalambos

2017-01-01

Full Text Available We introduce Proscene, a feature-rich, open-source framework for interactive environments. The design of Proscene comprises a three-layered onion-like software architecture, promoting different possible development scenarios. The framework innermost layer decouples user gesture parsing from user-defined actions. The in-between layer implements a feature-rich set of widely-used motion actions allowing the selection and manipulation of objects, including the scene viewpoint. The outermost layer exposes those features as a Processing library. The results have shown the feasibility of our approach together with the simplicity and flexibility of the Proscene framework API.

The semiology of febrile seizures: Focal features are frequent.

Science.gov (United States)

Takasu, Michihiko; Kubota, Tetsuo; Tsuji, Takeshi; Kurahashi, Hirokazu; Numoto, Shingo; Watanabe, Kazuyoshi; Okumura, Akihisa

2017-08-01

To clarify the semiology of febrile seizures (FS) and to determine the frequency of FS with symptoms suggestive of focal onset. FS symptoms in children were reported within 24h of seizure onset by the parents using a structured questionnaire consisting principally of closed-ended questions. We focused on events at seizure commencement, including changes in behavior and facial expression, and ocular and oral symptoms. We also investigated the autonomic and motor symptoms developing during seizures. The presence or absence of focal and limbic features was determined for each patient. The associations of certain focal and limbic features with patient characteristics were assessed. Information was obtained on FS in 106 children. Various events were recorded at seizure commencement. Behavioral changes were observed in 35 children, changes in facial expression in 53, ocular symptoms in 78, and oral symptoms in 90. In terms of events during seizures, autonomic symptoms were recognized in 78, and convulsive motor symptoms were recognized in 68 children. Focal features were evident in 81 children; 38 children had two or more such features. Limbic features were observed in 44 children, 9 of whom had two or more such features. There was no significant relationship between any patient characteristic and the numbers of focal or limbic features. The semiology of FS varied widely among children, and symptoms suggestive of focal onset were frequent. FS of focal onset may be more common than is generally thought. Copyright © 2017 Elsevier Inc. All rights reserved.

Hemorrhage detection in MRI brain images using images features

Science.gov (United States)

Moraru, Luminita; Moldovanu, Simona; Bibicu, Dorin; Stratulat (Visan), Mirela

2013-11-01

The abnormalities appear frequently on Magnetic Resonance Images (MRI) of brain in elderly patients presenting either stroke or cognitive impairment. Detection of brain hemorrhage lesions in MRI is an important but very time-consuming task. This research aims to develop a method to extract brain tissue features from T2-weighted MR images of the brain using a selection of the most valuable texture features in order to discriminate between normal and affected areas of the brain. Due to textural similarity between normal and affected areas in brain MR images these operation are very challenging. A trauma may cause microstructural changes, which are not necessarily perceptible by visual inspection, but they could be detected by using a texture analysis. The proposed analysis is developed in five steps: i) in the pre-processing step: the de-noising operation is performed using the Daubechies wavelets; ii) the original images were transformed in image features using the first order descriptors; iii) the regions of interest (ROIs) were cropped from images feature following up the axial symmetry properties with respect to the mid - sagittal plan; iv) the variation in the measurement of features was quantified using the two descriptors of the co-occurrence matrix, namely energy and homogeneity; v) finally, the meaningful of the image features is analyzed by using the t-test method. P-value has been applied to the pair of features in order to measure they efficacy.

Improved Feature Matching for Mobile Devices with IMU

Directory of Open Access Journals (Sweden)

Andrea Masiero

2016-08-01

Full Text Available Thanks to the recent diffusion of low-cost high-resolution digital cameras and to the development of mostly automated procedures for image-based 3D reconstruction, the popularity of photogrammetry for environment surveys is constantly increasing in the last years. Automatic feature matching is an important step in order to successfully complete the photogrammetric 3D reconstruction: this step is the fundamental basis for the subsequent estimation of the geometry of the scene. This paper reconsiders the feature matching problem when dealing with smart mobile devices (e.g., when using the standard camera embedded in a smartphone as imaging sensor. More specifically, this paper aims at exploiting the information on camera movements provided by the inertial navigation system (INS in order to make the feature matching step more robust and, possibly, computationally more efficient. First, a revised version of the affine scale-invariant feature transform (ASIFT is considered: this version reduces the computational complexity of the original ASIFT, while still ensuring an increase of correct feature matches with respect to the SIFT. Furthermore, a new two-step procedure for the estimation of the essential matrix E (and the camera pose is proposed in order to increase its estimation robustness and computational efficiency.

Engineering safety features for high power experimental reactors

International Nuclear Information System (INIS)

Doval, A.; Villarino, E.; Vertullo, A.

2000-01-01

In the present analysis we will focus our attention in the way engineering safety features are designed in order to prevent fuel damage in case of abnormal or accidental situations. To prevent fuel damage two main facts must be considered, the shutdown of the reactor and the adequate core cooling capacity, it means that both, neutronic and thermohydraulic aspects must be analysed. Some neutronic safety features are common to all power ranges like negative feedback reactivity coefficients and the required number of control rods containing the proper absorber material to shutdown the reactor. From the thermohydraulic point of view common features are siphon-breaker devices and flap valves for those powers requiring cooling in the forced convection regime. For the high power reactor group, the engineering safety features specially designed for a generic reactor of 20 MW, will be presented here. From the neutronic point of view besides the common features, and to comply with our National Regulatory Authority, a Second Shutdown System was designed as a redundant shutdown system in case the control plates fail. Concerning thermohydraulic aspects besides the pump flywheels and the flap valves providing the natural convection loop, a metallic Chimney and a Chimney Water Injection System were supplied. (author)

Features of Fragile X Syndrome

Science.gov (United States)

... Disabilities in FXS include a range from moderate learning disabilities to more severe intellectual disabilities. Physical features may ... intellectual disability. Others may have moderate or mild learning disabilities, emotional/mental health issues, general anxiety and/or ...

Biomedical Imaging Modality Classification Using Combined Visual Features and Textual Terms

Directory of Open Access Journals (Sweden)

Xian-Hua Han

2011-01-01

extraction from medical images and fuses the different extracted visual features and textual feature for modality classification. To extract visual features from the images, we used histogram descriptor of edge, gray, or color intensity and block-based variation as global features and SIFT histogram as local feature. For textual feature of image representation, the binary histogram of some predefined vocabulary words from image captions is used. Then, we combine the different features using normalized kernel functions for SVM classification. Furthermore, for some easy misclassified modality pairs such as CT and MR or PET and NM modalities, a local classifier is used for distinguishing samples in the pair modality to improve performance. The proposed strategy is evaluated with the provided modality dataset by ImageCLEF 2010.

An adaptation study of internal and external features in facial representations.

Science.gov (United States)

Hills, Charlotte; Romano, Kali; Davies-Thompson, Jodie; Barton, Jason J S

2014-07-01

Prior work suggests that internal features contribute more than external features to face processing. Whether this asymmetry is also true of the mental representations of faces is not known. We used face adaptation to determine whether the internal and external features of faces contribute differently to the representation of facial identity, whether this was affected by familiarity, and whether the results differed if the features were presented in isolation or as part of a whole face. In a first experiment, subjects performed a study of identity adaptation for famous and novel faces, in which the adapting stimuli were whole faces, the internal features alone, or the external features alone. In a second experiment, the same faces were used, but the adapting internal and external features were superimposed on whole faces that were ambiguous to identity. The first experiment showed larger aftereffects for unfamiliar faces, and greater aftereffects from internal than from external features, and the latter was true for both familiar and unfamiliar faces. When internal and external features were presented in a whole-face context in the second experiment, aftereffects from either internal or external features was less than that from the whole face, and did not differ from each other. While we reproduce the greater importance of internal features when presented in isolation, we find this is equally true for familiar and unfamiliar faces. The dominant influence of internal features is reduced when integrated into a whole-face context, suggesting another facet of expert face processing. Copyright © 2014 Elsevier B.V. All rights reserved.

A feature-based approach to modeling protein-protein interaction hot spots.

Science.gov (United States)

Cho, Kyu-il; Kim, Dongsup; Lee, Doheon

2009-05-01

Identifying features that effectively represent the energetic contribution of an individual interface residue to the interactions between proteins remains problematic. Here, we present several new features and show that they are more effective than conventional features. By combining the proposed features with conventional features, we develop a predictive model for interaction hot spots. Initially, 54 multifaceted features, composed of different levels of information including structure, sequence and molecular interaction information, are quantified. Then, to identify the best subset of features for predicting hot spots, feature selection is performed using a decision tree. Based on the selected features, a predictive model for hot spots is created using support vector machine (SVM) and tested on an independent test set. Our model shows better overall predictive accuracy than previous methods such as the alanine scanning methods Robetta and FOLDEF, and the knowledge-based method KFC. Subsequent analysis yields several findings about hot spots. As expected, hot spots have a larger relative surface area burial and are more hydrophobic than other residues. Unexpectedly, however, residue conservation displays a rather complicated tendency depending on the types of protein complexes, indicating that this feature is not good for identifying hot spots. Of the selected features, the weighted atomic packing density, relative surface area burial and weighted hydrophobicity are the top 3, with the weighted atomic packing density proving to be the most effective feature for predicting hot spots. Notably, we find that hot spots are closely related to pi-related interactions, especially pi . . . pi interactions.

A feature-based approach to modeling protein–protein interaction hot spots

Science.gov (United States)

Cho, Kyu-il; Kim, Dongsup; Lee, Doheon

2009-01-01

Identifying features that effectively represent the energetic contribution of an individual interface residue to the interactions between proteins remains problematic. Here, we present several new features and show that they are more effective than conventional features. By combining the proposed features with conventional features, we develop a predictive model for interaction hot spots. Initially, 54 multifaceted features, composed of different levels of information including structure, sequence and molecular interaction information, are quantified. Then, to identify the best subset of features for predicting hot spots, feature selection is performed using a decision tree. Based on the selected features, a predictive model for hot spots is created using support vector machine (SVM) and tested on an independent test set. Our model shows better overall predictive accuracy than previous methods such as the alanine scanning methods Robetta and FOLDEF, and the knowledge-based method KFC. Subsequent analysis yields several findings about hot spots. As expected, hot spots have a larger relative surface area burial and are more hydrophobic than other residues. Unexpectedly, however, residue conservation displays a rather complicated tendency depending on the types of protein complexes, indicating that this feature is not good for identifying hot spots. Of the selected features, the weighted atomic packing density, relative surface area burial and weighted hydrophobicity are the top 3, with the weighted atomic packing density proving to be the most effective feature for predicting hot spots. Notably, we find that hot spots are closely related to π–related interactions, especially π · · · π interactions. PMID:19273533

Global seafloor geomorphic features map: applications for ocean conservation and management

Science.gov (United States)

Harris, P. T.; Macmillan-Lawler, M.; Rupp, J.; Baker, E.

2013-12-01

Seafloor geomorphology, mapped and measured by marine scientists, has proven to be a very useful physical attribute for ocean management because different geomorphic features (eg. submarine canyons, seamounts, spreading ridges, escarpments, plateaus, trenches etc.) are commonly associated with particular suites of habitats and biological communities. Although we now have better bathymetric datasets than ever before, there has been little effort to integrate these data to create an updated map of seabed geomorphic features or habitats. Currently the best available global seafloor geomorphic features map is over 30 years old. A new global seafloor geomorphic features map (GSGM) has been created based on the analysis and interpretation of the SRTM (Shuttle Radar Topography Mission) 30 arc-second (~1 km) global bathymetry grid. The new map includes global spatial data layers for 29 categories of geomorphic features, defined by the International Hydrographic Organisation. The new geomorphic features map will allow: 1) Characterization of bioregions in terms of their geomorphic content (eg. GOODS bioregions, Large Marine Ecosystems (LMEs), ecologically or biologically significant areas (EBSA)); 2) Prediction of the potential spatial distribution of vulnerable marine ecosystems (VME) and marine genetic resources (MGR; eg. associated with hydrothermal vent communities, shelf-incising submarine canyons and seamounts rising to a specified depth); and 3) Characterization of national marine jurisdictions in terms of their inventory of geomorphic features and their global representativeness of features. To demonstrate the utility of the GSGM, we have conducted an analysis of the geomorphic feature content of the current global inventory of marine protected areas (MPAs) to assess the extent to which features are currently represented. The analysis shows that many features have very low representation, for example fans and rises have less than 1 per cent of their total area

SVM-based glioma grading. Optimization by feature reduction analysis

International Nuclear Information System (INIS)

Zoellner, Frank G.; Schad, Lothar R.; Emblem, Kyrre E.; Harvard Medical School, Boston, MA; Oslo Univ. Hospital

2012-01-01

We investigated the predictive power of feature reduction analysis approaches in support vector machine (SVM)-based classification of glioma grade. In 101 untreated glioma patients, three analytic approaches were evaluated to derive an optimal reduction in features; (i) Pearson's correlation coefficients (PCC), (ii) principal component analysis (PCA) and (iii) independent component analysis (ICA). Tumor grading was performed using a previously reported SVM approach including whole-tumor cerebral blood volume (CBV) histograms and patient age. Best classification accuracy was found using PCA at 85% (sensitivity = 89%, specificity = 84%) when reducing the feature vector from 101 (100-bins rCBV histogram + age) to 3 principal components. In comparison, classification accuracy by PCC was 82% (89%, 77%, 2 dimensions) and 79% by ICA (87%, 75%, 9 dimensions). For improved speed (up to 30%) and simplicity, feature reduction by all three methods provided similar classification accuracy to literature values (∝87%) while reducing the number of features by up to 98%. (orig.)

Multiscale deep features learning for land-use scene recognition

Science.gov (United States)

Yuan, Baohua; Li, Shijin; Li, Ning

2018-01-01

The features extracted from deep convolutional neural networks (CNNs) have shown their promise as generic descriptors for land-use scene recognition. However, most of the work directly adopts the deep features for the classification of remote sensing images, and does not encode the deep features for improving their discriminative power, which can affect the performance of deep feature representations. To address this issue, we propose an effective framework, LASC-CNN, obtained by locality-constrained affine subspace coding (LASC) pooling of a CNN filter bank. LASC-CNN obtains more discriminative deep features than directly extracted from CNNs. Furthermore, LASC-CNN builds on the top convolutional layers of CNNs, which can incorporate multiscale information and regions of arbitrary resolution and sizes. Our experiments have been conducted using two widely used remote sensing image databases, and the results show that the proposed method significantly improves the performance when compared to other state-of-the-art methods.

The Perceptions of Users’ on eBook Readers’ Features

Directory of Open Access Journals (Sweden)

Erhan DELEN

2014-12-01

Full Text Available The purpose of this study was to investigate eBook reader (ER users’ perceptions on eBook readers’ features and explore how users’ opinions differ based on their personal characteristics. The sample of the study was 82 ER users who had at least a bachelor’s degree. In order to figure out the reasons of using ERs, participants were asked several questions about technical, mobility, and access features of ERs. The collected data was analyzed with t-test and ANOVA. As a result, it was found that mobility features of ERs are the most important reasons for users to prefer using an ER. When users’ personal characteristics were considered, it was found that, users who use an ER in daily basis or for an academic purpose, use ERs’ technical and access features more than other users. Results also show that users don't tend to use very specific features of ERs such as text to speech and printing

Iris recognition using possibilistic fuzzy matching on local features.

Science.gov (United States)

Tsai, Chung-Chih; Lin, Heng-Yi; Taur, Jinshiuh; Tao, Chin-Wang

2012-02-01

In this paper, we propose a novel possibilistic fuzzy matching strategy with invariant properties, which can provide a robust and effective matching scheme for two sets of iris feature points. In addition, the nonlinear normalization model is adopted to provide more accurate position before matching. Moreover, an effective iris segmentation method is proposed to refine the detected inner and outer boundaries to smooth curves. For feature extraction, the Gabor filters are adopted to detect the local feature points from the segmented iris image in the Cartesian coordinate system and to generate a rotation-invariant descriptor for each detected point. After that, the proposed matching algorithm is used to compute a similarity score for two sets of feature points from a pair of iris images. The experimental results show that the performance of our system is better than those of the systems based on the local features and is comparable to those of the typical systems.

SVM-based glioma grading. Optimization by feature reduction analysis

Energy Technology Data Exchange (ETDEWEB)

Zoellner, Frank G.; Schad, Lothar R. [University Medical Center Mannheim, Heidelberg Univ., Mannheim (Germany). Computer Assisted Clinical Medicine; Emblem, Kyrre E. [Massachusetts General Hospital, Charlestown, A.A. Martinos Center for Biomedical Imaging, Boston MA (United States). Dept. of Radiology; Harvard Medical School, Boston, MA (United States); Oslo Univ. Hospital (Norway). The Intervention Center

2012-11-01

We investigated the predictive power of feature reduction analysis approaches in support vector machine (SVM)-based classification of glioma grade. In 101 untreated glioma patients, three analytic approaches were evaluated to derive an optimal reduction in features; (i) Pearson's correlation coefficients (PCC), (ii) principal component analysis (PCA) and (iii) independent component analysis (ICA). Tumor grading was performed using a previously reported SVM approach including whole-tumor cerebral blood volume (CBV) histograms and patient age. Best classification accuracy was found using PCA at 85% (sensitivity = 89%, specificity = 84%) when reducing the feature vector from 101 (100-bins rCBV histogram + age) to 3 principal components. In comparison, classification accuracy by PCC was 82% (89%, 77%, 2 dimensions) and 79% by ICA (87%, 75%, 9 dimensions). For improved speed (up to 30%) and simplicity, feature reduction by all three methods provided similar classification accuracy to literature values ({proportional_to}87%) while reducing the number of features by up to 98%. (orig.)

Generalised Brown Clustering and Roll-up Feature Generation

DEFF Research Database (Denmark)

Derczynski, Leon; Chester, Sean

2016-01-01

active set size. Moreover, the generalisation permits a novel approach to feature selection from Brown clusters: We show that the standard approach of shearing the Brown clustering output tree at arbitrary bitlengths is lossy and that features should be chosen instead by rolling up Generalised Brown...

Person Re-Identification by Camera Correlation Aware Feature Augmentation.

Science.gov (United States)

Chen, Ying-Cong; Zhu, Xiatian; Zheng, Wei-Shi; Lai, Jian-Huang

2018-02-01

The challenge of person re-identification (re-id) is to match individual images of the same person captured by different non-overlapping camera views against significant and unknown cross-view feature distortion. While a large number of distance metric/subspace learning models have been developed for re-id, the cross-view transformations they learned are view-generic and thus potentially less effective in quantifying the feature distortion inherent to each camera view. Learning view-specific feature transformations for re-id (i.e., view-specific re-id), an under-studied approach, becomes an alternative resort for this problem. In this work, we formulate a novel view-specific person re-identification framework from the feature augmentation point of view, called Camera coR relation Aware Feature augmenTation (CRAFT). Specifically, CRAFT performs cross-view adaptation by automatically measuring camera correlation from cross-view visual data distribution and adaptively conducting feature augmentation to transform the original features into a new adaptive space. Through our augmentation framework, view-generic learning algorithms can be readily generalized to learn and optimize view-specific sub-models whilst simultaneously modelling view-generic discrimination information. Therefore, our framework not only inherits the strength of view-generic model learning but also provides an effective way to take into account view specific characteristics. Our CRAFT framework can be extended to jointly learn view-specific feature transformations for person re-id across a large network with more than two cameras, a largely under-investigated but realistic re-id setting. Additionally, we present a domain-generic deep person appearance representation which is designed particularly to be towards view invariant for facilitating cross-view adaptation by CRAFT. We conducted extensively comparative experiments to validate the superiority and advantages of our proposed framework over state

Evolutionary Feature Selection for Big Data Classification: A MapReduce Approach

Directory of Open Access Journals (Sweden)

Daniel Peralta

2015-01-01

Full Text Available Nowadays, many disciplines have to deal with big datasets that additionally involve a high number of features. Feature selection methods aim at eliminating noisy, redundant, or irrelevant features that may deteriorate the classification performance. However, traditional methods lack enough scalability to cope with datasets of millions of instances and extract successful results in a delimited time. This paper presents a feature selection algorithm based on evolutionary computation that uses the MapReduce paradigm to obtain subsets of features from big datasets. The algorithm decomposes the original dataset in blocks of instances to learn from them in the map phase; then, the reduce phase merges the obtained partial results into a final vector of feature weights, which allows a flexible application of the feature selection procedure using a threshold to determine the selected subset of features. The feature selection method is evaluated by using three well-known classifiers (SVM, Logistic Regression, and Naive Bayes implemented within the Spark framework to address big data problems. In the experiments, datasets up to 67 millions of instances and up to 2000 attributes have been managed, showing that this is a suitable framework to perform evolutionary feature selection, improving both the classification accuracy and its runtime when dealing with big data problems.

Youth job market specific features

Directory of Open Access Journals (Sweden)

Evgeniya Yu. Zhuravleva

2011-05-01

Full Text Available The article considers youth job market peculiarities, its specific features and regulation means, determines theoretical and application tasks of qualitative and quantitative comparison of vocations, which are highly in demand at the job market.

Radiographic Features of Acute Patellar Tendon Rupture.

Science.gov (United States)

Fazal, Muhammad Ali; Moonot, Pradeep; Haddad, Fares

2015-11-01

The purpose of our study was to assess soft tissue features of acute patellar tendon rupture on lateral knee radiograph that would facilitate early diagnosis. The participants were divided into two groups of 35 patients each. There were 28 men and seven women with a mean age of 46 years in the control group and 26 men and nine women with a mean age of 47 years in the rupture group. The lateral knee radiograph of each patient was evaluated for Insall-Salvati ratio for patella alta, increased density of the infrapatellar fat pad, appearance of the soft tissue margin of the patellar tendon and bony avulsions. In the rupture group there were three consistent soft tissue radiographic features in addition to patellar alta. These were increased density of infrapatellar fat pad; loss of sharp, well-defined linear margins of the patellar tendon and angulated wavy margin of the patellar tendon while in the control group these features were not observed. The soft tissue radiographic features described in the rupture group are consistent and reliable. When coupled with careful clinical assessment, these will aid in early diagnosis and further imaging will be seldom required. © 2015 Chinese Orthopaedic Association and Wiley Publishing Asia Pty Ltd.