Podiatry Ankle Duplex Scan: Readily Learned and Accurate in Diabetes.

Science.gov (United States)

Normahani, Pasha; Powezka, Katarzyna; Aslam, Mohammed; Standfield, Nigel J; Jaffer, Usman

2018-03-01

We aimed to train podiatrists to perform a focused duplex ultrasound scan (DUS) of the tibial vessels at the ankle in diabetic patients; podiatry ankle (PodAnk) duplex scan. Thirteen podiatrists underwent an intensive 3-hour long simulation training session. Participants were then assessed performing bilateral PodAnk duplex scans of 3 diabetic patients with peripheral arterial disease. Participants were assessed using the duplex ultrasound objective structured assessment of technical skills (DUOSATS) tool and an "Imaging Score". A total of 156 vessel assessments were performed. All patients had abnormal waveforms with a loss of triphasic flow. Loss of triphasic flow was accurately detected in 145 (92.9%) vessels; the correct waveform was identified in 139 (89.1%) cases. Participants achieved excellent DUOSATS scores (median 24 [interquartile range: 23-25], max attainable score of 26) as well as "Imaging Scores" (8 [8-8], max attainable score of 8) indicating proficiency in technical skills. The mean time taken for each bilateral ankle assessment was 20.4 minutes (standard deviation ±6.7). We have demonstrated that a focused DUS for the purpose of vascular assessment of the diabetic foot is readily learned using intensive simulation training.

A machine learned classifier that uses gene expression data to accurately predict estrogen receptor status.

Directory of Open Access Journals (Sweden)

Meysam Bastani

Full Text Available BACKGROUND: Selecting the appropriate treatment for breast cancer requires accurately determining the estrogen receptor (ER status of the tumor. However, the standard for determining this status, immunohistochemical analysis of formalin-fixed paraffin embedded samples, suffers from numerous technical and reproducibility issues. Assessment of ER-status based on RNA expression can provide more objective, quantitative and reproducible test results. METHODS: To learn a parsimonious RNA-based classifier of hormone receptor status, we applied a machine learning tool to a training dataset of gene expression microarray data obtained from 176 frozen breast tumors, whose ER-status was determined by applying ASCO-CAP guidelines to standardized immunohistochemical testing of formalin fixed tumor. RESULTS: This produced a three-gene classifier that can predict the ER-status of a novel tumor, with a cross-validation accuracy of 93.17±2.44%. When applied to an independent validation set and to four other public databases, some on different platforms, this classifier obtained over 90% accuracy in each. In addition, we found that this prediction rule separated the patients' recurrence-free survival curves with a hazard ratio lower than the one based on the IHC analysis of ER-status. CONCLUSIONS: Our efficient and parsimonious classifier lends itself to high throughput, highly accurate and low-cost RNA-based assessments of ER-status, suitable for routine high-throughput clinical use. This analytic method provides a proof-of-principle that may be applicable to developing effective RNA-based tests for other biomarkers and conditions.

ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction

Science.gov (United States)

2013-01-01

Background Population stratification is a systematic difference in allele frequencies between subpopulations. This can lead to spurious association findings in the case–control genome wide association studies (GWASs) used to identify single nucleotide polymorphisms (SNPs) associated with disease-linked phenotypes. Methods such as self-declared ancestry, ancestry informative markers, genomic control, structured association, and principal component analysis are used to assess and correct population stratification but each has limitations. We provide an alternative technique to address population stratification. Results We propose a novel machine learning method, ETHNOPRED, which uses the genotype and ethnicity data from the HapMap project to learn ensembles of disjoint decision trees, capable of accurately predicting an individual’s continental and sub-continental ancestry. To predict an individual’s continental ancestry, ETHNOPRED produced an ensemble of 3 decision trees involving a total of 10 SNPs, with 10-fold cross validation accuracy of 100% using HapMap II dataset. We extended this model to involve 29 disjoint decision trees over 149 SNPs, and showed that this ensemble has an accuracy of ≥ 99.9%, even if some of those 149 SNP values were missing. On an independent dataset, predominantly of Caucasian origin, our continental classifier showed 96.8% accuracy and improved genomic control’s λ from 1.22 to 1.11. We next used the HapMap III dataset to learn classifiers to distinguish European subpopulations (North-Western vs. Southern), East Asian subpopulations (Chinese vs. Japanese), African subpopulations (Eastern vs. Western), North American subpopulations (European vs. Chinese vs. African vs. Mexican vs. Indian), and Kenyan subpopulations (Luhya vs. Maasai). In these cases, ETHNOPRED produced ensembles of 3, 39, 21, 11, and 25 disjoint decision trees, respectively involving 31, 502, 526, 242 and 271 SNPs, with 10-fold cross validation accuracy of

Structure-based sampling and self-correcting machine learning for accurate calculations of potential energy surfaces and vibrational levels

Science.gov (United States)

Dral, Pavlo O.; Owens, Alec; Yurchenko, Sergei N.; Thiel, Walter

2017-06-01

We present an efficient approach for generating highly accurate molecular potential energy surfaces (PESs) using self-correcting, kernel ridge regression (KRR) based machine learning (ML). We introduce structure-based sampling to automatically assign nuclear configurations from a pre-defined grid to the training and prediction sets, respectively. Accurate high-level ab initio energies are required only for the points in the training set, while the energies for the remaining points are provided by the ML model with negligible computational cost. The proposed sampling procedure is shown to be superior to random sampling and also eliminates the need for training several ML models. Self-correcting machine learning has been implemented such that each additional layer corrects errors from the previous layer. The performance of our approach is demonstrated in a case study on a published high-level ab initio PES of methyl chloride with 44 819 points. The ML model is trained on sets of different sizes and then used to predict the energies for tens of thousands of nuclear configurations within seconds. The resulting datasets are utilized in variational calculations of the vibrational energy levels of CH3Cl. By using both structure-based sampling and self-correction, the size of the training set can be kept small (e.g., 10% of the points) without any significant loss of accuracy. In ab initio rovibrational spectroscopy, it is thus possible to reduce the number of computationally costly electronic structure calculations through structure-based sampling and self-correcting KRR-based machine learning by up to 90%.

Rapid and Accurate Machine Learning Recognition of High Performing Metal Organic Frameworks for CO2 Capture.

Science.gov (United States)

Fernandez, Michael; Boyd, Peter G; Daff, Thomas D; Aghaji, Mohammad Zein; Woo, Tom K

2014-09-04

In this work, we have developed quantitative structure-property relationship (QSPR) models using advanced machine learning algorithms that can rapidly and accurately recognize high-performing metal organic framework (MOF) materials for CO2 capture. More specifically, QSPR classifiers have been developed that can, in a fraction of a section, identify candidate MOFs with enhanced CO2 adsorption capacity (>1 mmol/g at 0.15 bar and >4 mmol/g at 1 bar). The models were tested on a large set of 292 050 MOFs that were not part of the training set. The QSPR classifier could recover 945 of the top 1000 MOFs in the test set while flagging only 10% of the whole library for compute intensive screening. Thus, using the machine learning classifiers as part of a high-throughput screening protocol would result in an order of magnitude reduction in compute time and allow intractably large structure libraries and search spaces to be screened.

Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space

International Nuclear Information System (INIS)

Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan; Pronobis, Wiktor; Lilienfeld, O. Anatole von; Müller, Klaus-Robert; Tkatchenko, Alexandre

2015-01-01

Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the 'holy grail' of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. The same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies

Automatical and accurate segmentation of cerebral tissues in fMRI dataset with combination of image processing and deep learning

Science.gov (United States)

Kong, Zhenglun; Luo, Junyi; Xu, Shengpu; Li, Ting

2018-02-01

Image segmentation plays an important role in medical science. One application is multimodality imaging, especially the fusion of structural imaging with functional imaging, which includes CT, MRI and new types of imaging technology such as optical imaging to obtain functional images. The fusion process require precisely extracted structural information, in order to register the image to it. Here we used image enhancement, morphometry methods to extract the accurate contours of different tissues such as skull, cerebrospinal fluid (CSF), grey matter (GM) and white matter (WM) on 5 fMRI head image datasets. Then we utilized convolutional neural network to realize automatic segmentation of images in deep learning way. Such approach greatly reduced the processing time compared to manual and semi-automatic segmentation and is of great importance in improving speed and accuracy as more and more samples being learned. The contours of the borders of different tissues on all images were accurately extracted and 3D visualized. This can be used in low-level light therapy and optical simulation software such as MCVM. We obtained a precise three-dimensional distribution of brain, which offered doctors and researchers quantitative volume data and detailed morphological characterization for personal precise medicine of Cerebral atrophy/expansion. We hope this technique can bring convenience to visualization medical and personalized medicine.

Using machine learning and surface reconstruction to accurately differentiate different trajectories of mood and energy dysregulation in youth.

Science.gov (United States)

Versace, Amelia; Sharma, Vinod; Bertocci, Michele A; Bebko, Genna; Iyengar, Satish; Dwojak, Amanda; Bonar, Lisa; Perlman, Susan B; Schirda, Claudiu; Travis, Michael; Gill, Mary Kay; Diwadkar, Vaibhav A; Sunshine, Jeffrey L; Holland, Scott K; Kowatch, Robert A; Birmaher, Boris; Axelson, David; Frazier, Thomas W; Arnold, L Eugene; Fristad, Mary A; Youngstrom, Eric A; Horwitz, Sarah M; Findling, Robert L; Phillips, Mary L

2017-01-01

Difficulty regulating positive mood and energy is a feature that cuts across different pediatric psychiatric disorders. Yet, little is known regarding the neural mechanisms underlying different developmental trajectories of positive mood and energy regulation in youth. Recent studies indicate that machine learning techniques can help elucidate the role of neuroimaging measures in classifying individual subjects by specific symptom trajectory. Cortical thickness measures were extracted in sixty-eight anatomical regions covering the entire brain in 115 participants from the Longitudinal Assessment of Manic Symptoms (LAMS) study and 31 healthy comparison youth (12.5 y/o;-Male/Female = 15/16;-IQ = 104;-Right/Left handedness = 24/5). Using a combination of trajectories analyses, surface reconstruction, and machine learning techniques, the present study aims to identify the extent to which measures of cortical thickness can accurately distinguish youth with higher (n = 18) from those with lower (n = 34) trajectories of manic-like behaviors in a large sample of LAMS youth (n = 115; 13.6 y/o; M/F = 68/47, IQ = 100.1, R/L = 108/7). Machine learning analyses revealed that widespread cortical thickening in portions of the left dorsolateral prefrontal cortex, right inferior and middle temporal gyrus, bilateral precuneus, and bilateral paracentral gyri and cortical thinning in portions of the right dorsolateral prefrontal cortex, left ventrolateral prefrontal cortex, and right parahippocampal gyrus accurately differentiate (Area Under Curve = 0.89;p = 0.03) youth with different (higher vs lower) trajectories of positive mood and energy dysregulation over a period up to 5years, as measured by the Parent General Behavior Inventory-10 Item Mania Scale. Our findings suggest that specific patterns of cortical thickness may reflect transdiagnostic neural mechanisms associated with different temporal trajectories of positive mood and energy dysregulation in youth. This approach has

Using machine learning and surface reconstruction to accurately differentiate different trajectories of mood and energy dysregulation in youth.

Directory of Open Access Journals (Sweden)

Amelia Versace

Full Text Available Difficulty regulating positive mood and energy is a feature that cuts across different pediatric psychiatric disorders. Yet, little is known regarding the neural mechanisms underlying different developmental trajectories of positive mood and energy regulation in youth. Recent studies indicate that machine learning techniques can help elucidate the role of neuroimaging measures in classifying individual subjects by specific symptom trajectory. Cortical thickness measures were extracted in sixty-eight anatomical regions covering the entire brain in 115 participants from the Longitudinal Assessment of Manic Symptoms (LAMS study and 31 healthy comparison youth (12.5 y/o;-Male/Female = 15/16;-IQ = 104;-Right/Left handedness = 24/5. Using a combination of trajectories analyses, surface reconstruction, and machine learning techniques, the present study aims to identify the extent to which measures of cortical thickness can accurately distinguish youth with higher (n = 18 from those with lower (n = 34 trajectories of manic-like behaviors in a large sample of LAMS youth (n = 115; 13.6 y/o; M/F = 68/47, IQ = 100.1, R/L = 108/7. Machine learning analyses revealed that widespread cortical thickening in portions of the left dorsolateral prefrontal cortex, right inferior and middle temporal gyrus, bilateral precuneus, and bilateral paracentral gyri and cortical thinning in portions of the right dorsolateral prefrontal cortex, left ventrolateral prefrontal cortex, and right parahippocampal gyrus accurately differentiate (Area Under Curve = 0.89;p = 0.03 youth with different (higher vs lower trajectories of positive mood and energy dysregulation over a period up to 5years, as measured by the Parent General Behavior Inventory-10 Item Mania Scale. Our findings suggest that specific patterns of cortical thickness may reflect transdiagnostic neural mechanisms associated with different temporal trajectories of positive mood and energy dysregulation in youth. This

Media and Information Literacy (MIL) in journalistic learning: strategies for accurately engaging with information and reporting news

Science.gov (United States)

Inayatillah, F.

2018-01-01

In the era of digital technology, there is abundant information from various sources. This ease of access needs to be accompanied by the ability to engage with the information wisely. Thus, information and media literacy is required. From the results of preliminary observations, it was found that the students of Universitas Negeri Surabaya, whose major is Indonesian Literature, and they take journalistic course lack of the skill of media and information literacy (MIL). Therefore, they need to be equipped with MIL. The method used is descriptive qualitative, which includes data collection, data analysis, and presentation of data analysis. Observation and documentation techniques were used to obtain data of MIL’s impact on journalistic learning for students. This study aims at describing the important role of MIL for students of journalistic and its impact on journalistic learning for students of Indonesian literature batch 2014. The results of this research indicate that journalistic is a science that is essential for students because it affects how a person perceives news report. Through the reinforcement of the course, students can avoid a hoax. MIL-based journalistic learning makes students will be more skillful at absorbing, processing, and presenting information accurately. The subject influences students in engaging with information so that they can report news credibly.

Store skadar på poppel

OpenAIRE

Talgø, Venche; Sletten, Arild; Gjærum, Halvor B.; Stensvand, Arne

2009-01-01

I vekstsesongen 2007 kom det inn fleire rapportar frå Oslo og omegn om poppel (Populus spp.) med visne blad og greiner. Gjennom prosjektet ”Planter for norsk klima” undersøkte vi i 2008 poppel frå fleire lokalitetar på Austlandet og fann ulike skadar. Også poppel frå to lokalitetar i Rogaland vart undersøkte. Store tre stod med visne greiner stikkande ut frå nærast bladlause kroner. Mest alvorleg var kreftsår på greiner og stammer som etter alt å døma skuldast bakterien Xanthomonas populi. I ...

Accurate Identification of Cancerlectins through Hybrid Machine Learning Technology.

Science.gov (United States)

Zhang, Jieru; Ju, Ying; Lu, Huijuan; Xuan, Ping; Zou, Quan

2016-01-01

Cancerlectins are cancer-related proteins that function as lectins. They have been identified through computational identification techniques, but these techniques have sometimes failed to identify proteins because of sequence diversity among the cancerlectins. Advanced machine learning identification methods, such as support vector machine and basic sequence features (n-gram), have also been used to identify cancerlectins. In this study, various protein fingerprint features and advanced classifiers, including ensemble learning techniques, were utilized to identify this group of proteins. We improved the prediction accuracy of the original feature extraction methods and classification algorithms by more than 10% on average. Our work provides a basis for the computational identification of cancerlectins and reveals the power of hybrid machine learning techniques in computational proteomics.

A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis.

Science.gov (United States)

Liang, Liang; Liu, Minliang; Martin, Caitlin; Sun, Wei

2018-01-01

Structural finite-element analysis (FEA) has been widely used to study the biomechanics of human tissues and organs, as well as tissue-medical device interactions, and treatment strategies. However, patient-specific FEA models usually require complex procedures to set up and long computing times to obtain final simulation results, preventing prompt feedback to clinicians in time-sensitive clinical applications. In this study, by using machine learning techniques, we developed a deep learning (DL) model to directly estimate the stress distributions of the aorta. The DL model was designed and trained to take the input of FEA and directly output the aortic wall stress distributions, bypassing the FEA calculation process. The trained DL model is capable of predicting the stress distributions with average errors of 0.492% and 0.891% in the Von Mises stress distribution and peak Von Mises stress, respectively. This study marks, to our knowledge, the first study that demonstrates the feasibility and great potential of using the DL technique as a fast and accurate surrogate of FEA for stress analysis. © 2018 The Author(s).

Accurate Classification of Protein Subcellular Localization from High-Throughput Microscopy Images Using Deep Learning

Directory of Open Access Journals (Sweden)

Tanel Pärnamaa

2017-05-01

Full Text Available High-throughput microscopy of many single cells generates high-dimensional data that are far from straightforward to analyze. One important problem is automatically detecting the cellular compartment where a fluorescently-tagged protein resides, a task relatively simple for an experienced human, but difficult to automate on a computer. Here, we train an 11-layer neural network on data from mapping thousands of yeast proteins, achieving per cell localization classification accuracy of 91%, and per protein accuracy of 99% on held-out images. We confirm that low-level network features correspond to basic image characteristics, while deeper layers separate localization classes. Using this network as a feature calculator, we train standard classifiers that assign proteins to previously unseen compartments after observing only a small number of training examples. Our results are the most accurate subcellular localization classifications to date, and demonstrate the usefulness of deep learning for high-throughput microscopy.

Accurate Classification of Protein Subcellular Localization from High-Throughput Microscopy Images Using Deep Learning.

Science.gov (United States)

Pärnamaa, Tanel; Parts, Leopold

2017-05-05

High-throughput microscopy of many single cells generates high-dimensional data that are far from straightforward to analyze. One important problem is automatically detecting the cellular compartment where a fluorescently-tagged protein resides, a task relatively simple for an experienced human, but difficult to automate on a computer. Here, we train an 11-layer neural network on data from mapping thousands of yeast proteins, achieving per cell localization classification accuracy of 91%, and per protein accuracy of 99% on held-out images. We confirm that low-level network features correspond to basic image characteristics, while deeper layers separate localization classes. Using this network as a feature calculator, we train standard classifiers that assign proteins to previously unseen compartments after observing only a small number of training examples. Our results are the most accurate subcellular localization classifications to date, and demonstrate the usefulness of deep learning for high-throughput microscopy. Copyright © 2017 Parnamaa and Parts.

Combining structural modeling with ensemble machine learning to accurately predict protein fold stability and binding affinity effects upon mutation.

Directory of Open Access Journals (Sweden)

Niklas Berliner

Full Text Available Advances in sequencing have led to a rapid accumulation of mutations, some of which are associated with diseases. However, to draw mechanistic conclusions, a biochemical understanding of these mutations is necessary. For coding mutations, accurate prediction of significant changes in either the stability of proteins or their affinity to their binding partners is required. Traditional methods have used semi-empirical force fields, while newer methods employ machine learning of sequence and structural features. Here, we show how combining both of these approaches leads to a marked boost in accuracy. We introduce ELASPIC, a novel ensemble machine learning approach that is able to predict stability effects upon mutation in both, domain cores and domain-domain interfaces. We combine semi-empirical energy terms, sequence conservation, and a wide variety of molecular details with a Stochastic Gradient Boosting of Decision Trees (SGB-DT algorithm. The accuracy of our predictions surpasses existing methods by a considerable margin, achieving correlation coefficients of 0.77 for stability, and 0.75 for affinity predictions. Notably, we integrated homology modeling to enable proteome-wide prediction and show that accurate prediction on modeled structures is possible. Lastly, ELASPIC showed significant differences between various types of disease-associated mutations, as well as between disease and common neutral mutations. Unlike pure sequence-based prediction methods that try to predict phenotypic effects of mutations, our predictions unravel the molecular details governing the protein instability, and help us better understand the molecular causes of diseases.

When Is Network Lasso Accurate?

Directory of Open Access Journals (Sweden)

Alexander Jung

2018-01-01

Full Text Available The “least absolute shrinkage and selection operator” (Lasso method has been adapted recently for network-structured datasets. In particular, this network Lasso method allows to learn graph signals from a small number of noisy signal samples by using the total variation of a graph signal for regularization. While efficient and scalable implementations of the network Lasso are available, only little is known about the conditions on the underlying network structure which ensure network Lasso to be accurate. By leveraging concepts of compressed sensing, we address this gap and derive precise conditions on the underlying network topology and sampling set which guarantee the network Lasso for a particular loss function to deliver an accurate estimate of the entire underlying graph signal. We also quantify the error incurred by network Lasso in terms of two constants which reflect the connectivity of the sampled nodes.

Leveraging Two Kinect Sensors for Accurate Full-Body Motion Capture

Directory of Open Access Journals (Sweden)

Zhiquan Gao

2015-09-01

Full Text Available Accurate motion capture plays an important role in sports analysis, the medical field and virtual reality. Current methods for motion capture often suffer from occlusions, which limits the accuracy of their pose estimation. In this paper, we propose a complete system to measure the pose parameters of the human body accurately. Different from previous monocular depth camera systems, we leverage two Kinect sensors to acquire more information about human movements, which ensures that we can still get an accurate estimation even when significant occlusion occurs. Because human motion is temporally constant, we adopt a learning analysis to mine the temporal information across the posture variations. Using this information, we estimate human pose parameters accurately, regardless of rapid movement. Our experimental results show that our system can perform an accurate pose estimation of the human body with the constraint of information from the temporal domain.

Towards accurate de novo assembly for genomes with repeats

NARCIS (Netherlands)

Bucur, Doina

2017-01-01

De novo genome assemblers designed for short k-mer length or using short raw reads are unlikely to recover complex features of the underlying genome, such as repeats hundreds of bases long. We implement a stochastic machine-learning method which obtains accurate assemblies with repeats and

Accurate estimation of indoor travel times

DEFF Research Database (Denmark)

Prentow, Thor Siiger; Blunck, Henrik; Stisen, Allan

2014-01-01

The ability to accurately estimate indoor travel times is crucial for enabling improvements within application areas such as indoor navigation, logistics for mobile workers, and facility management. In this paper, we study the challenges inherent in indoor travel time estimation, and we propose...... the InTraTime method for accurately estimating indoor travel times via mining of historical and real-time indoor position traces. The method learns during operation both travel routes, travel times and their respective likelihood---both for routes traveled as well as for sub-routes thereof. InTraTime...... allows to specify temporal and other query parameters, such as time-of-day, day-of-week or the identity of the traveling individual. As input the method is designed to take generic position traces and is thus interoperable with a variety of indoor positioning systems. The method's advantages include...

Data Mining for Efficient and Accurate Large Scale Retrieval of Geophysical Parameters

Science.gov (United States)

Obradovic, Z.; Vucetic, S.; Peng, K.; Han, B.

2004-12-01

Our effort is devoted to developing data mining technology for improving efficiency and accuracy of the geophysical parameter retrievals by learning a mapping from observation attributes to the corresponding parameters within the framework of classification and regression. We will describe a method for efficient learning of neural network-based classification and regression models from high-volume data streams. The proposed procedure automatically learns a series of neural networks of different complexities on smaller data stream chunks and then properly combines them into an ensemble predictor through averaging. Based on the idea of progressive sampling the proposed approach starts with a very simple network trained on a very small chunk and then gradually increases the model complexity and the chunk size until the learning performance no longer improves. Our empirical study on aerosol retrievals from data obtained with the MISR instrument mounted at Terra satellite suggests that the proposed method is successful in learning complex concepts from large data streams with near-optimal computational effort. We will also report on a method that complements deterministic retrievals by constructing accurate predictive algorithms and applying them on appropriately selected subsets of observed data. The method is based on developing more accurate predictors aimed to catch global and local properties synthesized in a region. The procedure starts by learning the global properties of data sampled over the entire space, and continues by constructing specialized models on selected localized regions. The global and local models are integrated through an automated procedure that determines the optimal trade-off between the two components with the objective of minimizing the overall mean square errors over a specific region. Our experimental results on MISR data showed that the combined model can increase the retrieval accuracy significantly. The preliminary results on various

Deep Learning Accurately Predicts Estrogen Receptor Status in Breast Cancer Metabolomics Data.

Science.gov (United States)

Alakwaa, Fadhl M; Chaudhary, Kumardeep; Garmire, Lana X

2018-01-05

Metabolomics holds the promise as a new technology to diagnose highly heterogeneous diseases. Conventionally, metabolomics data analysis for diagnosis is done using various statistical and machine learning based classification methods. However, it remains unknown if deep neural network, a class of increasingly popular machine learning methods, is suitable to classify metabolomics data. Here we use a cohort of 271 breast cancer tissues, 204 positive estrogen receptor (ER+), and 67 negative estrogen receptor (ER-) to test the accuracies of feed-forward networks, a deep learning (DL) framework, as well as six widely used machine learning models, namely random forest (RF), support vector machines (SVM), recursive partitioning and regression trees (RPART), linear discriminant analysis (LDA), prediction analysis for microarrays (PAM), and generalized boosted models (GBM). DL framework has the highest area under the curve (AUC) of 0.93 in classifying ER+/ER- patients, compared to the other six machine learning algorithms. Furthermore, the biological interpretation of the first hidden layer reveals eight commonly enriched significant metabolomics pathways (adjusted P-value learning methods. Among them, protein digestion and absorption and ATP-binding cassette (ABC) transporters pathways are also confirmed in integrated analysis between metabolomics and gene expression data in these samples. In summary, deep learning method shows advantages for metabolomics based breast cancer ER status classification, with both the highest prediction accuracy (AUC = 0.93) and better revelation of disease biology. We encourage the adoption of feed-forward networks based deep learning method in the metabolomics research community for classification.

On the Interpretation of the Fermi-GBM Transient Observed in Coincidence with LIGO Gravitational-wave Event GW150914

Science.gov (United States)

Connaughton, V.; Burns, E.; Goldstein, A.; Blackburn, L.; Briggs, M. S.; Christensen, N.; Hui, C. M.; Kocevski, D.; Littenberg, T.; McEnery, J. E.; Racusin, J.; Shawhan, P.; Veitch, J.; Wilson-Hodge, C. A.; Bhat, P. N.; Bissaldi, E.; Cleveland, W.; Giles, M. M.; Gibby, M. H.; von Kienlin, A.; Kippen, R. M.; McBreen, S.; Meegan, C. A.; Paciesas, W. S.; Preece, R. D.; Roberts, O. J.; Stanbro, M.; Veres, P.

2018-01-01

The weak transient detected by the Fermi Gamma-ray Burst Monitor (GBM) 0.4 s after GW150914 has generated much speculation regarding its possible association with the black hole binary merger. Investigation of the GBM data by Connaughton et al. revealed a source location consistent with GW150914 and a spectrum consistent with a weak, short gamma-ray burst. Greiner et al. present an alternative technique for fitting background-limited data in the low-count regime, and call into question the spectral analysis and the significance of the detection of GW150914-GBM presented in Connaughton et al. The spectral analysis of Connaughton et al. is not subject to the limitations of the low-count regime noted by Greiner et al. We find Greiner et al. used an inconsistent source position and did not follow the steps taken in Connaughton et al. to mitigate the statistical shortcomings of their software when analyzing this weak event. We use the approach of Greiner et al. to verify that our original spectral analysis is not biased. The detection significance of GW150914-GBM is established empirically, with a false-alarm rate (FAR) of ∼ {10}-4 Hz. A post-trials false-alarm probability (FAP) of 2.2× {10}-3 (2.9σ ) of this transient being associated with GW150914 is based on the proximity in time to the gravitational-wave event of a transient with that FAR. The FAR and the FAP are unaffected by the spectral analysis that is the focus of Greiner et al.

A fast and accurate online sequential learning algorithm for feedforward networks.

Science.gov (United States)

Liang, Nan-Ying; Huang, Guang-Bin; Saratchandran, P; Sundararajan, N

2006-11-01

In this paper, we develop an online sequential learning algorithm for single hidden layer feedforward networks (SLFNs) with additive or radial basis function (RBF) hidden nodes in a unified framework. The algorithm is referred to as online sequential extreme learning machine (OS-ELM) and can learn data one-by-one or chunk-by-chunk (a block of data) with fixed or varying chunk size. The activation functions for additive nodes in OS-ELM can be any bounded nonconstant piecewise continuous functions and the activation functions for RBF nodes can be any integrable piecewise continuous functions. In OS-ELM, the parameters of hidden nodes (the input weights and biases of additive nodes or the centers and impact factors of RBF nodes) are randomly selected and the output weights are analytically determined based on the sequentially arriving data. The algorithm uses the ideas of ELM of Huang et al. developed for batch learning which has been shown to be extremely fast with generalization performance better than other batch training methods. Apart from selecting the number of hidden nodes, no other control parameters have to be manually chosen. Detailed performance comparison of OS-ELM is done with other popular sequential learning algorithms on benchmark problems drawn from the regression, classification and time series prediction areas. The results show that the OS-ELM is faster than the other sequential algorithms and produces better generalization performance.

Accurate prediction of stability changes in protein mutants by combining machine learning with structure based computational mutagenesis.

Science.gov (United States)

Masso, Majid; Vaisman, Iosif I

2008-09-15

Accurate predictive models for the impact of single amino acid substitutions on protein stability provide insight into protein structure and function. Such models are also valuable for the design and engineering of new proteins. Previously described methods have utilized properties of protein sequence or structure to predict the free energy change of mutants due to thermal (DeltaDeltaG) and denaturant (DeltaDeltaG(H2O)) denaturations, as well as mutant thermal stability (DeltaT(m)), through the application of either computational energy-based approaches or machine learning techniques. However, accuracy associated with applying these methods separately is frequently far from optimal. We detail a computational mutagenesis technique based on a four-body, knowledge-based, statistical contact potential. For any mutation due to a single amino acid replacement in a protein, the method provides an empirical normalized measure of the ensuing environmental perturbation occurring at every residue position. A feature vector is generated for the mutant by considering perturbations at the mutated position and it's ordered six nearest neighbors in the 3-dimensional (3D) protein structure. These predictors of stability change are evaluated by applying machine learning tools to large training sets of mutants derived from diverse proteins that have been experimentally studied and described. Predictive models based on our combined approach are either comparable to, or in many cases significantly outperform, previously published results. A web server with supporting documentation is available at http://proteins.gmu.edu/automute.

A Deep Learning Framework for Robust and Accurate Prediction of ncRNA-Protein Interactions Using Evolutionary Information.

Science.gov (United States)

Yi, Hai-Cheng; You, Zhu-Hong; Huang, De-Shuang; Li, Xiao; Jiang, Tong-Hai; Li, Li-Ping

2018-06-01

The interactions between non-coding RNAs (ncRNAs) and proteins play an important role in many biological processes, and their biological functions are primarily achieved by binding with a variety of proteins. High-throughput biological techniques are used to identify protein molecules bound with specific ncRNA, but they are usually expensive and time consuming. Deep learning provides a powerful solution to computationally predict RNA-protein interactions. In this work, we propose the RPI-SAN model by using the deep-learning stacked auto-encoder network to mine the hidden high-level features from RNA and protein sequences and feed them into a random forest (RF) model to predict ncRNA binding proteins. Stacked assembling is further used to improve the accuracy of the proposed method. Four benchmark datasets, including RPI2241, RPI488, RPI1807, and NPInter v2.0, were employed for the unbiased evaluation of five established prediction tools: RPI-Pred, IPMiner, RPISeq-RF, lncPro, and RPI-SAN. The experimental results show that our RPI-SAN model achieves much better performance than other methods, with accuracies of 90.77%, 89.7%, 96.1%, and 99.33%, respectively. It is anticipated that RPI-SAN can be used as an effective computational tool for future biomedical researches and can accurately predict the potential ncRNA-protein interacted pairs, which provides reliable guidance for biological research. Copyright © 2018 The Author(s). Published by Elsevier Inc. All rights reserved.

Accurate lithography simulation model based on convolutional neural networks

Science.gov (United States)

Watanabe, Yuki; Kimura, Taiki; Matsunawa, Tetsuaki; Nojima, Shigeki

2017-07-01

Lithography simulation is an essential technique for today's semiconductor manufacturing process. In order to calculate an entire chip in realistic time, compact resist model is commonly used. The model is established for faster calculation. To have accurate compact resist model, it is necessary to fix a complicated non-linear model function. However, it is difficult to decide an appropriate function manually because there are many options. This paper proposes a new compact resist model using CNN (Convolutional Neural Networks) which is one of deep learning techniques. CNN model makes it possible to determine an appropriate model function and achieve accurate simulation. Experimental results show CNN model can reduce CD prediction errors by 70% compared with the conventional model.

Two fast and accurate heuristic RBF learning rules for data classification.

Science.gov (United States)

Rouhani, Modjtaba; Javan, Dawood S

2016-03-01

This paper presents new Radial Basis Function (RBF) learning methods for classification problems. The proposed methods use some heuristics to determine the spreads, the centers and the number of hidden neurons of network in such a way that the higher efficiency is achieved by fewer numbers of neurons, while the learning algorithm remains fast and simple. To retain network size limited, neurons are added to network recursively until termination condition is met. Each neuron covers some of train data. The termination condition is to cover all training data or to reach the maximum number of neurons. In each step, the center and spread of the new neuron are selected based on maximization of its coverage. Maximization of coverage of the neurons leads to a network with fewer neurons and indeed lower VC dimension and better generalization property. Using power exponential distribution function as the activation function of hidden neurons, and in the light of new learning approaches, it is proved that all data became linearly separable in the space of hidden layer outputs which implies that there exist linear output layer weights with zero training error. The proposed methods are applied to some well-known datasets and the simulation results, compared with SVM and some other leading RBF learning methods, show their satisfactory and comparable performance. Copyright © 2015 Elsevier Ltd. All rights reserved.

Fast and accurate semantic annotation of bioassays exploiting a hybrid of machine learning and user confirmation.

Science.gov (United States)

Clark, Alex M; Bunin, Barry A; Litterman, Nadia K; Schürer, Stephan C; Visser, Ubbo

2014-01-01

Bioinformatics and computer aided drug design rely on the curation of a large number of protocols for biological assays that measure the ability of potential drugs to achieve a therapeutic effect. These assay protocols are generally published by scientists in the form of plain text, which needs to be more precisely annotated in order to be useful to software methods. We have developed a pragmatic approach to describing assays according to the semantic definitions of the BioAssay Ontology (BAO) project, using a hybrid of machine learning based on natural language processing, and a simplified user interface designed to help scientists curate their data with minimum effort. We have carried out this work based on the premise that pure machine learning is insufficiently accurate, and that expecting scientists to find the time to annotate their protocols manually is unrealistic. By combining these approaches, we have created an effective prototype for which annotation of bioassay text within the domain of the training set can be accomplished very quickly. Well-trained annotations require single-click user approval, while annotations from outside the training set domain can be identified using the search feature of a well-designed user interface, and subsequently used to improve the underlying models. By drastically reducing the time required for scientists to annotate their assays, we can realistically advocate for semantic annotation to become a standard part of the publication process. Once even a small proportion of the public body of bioassay data is marked up, bioinformatics researchers can begin to construct sophisticated and useful searching and analysis algorithms that will provide a diverse and powerful set of tools for drug discovery researchers.

Fast and accurate semantic annotation of bioassays exploiting a hybrid of machine learning and user confirmation

Directory of Open Access Journals (Sweden)

Alex M. Clark

2014-08-01

Full Text Available Bioinformatics and computer aided drug design rely on the curation of a large number of protocols for biological assays that measure the ability of potential drugs to achieve a therapeutic effect. These assay protocols are generally published by scientists in the form of plain text, which needs to be more precisely annotated in order to be useful to software methods. We have developed a pragmatic approach to describing assays according to the semantic definitions of the BioAssay Ontology (BAO project, using a hybrid of machine learning based on natural language processing, and a simplified user interface designed to help scientists curate their data with minimum effort. We have carried out this work based on the premise that pure machine learning is insufficiently accurate, and that expecting scientists to find the time to annotate their protocols manually is unrealistic. By combining these approaches, we have created an effective prototype for which annotation of bioassay text within the domain of the training set can be accomplished very quickly. Well-trained annotations require single-click user approval, while annotations from outside the training set domain can be identified using the search feature of a well-designed user interface, and subsequently used to improve the underlying models. By drastically reducing the time required for scientists to annotate their assays, we can realistically advocate for semantic annotation to become a standard part of the publication process. Once even a small proportion of the public body of bioassay data is marked up, bioinformatics researchers can begin to construct sophisticated and useful searching and analysis algorithms that will provide a diverse and powerful set of tools for drug discovery researchers.

Deep learning versus traditional machine learning methods for aggregated energy demand prediction

NARCIS (Netherlands)

Paterakis, N.G.; Mocanu, E.; Gibescu, M.; Stappers, B.; van Alst, W.

2018-01-01

In this paper the more advanced, in comparison with traditional machine learning approaches, deep learning methods are explored with the purpose of accurately predicting the aggregated energy consumption. Despite the fact that a wide range of machine learning methods have been applied to

Superior cognitive mapping through single landmark-related learning than through boundary-related learning.

Science.gov (United States)

Zhou, Ruojing; Mou, Weimin

2016-08-01

Cognitive mapping is assumed to be through hippocampus-dependent place learning rather than striatum-dependent response learning. However, we proposed that either type of spatial learning, as long as it involves encoding metric relations between locations and reference points, could lead to a cognitive map. Furthermore, the fewer reference points to specify individual locations, the more accurate a cognitive map of these locations will be. We demonstrated that participants have more accurate representations of vectors between 2 locations and of configurations among 3 locations when locations are individually encoded in terms of a single landmark than when locations are encoded in terms of a boundary. Previous findings have shown that learning locations relative to a boundary involve stronger place learning and higher hippocampal activation whereas learning relative to a single landmark involves stronger response learning and higher striatal activation. Recognizing this, we have provided evidence challenging the cognitive map theory but favoring our proposal. (PsycINFO Database Record (c) 2016 APA, all rights reserved).

Category learning in the color-word contingency learning paradigm.

Science.gov (United States)

Schmidt, James R; Augustinova, Maria; De Houwer, Jan

2018-04-01

In the typical color-word contingency learning paradigm, participants respond to the print color of words where each word is presented most often in one color. Learning is indicated by faster and more accurate responses when a word is presented in its usual color, relative to another color. To eliminate the possibility that this effect is driven exclusively by the familiarity of item-specific word-color pairings, we examine whether contingency learning effects can be observed also when colors are related to categories of words rather than to individual words. To this end, the reported experiments used three categories of words (animals, verbs, and professions) that were each predictive of one color. Importantly, each individual word was presented only once, thus eliminating individual color-word contingencies. Nevertheless, for the first time, a category-based contingency effect was observed, with faster and more accurate responses when a category item was presented in the color in which most of the other items of that category were presented. This finding helps to constrain episodic learning models and sets the stage for new research on category-based contingency learning.

Energy dependence of the anisotropy of noncharacteristic x-rays emitted in fast ion-atom collisions

International Nuclear Information System (INIS)

Thoe, R.S.; Sellin, I.A.; Brown, M.D.; Forester, J.P.; Griffin, P.M.; Pegg, D.J.; Peterson, R.S.

1974-01-01

The effect of beam velocity and K-shell binding energy on the angular distributions of the noncharacteristic x-radiation emitted for various collision pairs. The results are in general agreement with the calculations of Mueller and Greiner, in that the anisotropy increases rapidly with energy, provided that the ions are still moving slowly, compared to the velocity of the K-shell electrons of the separated atoms. The anisotropy in some cases exceeds the maximum permitted by the Mueller--Greiner model for the zero alignment case, implying that strong alignment phenomena also occur

An Accurate CT Saturation Classification Using a Deep Learning Approach Based on Unsupervised Feature Extraction and Supervised Fine-Tuning Strategy

Directory of Open Access Journals (Sweden)

Muhammad Ali

2017-11-01

Full Text Available Current transformer (CT saturation is one of the significant problems for protection engineers. If CT saturation is not tackled properly, it can cause a disastrous effect on the stability of the power system, and may even create a complete blackout. To cope with CT saturation properly, an accurate detection or classification should be preceded. Recently, deep learning (DL methods have brought a subversive revolution in the field of artificial intelligence (AI. This paper presents a new DL classification method based on unsupervised feature extraction and supervised fine-tuning strategy to classify the saturated and unsaturated regions in case of CT saturation. In other words, if protection system is subjected to a CT saturation, proposed method will correctly classify the different levels of saturation with a high accuracy. Traditional AI methods are mostly based on supervised learning and rely heavily on human crafted features. This paper contributes to an unsupervised feature extraction, using autoencoders and deep neural networks (DNNs to extract features automatically without prior knowledge of optimal features. To validate the effectiveness of proposed method, a variety of simulation tests are conducted, and classification results are analyzed using standard classification metrics. Simulation results confirm that proposed method classifies the different levels of CT saturation with a remarkable accuracy and has unique feature extraction capabilities. Lastly, we provided a potential future research direction to conclude this paper.

Learning Markov models for stationary system behaviors

DEFF Research Database (Denmark)

Chen, Yingke; Mao, Hua; Jaeger, Manfred

2012-01-01

to a single long observation sequence, and in these situations existing automatic learning methods cannot be applied. In this paper, we adapt algorithms for learning variable order Markov chains from a single observation sequence of a target system, so that stationary system properties can be verified using......Establishing an accurate model for formal verification of an existing hardware or software system is often a manual process that is both time consuming and resource demanding. In order to ease the model construction phase, methods have recently been proposed for automatically learning accurate...... the learned model. Experiments demonstrate that system properties (formulated as stationary probabilities of LTL formulas) can be reliably identified using the learned model....

Long-term stability of glucose: glycolysis inhibitor vs. gel barrier tubes.

Science.gov (United States)

Winter, Theresa; Hannemann, Anke; Suchsland, Juliane; Nauck, Matthias; Petersmann, Astrid

2018-03-12

Measuring the glucose concentration in whole blood samples is critical due to unsatisfactory glycolysis inhibition. Previous studies showed that Terumo tubes were superior, but they were taken off the European market in 2016 and alternatives were required. This initiated the present evaluation of glucose stability in five available tube types. Venous blood samples were collected from 61 healthy volunteers to test tubes supplied by Terumo (two sets), Greiner FC-Mix, BD FX-Mixture and BD serum. After sampling, the contents were thoroughly mixed and centrifuged within an hour. The glucose concentrations were determined and the samples resuspended except for BD serum tubes (gel barrier). The first 30 samples were stored at room temperature and the remaining 31 at 4°C. After 24, 48, 72 and 96 h, all tubes were (re)centrifuged, and glucose concentration measurements were repeated. Changes in glucose concentrations over time differed significantly between the investigated tube types and to a certain extent between the two storing conditions. Glycolysis was most evident in the BD FX-mixture tubes. Good glucose stability was observed in samples retrieved form BD serum and Greiner tubes. The stability in both Terumo tubes was comparable to that in other studies. Although Greiner and both Terumo tubes are supposed to contain the same glycolysis inhibitor, glucose stability differed between these tubes. We showed that Greiner is an acceptable alternative to Terumo and that glucose in serum that was rapidly separated from corpuscles by a gel barrier is stable for an extended time.

Accurate or assumed: visual learning in children with ASD.

Science.gov (United States)

Trembath, David; Vivanti, Giacomo; Iacono, Teresa; Dissanayake, Cheryl

2015-10-01

Children with autism spectrum disorder (ASD) are often described as visual learners. We tested this assumption in an experiment in which 25 children with ASD, 19 children with global developmental delay (GDD), and 17 typically developing (TD) children were presented a series of videos via an eye tracker in which an actor instructed them to manipulate objects in speech-only and speech + pictures conditions. We found no group differences in visual attention to the stimuli. The GDD and TD groups performed better when pictures were available, whereas the ASD group did not. Performance of children with ASD and GDD was positively correlated with visual attention and receptive language. We found no evidence of a prominent visual learning style in the ASD group.

The planning illusion: Does active planning of a learning route support learning as well as learners think it does?

NARCIS (Netherlands)

Bonestroo, W.J.; de Jong, Anthonius J.M.

2012-01-01

Is actively planning one’s learning route through a learning domain beneficial for learning? Moreover, can learners accurately judge the extent to which planning has been beneficial for them? This study examined the effects of active planning on learning. Participants received a tool in which they

Balancing the Assessment "of" Learning and "for" Learning in Support of Student Literacy Achievement

Science.gov (United States)

Edwards, Patricia A.; Turner, Jennifer D.; Mokhtari, Kouider

2008-01-01

There is a delicate balance between the assessment of learning and assessment for learning. The recommendations included in this Assessment department may be useful for teachers working to achieve this balance and find a more accurate and complete understandings of students' literacy strengths and needs.

Do Voters Learn? Evidence that Voters Respond Accurately to Changes in Political Parties’ Policy Positions

DEFF Research Database (Denmark)

Seeberg, Henrik Bech; Slothuus, Rune; Stubager, Rune

2017-01-01

A premise of the mass–elite linkage at the heart of representative democracy is that voters notice changes in political parties’ policy positions and update their party perceptions accordingly. However, recent studies question the ability of voters accurately to perceive changes in parties...... attention to parties when they visibly change policy position. Second, voters update their perceptions of the party positions much more accurately than would have been expected if they merely relied on a ‘coalition heuristic’ as a rule-of-thumb. These findings imply that under some conditions voters...

An accurate determination of the flux within a slab

International Nuclear Information System (INIS)

Ganapol, B.D.; Lapenta, G.

1993-01-01

During the past decade, several articles have been written concerning accurate solutions to the monoenergetic neutron transport equation in infinite and semi-infinite geometries. The numerical formulations found in these articles were based primarily on the extensive theoretical investigations performed by the open-quotes transport greatsclose quotes such as Chandrasekhar, Busbridge, Sobolev, and Ivanov, to name a few. The development of numerical solutions in infinite and semi-infinite geometries represents an example of how mathematical transport theory can be utilized to provide highly accurate and efficient numerical transport solutions. These solutions, or analytical benchmarks, are useful as open-quotes industry standards,close quotes which provide guidance to code developers and promote learning in the classroom. The high accuracy of these benchmarks is directly attributable to the rapid advancement of the state of computing and computational methods. Transport calculations that were beyond the capability of the open-quotes supercomputersclose quotes of just a few years ago are now possible at one's desk. In this paper, we again build upon the past to tackle the slab problem, which is of the next level of difficulty in comparison to infinite media problems. The formulation is based on the monoenergetic Green's function, which is the most fundamental transport solution. This method of solution requires a fast and accurate evaluation of the Green's function, which, with today's computational power, is now readily available

Production of Accurate Skeletal Models of Domestic Animals Using Three-Dimensional Scanning and Printing Technology

Science.gov (United States)

Li, Fangzheng; Liu, Chunying; Song, Xuexiong; Huan, Yanjun; Gao, Shansong; Jiang, Zhongling

2018-01-01

Access to adequate anatomical specimens can be an important aspect in learning the anatomy of domestic animals. In this study, the authors utilized a structured light scanner and fused deposition modeling (FDM) printer to produce highly accurate animal skeletal models. First, various components of the bovine skeleton, including the femur, the…

An efficient flow-based botnet detection using supervised machine learning

DEFF Research Database (Denmark)

Stevanovic, Matija; Pedersen, Jens Myrup

2014-01-01

Botnet detection represents one of the most crucial prerequisites of successful botnet neutralization. This paper explores how accurate and timely detection can be achieved by using supervised machine learning as the tool of inferring about malicious botnet traffic. In order to do so, the paper...... introduces a novel flow-based detection system that relies on supervised machine learning for identifying botnet network traffic. For use in the system we consider eight highly regarded machine learning algorithms, indicating the best performing one. Furthermore, the paper evaluates how much traffic needs...... to accurately and timely detect botnet traffic using purely flow-based traffic analysis and supervised machine learning. Additionally, the results show that in order to achieve accurate detection traffic flows need to be monitored for only a limited time period and number of packets per flow. This indicates...

Training self-assessment and task-selection skills : A cognitive approach to improving self-regulated learning

NARCIS (Netherlands)

Kostons, Danny; van Gog, Tamara; Paas, Fred

For self-regulated learning to be effective, students need to be able to accurately assess their own performance on a learning task and use this assessment for the selection of a new learning task. Evidence suggests, however, that students have difficulties with accurate self-assessment and task

The Scientific Status of Learning Styles Theories

Science.gov (United States)

Willingham, Daniel T.; Hughes, Elizabeth M.; Dobolyi, David G.

2015-01-01

Theories of learning styles suggest that individuals think and learn best in different ways. These are not differences of ability but rather preferences for processing certain types of information or for processing information in certain types of way. If accurate, learning styles theories could have important implications for instruction because…

Prevention of Learned Helplessness in Humans.

Science.gov (United States)

Klee, Steven; Meyer, Robert G.

1979-01-01

Explored prevention of learned helplessness through the use of thermal biofeedback training and varied explanations of performance. It was found that only in the biofeedback group receiving accurate feedback was there any prevention of the subsequent development of learned helplessness behavior. (Author)

Deep-Learning Convolutional Neural Networks Accurately Classify Genetic Mutations in Gliomas.

Science.gov (United States)

Chang, P; Grinband, J; Weinberg, B D; Bardis, M; Khy, M; Cadena, G; Su, M-Y; Cha, S; Filippi, C G; Bota, D; Baldi, P; Poisson, L M; Jain, R; Chow, D

2018-05-10

The World Health Organization has recently placed new emphasis on the integration of genetic information for gliomas. While tissue sampling remains the criterion standard, noninvasive imaging techniques may provide complimentary insight into clinically relevant genetic mutations. Our aim was to train a convolutional neural network to independently predict underlying molecular genetic mutation status in gliomas with high accuracy and identify the most predictive imaging features for each mutation. MR imaging data and molecular information were retrospectively obtained from The Cancer Imaging Archives for 259 patients with either low- or high-grade gliomas. A convolutional neural network was trained to classify isocitrate dehydrogenase 1 ( IDH1 ) mutation status, 1p/19q codeletion, and O6-methylguanine-DNA methyltransferase ( MGMT ) promotor methylation status. Principal component analysis of the final convolutional neural network layer was used to extract the key imaging features critical for successful classification. Classification had high accuracy: IDH1 mutation status, 94%; 1p/19q codeletion, 92%; and MGMT promotor methylation status, 83%. Each genetic category was also associated with distinctive imaging features such as definition of tumor margins, T1 and FLAIR suppression, extent of edema, extent of necrosis, and textural features. Our results indicate that for The Cancer Imaging Archives dataset, machine-learning approaches allow classification of individual genetic mutations of both low- and high-grade gliomas. We show that relevant MR imaging features acquired from an added dimensionality-reduction technique demonstrate that neural networks are capable of learning key imaging components without prior feature selection or human-directed training. © 2018 by American Journal of Neuroradiology.

Accurate in silico identification of protein succinylation sites using an iterative semi-supervised learning technique.

Science.gov (United States)

Zhao, Xiaowei; Ning, Qiao; Chai, Haiting; Ma, Zhiqiang

2015-06-07

As a widespread type of protein post-translational modifications (PTMs), succinylation plays an important role in regulating protein conformation, function and physicochemical properties. Compared with the labor-intensive and time-consuming experimental approaches, computational predictions of succinylation sites are much desirable due to their convenient and fast speed. Currently, numerous computational models have been developed to identify PTMs sites through various types of two-class machine learning algorithms. These methods require both positive and negative samples for training. However, designation of the negative samples of PTMs was difficult and if it is not properly done can affect the performance of computational models dramatically. So that in this work, we implemented the first application of positive samples only learning (PSoL) algorithm to succinylation sites prediction problem, which was a special class of semi-supervised machine learning that used positive samples and unlabeled samples to train the model. Meanwhile, we proposed a novel succinylation sites computational predictor called SucPred (succinylation site predictor) by using multiple feature encoding schemes. Promising results were obtained by the SucPred predictor with an accuracy of 88.65% using 5-fold cross validation on the training dataset and an accuracy of 84.40% on the independent testing dataset, which demonstrated that the positive samples only learning algorithm presented here was particularly useful for identification of protein succinylation sites. Besides, the positive samples only learning algorithm can be applied to build predictors for other types of PTMs sites with ease. A web server for predicting succinylation sites was developed and was freely accessible at http://59.73.198.144:8088/SucPred/. Copyright © 2015 Elsevier Ltd. All rights reserved.

76 FR 64428 - Senior Executive Service; Combined Performance Review Board (PRB)

Science.gov (United States)

2011-10-18

... Greiner, Chief Financial Officer, United States Mint. John J. Manfreda, Administrator, TTB. Diane K. Wade... of Engraving and Printing (BEP), the Financial Management Service (FMS), the United [[Page 64429

Machine learning systems

Energy Technology Data Exchange (ETDEWEB)

Forsyth, R

1984-05-01

With the dramatic rise of expert systems has come a renewed interest in the fuel that drives them-knowledge. For it is specialist knowledge which gives expert systems their power. But extracting knowledge from human experts in symbolic form has proved arduous and labour-intensive. So the idea of machine learning is enjoying a renaissance. Machine learning is any automatic improvement in the performance of a computer system over time, as a result of experience. Thus a learning algorithm seeks to do one or more of the following: cover a wider range of problems, deliver more accurate solutions, obtain answers more cheaply, and simplify codified knowledge. 6 references.

Reverse inference of memory retrieval processes underlying metacognitive monitoring of learning using multivariate pattern analysis

NARCIS (Netherlands)

Stiers, Peter; Falbo, Luciana; Goulas, Alexandros; van Gog, Tamara; de Bruin, Anique

2016-01-01

Monitoring of learning is only accurate at some time after learning. It is thought that immediate monitoring is based on working memory, whereas later monitoring requires re-activation of stored items, yielding accurate judgements. Such interpretations are difficult to test because they require

Depth Value Pre-Processing for Accurate Transfer Learning Based RGB-D Object Recognition

DEFF Research Database (Denmark)

Aakerberg, Andreas; Nasrollahi, Kamal; Rasmussen, Christoffer Bøgelund

2017-01-01

of an existing deeplearning based RGB-D object recognition model, namely the FusionNet proposed by Eitel et al. First, we showthat encoding the depth values as colorized surface normals is beneficial, when the model is initialized withweights learned from training on ImageNet data. Additionally, we show...

On the organizational learning work process

International Nuclear Information System (INIS)

Weil, Richard; Apostolakis, George

2000-01-01

This paper presents an organizational learning work process for use at nuclear power plants or other high-risk industries. Relying on insights gained from surveying organizational learning activities at nuclear power plants, the proposed work process synthesizes distributed learning activities and improves upon existing organizational learning processes. A root-cause analysis that targets organizational factors is presented. Additionally, a more accurate and objective methodology for prioritizing operating experience is presented. This methodology was applied to a case study during a workshop with utility personnel held at MIT. (author)

Active learning of neuron morphology for accurate automated tracing of neurites

Science.gov (United States)

Gala, Rohan; Chapeton, Julio; Jitesh, Jayant; Bhavsar, Chintan; Stepanyants, Armen

2014-01-01

Automating the process of neurite tracing from light microscopy stacks of images is essential for large-scale or high-throughput quantitative studies of neural circuits. While the general layout of labeled neurites can be captured by many automated tracing algorithms, it is often not possible to differentiate reliably between the processes belonging to different cells. The reason is that some neurites in the stack may appear broken due to imperfect labeling, while others may appear fused due to the limited resolution of optical microscopy. Trained neuroanatomists routinely resolve such topological ambiguities during manual tracing tasks by combining information about distances between branches, branch orientations, intensities, calibers, tortuosities, colors, as well as the presence of spines or boutons. Likewise, to evaluate different topological scenarios automatically, we developed a machine learning approach that combines many of the above mentioned features. A specifically designed confidence measure was used to actively train the algorithm during user-assisted tracing procedure. Active learning significantly reduces the training time and makes it possible to obtain less than 1% generalization error rates by providing few training examples. To evaluate the overall performance of the algorithm a number of image stacks were reconstructed automatically, as well as manually by several trained users, making it possible to compare the automated traces to the baseline inter-user variability. Several geometrical and topological features of the traces were selected for the comparisons. These features include the total trace length, the total numbers of branch and terminal points, the affinity of corresponding traces, and the distances between corresponding branch and terminal points. Our results show that when the density of labeled neurites is sufficiently low, automated traces are not significantly different from manual reconstructions obtained by trained users. PMID

Active learning of neuron morphology for accurate automated tracing of neurites

Directory of Open Access Journals (Sweden)

Rohan eGala

2014-05-01

Full Text Available Automating the process of neurite tracing from light microscopy stacks of images is essential for large-scale or high-throughput quantitative studies of neural circuits. While the general layout of labeled neurites can be captured by many automated tracing algorithms, it is often not possible to differentiate reliably between the processes belonging to different cells. The reason is that some neurites in the stack may appear broken due to imperfect labeling, while others may appear fused due to the limited resolution of optical microscopy. Trained neuroanatomists routinely resolve such topological ambiguities during manual tracing tasks by combining information about distances between branches, branch orientations, intensities, calibers, tortuosities, colors, as well as the presence of spines or boutons. Likewise, to evaluate different topological scenarios automatically, we developed a machine learning approach that combines many of the above mentioned features. A specifically designed confidence measure was used to actively train the algorithm during user-assisted tracing procedure. Active learning significantly reduces the training time and makes it possible to obtain less than 1% generalization error rates by providing few training examples. To evaluate the overall performance of the algorithm a number of image stacks were reconstructed automatically, as well as manually by several trained users, making it possible to compare the automated traces to the baseline inter-user variability. Several geometrical and topological features of the traces were selected for the comparisons. These features include the total trace length, the total numbers of branch and terminal points, the affinity of corresponding traces, and the distances between corresponding branch and terminal points. Our results show that when the density of labeled neurites is sufficiently low, automated traces are not significantly different from manual reconstructions obtained by

Computer-based personality judgments are more accurate than those made by humans.

Science.gov (United States)

Youyou, Wu; Kosinski, Michal; Stillwell, David

2015-01-27

Judging others' personalities is an essential skill in successful social living, as personality is a key driver behind people's interactions, behaviors, and emotions. Although accurate personality judgments stem from social-cognitive skills, developments in machine learning show that computer models can also make valid judgments. This study compares the accuracy of human and computer-based personality judgments, using a sample of 86,220 volunteers who completed a 100-item personality questionnaire. We show that (i) computer predictions based on a generic digital footprint (Facebook Likes) are more accurate (r = 0.56) than those made by the participants' Facebook friends using a personality questionnaire (r = 0.49); (ii) computer models show higher interjudge agreement; and (iii) computer personality judgments have higher external validity when predicting life outcomes such as substance use, political attitudes, and physical health; for some outcomes, they even outperform the self-rated personality scores. Computers outpacing humans in personality judgment presents significant opportunities and challenges in the areas of psychological assessment, marketing, and privacy.

A Multianalyzer Machine Learning Model for Marine Heterogeneous Data Schema Mapping

Science.gov (United States)

Yan, Wang; Jiajin, Le; Yun, Zhang

2014-01-01

The main challenges that marine heterogeneous data integration faces are the problem of accurate schema mapping between heterogeneous data sources. In order to improve the schema mapping efficiency and get more accurate learning results, this paper proposes a heterogeneous data schema mapping method basing on multianalyzer machine learning model. The multianalyzer analysis the learning results comprehensively, and a fuzzy comprehensive evaluation system is introduced for output results' evaluation and multi factor quantitative judging. Finally, the data mapping comparison experiment on the East China Sea observing data confirms the effectiveness of the model and shows multianalyzer's obvious improvement of mapping error rate. PMID:25250372

Learning a Nonnegative Sparse Graph for Linear Regression.

Science.gov (United States)

Fang, Xiaozhao; Xu, Yong; Li, Xuelong; Lai, Zhihui; Wong, Wai Keung

2015-09-01

Previous graph-based semisupervised learning (G-SSL) methods have the following drawbacks: 1) they usually predefine the graph structure and then use it to perform label prediction, which cannot guarantee an overall optimum and 2) they only focus on the label prediction or the graph structure construction but are not competent in handling new samples. To this end, a novel nonnegative sparse graph (NNSG) learning method was first proposed. Then, both the label prediction and projection learning were integrated into linear regression. Finally, the linear regression and graph structure learning were unified within the same framework to overcome these two drawbacks. Therefore, a novel method, named learning a NNSG for linear regression was presented, in which the linear regression and graph learning were simultaneously performed to guarantee an overall optimum. In the learning process, the label information can be accurately propagated via the graph structure so that the linear regression can learn a discriminative projection to better fit sample labels and accurately classify new samples. An effective algorithm was designed to solve the corresponding optimization problem with fast convergence. Furthermore, NNSG provides a unified perceptiveness for a number of graph-based learning methods and linear regression methods. The experimental results showed that NNSG can obtain very high classification accuracy and greatly outperforms conventional G-SSL methods, especially some conventional graph construction methods.

A Machine LearningFramework to Forecast Wave Conditions

Science.gov (United States)

Zhang, Y.; James, S. C.; O'Donncha, F.

2017-12-01

Recently, significant effort has been undertaken to quantify and extract wave energy because it is renewable, environmental friendly, abundant, and often close to population centers. However, a major challenge is the ability to accurately and quickly predict energy production, especially across a 48-hour cycle. Accurate forecasting of wave conditions is a challenging undertaking that typically involves solving the spectral action-balance equation on a discretized grid with high spatial resolution. The nature of the computations typically demands high-performance computing infrastructure. Using a case-study site at Monterey Bay, California, a machine learning framework was trained to replicate numerically simulated wave conditions at a fraction of the typical computational cost. Specifically, the physics-based Simulating WAves Nearshore (SWAN) model, driven by measured wave conditions, nowcast ocean currents, and wind data, was used to generate training data for machine learning algorithms. The model was run between April 1st, 2013 and May 31st, 2017 generating forecasts at three-hour intervals yielding 11,078 distinct model outputs. SWAN-generated fields of 3,104 wave heights and a characteristic period could be replicated through simple matrix multiplications using the mapping matrices from machine learning algorithms. In fact, wave-height RMSEs from the machine learning algorithms (9 cm) were less than those for the SWAN model-verification exercise where those simulations were compared to buoy wave data within the model domain (>40 cm). The validated machine learning approach, which acts as an accurate surrogate for the SWAN model, can now be used to perform real-time forecasts of wave conditions for the next 48 hours using available forecasted boundary wave conditions, ocean currents, and winds. This solution has obvious applications to wave-energy generation as accurate wave conditions can be forecasted with over a three-order-of-magnitude reduction in

Eile avati Harku vallas Raja tööstuskeskuse uus juurdepääsutee

Index Scriptorium Estoniae

2003-01-01

Kahe Harku valla ettevõtte algatusel ja riigi toel sai Raja tööstuskeskus Tabasalus kaasaegse juurdepääsutee, rahastasid Ettevõtluse Arendamise Sihtasutus ning eraettevõtted Greiner Packaging ja Palmatin

The effectiveness of nurses' ability to interpret basic electrocardiogram strips accurately using different learning modalities.

Science.gov (United States)

Spiva, LeeAnna; Johnson, Kimberly; Robertson, Bethany; Barrett, Darcy T; Jarrell, Nicole M; Hunter, Donna; Mendoza, Inocencia

2012-02-01

Historically, the instructional method of choice has been traditional lecture or face-to-face education; however, changes in the health care environment, including resource constraints, have necessitated examination of this practice. A descriptive pre-/posttest method was used to determine the effectiveness of alternative teaching modalities on nurses' knowledge and confidence in electrocardiogram (EKG) interpretation. A convenience sample of 135 nurses was recruited in an integrated health care system in the Southeastern United States. Nurses attended an instructor-led course, an online learning (e-learning) platform with no study time or 1 week of study time, or an e-learning platform coupled with a 2-hour post-course instructor-facilitated debriefing with no study time or 1 week of study time. Instruments included a confidence scale, an online EKG test, and a course evaluation. Statistically significant differences in knowledge and confidence were found for individual groups after nurses participated in the intervention. Statistically significant differences were found in pre-knowledge and post-confidence when groups were compared. Organizations that use various instructional methods to educate nurses in EKG interpretation can use different teaching modalities without negatively affecting nurses' knowledge or confidence in this skill. Copyright 2012, SLACK Incorporated.

Theory of mind selectively predicts preschoolers' knowledge-based selective word learning.

Science.gov (United States)

Brosseau-Liard, Patricia; Penney, Danielle; Poulin-Dubois, Diane

2015-11-01

Children can selectively attend to various attributes of a model, such as past accuracy or physical strength, to guide their social learning. There is a debate regarding whether a relation exists between theory-of-mind skills and selective learning. We hypothesized that high performance on theory-of-mind tasks would predict preference for learning new words from accurate informants (an epistemic attribute), but not from physically strong informants (a non-epistemic attribute). Three- and 4-year-olds (N = 65) completed two selective learning tasks, and their theory-of-mind abilities were assessed. As expected, performance on a theory-of-mind battery predicted children's preference to learn from more accurate informants but not from physically stronger informants. Results thus suggest that preschoolers with more advanced theory of mind have a better understanding of knowledge and apply that understanding to guide their selection of informants. This work has important implications for research on children's developing social cognition and early learning. © 2015 The British Psychological Society.

Theory of mind selectively predicts preschoolers’ knowledge-based selective word learning

Science.gov (United States)

Brosseau-Liard, Patricia; Penney, Danielle; Poulin-Dubois, Diane

2015-01-01

Children can selectively attend to various attributes of a model, such as past accuracy or physical strength, to guide their social learning. There is a debate regarding whether a relation exists between theory-of-mind skills and selective learning. We hypothesized that high performance on theory-of-mind tasks would predict preference for learning new words from accurate informants (an epistemic attribute), but not from physically strong informants (a non-epistemic attribute). Three- and 4-year-olds (N = 65) completed two selective learning tasks, and their theory of mind abilities were assessed. As expected, performance on a theory-of-mind battery predicted children’s preference to learn from more accurate informants but not from physically stronger informants. Results thus suggest that preschoolers with more advanced theory of mind have a better understanding of knowledge and apply that understanding to guide their selection of informants. This work has important implications for research on children’s developing social cognition and early learning. PMID:26211504

A Multianalyzer Machine Learning Model for Marine Heterogeneous Data Schema Mapping

Directory of Open Access Journals (Sweden)

Wang Yan

2014-01-01

Full Text Available The main challenges that marine heterogeneous data integration faces are the problem of accurate schema mapping between heterogeneous data sources. In order to improve the schema mapping efficiency and get more accurate learning results, this paper proposes a heterogeneous data schema mapping method basing on multianalyzer machine learning model. The multianalyzer analysis the learning results comprehensively, and a fuzzy comprehensive evaluation system is introduced for output results’ evaluation and multi factor quantitative judging. Finally, the data mapping comparison experiment on the East China Sea observing data confirms the effectiveness of the model and shows multianalyzer’s obvious improvement of mapping error rate.

Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression

OpenAIRE

Sato, Jo?o R.; Moll, Jorge; Green, Sophie; Deakin, John F.W.; Thomaz, Carlos E.; Zahn, Roland

2015-01-01

Standard functional magnetic resonance imaging (fMRI) analyses cannot assess the potential of a neuroimaging signature as a biomarker to predict individual vulnerability to major depression (MD). Here, we use machine learning for the first time to address this question. Using a recently identified neural signature of guilt-selective functional disconnection, the classification algorithm was able to distinguish remitted MD from control participants with 78.3% accuracy. This demonstrates the hi...

Computer-based personality judgments are more accurate than those made by humans

Science.gov (United States)

Youyou, Wu; Kosinski, Michal; Stillwell, David

2015-01-01

Judging others’ personalities is an essential skill in successful social living, as personality is a key driver behind people’s interactions, behaviors, and emotions. Although accurate personality judgments stem from social-cognitive skills, developments in machine learning show that computer models can also make valid judgments. This study compares the accuracy of human and computer-based personality judgments, using a sample of 86,220 volunteers who completed a 100-item personality questionnaire. We show that (i) computer predictions based on a generic digital footprint (Facebook Likes) are more accurate (r = 0.56) than those made by the participants’ Facebook friends using a personality questionnaire (r = 0.49); (ii) computer models show higher interjudge agreement; and (iii) computer personality judgments have higher external validity when predicting life outcomes such as substance use, political attitudes, and physical health; for some outcomes, they even outperform the self-rated personality scores. Computers outpacing humans in personality judgment presents significant opportunities and challenges in the areas of psychological assessment, marketing, and privacy. PMID:25583507

Observing Animal Behavior at the Zoo: A Learning Laboratory

Science.gov (United States)

Hull, Debra B.

2003-01-01

Undergraduate students in a learning laboratory course initially chose a species to study; researched that species' physical and behavioral characteristics; then learned skills necessary to select, operationalize, observe, and record animal behavior accurately. After their classroom preparation, students went to a local zoo to observe the behavior…

A machine learning approach to the accurate prediction of monitor units for a compact proton machine.

Science.gov (United States)

Sun, Baozhou; Lam, Dao; Yang, Deshan; Grantham, Kevin; Zhang, Tiezhi; Mutic, Sasa; Zhao, Tianyu

2018-05-01

Clinical treatment planning systems for proton therapy currently do not calculate monitor units (MUs) in passive scatter proton therapy due to the complexity of the beam delivery systems. Physical phantom measurements are commonly employed to determine the field-specific output factors (OFs) but are often subject to limited machine time, measurement uncertainties and intensive labor. In this study, a machine learning-based approach was developed to predict output (cGy/MU) and derive MUs, incorporating the dependencies on gantry angle and field size for a single-room proton therapy system. The goal of this study was to develop a secondary check tool for OF measurements and eventually eliminate patient-specific OF measurements. The OFs of 1754 fields previously measured in a water phantom with calibrated ionization chambers and electrometers for patient-specific fields with various range and modulation width combinations for 23 options were included in this study. The training data sets for machine learning models in three different methods (Random Forest, XGBoost and Cubist) included 1431 (~81%) OFs. Ten-fold cross-validation was used to prevent "overfitting" and to validate each model. The remaining 323 (~19%) OFs were used to test the trained models. The difference between the measured and predicted values from machine learning models was analyzed. Model prediction accuracy was also compared with that of the semi-empirical model developed by Kooy (Phys. Med. Biol. 50, 2005). Additionally, gantry angle dependence of OFs was measured for three groups of options categorized on the selection of the second scatters. Field size dependence of OFs was investigated for the measurements with and without patient-specific apertures. All three machine learning methods showed higher accuracy than the semi-empirical model which shows considerably large discrepancy of up to 7.7% for the treatment fields with full range and full modulation width. The Cubist-based solution

Learning styles and courseware design

OpenAIRE

Valley, Karen

1997-01-01

In this paper we examine how (courseware) can accommodate differences in preferred learning style. A review of the literature on learning styles is followed by a discussion of the implications of being able to accurately classify learners, and key issues that must be addressed are raised. We then present two courseware design solutions that take into account individual learning‐style preference: the first follows on from traditional research in this area and assumes that learners can be class...

Label-Driven Learning Framework: Towards More Accurate Bayesian Network Classifiers through Discrimination of High-Confidence Labels

Directory of Open Access Journals (Sweden)

Yi Sun

2017-12-01

Full Text Available Bayesian network classifiers (BNCs have demonstrated competitive classification accuracy in a variety of real-world applications. However, it is error-prone for BNCs to discriminate among high-confidence labels. To address this issue, we propose the label-driven learning framework, which incorporates instance-based learning and ensemble learning. For each testing instance, high-confidence labels are first selected by a generalist classifier, e.g., the tree-augmented naive Bayes (TAN classifier. Then, by focusing on these labels, conditional mutual information is redefined to more precisely measure mutual dependence between attributes, thus leading to a refined generalist with a more reasonable network structure. To enable finer discrimination, an expert classifier is tailored for each high-confidence label. Finally, the predictions of the refined generalist and the experts are aggregated. We extend TAN to LTAN (Label-driven TAN by applying the proposed framework. Extensive experimental results demonstrate that LTAN delivers superior classification accuracy to not only several state-of-the-art single-structure BNCs but also some established ensemble BNCs at the expense of reasonable computation overhead.

Accurate crop classification using hierarchical genetic fuzzy rule-based systems

Science.gov (United States)

Topaloglou, Charalampos A.; Mylonas, Stelios K.; Stavrakoudis, Dimitris G.; Mastorocostas, Paris A.; Theocharis, John B.

2014-10-01

This paper investigates the effectiveness of an advanced classification system for accurate crop classification using very high resolution (VHR) satellite imagery. Specifically, a recently proposed genetic fuzzy rule-based classification system (GFRBCS) is employed, namely, the Hierarchical Rule-based Linguistic Classifier (HiRLiC). HiRLiC's model comprises a small set of simple IF-THEN fuzzy rules, easily interpretable by humans. One of its most important attributes is that its learning algorithm requires minimum user interaction, since the most important learning parameters affecting the classification accuracy are determined by the learning algorithm automatically. HiRLiC is applied in a challenging crop classification task, using a SPOT5 satellite image over an intensively cultivated area in a lake-wetland ecosystem in northern Greece. A rich set of higher-order spectral and textural features is derived from the initial bands of the (pan-sharpened) image, resulting in an input space comprising 119 features. The experimental analysis proves that HiRLiC compares favorably to other interpretable classifiers of the literature, both in terms of structural complexity and classification accuracy. Its testing accuracy was very close to that obtained by complex state-of-the-art classification systems, such as the support vector machines (SVM) and random forest (RF) classifiers. Nevertheless, visual inspection of the derived classification maps shows that HiRLiC is characterized by higher generalization properties, providing more homogeneous classifications that the competitors. Moreover, the runtime requirements for producing the thematic map was orders of magnitude lower than the respective for the competitors.

Active learning of Pareto fronts.

Science.gov (United States)

Campigotto, Paolo; Passerini, Andrea; Battiti, Roberto

2014-03-01

This paper introduces the active learning of Pareto fronts (ALP) algorithm, a novel approach to recover the Pareto front of a multiobjective optimization problem. ALP casts the identification of the Pareto front into a supervised machine learning task. This approach enables an analytical model of the Pareto front to be built. The computational effort in generating the supervised information is reduced by an active learning strategy. In particular, the model is learned from a set of informative training objective vectors. The training objective vectors are approximated Pareto-optimal vectors obtained by solving different scalarized problem instances. The experimental results show that ALP achieves an accurate Pareto front approximation with a lower computational effort than state-of-the-art estimation of distribution algorithms and widely known genetic techniques.

Learning Markov Decision Processes for Model Checking

DEFF Research Database (Denmark)

Mao, Hua; Chen, Yingke; Jaeger, Manfred

2012-01-01

. The proposed learning algorithm is adapted from algorithms for learning deterministic probabilistic finite automata, and extended to include both probabilistic and nondeterministic transitions. The algorithm is empirically analyzed and evaluated by learning system models of slot machines. The evaluation......Constructing an accurate system model for formal model verification can be both resource demanding and time-consuming. To alleviate this shortcoming, algorithms have been proposed for automatically learning system models based on observed system behaviors. In this paper we extend the algorithm...... on learning probabilistic automata to reactive systems, where the observed system behavior is in the form of alternating sequences of inputs and outputs. We propose an algorithm for automatically learning a deterministic labeled Markov decision process model from the observed behavior of a reactive system...

Augmented Reality, the Future of Contextual Mobile Learning

Science.gov (United States)

Sungkur, Roopesh Kevin; Panchoo, Akshay; Bhoyroo, Nitisha Kirtee

2016-01-01

Purpose: This study aims to show the relevance of augmented reality (AR) in mobile learning for the 21st century. With AR, any real-world environment can be augmented by providing users with accurate digital overlays. AR is a promising technology that has the potential to encourage learners to explore learning materials from a totally new…

On Combining Multiple-Instance Learning and Active Learning for Computer-Aided Detection of Tuberculosis

NARCIS (Netherlands)

Melendez Rodriguez, J.C.; Ginneken, B. van; Maduskar, P.; Philipsen, R.H.H.M.; Ayles, H.; Sanchez, C.I.

2016-01-01

The major advantage of multiple-instance learning (MIL) applied to a computer-aided detection (CAD) system is that it allows optimizing the latter with case-level labels instead of accurate lesion outlines as traditionally required for a supervised approach. As shown in previous work, a MIL-based

Automatic generation of a subject-specific model for accurate markerless motion capture and biomechanical applications.

Science.gov (United States)

Corazza, Stefano; Gambaretto, Emiliano; Mündermann, Lars; Andriacchi, Thomas P

2010-04-01

A novel approach for the automatic generation of a subject-specific model consisting of morphological and joint location information is described. The aim is to address the need for efficient and accurate model generation for markerless motion capture (MMC) and biomechanical studies. The algorithm applied and expanded on previous work on human shapes space by embedding location information for ten joint centers in a subject-specific free-form surface. The optimal locations of joint centers in the 3-D mesh were learned through linear regression over a set of nine subjects whose joint centers were known. The model was shown to be sufficiently accurate for both kinematic (joint centers) and morphological (shape of the body) information to allow accurate tracking with MMC systems. The automatic model generation algorithm was applied to 3-D meshes of different quality and resolution such as laser scans and visual hulls. The complete method was tested using nine subjects of different gender, body mass index (BMI), age, and ethnicity. Experimental training error and cross-validation errors were 19 and 25 mm, respectively, on average over the joints of the ten subjects analyzed in the study.

Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties

Science.gov (United States)

Xie, Tian; Grossman, Jeffrey C.

2018-04-01

The use of machine learning methods for accelerating the design of crystalline materials usually requires manually constructed feature vectors or complex transformation of atom coordinates to input the crystal structure, which either constrains the model to certain crystal types or makes it difficult to provide chemical insights. Here, we develop a crystal graph convolutional neural networks framework to directly learn material properties from the connection of atoms in the crystal, providing a universal and interpretable representation of crystalline materials. Our method provides a highly accurate prediction of density functional theory calculated properties for eight different properties of crystals with various structure types and compositions after being trained with 1 04 data points. Further, our framework is interpretable because one can extract the contributions from local chemical environments to global properties. Using an example of perovskites, we show how this information can be utilized to discover empirical rules for materials design.

Towards accurate emergency response behavior

International Nuclear Information System (INIS)

Sargent, T.O.

1981-01-01

Nuclear reactor operator emergency response behavior has persisted as a training problem through lack of information. The industry needs an accurate definition of operator behavior in adverse stress conditions, and training methods which will produce the desired behavior. Newly assembled information from fifty years of research into human behavior in both high and low stress provides a more accurate definition of appropriate operator response, and supports training methods which will produce the needed control room behavior. The research indicates that operator response in emergencies is divided into two modes, conditioned behavior and knowledge based behavior. Methods which assure accurate conditioned behavior, and provide for the recovery of knowledge based behavior, are described in detail

77 FR 66663 - Senior Executive Service; Combined Performance Review Board (PRB)

Science.gov (United States)

2012-11-06

... Director, BPD; Leonard R. Olijar, Chief Financial Officer/Associate Director, BEP; Beverly Ortega Babers, Chief Administrative Officer, United States Mint; Cheri Mitchell, Chief Financial Officer/Assistant... States Mint; Mary G. Ryan, Deputy Administrator, TTB. Alternate Members Marty Greiner, Chief Financial...

Machine learning algorithm accurately detects fMRI signature of vulnerability to major depression.

Science.gov (United States)

Sato, João R; Moll, Jorge; Green, Sophie; Deakin, John F W; Thomaz, Carlos E; Zahn, Roland

2015-08-30

Standard functional magnetic resonance imaging (fMRI) analyses cannot assess the potential of a neuroimaging signature as a biomarker to predict individual vulnerability to major depression (MD). Here, we use machine learning for the first time to address this question. Using a recently identified neural signature of guilt-selective functional disconnection, the classification algorithm was able to distinguish remitted MD from control participants with 78.3% accuracy. This demonstrates the high potential of our fMRI signature as a biomarker of MD vulnerability. Crown Copyright © 2015. Published by Elsevier Ireland Ltd. All rights reserved.

Active machine learning-driven experimentation to determine compound effects on protein patterns.

Science.gov (United States)

Naik, Armaghan W; Kangas, Joshua D; Sullivan, Devin P; Murphy, Robert F

2016-02-03

High throughput screening determines the effects of many conditions on a given biological target. Currently, to estimate the effects of those conditions on other targets requires either strong modeling assumptions (e.g. similarities among targets) or separate screens. Ideally, data-driven experimentation could be used to learn accurate models for many conditions and targets without doing all possible experiments. We have previously described an active machine learning algorithm that can iteratively choose small sets of experiments to learn models of multiple effects. We now show that, with no prior knowledge and with liquid handling robotics and automated microscopy under its control, this learner accurately learned the effects of 48 chemical compounds on the subcellular localization of 48 proteins while performing only 29% of all possible experiments. The results represent the first practical demonstration of the utility of active learning-driven biological experimentation in which the set of possible phenotypes is unknown in advance.

Less is more: Sampling chemical space with active learning

Science.gov (United States)

Smith, Justin S.; Nebgen, Ben; Lubbers, Nicholas; Isayev, Olexandr; Roitberg, Adrian E.

2018-06-01

The development of accurate and transferable machine learning (ML) potentials for predicting molecular energetics is a challenging task. The process of data generation to train such ML potentials is a task neither well understood nor researched in detail. In this work, we present a fully automated approach for the generation of datasets with the intent of training universal ML potentials. It is based on the concept of active learning (AL) via Query by Committee (QBC), which uses the disagreement between an ensemble of ML potentials to infer the reliability of the ensemble's prediction. QBC allows the presented AL algorithm to automatically sample regions of chemical space where the ML potential fails to accurately predict the potential energy. AL improves the overall fitness of ANAKIN-ME (ANI) deep learning potentials in rigorous test cases by mitigating human biases in deciding what new training data to use. AL also reduces the training set size to a fraction of the data required when using naive random sampling techniques. To provide validation of our AL approach, we develop the COmprehensive Machine-learning Potential (COMP6) benchmark (publicly available on GitHub) which contains a diverse set of organic molecules. Active learning-based ANI potentials outperform the original random sampled ANI-1 potential with only 10% of the data, while the final active learning-based model vastly outperforms ANI-1 on the COMP6 benchmark after training to only 25% of the data. Finally, we show that our proposed AL technique develops a universal ANI potential (ANI-1x) that provides accurate energy and force predictions on the entire COMP6 benchmark. This universal ML potential achieves a level of accuracy on par with the best ML potentials for single molecules or materials, while remaining applicable to the general class of organic molecules composed of the elements CHNO.

A hypothesis on improving foreign accents by optimizing variability in vocal learning brain circuits.

Science.gov (United States)

Simmonds, Anna J

2015-01-01

Rapid vocal motor learning is observed when acquiring a language in early childhood, or learning to speak another language later in life. Accurate pronunciation is one of the hardest things for late learners to master and they are almost always left with a non-native accent. Here, I propose a novel hypothesis that this accent could be improved by optimizing variability in vocal learning brain circuits during learning. Much of the neurobiology of human vocal motor learning has been inferred from studies on songbirds. Jarvis (2004) proposed the hypothesis that as in songbirds there are two pathways in humans: one for learning speech (the striatal vocal learning pathway), and one for production of previously learnt speech (the motor pathway). Learning new motor sequences necessary for accurate non-native pronunciation is challenging and I argue that in late learners of a foreign language the vocal learning pathway becomes inactive prematurely. The motor pathway is engaged once again and learners maintain their original native motor patterns for producing speech, resulting in speaking with a foreign accent. Further, I argue that variability in neural activity within vocal motor circuitry generates vocal variability that supports accurate non-native pronunciation. Recent theoretical and experimental work on motor learning suggests that variability in the motor movement is necessary for the development of expertise. I propose that there is little trial-by-trial variability when using the motor pathway. When using the vocal learning pathway variability gradually increases, reflecting an exploratory phase in which learners try out different ways of pronouncing words, before decreasing and stabilizing once the "best" performance has been identified. The hypothesis proposed here could be tested using behavioral interventions that optimize variability and engage the vocal learning pathway for longer, with the prediction that this would allow learners to develop new motor

Model-Agnostic Interpretability of Machine Learning

OpenAIRE

Ribeiro, Marco Tulio; Singh, Sameer; Guestrin, Carlos

2016-01-01

Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user interfaces. Thus, interpretability has become a vital concern in machine learning, and work in the area of interpretable models has found renewed interest. In some applications, such models are as accurate as non-interpretable ones, and thus are preferred f...

Representation learning with deep extreme learning machines for efficient image set classification

KAUST Repository

Uzair, Muhammad

2016-12-09

Efficient and accurate representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the nonlinear structure of image sets with deep extreme learning machines that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy.

Representation learning with deep extreme learning machines for efficient image set classification

KAUST Repository

Uzair, Muhammad; Shafait, Faisal; Ghanem, Bernard; Mian, Ajmal

2016-01-01

Efficient and accurate representation of a collection of images, that belong to the same class, is a major research challenge for practical image set classification. Existing methods either make prior assumptions about the data structure, or perform heavy computations to learn structure from the data itself. In this paper, we propose an efficient image set representation that does not make any prior assumptions about the structure of the underlying data. We learn the nonlinear structure of image sets with deep extreme learning machines that are very efficient and generalize well even on a limited number of training samples. Extensive experiments on a broad range of public datasets for image set classification show that the proposed algorithm consistently outperforms state-of-the-art image set classification methods both in terms of speed and accuracy.

Learning from neural control.

Science.gov (United States)

Wang, Cong; Hill, David J

2006-01-01

One of the amazing successes of biological systems is their ability to "learn by doing" and so adapt to their environment. In this paper, first, a deterministic learning mechanism is presented, by which an appropriately designed adaptive neural controller is capable of learning closed-loop system dynamics during tracking control to a periodic reference orbit. Among various neural network (NN) architectures, the localized radial basis function (RBF) network is employed. A property of persistence of excitation (PE) for RBF networks is established, and a partial PE condition of closed-loop signals, i.e., the PE condition of a regression subvector constructed out of the RBFs along a periodic state trajectory, is proven to be satisfied. Accurate NN approximation for closed-loop system dynamics is achieved in a local region along the periodic state trajectory, and a learning ability is implemented during a closed-loop feedback control process. Second, based on the deterministic learning mechanism, a neural learning control scheme is proposed which can effectively recall and reuse the learned knowledge to achieve closed-loop stability and improved control performance. The significance of this paper is that the presented deterministic learning mechanism and the neural learning control scheme provide elementary components toward the development of a biologically-plausible learning and control methodology. Simulation studies are included to demonstrate the effectiveness of the approach.

Spectrally accurate contour dynamics

International Nuclear Information System (INIS)

Van Buskirk, R.D.; Marcus, P.S.

1994-01-01

We present an exponentially accurate boundary integral method for calculation the equilibria and dynamics of piece-wise constant distributions of potential vorticity. The method represents contours of potential vorticity as a spectral sum and solves the Biot-Savart equation for the velocity by spectrally evaluating a desingularized contour integral. We use the technique in both an initial-value code and a newton continuation method. Our methods are tested by comparing the numerical solutions with known analytic results, and it is shown that for the same amount of computational work our spectral methods are more accurate than other contour dynamics methods currently in use

Do Skilled Elementary Teachers Hold Scientific Conceptions and Can They Accurately Predict the Type and Source of Students' Preconceptions of Electric Circuits?

Science.gov (United States)

Lin, Jing-Wen

2016-01-01

Holding scientific conceptions and having the ability to accurately predict students' preconceptions are a prerequisite for science teachers to design appropriate constructivist-oriented learning experiences. This study explored the types and sources of students' preconceptions of electric circuits. First, 438 grade 3 (9 years old) students were…

Deep learning for multi-task plant phenotyping

OpenAIRE

Pound, Michael P.; Atkinson, Jonathan A.; Wells, Darren M.; Pridmore, Tony P.; French, Andrew P.

2017-01-01

Plant phenotyping has continued to pose a challenge to computer vision for many years. There is a particular demand to accurately quantify images of crops, and the natural variability and structure of these plants presents unique difficulties. Recently, machine learning approaches have shown impressive results in many areas of computer vision, but these rely on large datasets that are at present not available for crops. We present a new dataset, called ACID, that provides hundreds of accurate...

PROJECT BASED LEARNING BERMUATAN ETNOMATEMATIKA DALAM PEMBELAJAR MATEMATIKA

Directory of Open Access Journals (Sweden)

I Wayan Eka Mahendra

2017-03-01

Full Text Available This study aims to determine differences simultaneously in motivation and mathematics learning outcomes between students taking project based learningmodel charged ethnomathematics and students who followed the conventional learning modelon the class VIII SMP Negeri 3 Abiansemalyear 2016/2017. It was a quasi experiment with a sample of 71 student obtain by using simple random sampling. The data were analyzed by one-way multivariate analysis (Manova.The results of this study indicate that there are differences in simultaneously in learning motivation and learning outcomes between students taking mathematics model project based learning charged ethnomathematics and students who followed the conventional learning model on the class VIII SMP Negeri 3 Abiansemal year 2016/2017. Besed on the research findings, junior high school teachers are suggested to improve their student learning outcome for mathematics. Teachers also need to use a learning models accurately and correctly.

Accurate Evaluation of Quantum Integrals

Science.gov (United States)

Galant, D. C.; Goorvitch, D.; Witteborn, Fred C. (Technical Monitor)

1995-01-01

Combining an appropriate finite difference method with Richardson's extrapolation results in a simple, highly accurate numerical method for solving a Schrodinger's equation. Important results are that error estimates are provided, and that one can extrapolate expectation values rather than the wavefunctions to obtain highly accurate expectation values. We discuss the eigenvalues, the error growth in repeated Richardson's extrapolation, and show that the expectation values calculated on a crude mesh can be extrapolated to obtain expectation values of high accuracy.

E-learning: Web-based education.

Science.gov (United States)

Sajeva, Marco

2006-12-01

This review introduces state-of-the-art Web-based education and shows how the e-learning model can be applied to an anaesthesia department using Open Source solutions, as well as lifelong learning programs, which is happening in several European research projects. The definition of the term e-learning is still a work in progress due to the fact that technologies are evolving every day and it is difficult to improve teaching methodologies or to adapt traditional methods to a new or already existing educational model. The European Community is funding several research projects to define the new common market place for tomorrow's educational system; this is leading to new frontiers like virtual Erasmus inter-exchange programs based on e-learning. The first step when adapting a course to e-learning is to re-define the educational/learning model adopted: cooperative learning and tutoring are the two key concepts. This means that traditional lecture notes, books and exercises are no longer effective; teaching files must use rich multimedia content and have to be developed using the new media. This can lead to several pitfalls that can be avoided with an accurate design phase.

Dynamic gradient descent learning algorithms for enhanced empirical modeling of power plants

International Nuclear Information System (INIS)

Parlos, A.G.; Atiya, Amir; Chong, K.T.

1991-01-01

A newly developed dynamic gradient descent-based learning algorithm is used to train a recurrent multilayer perceptron network for use in empirical modeling of power plants. The two main advantages of the proposed learning algorithm are its ability to consider past error gradient information for future use and the two forward passes associated with its implementation, instead of one forward and one backward pass of the backpropagation algorithm. The latter advantage results in computational time saving because both passes can be performed simultaneously. The dynamic learning algorithm is used to train a hybrid feedforward/feedback neural network, a recurrent multilayer perceptron, which was previously found to exhibit good interpolation and extrapolation capabilities in modeling nonlinear dynamic systems. One of the drawbacks, however, of the previously reported work has been the long training times associated with accurate empirical models. The enhanced learning capabilities provided by the dynamic gradient descent-based learning algorithm are demonstrated by a case study of a steam power plant. The number of iterations required for accurate empirical modeling has been reduced from tens of thousands to hundreds, thus significantly expediting the learning process

Evolving autonomous learning in cognitive networks.

Science.gov (United States)

Sheneman, Leigh; Hintze, Arend

2017-12-01

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

Approaching system equilibrium with accurate or not accurate feedback information in a two-route system

Science.gov (United States)

Zhao, Xiao-mei; Xie, Dong-fan; Li, Qi

2015-02-01

With the development of intelligent transport system, advanced information feedback strategies have been developed to reduce traffic congestion and enhance the capacity. However, previous strategies provide accurate information to travelers and our simulation results show that accurate information brings negative effects, especially in delay case. Because travelers prefer to the best condition route with accurate information, and delayed information cannot reflect current traffic condition but past. Then travelers make wrong routing decisions, causing the decrease of the capacity and the increase of oscillations and the system deviating from the equilibrium. To avoid the negative effect, bounded rationality is taken into account by introducing a boundedly rational threshold BR. When difference between two routes is less than the BR, routes have equal probability to be chosen. The bounded rationality is helpful to improve the efficiency in terms of capacity, oscillation and the gap deviating from the system equilibrium.

Parallelization of learning problems by artificial neural networks. Application in external radiotherapy

International Nuclear Information System (INIS)

Sauget, M.

2007-12-01

This research is about the application of neural networks used in the external radiotherapy domain. The goal is to elaborate a new evaluating system for the radiation dose distributions in heterogeneous environments. The al objective of this work is to build a complete tool kit to evaluate the optimal treatment planning. My st research point is about the conception of an incremental learning algorithm. The interest of my work is to combine different optimizations specialized in the function interpolation and to propose a new algorithm allowing to change the neural network architecture during the learning phase. This algorithm allows to minimise the al size of the neural network while keeping a good accuracy. The second part of my research is to parallelize the previous incremental learning algorithm. The goal of that work is to increase the speed of the learning step as well as the size of the learned dataset needed in a clinical case. For that, our incremental learning algorithm presents an original data decomposition with overlapping, together with a fault tolerance mechanism. My last research point is about a fast and accurate algorithm computing the radiation dose deposit in any heterogeneous environment. At the present time, the existing solutions used are not optimal. The fast solution are not accurate and do not give an optimal treatment planning. On the other hand, the accurate solutions are far too slow to be used in a clinical context. Our algorithm answers to this problem by bringing rapidity and accuracy. The concept is to use a neural network adequately learned together with a mechanism taking into account the environment changes. The advantages of this algorithm is to avoid the use of a complex physical code while keeping a good accuracy and reasonable computation times. (author)

Auditory Perceptual Learning for Speech Perception Can be Enhanced by Audiovisual Training.

Science.gov (United States)

Bernstein, Lynne E; Auer, Edward T; Eberhardt, Silvio P; Jiang, Jintao

2013-01-01

Speech perception under audiovisual (AV) conditions is well known to confer benefits to perception such as increased speed and accuracy. Here, we investigated how AV training might benefit or impede auditory perceptual learning of speech degraded by vocoding. In Experiments 1 and 3, participants learned paired associations between vocoded spoken nonsense words and nonsense pictures. In Experiment 1, paired-associates (PA) AV training of one group of participants was compared with audio-only (AO) training of another group. When tested under AO conditions, the AV-trained group was significantly more accurate than the AO-trained group. In addition, pre- and post-training AO forced-choice consonant identification with untrained nonsense words showed that AV-trained participants had learned significantly more than AO participants. The pattern of results pointed to their having learned at the level of the auditory phonetic features of the vocoded stimuli. Experiment 2, a no-training control with testing and re-testing on the AO consonant identification, showed that the controls were as accurate as the AO-trained participants in Experiment 1 but less accurate than the AV-trained participants. In Experiment 3, PA training alternated AV and AO conditions on a list-by-list basis within participants, and training was to criterion (92% correct). PA training with AO stimuli was reliably more effective than training with AV stimuli. We explain these discrepant results in terms of the so-called "reverse hierarchy theory" of perceptual learning and in terms of the diverse multisensory and unisensory processing resources available to speech perception. We propose that early AV speech integration can potentially impede auditory perceptual learning; but visual top-down access to relevant auditory features can promote auditory perceptual learning.

Diagnosing Coronary Heart Disease using Ensemble Machine Learning

OpenAIRE

Kathleen H. Miao; Julia H. Miao; George J. Miao

2016-01-01

Globally, heart disease is the leading cause of death for both men and women. One in every four people is afflicted with and dies of heart disease. Early and accurate diagnoses of heart disease thus are crucial in improving the chances of long-term survival for patients and saving millions of lives. In this research, an advanced ensemble machine learning technology, utilizing an adaptive Boosting algorithm, is developed for accurate coronary heart disease diagnosis and outcome predictions. Th...

A collective model description of the low lying and giant dipole resonant properties of 40424446Ca

International Nuclear Information System (INIS)

Weise, J.I.

1982-01-01

The low-lying and giant dipole resonant properties of the even-even calcium isotopes are calculated within the framework of the Gneuss-Greiner model and compared with the experimental data. In the low energy region, comparison is also made with the predictions of a coexistence model

Training with Differential Outcomes Enhances Discriminative Learning and Visuospatial Recognition Memory in Children Born Prematurely

Science.gov (United States)

Martinez, Lourdes; Mari-Beffa, Paloma; Roldan-Tapia, Dolores; Ramos-Lizana, Julio; Fuentes, Luis J.; Estevez, Angeles F.

2012-01-01

Previous studies have demonstrated that discriminative learning is facilitated when a particular outcome is associated with each relation to be learned. When this training procedure is applied (the differential outcome procedure; DOP), learning is faster and more accurate than when the more common non-differential outcome procedure is used. This…

DeepRT: deep learning for peptide retention time prediction in proteomics

OpenAIRE

Ma, Chunwei; Zhu, Zhiyong; Ye, Jun; Yang, Jiarui; Pei, Jianguo; Xu, Shaohang; Zhou, Ruo; Yu, Chang; Mo, Fan; Wen, Bo; Liu, Siqi

2017-01-01

Accurate predictions of peptide retention times (RT) in liquid chromatography have many applications in mass spectrometry-based proteomics. Herein, we present DeepRT, a deep learning based software for peptide retention time prediction. DeepRT automatically learns features directly from the peptide sequences using the deep convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) model, which eliminates the need to use hand-crafted features or rules. After the feature learning, pr...

Quantum mechanics symmetries

CERN Document Server

Greiner, Walter

1989-01-01

"Quantum Dynamics" is a major survey of quantum theory based on Walter Greiner's long-running and highly successful courses at the University of Frankfurt. The key to understanding in quantum theory is to reinforce lecture attendance and textual study by working through plenty of representative and detailed examples. Firm belief in this principle led Greiner to develop his unique course and to transform it into a remarkable and comprehensive text. The text features a large number of examples and exercises involving many of the most advanced topics in quantum theory. These examples give practical and precise demonstrations of how to use the often subtle mathematics behind quantum theory. The text is divided into five volumes: Quantum Mechanics I - An Introduction, Quantum Mechanics II - Symmetries, Relativistic Quantum Mechanics, Quantum Electrodynamics, Gauge Theory of Weak Interactions. These five volumes take the reader from the fundamental postulates of quantum mechanics up to the latest research in partic...

Cross-Situational Learning with Bayesian Generative Models for Multimodal Category and Word Learning in Robots

Directory of Open Access Journals (Sweden)

Akira Taniguchi

2017-12-01

Full Text Available In this paper, we propose a Bayesian generative model that can form multiple categories based on each sensory-channel and can associate words with any of the four sensory-channels (action, position, object, and color. This paper focuses on cross-situational learning using the co-occurrence between words and information of sensory-channels in complex situations rather than conventional situations of cross-situational learning. We conducted a learning scenario using a simulator and a real humanoid iCub robot. In the scenario, a human tutor provided a sentence that describes an object of visual attention and an accompanying action to the robot. The scenario was set as follows: the number of words per sensory-channel was three or four, and the number of trials for learning was 20 and 40 for the simulator and 25 and 40 for the real robot. The experimental results showed that the proposed method was able to estimate the multiple categorizations and to learn the relationships between multiple sensory-channels and words accurately. In addition, we conducted an action generation task and an action description task based on word meanings learned in the cross-situational learning scenario. The experimental results showed that the robot could successfully use the word meanings learned by using the proposed method.

Weakly Supervised Dictionary Learning

Science.gov (United States)

You, Zeyu; Raich, Raviv; Fern, Xiaoli Z.; Kim, Jinsub

2018-05-01

We present a probabilistic modeling and inference framework for discriminative analysis dictionary learning under a weak supervision setting. Dictionary learning approaches have been widely used for tasks such as low-level signal denoising and restoration as well as high-level classification tasks, which can be applied to audio and image analysis. Synthesis dictionary learning aims at jointly learning a dictionary and corresponding sparse coefficients to provide accurate data representation. This approach is useful for denoising and signal restoration, but may lead to sub-optimal classification performance. By contrast, analysis dictionary learning provides a transform that maps data to a sparse discriminative representation suitable for classification. We consider the problem of analysis dictionary learning for time-series data under a weak supervision setting in which signals are assigned with a global label instead of an instantaneous label signal. We propose a discriminative probabilistic model that incorporates both label information and sparsity constraints on the underlying latent instantaneous label signal using cardinality control. We present the expectation maximization (EM) procedure for maximum likelihood estimation (MLE) of the proposed model. To facilitate a computationally efficient E-step, we propose both a chain and a novel tree graph reformulation of the graphical model. The performance of the proposed model is demonstrated on both synthetic and real-world data.

Studying depression using imaging and machine learning methods.

Science.gov (United States)

Patel, Meenal J; Khalaf, Alexander; Aizenstein, Howard J

2016-01-01

Depression is a complex clinical entity that can pose challenges for clinicians regarding both accurate diagnosis and effective timely treatment. These challenges have prompted the development of multiple machine learning methods to help improve the management of this disease. These methods utilize anatomical and physiological data acquired from neuroimaging to create models that can identify depressed patients vs. non-depressed patients and predict treatment outcomes. This article (1) presents a background on depression, imaging, and machine learning methodologies; (2) reviews methodologies of past studies that have used imaging and machine learning to study depression; and (3) suggests directions for future depression-related studies.

Mean-field learning for satisfactory solutions

KAUST Repository

Tembine, Hamidou

2013-12-01

One of the fundamental challenges in distributed interactive systems is to design efficient, accurate, and fair solutions. In such systems, a satisfactory solution is an innovative approach that aims to provide all players with a satisfactory payoff anytime and anywhere. In this paper we study fully distributed learning schemes for satisfactory solutions in games with continuous action space. Considering games where the payoff function depends only on own-action and an aggregate term, we show that the complexity of learning systems can be significantly reduced, leading to the so-called mean-field learning. We provide sufficient conditions for convergence to a satisfactory solution and we give explicit convergence time bounds. Then, several acceleration techniques are used in order to improve the convergence rate. We illustrate numerically the proposed mean-field learning schemes for quality-of-service management in communication networks. © 2013 IEEE.

A Theory of Causal Learning in Children: Causal Maps and Bayes Nets

Science.gov (United States)

Gopnik, Alison; Glymour, Clark; Sobel, David M.; Schulz, Laura E.; Kushnir, Tamar; Danks, David

2004-01-01

The authors outline a cognitive and computational account of causal learning in children. They propose that children use specialized cognitive systems that allow them to recover an accurate "causal map" of the world: an abstract, coherent, learned representation of the causal relations among events. This kind of knowledge can be perspicuously…

The Conflicting Forces Driving Future Avionics Acquisition (Les Arguments Contradictoires pour les Futurs Achats d’Equipements d’Avionique)

Science.gov (United States)

1991-09-01

Sep 1983 "Reliability Parameter of Additive Plated Through Hoics," William E. Greiner , Kollmorgen Corporation, 1rAnnual "Guidelines for Surface Mounting...Militare Etat-Major delIs Force Adienne Ufficio del Delegato Nazionaic all*AGARD Quartier Reine Elisabeth Aeroporto Pratica di Mare Rue d’Evere, 1140

A hypothesis on improving foreign accents by optimizing variability in vocal learning brain circuits

OpenAIRE

Simmonds, Anna J.

2015-01-01

Rapid vocal motor learning is observed when acquiring a language in early childhood, or learning to speak another language later in life. Accurate pronunciation is one of the hardest things for late learners to master and they are almost always left with a non-native accent. Here, I propose a novel hypothesis that this accent could be improved by optimizing variability in vocal learning brain circuits during learning. Much of the neurobiology of human vocal motor learning has been inferred fr...

Four wind speed multi-step forecasting models using extreme learning machines and signal decomposing algorithms

International Nuclear Information System (INIS)

Liu, Hui; Tian, Hong-qi; Li, Yan-fei

2015-01-01

Highlights: • A hybrid architecture is proposed for the wind speed forecasting. • Four algorithms are used for the wind speed multi-scale decomposition. • The extreme learning machines are employed for the wind speed forecasting. • All the proposed hybrid models can generate the accurate results. - Abstract: Realization of accurate wind speed forecasting is important to guarantee the safety of wind power utilization. In this paper, a new hybrid forecasting architecture is proposed to realize the wind speed accurate forecasting. In this architecture, four different hybrid models are presented by combining four signal decomposing algorithms (e.g., Wavelet Decomposition/Wavelet Packet Decomposition/Empirical Mode Decomposition/Fast Ensemble Empirical Mode Decomposition) and Extreme Learning Machines. The originality of the study is to investigate the promoted percentages of the Extreme Learning Machines by those mainstream signal decomposing algorithms in the multiple step wind speed forecasting. The results of two forecasting experiments indicate that: (1) the method of Extreme Learning Machines is suitable for the wind speed forecasting; (2) by utilizing the decomposing algorithms, all the proposed hybrid algorithms have better performance than the single Extreme Learning Machines; (3) in the comparisons of the decomposing algorithms in the proposed hybrid architecture, the Fast Ensemble Empirical Mode Decomposition has the best performance in the three-step forecasting results while the Wavelet Packet Decomposition has the best performance in the one and two step forecasting results. At the same time, the Wavelet Packet Decomposition and the Fast Ensemble Empirical Mode Decomposition are better than the Wavelet Decomposition and the Empirical Mode Decomposition in all the step predictions, respectively; and (4) the proposed algorithms are effective in the wind speed accurate predictions

A theory of causal learning in children: Causal maps and Bayes nets

OpenAIRE

Gopnik, A; Glymour, C; Sobel, D M; Schulz, L E; Kushnir, T; Danks, D

2004-01-01

The authors outline a cognitive and computational account of causal learning in children. They propose that children use specialized cognitive systems that allow them to recover an accurate "causal map" of the world: an abstract, coherent, learned representation of the causal relations among events. This kind of knowledge can be perspicuously understood in terms of the formalism of directed graphical causal models, or Bayes nets. Children's causal learning and inference may involve computatio...

A deep learning-based multi-model ensemble method for cancer prediction.

Science.gov (United States)

Xiao, Yawen; Wu, Jun; Lin, Zongli; Zhao, Xiaodong

2018-01-01

Cancer is a complex worldwide health problem associated with high mortality. With the rapid development of the high-throughput sequencing technology and the application of various machine learning methods that have emerged in recent years, progress in cancer prediction has been increasingly made based on gene expression, providing insight into effective and accurate treatment decision making. Thus, developing machine learning methods, which can successfully distinguish cancer patients from healthy persons, is of great current interest. However, among the classification methods applied to cancer prediction so far, no one method outperforms all the others. In this paper, we demonstrate a new strategy, which applies deep learning to an ensemble approach that incorporates multiple different machine learning models. We supply informative gene data selected by differential gene expression analysis to five different classification models. Then, a deep learning method is employed to ensemble the outputs of the five classifiers. The proposed deep learning-based multi-model ensemble method was tested on three public RNA-seq data sets of three kinds of cancers, Lung Adenocarcinoma, Stomach Adenocarcinoma and Breast Invasive Carcinoma. The test results indicate that it increases the prediction accuracy of cancer for all the tested RNA-seq data sets as compared to using a single classifier or the majority voting algorithm. By taking full advantage of different classifiers, the proposed deep learning-based multi-model ensemble method is shown to be accurate and effective for cancer prediction. Copyright © 2017 Elsevier B.V. All rights reserved.

Drag Reduction of an Airfoil Using Deep Learning

Science.gov (United States)

Jiang, Chiyu; Sun, Anzhu; Marcus, Philip

2017-11-01

We reduced the drag of a 2D airfoil by starting with a NACA-0012 airfoil and used deep learning methods. We created a database which consists of simulations of 2D external flow over randomly generated shapes. We then developed a machine learning framework for external flow field inference given input shapes. Past work which utilized machine learning in Computational Fluid Dynamics focused on estimations of specific flow parameters, but this work is novel in the inference of entire flow fields. We further showed that learned flow patterns are transferable to cases that share certain similarities. This study illustrates the prospects of deeper integration of data-based modeling into current CFD simulation frameworks for faster flow inference and more accurate flow modeling.

Rapid and accurate prediction and scoring of water molecules in protein binding sites.

Directory of Open Access Journals (Sweden)

Gregory A Ross

Full Text Available Water plays a critical role in ligand-protein interactions. However, it is still challenging to predict accurately not only where water molecules prefer to bind, but also which of those water molecules might be displaceable. The latter is often seen as a route to optimizing affinity of potential drug candidates. Using a protocol we call WaterDock, we show that the freely available AutoDock Vina tool can be used to predict accurately the binding sites of water molecules. WaterDock was validated using data from X-ray crystallography, neutron diffraction and molecular dynamics simulations and correctly predicted 97% of the water molecules in the test set. In addition, we combined data-mining, heuristic and machine learning techniques to develop probabilistic water molecule classifiers. When applied to WaterDock predictions in the Astex Diverse Set of protein ligand complexes, we could identify whether a water molecule was conserved or displaced to an accuracy of 75%. A second model predicted whether water molecules were displaced by polar groups or by non-polar groups to an accuracy of 80%. These results should prove useful for anyone wishing to undertake rational design of new compounds where the displacement of water molecules is being considered as a route to improved affinity.

Parachanna obscura

African Journals Online (AJOL)

assured for economic development of this sector (Ravindranath, 1988; Sirima et al.,. 2009; Greiner and Gregg, ... It has a high economic value for. African aquaculture, and a better growth rate. (2 g/day), few bones, ..... Assessment: USGS Circular 1251, 143 p. De Lapeyre BA, Muller-Belecke A, Horstgen-. Sehwark G. 2010.

Environmental Identity: A New Approach to Understanding Students' Participation in Environmental Learning Programs

Science.gov (United States)

Jaksha, Amanda P.

2013-01-01

The goal of this study is to develop an understanding of how participants express their environmental identities during an environmental learning program. Past research on the outcomes of environmental learning programs has focused primarily on changes in knowledge and attitudes. However, even if knowledge or attitudes can be accurately measured,…

Taxi-Out Time Prediction for Departures at Charlotte Airport Using Machine Learning Techniques

Science.gov (United States)

Lee, Hanbong; Malik, Waqar; Jung, Yoon C.

2016-01-01

Predicting the taxi-out times of departures accurately is important for improving airport efficiency and takeoff time predictability. In this paper, we attempt to apply machine learning techniques to actual traffic data at Charlotte Douglas International Airport for taxi-out time prediction. To find the key factors affecting aircraft taxi times, surface surveillance data is first analyzed. From this data analysis, several variables, including terminal concourse, spot, runway, departure fix and weight class, are selected for taxi time prediction. Then, various machine learning methods such as linear regression, support vector machines, k-nearest neighbors, random forest, and neural networks model are applied to actual flight data. Different traffic flow and weather conditions at Charlotte airport are also taken into account for more accurate prediction. The taxi-out time prediction results show that linear regression and random forest techniques can provide the most accurate prediction in terms of root-mean-square errors. We also discuss the operational complexity and uncertainties that make it difficult to predict the taxi times accurately.

Studying depression using imaging and machine learning methods

Directory of Open Access Journals (Sweden)

Meenal J. Patel

2016-01-01

Full Text Available Depression is a complex clinical entity that can pose challenges for clinicians regarding both accurate diagnosis and effective timely treatment. These challenges have prompted the development of multiple machine learning methods to help improve the management of this disease. These methods utilize anatomical and physiological data acquired from neuroimaging to create models that can identify depressed patients vs. non-depressed patients and predict treatment outcomes. This article (1 presents a background on depression, imaging, and machine learning methodologies; (2 reviews methodologies of past studies that have used imaging and machine learning to study depression; and (3 suggests directions for future depression-related studies.

Game-powered machine learning.

Science.gov (United States)

Barrington, Luke; Turnbull, Douglas; Lanckriet, Gert

2012-04-24

Searching for relevant content in a massive amount of multimedia information is facilitated by accurately annotating each image, video, or song with a large number of relevant semantic keywords, or tags. We introduce game-powered machine learning, an integrated approach to annotating multimedia content that combines the effectiveness of human computation, through online games, with the scalability of machine learning. We investigate this framework for labeling music. First, a socially-oriented music annotation game called Herd It collects reliable music annotations based on the "wisdom of the crowds." Second, these annotated examples are used to train a supervised machine learning system. Third, the machine learning system actively directs the annotation games to collect new data that will most benefit future model iterations. Once trained, the system can automatically annotate a corpus of music much larger than what could be labeled using human computation alone. Automatically annotated songs can be retrieved based on their semantic relevance to text-based queries (e.g., "funky jazz with saxophone," "spooky electronica," etc.). Based on the results presented in this paper, we find that actively coupling annotation games with machine learning provides a reliable and scalable approach to making searchable massive amounts of multimedia data.

Keep it Accurate and Diverse

DEFF Research Database (Denmark)

Ali Bagheri, Mohammad; Gao, Qigang; Guerrero, Sergio Escalera

2015-01-01

the performance of an ensemble of action learning techniques, each performing the recognition task from a different per- spective. The underlying idea is that instead of aiming a very sophisticated and powerful representation/learning technique, we can learn action categories using a set of relatively simple...... to improve the recognition perfor- mance, a powerful combination strategy is utilized based on the Dempster-Shafer theory, which can effectively make use of diversity of base learners trained on different sources of information. The recognition results of the individual clas- sifiers are compared with those...... obtained from fusing the classifiers’ output, showing enhanced performance of the proposed methodology....

Constant size descriptors for accurate machine learning models of molecular properties

Science.gov (United States)

Collins, Christopher R.; Gordon, Geoffrey J.; von Lilienfeld, O. Anatole; Yaron, David J.

2018-06-01

Two different classes of molecular representations for use in machine learning of thermodynamic and electronic properties are studied. The representations are evaluated by monitoring the performance of linear and kernel ridge regression models on well-studied data sets of small organic molecules. One class of representations studied here counts the occurrence of bonding patterns in the molecule. These require only the connectivity of atoms in the molecule as may be obtained from a line diagram or a SMILES string. The second class utilizes the three-dimensional structure of the molecule. These include the Coulomb matrix and Bag of Bonds, which list the inter-atomic distances present in the molecule, and Encoded Bonds, which encode such lists into a feature vector whose length is independent of molecular size. Encoded Bonds' features introduced here have the advantage of leading to models that may be trained on smaller molecules and then used successfully on larger molecules. A wide range of feature sets are constructed by selecting, at each rank, either a graph or geometry-based feature. Here, rank refers to the number of atoms involved in the feature, e.g., atom counts are rank 1, while Encoded Bonds are rank 2. For atomization energies in the QM7 data set, the best graph-based feature set gives a mean absolute error of 3.4 kcal/mol. Inclusion of 3D geometry substantially enhances the performance, with Encoded Bonds giving 2.4 kcal/mol, when used alone, and 1.19 kcal/mol, when combined with graph features.

Learning curves in health professions education.

Science.gov (United States)

Pusic, Martin V; Boutis, Kathy; Hatala, Rose; Cook, David A

2015-08-01

Learning curves, which graphically show the relationship between learning effort and achievement, are common in published education research but are not often used in day-to-day educational activities. The purpose of this article is to describe the generation and analysis of learning curves and their applicability to health professions education. The authors argue that the time is right for a closer look at using learning curves-given their desirable properties-to inform both self-directed instruction by individuals and education management by instructors.A typical learning curve is made up of a measure of learning (y-axis), a measure of effort (x-axis), and a mathematical linking function. At the individual level, learning curves make manifest a single person's progress towards competence including his/her rate of learning, the inflection point where learning becomes more effortful, and the remaining distance to mastery attainment. At the group level, overlaid learning curves show the full variation of a group of learners' paths through a given learning domain. Specifically, they make overt the difference between time-based and competency-based approaches to instruction. Additionally, instructors can use learning curve information to more accurately target educational resources to those who most require them.The learning curve approach requires a fine-grained collection of data that will not be possible in all educational settings; however, the increased use of an assessment paradigm that explicitly includes effort and its link to individual achievement could result in increased learner engagement and more effective instructional design.

The Role of Interpretation and Diagnosis in Signal Processing

Science.gov (United States)

1988-01-01

122b. TELEPHONE (Incude Area Code) 2cOFIESYMBOL Elisabeth Colford - RLE Contract Reports I(617)258-5871I DO Form 1473, JUN 84 Previous editions ame...6] S. Lee, E. Milios, R. Greiner , and J. Rossiter. Signal ab- stractions in the machine analysis of radar signals for ice profiling. In International

A theory of causal learning in children: causal maps and Bayes nets.

Science.gov (United States)

Gopnik, Alison; Glymour, Clark; Sobel, David M; Schulz, Laura E; Kushnir, Tamar; Danks, David

2004-01-01

The authors outline a cognitive and computational account of causal learning in children. They propose that children use specialized cognitive systems that allow them to recover an accurate "causal map" of the world: an abstract, coherent, learned representation of the causal relations among events. This kind of knowledge can be perspicuously understood in terms of the formalism of directed graphical causal models, or Bayes nets. Children's causal learning and inference may involve computations similar to those for learning causal Bayes nets and for predicting with them. Experimental results suggest that 2- to 4-year-old children construct new causal maps and that their learning is consistent with the Bayes net formalism.

Recommendation System Based On Association Rules For Distributed E-Learning Management Systems

Science.gov (United States)

Mihai, Gabroveanu

2015-09-01

Traditional Learning Management Systems are installed on a single server where learning materials and user data are kept. To increase its performance, the Learning Management System can be installed on multiple servers; learning materials and user data could be distributed across these servers obtaining a Distributed Learning Management System. In this paper is proposed the prototype of a recommendation system based on association rules for Distributed Learning Management System. Information from LMS databases is analyzed using distributed data mining algorithms in order to extract the association rules. Then the extracted rules are used as inference rules to provide personalized recommendations. The quality of provided recommendations is improved because the rules used to make the inferences are more accurate, since these rules aggregate knowledge from all e-Learning systems included in Distributed Learning Management System.

Computational advantages of reverberating loops for sensorimotor learning.

Science.gov (United States)

Fortney, Kristen; Tweed, Douglas B

2012-03-01

When we learn something new, our brain may store the information in synapses or in reverberating loops of electrical activity, but current theories of motor learning focus almost entirely on the synapses. Here we show that loops could also play a role and would bring advantages: loop-based algorithms can learn complex control tasks faster, with exponentially fewer neurons, and avoid the problem of weight transport. They do all this at a cost: in the presence of long feedback delays, loop algorithms cannot control very fast movements, but in this case, loop and synaptic mechanisms can complement each other-mixed systems quickly learn to make accurate but not very fast motions and then gradually speed up. Loop algorithms explain aspects of consolidation, the role of attention, and the relapses that are sometimes seen after a task has apparently been learned, and they make further predictions.

Deep learning classification in asteroseismology

Science.gov (United States)

Hon, Marc; Stello, Dennis; Yu, Jie

2017-08-01

In the power spectra of oscillating red giants, there are visually distinct features defining stars ascending the red giant branch from those that have commenced helium core burning. We train a 1D convolutional neural network by supervised learning to automatically learn these visual features from images of folded oscillation spectra. By training and testing on Kepler red giants, we achieve an accuracy of up to 99 per cent in separating helium-burning red giants from those ascending the red giant branch. The convolutional neural network additionally shows capability in accurately predicting the evolutionary states of 5379 previously unclassified Kepler red giants, by which we now have greatly increased the number of classified stars.

Machine learning molecular dynamics for the simulation of infrared spectra.

Science.gov (United States)

Gastegger, Michael; Behler, Jörg; Marquetand, Philipp

2017-10-01

Machine learning has emerged as an invaluable tool in many research areas. In the present work, we harness this power to predict highly accurate molecular infrared spectra with unprecedented computational efficiency. To account for vibrational anharmonic and dynamical effects - typically neglected by conventional quantum chemistry approaches - we base our machine learning strategy on ab initio molecular dynamics simulations. While these simulations are usually extremely time consuming even for small molecules, we overcome these limitations by leveraging the power of a variety of machine learning techniques, not only accelerating simulations by several orders of magnitude, but also greatly extending the size of systems that can be treated. To this end, we develop a molecular dipole moment model based on environment dependent neural network charges and combine it with the neural network potential approach of Behler and Parrinello. Contrary to the prevalent big data philosophy, we are able to obtain very accurate machine learning models for the prediction of infrared spectra based on only a few hundreds of electronic structure reference points. This is made possible through the use of molecular forces during neural network potential training and the introduction of a fully automated sampling scheme. We demonstrate the power of our machine learning approach by applying it to model the infrared spectra of a methanol molecule, n -alkanes containing up to 200 atoms and the protonated alanine tripeptide, which at the same time represents the first application of machine learning techniques to simulate the dynamics of a peptide. In all of these case studies we find an excellent agreement between the infrared spectra predicted via machine learning models and the respective theoretical and experimental spectra.

Perceptual learning modifies the functional specializations of visual cortical areas.

Science.gov (United States)

Chen, Nihong; Cai, Peng; Zhou, Tiangang; Thompson, Benjamin; Fang, Fang

2016-05-17

Training can improve performance of perceptual tasks. This phenomenon, known as perceptual learning, is strongest for the trained task and stimulus, leading to a widely accepted assumption that the associated neuronal plasticity is restricted to brain circuits that mediate performance of the trained task. Nevertheless, learning does transfer to other tasks and stimuli, implying the presence of more widespread plasticity. Here, we trained human subjects to discriminate the direction of coherent motion stimuli. The behavioral learning effect substantially transferred to noisy motion stimuli. We used transcranial magnetic stimulation (TMS) and functional magnetic resonance imaging (fMRI) to investigate the neural mechanisms underlying the transfer of learning. The TMS experiment revealed dissociable, causal contributions of V3A (one of the visual areas in the extrastriate visual cortex) and MT+ (middle temporal/medial superior temporal cortex) to coherent and noisy motion processing. Surprisingly, the contribution of MT+ to noisy motion processing was replaced by V3A after perceptual training. The fMRI experiment complemented and corroborated the TMS finding. Multivariate pattern analysis showed that, before training, among visual cortical areas, coherent and noisy motion was decoded most accurately in V3A and MT+, respectively. After training, both kinds of motion were decoded most accurately in V3A. Our findings demonstrate that the effects of perceptual learning extend far beyond the retuning of specific neural populations for the trained stimuli. Learning could dramatically modify the inherent functional specializations of visual cortical areas and dynamically reweight their contributions to perceptual decisions based on their representational qualities. These neural changes might serve as the neural substrate for the transfer of perceptual learning.

Machine learning-based dual-energy CT parametric mapping.

Science.gov (United States)

Su, Kuan-Hao; Kuo, Jung-Wen; Jordan, David W; Van Hedent, Steven; Klahr, Paul; Wei, Zhouping; Al Helo, Rose; Liang, Fan; Qian, Pengjiang; Pereira, Gisele C; Rassouli, Negin; Gilkeson, Robert C; Traughber, Bryan J; Cheng, Chee-Wai; Muzic, Raymond F

2018-05-22

The aim is to develop and evaluate machine learning methods for generating quantitative parametric maps of effective atomic number (Z_eff), relative electron density (ρ_e), mean excitation energy (I_x), and relative stopping power (RSP) from clinical dual-energy CT data. The maps could be used for material identification and radiation dose calculation. Machine learning methods of historical centroid (HC), random forest (RF), and artificial neural networks (ANN) were used to learn the relationship between dual-energy CT input data and ideal output parametric maps calculated for phantoms from the known compositions of 13 tissue substitutes. After training and model selection steps, the machine learning predictors were used to generate parametric maps from independent phantom and patient input data. Precision and accuracy were evaluated using the ideal maps. This process was repeated for a range of exposure doses, and performance was compared to that of the clinically-used dual-energy, physics-based method which served as the reference. The machine learning methods generated more accurate and precise parametric maps than those obtained using the reference method. Their performance advantage was particularly evident when using data from the lowest exposure, one-fifth of a typical clinical abdomen CT acquisition. The RF method achieved the greatest accuracy. In comparison, the ANN method was only 1% less accurate but had much better computational efficiency than RF, being able to produce parametric maps in 15 seconds. Machine learning methods outperformed the reference method in terms of accuracy and noise tolerance when generating parametric maps, encouraging further exploration of the techniques. Among the methods we evaluated, ANN is the most suitable for clinical use due to its combination of accuracy, excellent low-noise performance, and computational efficiency. . © 2018 Institute of Physics and Engineering in

Machine learning to analyze images of shocked materials for precise and accurate measurements

Energy Technology Data Exchange (ETDEWEB)

Dresselhaus-Cooper, Leora; Howard, Marylesa; Hock, Margaret C.; Meehan, B. T.; Ramos, Kyle J.; Bolme, Cindy A.; Sandberg, Richard L.; Nelson, Keith A.

2017-09-14

A supervised machine learning algorithm, called locally adaptive discriminant analysis (LADA), has been developed to locate boundaries between identifiable image features that have varying intensities. LADA is an adaptation of image segmentation, which includes techniques that find the positions of image features (classes) using statistical intensity distributions for each class in the image. In order to place a pixel in the proper class, LADA considers the intensity at that pixel and the distribution of intensities in local (nearby) pixels. This paper presents the use of LADA to provide, with statistical uncertainties, the positions and shapes of features within ultrafast images of shock waves. We demonstrate the ability to locate image features including crystals, density changes associated with shock waves, and material jetting caused by shock waves. This algorithm can analyze images that exhibit a wide range of physical phenomena because it does not rely on comparison to a model. LADA enables analysis of images from shock physics with statistical rigor independent of underlying models or simulations.

Application of parsimonious learning feedforward control to mechatronic systems

NARCIS (Netherlands)

de Vries, Theodorus J.A.; Velthuis, W.J.R.; Idema, L.J.

2001-01-01

For motion control, learning feedforward controllers (LFFCs) should be applied when accurate process modelling is difficult. When controlling such processes with LFFCs in the form of multidimensional B-spline networks, large network sizes and a poor generalising ability may result, known as the

A Comparative Analysis of Machine Learning Techniques for Credit Scoring

OpenAIRE

Nwulu, Nnamdi; Oroja, Shola; İlkan, Mustafa

2012-01-01

Abstract Credit Scoring has become an oft researched topic in light of the increasing volatility of the global economy and the recent world financial crisis. Amidst the many methods used for credit scoring, machine learning techniques are becoming increasingly popular due to their efficient and accurate nature and relative simplicity. Furthermore machine learning techniques minimize the risk of human bias and error and maximize speed as they are able to perform computation...

Accurate Fall Detection in a Top View Privacy Preserving Configuration.

Science.gov (United States)

Ricciuti, Manola; Spinsante, Susanna; Gambi, Ennio

2018-05-29

Fall detection is one of the most investigated themes in the research on assistive solutions for aged people. In particular, a false-alarm-free discrimination between falls and non-falls is indispensable, especially to assist elderly people living alone. Current technological solutions designed to monitor several types of activities in indoor environments can guarantee absolute privacy to the people that decide to rely on them. Devices integrating RGB and depth cameras, such as the Microsoft Kinect, can ensure privacy and anonymity, since the depth information is considered to extract only meaningful information from video streams. In this paper, we propose an accurate fall detection method investigating the depth frames of the human body using a single device in a top-view configuration, with the subjects located under the device inside a room. Features extracted from depth frames train a classifier based on a binary support vector machine learning algorithm. The dataset includes 32 falls and 8 activities considered for comparison, for a total of 800 sequences performed by 20 adults. The system showed an accuracy of 98.6% and only one false positive.

Active learning for noisy oracle via density power divergence.

Science.gov (United States)

Sogawa, Yasuhiro; Ueno, Tsuyoshi; Kawahara, Yoshinobu; Washio, Takashi

2013-10-01

The accuracy of active learning is critically influenced by the existence of noisy labels given by a noisy oracle. In this paper, we propose a novel pool-based active learning framework through robust measures based on density power divergence. By minimizing density power divergence, such as β-divergence and γ-divergence, one can estimate the model accurately even under the existence of noisy labels within data. Accordingly, we develop query selecting measures for pool-based active learning using these divergences. In addition, we propose an evaluation scheme for these measures based on asymptotic statistical analyses, which enables us to perform active learning by evaluating an estimation error directly. Experiments with benchmark datasets and real-world image datasets show that our active learning scheme performs better than several baseline methods. Copyright © 2013 Elsevier Ltd. All rights reserved.

Less is more: regularization perspectives on large scale machine learning

CERN Multimedia

CERN. Geneva

2017-01-01

Deep learning based techniques provide a possible solution at the expanse of theoretical guidance and, especially, of computational requirements. It is then a key challenge for large scale machine learning to devise approaches guaranteed to be accurate and yet computationally efficient. In this talk, we will consider a regularization perspectives on machine learning appealing to classical ideas in linear algebra and inverse problems to scale-up dramatically nonparametric methods such as kernel methods, often dismissed because of prohibitive costs. Our analysis derives optimal theoretical guarantees while providing experimental results at par or out-performing state of the art approaches.

A Learning Method for Neural Networks Based on a Pseudoinverse Technique

Directory of Open Access Journals (Sweden)

Chinmoy Pal

1996-01-01

Full Text Available A theoretical formulation of a fast learning method based on a pseudoinverse technique is presented. The efficiency and robustness of the method are verified with the help of an Exclusive OR problem and a dynamic system identification of a linear single degree of freedom mass–spring problem. It is observed that, compared with the conventional backpropagation method, the proposed method has a better convergence rate and a higher degree of learning accuracy with a lower equivalent learning coefficient. It is also found that unlike the steepest descent method, the learning capability of which is dependent on the value of the learning coefficient ν, the proposed pseudoinverse based backpropagation algorithm is comparatively robust with respect to its equivalent variable learning coefficient. A combination of the pseudoinverse method and the steepest descent method is proposed for a faster, more accurate learning capability.

Development of a machine learning potential for graphene

Science.gov (United States)

Rowe, Patrick; Csányi, Gábor; Alfè, Dario; Michaelides, Angelos

2018-02-01

We present an accurate interatomic potential for graphene, constructed using the Gaussian approximation potential (GAP) machine learning methodology. This GAP model obtains a faithful representation of a density functional theory (DFT) potential energy surface, facilitating highly accurate (approaching the accuracy of ab initio methods) molecular dynamics simulations. This is achieved at a computational cost which is orders of magnitude lower than that of comparable calculations which directly invoke electronic structure methods. We evaluate the accuracy of our machine learning model alongside that of a number of popular empirical and bond-order potentials, using both experimental and ab initio data as references. We find that whilst significant discrepancies exist between the empirical interatomic potentials and the reference data—and amongst the empirical potentials themselves—the machine learning model introduced here provides exemplary performance in all of the tested areas. The calculated properties include: graphene phonon dispersion curves at 0 K (which we predict with sub-meV accuracy), phonon spectra at finite temperature, in-plane thermal expansion up to 2500 K as compared to NPT ab initio molecular dynamics simulations and a comparison of the thermally induced dispersion of graphene Raman bands to experimental observations. We have made our potential freely available online at [http://www.libatoms.org].

Bypassing the Kohn-Sham equations with machine learning.

Science.gov (United States)

Brockherde, Felix; Vogt, Leslie; Li, Li; Tuckerman, Mark E; Burke, Kieron; Müller, Klaus-Robert

2017-10-11

Last year, at least 30,000 scientific papers used the Kohn-Sham scheme of density functional theory to solve electronic structure problems in a wide variety of scientific fields. Machine learning holds the promise of learning the energy functional via examples, bypassing the need to solve the Kohn-Sham equations. This should yield substantial savings in computer time, allowing larger systems and/or longer time-scales to be tackled, but attempts to machine-learn this functional have been limited by the need to find its derivative. The present work overcomes this difficulty by directly learning the density-potential and energy-density maps for test systems and various molecules. We perform the first molecular dynamics simulation with a machine-learned density functional on malonaldehyde and are able to capture the intramolecular proton transfer process. Learning density models now allows the construction of accurate density functionals for realistic molecular systems.Machine learning allows electronic structure calculations to access larger system sizes and, in dynamical simulations, longer time scales. Here, the authors perform such a simulation using a machine-learned density functional that avoids direct solution of the Kohn-Sham equations.

Machine learning in the string landscape

Science.gov (United States)

Carifio, Jonathan; Halverson, James; Krioukov, Dmitri; Nelson, Brent D.

2017-09-01

We utilize machine learning to study the string landscape. Deep data dives and conjecture generation are proposed as useful frameworks for utilizing machine learning in the landscape, and examples of each are presented. A decision tree accurately predicts the number of weak Fano toric threefolds arising from reflexive polytopes, each of which determines a smooth F-theory compactification, and linear regression generates a previously proven conjecture for the gauge group rank in an ensemble of 4/3× 2.96× {10}^{755} F-theory compactifications. Logistic regression generates a new conjecture for when E 6 arises in the large ensemble of F-theory compactifications, which is then rigorously proven. This result may be relevant for the appearance of visible sectors in the ensemble. Through conjecture generation, machine learning is useful not only for numerics, but also for rigorous results.

Cerebellar motor learning: when is cortical plasticity not enough?

Directory of Open Access Journals (Sweden)

John Porrill

2007-10-01

Full Text Available Classical Marr-Albus theories of cerebellar learning employ only cortical sites of plasticity. However, tests of these theories using adaptive calibration of the vestibulo-ocular reflex (VOR have indicated plasticity in both cerebellar cortex and the brainstem. To resolve this long-standing conflict, we attempted to identify the computational role of the brainstem site, by using an adaptive filter version of the cerebellar microcircuit to model VOR calibration for changes in the oculomotor plant. With only cortical plasticity, introducing a realistic delay in the retinal-slip error signal of 100 ms prevented learning at frequencies higher than 2.5 Hz, although the VOR itself is accurate up to at least 25 Hz. However, the introduction of an additional brainstem site of plasticity, driven by the correlation between cerebellar and vestibular inputs, overcame the 2.5 Hz limitation and allowed learning of accurate high-frequency gains. This "cortex-first" learning mechanism is consistent with a wide variety of evidence concerning the role of the flocculus in VOR calibration, and complements rather than replaces the previously proposed "brainstem-first" mechanism that operates when ocular tracking mechanisms are effective. These results (i describe a process whereby information originally learnt in one area of the brain (cerebellar cortex can be transferred and expressed in another (brainstem, and (ii indicate for the first time why a brainstem site of plasticity is actually required by Marr-Albus type models when high-frequency gains must be learned in the presence of error delay.

Machine-Learning-Based Electronic Triage More Accurately Differentiates Patients With Respect to Clinical Outcomes Compared With the Emergency Severity Index.

Science.gov (United States)

Levin, Scott; Toerper, Matthew; Hamrock, Eric; Hinson, Jeremiah S; Barnes, Sean; Gardner, Heather; Dugas, Andrea; Linton, Bob; Kirsch, Tom; Kelen, Gabor

2018-05-01

Standards for emergency department (ED) triage in the United States rely heavily on subjective assessment and are limited in their ability to risk-stratify patients. This study seeks to evaluate an electronic triage system (e-triage) based on machine learning that predicts likelihood of acute outcomes enabling improved patient differentiation. A multisite, retrospective, cross-sectional study of 172,726 ED visits from urban and community EDs was conducted. E-triage is composed of a random forest model applied to triage data (vital signs, chief complaint, and active medical history) that predicts the need for critical care, an emergency procedure, and inpatient hospitalization in parallel and translates risk to triage level designations. Predicted outcomes and secondary outcomes of elevated troponin and lactate levels were evaluated and compared with the Emergency Severity Index (ESI). E-triage predictions had an area under the curve ranging from 0.73 to 0.92 and demonstrated equivalent or improved identification of clinical patient outcomes compared with ESI at both EDs. E-triage provided rationale for risk-based differentiation of the more than 65% of ED visits triaged to ESI level 3. Matching the ESI patient distribution for comparisons, e-triage identified more than 10% (14,326 patients) of ESI level 3 patients requiring up triage who had substantially increased risk of critical care or emergency procedure (1.7% ESI level 3 versus 6.2% up triaged) and hospitalization (18.9% versus 45.4%) across EDs. E-triage more accurately classifies ESI level 3 patients and highlights opportunities to use predictive analytics to support triage decisionmaking. Further prospective validation is needed. Copyright © 2017 American College of Emergency Physicians. Published by Elsevier Inc. All rights reserved.

Fast learning method for convolutional neural networks using extreme learning machine and its application to lane detection.

Science.gov (United States)

Kim, Jihun; Kim, Jonghong; Jang, Gil-Jin; Lee, Minho

2017-03-01

Deep learning has received significant attention recently as a promising solution to many problems in the area of artificial intelligence. Among several deep learning architectures, convolutional neural networks (CNNs) demonstrate superior performance when compared to other machine learning methods in the applications of object detection and recognition. We use a CNN for image enhancement and the detection of driving lanes on motorways. In general, the process of lane detection consists of edge extraction and line detection. A CNN can be used to enhance the input images before lane detection by excluding noise and obstacles that are irrelevant to the edge detection result. However, training conventional CNNs requires considerable computation and a big dataset. Therefore, we suggest a new learning algorithm for CNNs using an extreme learning machine (ELM). The ELM is a fast learning method used to calculate network weights between output and hidden layers in a single iteration and thus, can dramatically reduce learning time while producing accurate results with minimal training data. A conventional ELM can be applied to networks with a single hidden layer; as such, we propose a stacked ELM architecture in the CNN framework. Further, we modify the backpropagation algorithm to find the targets of hidden layers and effectively learn network weights while maintaining performance. Experimental results confirm that the proposed method is effective in reducing learning time and improving performance. Copyright © 2016 Elsevier Ltd. All rights reserved.

Skill learning from kinesthetic feedback.

Science.gov (United States)

Pinzon, David; Vega, Roberto; Sanchez, Yerly Paola; Zheng, Bin

2017-10-01

It is important for a surgeon to perform surgical tasks under appropriate guidance from visual and kinesthetic feedback. However, our knowledge on kinesthetic (muscle) memory and its role in learning motor skills remains elementary. To discover the effect of exclusive kinesthetic training on kinesthetic memory in both performance and learning. In Phase 1, a total of twenty participants duplicated five 2 dimensional movements of increasing complexity via passive kinesthetic guidance, without visual or auditory stimuli. Five participants were asked to repeat the task in the Phase 2 over a period of three weeks, for a total of nine sessions. Subjects accurately recalled movement direction using kinesthetic memory, but recalling movement length was less precise. Over the nine training sessions, error occurrence dropped after the sixth session. Muscle memory constructs the foundation for kinesthetic training. Knowledge gained helps surgeons learn skills from kinesthetic information in the condition where visual feedback is limited. Copyright © 2016 Elsevier Inc. All rights reserved.

An e-learning Programming Method And It's Implementation Based On Multimedia And Web

International Nuclear Information System (INIS)

Madenda, Sarifuddin; Tommy, F. R.

2001-01-01

New developments in information technology and telecommunication play an important rile in exchanging fast and accurate information which range from text, sound, graphic to video. These technologies seem to be very effective for Distance learning, Virtual University and E-learning. This paper presents an E-learning programming method and it's implementation based on multimedia and Web. An example of the study case corresponds to human organ, where the organ functions are presented as texts and sounds and the activities as graphic and video

A new model with an anatomically accurate human renal collecting system for training in fluoroscopy-guided percutaneous nephrolithotomy access.

Science.gov (United States)

Turney, Benjamin W

2014-03-01

Obtaining renal access is one of the most important and complex steps in learning percutaneous nephrolithotomy (PCNL). Ideally, this skill should be practiced outside the operating room. There is a need for anatomically accurate and cheap models for simulated training. The objective was to develop a cost-effective, anatomically accurate, nonbiologic training model for simulated PCNL access under fluoroscopic guidance. Collecting systems from routine computed tomography urograms were extracted and reformatted using specialized software. These images were printed in a water-soluble plastic on a three-dimensional (3D) printer to create biomodels. These models were embedded in silicone and then the models were dissolved in water to leave a hollow collecting system within a silicone model. These PCNL models were filled with contrast medium and sealed. A layer of dense foam acted as a spacer to replicate the tissues between skin and kidney. 3D printed models of human collecting systems are a useful adjunct in planning PCNL access. The PCNL access training model is relatively low cost and reproduces the anatomy of the renal collecting system faithfully. A range of models reflecting the variety and complexity of human collecting systems can be reproduced. The fluoroscopic triangulation process needed to target the calix of choice can be practiced successfully in this model. This silicone PCNL training model accurately replicates the anatomic architecture and orientation of the human renal collecting system. It provides a safe, clean, and effective model for training in accurate fluoroscopy-guided PCNL access.

The Sense of Confidence during Probabilistic Learning: A Normative Account.

Directory of Open Access Journals (Sweden)

Florent Meyniel

2015-06-01

Full Text Available Learning in a stochastic environment consists of estimating a model from a limited amount of noisy data, and is therefore inherently uncertain. However, many classical models reduce the learning process to the updating of parameter estimates and neglect the fact that learning is also frequently accompanied by a variable "feeling of knowing" or confidence. The characteristics and the origin of these subjective confidence estimates thus remain largely unknown. Here we investigate whether, during learning, humans not only infer a model of their environment, but also derive an accurate sense of confidence from their inferences. In our experiment, humans estimated the transition probabilities between two visual or auditory stimuli in a changing environment, and reported their mean estimate and their confidence in this report. To formalize the link between both kinds of estimate and assess their accuracy in comparison to a normative reference, we derive the optimal inference strategy for our task. Our results indicate that subjects accurately track the likelihood that their inferences are correct. Learning and estimating confidence in what has been learned appear to be two intimately related abilities, suggesting that they arise from a single inference process. We show that human performance matches several properties of the optimal probabilistic inference. In particular, subjective confidence is impacted by environmental uncertainty, both at the first level (uncertainty in stimulus occurrence given the inferred stochastic characteristics and at the second level (uncertainty due to unexpected changes in these stochastic characteristics. Confidence also increases appropriately with the number of observations within stable periods. Our results support the idea that humans possess a quantitative sense of confidence in their inferences about abstract non-sensory parameters of the environment. This ability cannot be reduced to simple heuristics, it seems

Towards Robust and Accurate Multi-View and Partially-Occluded Face Alignment.

Science.gov (United States)

Xing, Junliang; Niu, Zhiheng; Huang, Junshi; Hu, Weiming; Zhou, Xi; Yan, Shuicheng

2018-04-01

Face alignment acts as an important task in computer vision. Regression-based methods currently dominate the approach to solving this problem, which generally employ a series of mapping functions from the face appearance to iteratively update the face shape hypothesis. One keypoint here is thus how to perform the regression procedure. In this work, we formulate this regression procedure as a sparse coding problem. We learn two relational dictionaries, one for the face appearance and the other one for the face shape, with coupled reconstruction coefficient to capture their underlying relationships. To deploy this model for face alignment, we derive the relational dictionaries in a stage-wised manner to perform close-loop refinement of themselves, i.e., the face appearance dictionary is first learned from the face shape dictionary and then used to update the face shape hypothesis, and the updated face shape dictionary from the shape hypothesis is in return used to refine the face appearance dictionary. To improve the model accuracy, we extend this model hierarchically from the whole face shape to face part shapes, thus both the global and local view variations of a face are captured. To locate facial landmarks under occlusions, we further introduce an occlusion dictionary into the face appearance dictionary to recover face shape from partially occluded face appearance. The occlusion dictionary is learned in a data driven manner from background images to represent a set of elemental occlusion patterns, a sparse combination of which models various practical partial face occlusions. By integrating all these technical innovations, we obtain a robust and accurate approach to locate facial landmarks under different face views and possibly severe occlusions for face images in the wild. Extensive experimental analyses and evaluations on different benchmark datasets, as well as two new datasets built by ourselves, have demonstrated the robustness and accuracy of our proposed

Machine learning versus knowledge based classification of legal texts

NARCIS (Netherlands)

de Maat, E.; Krabben, K.; Winkels, R.; Winkels, R.G.F.

2010-01-01

This paper presents results of an experiment in which we used machine learning (ML) techniques to classify sentences in Dutch legislation. These results are compared to the results of a pattern-based classifier. Overall, the ML classifier performs as accurate (>90%) as the pattern based one, but

Decentralized indirect methods for learning automata games.

Science.gov (United States)

Tilak, Omkar; Martin, Ryan; Mukhopadhyay, Snehasis

2011-10-01

We discuss the application of indirect learning methods in zero-sum and identical payoff learning automata games. We propose a novel decentralized version of the well-known pursuit learning algorithm. Such a decentralized algorithm has significant computational advantages over its centralized counterpart. The theoretical study of such a decentralized algorithm requires the analysis to be carried out in a nonstationary environment. We use a novel bootstrapping argument to prove the convergence of the algorithm. To our knowledge, this is the first time that such analysis has been carried out for zero-sum and identical payoff games. Extensive simulation studies are reported, which demonstrate the proposed algorithm's fast and accurate convergence in a variety of game scenarios. We also introduce the framework of partial communication in the context of identical payoff games of learning automata. In such games, the automata may not communicate with each other or may communicate selectively. This comprehensive framework has the capability to model both centralized and decentralized games discussed in this paper.

A Human/Computer Learning Network to Improve Biodiversity Conservation and Research

OpenAIRE

Kelling, Steve; Gerbracht, Jeff; Fink, Daniel; Lagoze, Carl; Wong, Weng-Keen; Yu, Jun; Damoulas, Theodoros; Gomes, Carla

2012-01-01

In this paper we describe eBird, a citizen-science project that takes advantage of the human observational capacity to identify birds to species, which is then used to accurately represent patterns of bird occurrences across broad spatial and temporal extents. eBird employs artificial intelligence techniques such as machine learning to improve data quality by taking advantage of the synergies between human computation and mechanical computation. We call this a Human-Computer Learning Network,...

Classification of carcinogenic and mutagenic properties using machine learning method

DEFF Research Database (Denmark)

Moorthy, N. S.Hari Narayana; Kumar, Surendra; Poongavanam, Vasanthanathan

2017-01-01

An accurate calculation of carcinogenicity of chemicals became a serious challenge for the health assessment authority around the globe because of not only increased cost for experiments but also various ethical issues exist using animal models. In this study, we provide machine learning...

Accurate and Simple Calibration of DLP Projector Systems

DEFF Research Database (Denmark)

Wilm, Jakob; Olesen, Oline Vinter; Larsen, Rasmus

2014-01-01

does not rely on an initial camera calibration, and so does not carry over the error into projector calibration. A radial interpolation scheme is used to convert features coordinates into projector space, thereby allowing for a very accurate procedure. This allows for highly accurate determination...

Deep Learning for Brain MRI Segmentation: State of the Art and Future Directions.

Science.gov (United States)

Akkus, Zeynettin; Galimzianova, Alfiia; Hoogi, Assaf; Rubin, Daniel L; Erickson, Bradley J

2017-08-01

Quantitative analysis of brain MRI is routine for many neurological diseases and conditions and relies on accurate segmentation of structures of interest. Deep learning-based segmentation approaches for brain MRI are gaining interest due to their self-learning and generalization ability over large amounts of data. As the deep learning architectures are becoming more mature, they gradually outperform previous state-of-the-art classical machine learning algorithms. This review aims to provide an overview of current deep learning-based segmentation approaches for quantitative brain MRI. First we review the current deep learning architectures used for segmentation of anatomical brain structures and brain lesions. Next, the performance, speed, and properties of deep learning approaches are summarized and discussed. Finally, we provide a critical assessment of the current state and identify likely future developments and trends.

CircleBoard-Pro: Concrete manipulative-based learning cycle unit for learning geometry

Science.gov (United States)

Jamhari, Wongkia, Wararat

2018-01-01

Currently, a manipulative is commonly used in mathematics education as a supported tool for teaching and learning. With engaging natural interaction of a concrete manipulative and advantages of a learning cycle approach, we proposed the concrete manipulative-based learning cycle unit to promote mathematics learning. Our main objectives are to observe possibilities on the use of a concrete manipulative in learning geometry, and to assess students' understanding of a specific topic, angle properties in a circle, of secondary level students. To meet the first objective, the concrete manipulative, called CricleBoard-Pro, was designed. CircleBoard-Pro is built for easy to writing on or deleting from, accurate angle measurement, and flexible movement. Besides, learning activities and worksheets were created for helping students to learn angle properties in a circle. Twenty eighth graders on a lower secondary school in Indonesia were voluntarily involved to learn mathematics using CircleBoard-Pro with the designed learning activities and worksheets. We informally observed students' performance by focusing on criteria of using manipulative tools in learning mathematics while the learning activities were also observed in terms of whether they work and which step of activities need to be improved. The results of this part showed that CircleBoard-Pro complied the criteria of the use of the manipulative in learning mathematics. Nevertheless, parts of learning activities and worksheets need to be improved. Based on the results of the observation, CircleBoard-Pro, learning activities, and worksheets were merged together and became the CircleBoardPro embedded on 5E (Engage - Explore - Explain - Elaborate - Evaluate) learning cycle unit. Then, students understanding were assessed to reach the second objective. Six ninth graders from an Indonesian school in Thailand were recruited to participate in this study. Conceptual tests for both pre-and post-test, and semi

Highly accurate surface maps from profilometer measurements

Science.gov (United States)

Medicus, Kate M.; Nelson, Jessica D.; Mandina, Mike P.

2013-04-01

Many aspheres and free-form optical surfaces are measured using a single line trace profilometer which is limiting because accurate 3D corrections are not possible with the single trace. We show a method to produce an accurate fully 2.5D surface height map when measuring a surface with a profilometer using only 6 traces and without expensive hardware. The 6 traces are taken at varying angular positions of the lens, rotating the part between each trace. The output height map contains low form error only, the first 36 Zernikes. The accuracy of the height map is ±10% of the actual Zernike values and within ±3% of the actual peak to valley number. The calculated Zernike values are affected by errors in the angular positioning, by the centering of the lens, and to a small effect, choices made in the processing algorithm. We have found that the angular positioning of the part should be better than 1?, which is achievable with typical hardware. The centering of the lens is essential to achieving accurate measurements. The part must be centered to within 0.5% of the diameter to achieve accurate results. This value is achievable with care, with an indicator, but the part must be edged to a clean diameter.

Location-based language learning for migrants in a smart city

OpenAIRE

Gaved, Mark; Peasgood, Alice

2015-01-01

The SALSA (Sensors and Apps for Languages in Smart Areas) project, a winner of the Open University’s MK:Smart Open Challenge awards, is investigating how a smart city infrastructure can enable the provision of highly accurate, location-based learning activities for language learners, particularly recent migrants who have a real need to learn the language of their new home. \\ud \\ud Second language acquisition is perceived by adult migrants themselves, as well as host governments, “as a crucial...

[Specific learning disabilities - from DSM-IV to DSM-5].

Science.gov (United States)

Schulte-Körne, Gerd

2014-09-01

The publication of the DSM-5 means changes in the classification and recommendations for diagnosis of specific learning disabilities. Dyslexia and dyscalculia have been reintroduced into the DSM. Three specific learning disorders - impairment in reading, impairment in the written expression, and impairment in mathematics, described by subskills - are now part of the DSM-5. Three subcomponents of the reading disorder are expressly differentiated: word reading accuracy, reading rate, and fluency and reading comprehension. Impaired subskills of the specific learning disorder with impairment in written expression are spelling accuracy, grammar and punctuation accuracy, and clarity and organization of written expression. Four subskills are found in the mathematics disorder: number sense, memorization of arithmetic facts, accurate or fluent calculation, and accurate math reasoning. Each impaired academic domain and subskill should be recorded. A description of the severity degree was also included. The diagnosis is based on a variety of methods, including medical history, clinical interview, school report, teacher evaluation, rating scales, and psychometric tests. The IQ discrepancy criterion was abandoned, though that of age or class discrepancy criterion was retained. The application of a discrepancy is recommended by 1 to 2.5 SD. All three specific developmental disorders are common (prevalence 5 %-15 %), occur early during the first years of formal schooling, and persist into adulthood.

XenoSite: accurately predicting CYP-mediated sites of metabolism with neural networks.

Science.gov (United States)

Zaretzki, Jed; Matlock, Matthew; Swamidass, S Joshua

2013-12-23

Understanding how xenobiotic molecules are metabolized is important because it influences the safety, efficacy, and dose of medicines and how they can be modified to improve these properties. The cytochrome P450s (CYPs) are proteins responsible for metabolizing 90% of drugs on the market, and many computational methods can predict which atomic sites of a molecule--sites of metabolism (SOMs)--are modified during CYP-mediated metabolism. This study improves on prior methods of predicting CYP-mediated SOMs by using new descriptors and machine learning based on neural networks. The new method, XenoSite, is faster to train and more accurate by as much as 4% or 5% for some isozymes. Furthermore, some "incorrect" predictions made by XenoSite were subsequently validated as correct predictions by revaluation of the source literature. Moreover, XenoSite output is interpretable as a probability, which reflects both the confidence of the model that a particular atom is metabolized and the statistical likelihood that its prediction for that atom is correct.

Learning-based stochastic object models for characterizing anatomical variations

Science.gov (United States)

Dolly, Steven R.; Lou, Yang; Anastasio, Mark A.; Li, Hua

2018-03-01

It is widely known that the optimization of imaging systems based on objective, task-based measures of image quality via computer-simulation requires the use of a stochastic object model (SOM). However, the development of computationally tractable SOMs that can accurately model the statistical variations in human anatomy within a specified ensemble of patients remains a challenging task. Previously reported numerical anatomic models lack the ability to accurately model inter-patient and inter-organ variations in human anatomy among a broad patient population, mainly because they are established on image data corresponding to a few of patients and individual anatomic organs. This may introduce phantom-specific bias into computer-simulation studies, where the study result is heavily dependent on which phantom is used. In certain applications, however, databases of high-quality volumetric images and organ contours are available that can facilitate this SOM development. In this work, a novel and tractable methodology for learning a SOM and generating numerical phantoms from a set of volumetric training images is developed. The proposed methodology learns geometric attribute distributions (GAD) of human anatomic organs from a broad patient population, which characterize both centroid relationships between neighboring organs and anatomic shape similarity of individual organs among patients. By randomly sampling the learned centroid and shape GADs with the constraints of the respective principal attribute variations learned from the training data, an ensemble of stochastic objects can be created. The randomness in organ shape and position reflects the learned variability of human anatomy. To demonstrate the methodology, a SOM of an adult male pelvis is computed and examples of corresponding numerical phantoms are created.

Self-learning Monte Carlo with deep neural networks

Science.gov (United States)

Shen, Huitao; Liu, Junwei; Fu, Liang

2018-05-01

The self-learning Monte Carlo (SLMC) method is a general algorithm to speedup MC simulations. Its efficiency has been demonstrated in various systems by introducing an effective model to propose global moves in the configuration space. In this paper, we show that deep neural networks can be naturally incorporated into SLMC, and without any prior knowledge can learn the original model accurately and efficiently. Demonstrated in quantum impurity models, we reduce the complexity for a local update from O (β2) in Hirsch-Fye algorithm to O (β lnβ ) , which is a significant speedup especially for systems at low temperatures.

Reverse inference of memory retrieval processes underlying metacognitive monitoring of learning using multivariate pattern analysis.

Science.gov (United States)

Stiers, Peter; Falbo, Luciana; Goulas, Alexandros; van Gog, Tamara; de Bruin, Anique

2016-05-15

Monitoring of learning is only accurate at some time after learning. It is thought that immediate monitoring is based on working memory, whereas later monitoring requires re-activation of stored items, yielding accurate judgements. Such interpretations are difficult to test because they require reverse inference, which presupposes specificity of brain activity for the hidden cognitive processes. We investigated whether multivariate pattern classification can provide this specificity. We used a word recall task to create single trial examples of immediate and long term retrieval and trained a learning algorithm to discriminate them. Next, participants performed a similar task involving monitoring instead of recall. The recall-trained classifier recognized the retrieval patterns underlying immediate and long term monitoring and classified delayed monitoring examples as long-term retrieval. This result demonstrates the feasibility of decoding cognitive processes, instead of their content. Copyright © 2016 Elsevier Inc. All rights reserved.

Machine Learning for Optical Performance Monitoring from Directly Detected PDM-QAM Signals

DEFF Research Database (Denmark)

Wass, J.; Thrane, Jakob; Piels, Molly

2016-01-01

Supervised machine learning methods are applied and demonstrated experimentally for inband OSNR estimation and modulation format classification in optical communication systems. The proposed methods accurately evaluate coherent signals up to 64QAM using only intensity information....

Study on process evaluation model of students' learning in practical course

Science.gov (United States)

Huang, Jie; Liang, Pei; Shen, Wei-min; Ye, Youxiang

2017-08-01

In practical course teaching based on project object method, the traditional evaluation methods include class attendance, assignments and exams fails to give incentives to undergraduate students to learn innovatively and autonomously. In this paper, the element such as creative innovation, teamwork, document and reporting were put into process evaluation methods, and a process evaluation model was set up. Educational practice shows that the evaluation model makes process evaluation of students' learning more comprehensive, accurate, and fairly.

Managing Student Learning: Schools as Multipliers of Intangible Resources

Science.gov (United States)

Paletta, Angelo

2011-01-01

The conceptual categories that underlie the business analysis of intellectual capital are relevant to providing an explanation of school performance. By gathering data on student learning, this research provides empirical evidence for the use of school results as an accurate indicator of the effectiveness of the management of public education.…

Automatic Earthquake Detection by Active Learning

Science.gov (United States)

Bergen, K.; Beroza, G. C.

2017-12-01

In recent years, advances in machine learning have transformed fields such as image recognition, natural language processing and recommender systems. Many of these performance gains have relied on the availability of large, labeled data sets to train high-accuracy models; labeled data sets are those for which each sample includes a target class label, such as waveforms tagged as either earthquakes or noise. Earthquake seismologists are increasingly leveraging machine learning and data mining techniques to detect and analyze weak earthquake signals in large seismic data sets. One of the challenges in applying machine learning to seismic data sets is the limited labeled data problem; learning algorithms need to be given examples of earthquake waveforms, but the number of known events, taken from earthquake catalogs, may be insufficient to build an accurate detector. Furthermore, earthquake catalogs are known to be incomplete, resulting in training data that may be biased towards larger events and contain inaccurate labels. This challenge is compounded by the class imbalance problem; the events of interest, earthquakes, are infrequent relative to noise in continuous data sets, and many learning algorithms perform poorly on rare classes. In this work, we investigate the use of active learning for automatic earthquake detection. Active learning is a type of semi-supervised machine learning that uses a human-in-the-loop approach to strategically supplement a small initial training set. The learning algorithm incorporates domain expertise through interaction between a human expert and the algorithm, with the algorithm actively posing queries to the user to improve detection performance. We demonstrate the potential of active machine learning to improve earthquake detection performance with limited available training data.

Accurate Identification of Fatty Liver Disease in Data Warehouse Utilizing Natural Language Processing.

Science.gov (United States)

Redman, Joseph S; Natarajan, Yamini; Hou, Jason K; Wang, Jingqi; Hanif, Muzammil; Feng, Hua; Kramer, Jennifer R; Desiderio, Roxanne; Xu, Hua; El-Serag, Hashem B; Kanwal, Fasiha

2017-10-01

Natural language processing is a powerful technique of machine learning capable of maximizing data extraction from complex electronic medical records. We utilized this technique to develop algorithms capable of "reading" full-text radiology reports to accurately identify the presence of fatty liver disease. Abdominal ultrasound, computerized tomography, and magnetic resonance imaging reports were retrieved from the Veterans Affairs Corporate Data Warehouse from a random national sample of 652 patients. Radiographic fatty liver disease was determined by manual review by two physicians and verified with an expert radiologist. A split validation method was utilized for algorithm development. For all three imaging modalities, the algorithms could identify fatty liver disease with >90% recall and precision, with F-measures >90%. These algorithms could be used to rapidly screen patient records to establish a large cohort to facilitate epidemiological and clinical studies and examine the clinic course and outcomes of patients with radiographic hepatic steatosis.

Learning Local Components to Understand Large Bayesian Networks

DEFF Research Database (Denmark)

Zeng, Yifeng; Xiang, Yanping; Cordero, Jorge

2009-01-01

(domain experts) to extract accurate information from a large Bayesian network due to dimensional difficulty. We define a formulation of local components and propose a clustering algorithm to learn such local components given complete data. The algorithm groups together most inter-relevant attributes......Bayesian networks are known for providing an intuitive and compact representation of probabilistic information and allowing the creation of models over a large and complex domain. Bayesian learning and reasoning are nontrivial for a large Bayesian network. In parallel, it is a tough job for users...... in a domain. We evaluate its performance on three benchmark Bayesian networks and provide results in support. We further show that the learned components may represent local knowledge more precisely in comparison to the full Bayesian networks when working with a small amount of data....

Geologic Carbon Sequestration Leakage Detection: A Physics-Guided Machine Learning Approach

Science.gov (United States)

Lin, Y.; Harp, D. R.; Chen, B.; Pawar, R.

2017-12-01

One of the risks of large-scale geologic carbon sequestration is the potential migration of fluids out of the storage formations. Accurate and fast detection of this fluids migration is not only important but also challenging, due to the large subsurface uncertainty and complex governing physics. Traditional leakage detection and monitoring techniques rely on geophysical observations including pressure. However, the resulting accuracy of these methods is limited because of indirect information they provide requiring expert interpretation, therefore yielding in-accurate estimates of leakage rates and locations. In this work, we develop a novel machine-learning technique based on support vector regression to effectively and efficiently predict the leakage locations and leakage rates based on limited number of pressure observations. Compared to the conventional data-driven approaches, which can be usually seem as a "black box" procedure, we develop a physics-guided machine learning method to incorporate the governing physics into the learning procedure. To validate the performance of our proposed leakage detection method, we employ our method to both 2D and 3D synthetic subsurface models. Our novel CO2 leakage detection method has shown high detection accuracy in the example problems.

Machine Learning and Conflict Prediction: A Use Case

Directory of Open Access Journals (Sweden)

Chris Perry

2013-10-01

Full Text Available For at least the last two decades, the international community in general and the United Nations specifically have attempted to develop robust, accurate and effective conflict early warning system for conflict prevention. One potential and promising component of integrated early warning systems lies in the field of machine learning. This paper aims at giving conflict analysis a basic understanding of machine learning methodology as well as to test the feasibility and added value of such an approach. The paper finds that the selection of appropriate machine learning methodologies can offer substantial improvements in accuracy and performance. It also finds that even at this early stage in testing machine learning on conflict prediction, full models offer more predictive power than simply using a prior outbreak of violence as the leading indicator of current violence. This suggests that a refined data selection methodology combined with strategic use of machine learning algorithms could indeed offer a significant addition to the early warning toolkit. Finally, the paper suggests a number of steps moving forward to improve upon this initial test methodology.

Active-constructive-interactive: a conceptual framework for differentiating learning activities.

Science.gov (United States)

Chi, Michelene T H

2009-01-01

Active, constructive, and interactive are terms that are commonly used in the cognitive and learning sciences. They describe activities that can be undertaken by learners. However, the literature is actually not explicit about how these terms can be defined; whether they are distinct; and whether they refer to overt manifestations, learning processes, or learning outcomes. Thus, a framework is provided here that offers a way to differentiate active, constructive, and interactive in terms of observable overt activities and underlying learning processes. The framework generates a testable hypothesis for learning: that interactive activities are most likely to be better than constructive activities, which in turn might be better than active activities, which are better than being passive. Studies from the literature are cited to provide evidence in support of this hypothesis. Moreover, postulating underlying learning processes allows us to interpret evidence in the literature more accurately. Specifying distinct overt activities for active, constructive, and interactive also offers suggestions for how learning activities can be coded and how each kind of activity might be elicited. Copyright © 2009 Cognitive Science Society, Inc.

Medical Student Perspectives of Active Learning: A Focus Group Study.

Science.gov (United States)

Walling, Anne; Istas, Kathryn; Bonaminio, Giulia A; Paolo, Anthony M; Fontes, Joseph D; Davis, Nancy; Berardo, Benito A

2017-01-01

Phenomenon: Medical student perspectives were sought about active learning, including concerns, challenges, perceived advantages and disadvantages, and appropriate role in the educational process. Focus groups were conducted with students from all years and campuses of a large U.S. state medical school. Students had considerable experience with active learning prior to medical school and conveyed accurate understanding of the concept and its major strategies. They appreciated the potential of active learning to deepen and broaden learning and its value for long-term professional development but had significant concerns about the efficiency of the process, the clarity of expectations provided, and the importance of receiving preparatory materials. Most significantly, active learning experiences were perceived as disconnected from grading and even as impeding preparation for school and national examinations. Insights: Medical students understand the concepts of active learning and have considerable experience in several formats prior to medical school. They are generally supportive of active learning concepts but frustrated by perceived inefficiencies and lack of contribution to the urgencies of achieving optimal grades and passing United States Medical Licensing Examinations, especially Step 1.

PRAMANA Cluster radioactivity in xenon isotopes

Indian Academy of Sciences (India)

exotic decay or cluster radioactivity was first predicted by sandulescu et al [1] in. 1980 on the basis of ... separator by 58Ni(58Ni, 2n) reaction and carbon clusters were searched for by means of solid state nuclear ..... Lett. 55, 582 (1985). [22] D N Poenaru, W Greiner, K Depta, M Ivascu, D Mazilu and A Sandulescu, At. Data.

MoleculeNet: a benchmark for molecular machine learning.

Science.gov (United States)

Wu, Zhenqin; Ramsundar, Bharath; Feinberg, Evan N; Gomes, Joseph; Geniesse, Caleb; Pappu, Aneesh S; Leswing, Karl; Pande, Vijay

2018-01-14

Molecular machine learning has been maturing rapidly over the last few years. Improved methods and the presence of larger datasets have enabled machine learning algorithms to make increasingly accurate predictions about molecular properties. However, algorithmic progress has been limited due to the lack of a standard benchmark to compare the efficacy of proposed methods; most new algorithms are benchmarked on different datasets making it challenging to gauge the quality of proposed methods. This work introduces MoleculeNet, a large scale benchmark for molecular machine learning. MoleculeNet curates multiple public datasets, establishes metrics for evaluation, and offers high quality open-source implementations of multiple previously proposed molecular featurization and learning algorithms (released as part of the DeepChem open source library). MoleculeNet benchmarks demonstrate that learnable representations are powerful tools for molecular machine learning and broadly offer the best performance. However, this result comes with caveats. Learnable representations still struggle to deal with complex tasks under data scarcity and highly imbalanced classification. For quantum mechanical and biophysical datasets, the use of physics-aware featurizations can be more important than choice of particular learning algorithm.

Hybrid chickadees are deficient in learning and memory.

Science.gov (United States)

McQuillan, Michael A; Roth, Timothy C; Huynh, Alex V; Rice, Amber M

2018-05-01

Identifying the phenotypes underlying postzygotic reproductive isolation is crucial for fully understanding the evolution and maintenance of species. One potential postzygotic isolating barrier that has rarely been examined is learning and memory ability in hybrids. Learning and memory are important fitness-related traits, especially in scatter-hoarding species, where accurate retrieval of hoarded food is vital for winter survival. Here, we test the hypothesis that learning and memory ability can act as a postzygotic isolating barrier by comparing these traits among two scatter-hoarding songbird species, black-capped (Poecile atricapillus) and Carolina chickadees (Poecile carolinensis), and their naturally occurring hybrids. In an outdoor aviary setting, we find that hybrid chickadees perform significantly worse on an associative learning spatial task and are worse at solving a novel problem compared to both parental species. Deficiencies in learning and memory abilities could therefore contribute to postzygotic reproductive isolation between chickadee species. Given the importance of learning and memory for fitness, our results suggest that these traits may play an important, but as yet overlooked, role in postzygotic reproductive isolation. © 2018 The Author(s). Evolution © 2018 The Society for the Study of Evolution.

Semi-supervised Learning for Phenotyping Tasks.

Science.gov (United States)

Dligach, Dmitriy; Miller, Timothy; Savova, Guergana K

2015-01-01

Supervised learning is the dominant approach to automatic electronic health records-based phenotyping, but it is expensive due to the cost of manual chart review. Semi-supervised learning takes advantage of both scarce labeled and plentiful unlabeled data. In this work, we study a family of semi-supervised learning algorithms based on Expectation Maximization (EM) in the context of several phenotyping tasks. We first experiment with the basic EM algorithm. When the modeling assumptions are violated, basic EM leads to inaccurate parameter estimation. Augmented EM attenuates this shortcoming by introducing a weighting factor that downweights the unlabeled data. Cross-validation does not always lead to the best setting of the weighting factor and other heuristic methods may be preferred. We show that accurate phenotyping models can be trained with only a few hundred labeled (and a large number of unlabeled) examples, potentially providing substantial savings in the amount of the required manual chart review.

Financial Management of Distance Learning in Dual-Mode Institutions

Science.gov (United States)

Rumble, Greville

2012-01-01

Dual-mode universities operating in a tough economic environment need to be able to answer a range of questions concerning their use of different teaching modes accurately and with confidence. Only an activity-based costing approach will provide them with this tool. Cost studies of other distance learning projects may provide benchmarks against…

A new, accurate predictive model for incident hypertension

DEFF Research Database (Denmark)

Völzke, Henry; Fung, Glenn; Ittermann, Till

2013-01-01

Data mining represents an alternative approach to identify new predictors of multifactorial diseases. This work aimed at building an accurate predictive model for incident hypertension using data mining procedures.......Data mining represents an alternative approach to identify new predictors of multifactorial diseases. This work aimed at building an accurate predictive model for incident hypertension using data mining procedures....

Dissociable mechanisms of speed-accuracy tradeoff during visual perceptual learning are revealed by a hierarchical drift diffusion model

Directory of Open Access Journals (Sweden)

Jiaxiang eZhang

2014-04-01

Full Text Available Two phenomena are commonly observed in decision-making. First, there is a speed-accuracy tradeoff such that decisions are slower and more accurate when instructions emphasize accuracy over speed, and vice versa. Second, decision performance improves with practice, as a task is learnt. The speed-accuracy tradeoff and learning effects have been explained under a well-established evidence-accumulation framework for decision-making, which suggests that evidence supporting each choice is accumulated over time, and a decision is committed to when the accumulated evidence reaches a decision boundary. This framework suggests that changing the decision boundary creates the tradeoff between decision speed and accuracy, while increasing the rate of accumulation leads to more accurate and faster decisions after learning. However, recent studies challenged the view that speed-accuracy tradeoff and learning are associated with changes in distinct, single decision parameters. Further, the influence of speed-accuracy instructions over the course of learning remains largely unknown. Here, we used a hierarchical drift-diffusion model to examine the speed-accuracy tradeoff during learning of a coherent motion discrimination task across multiple training sessions, and a transfer test session. The influence of speed-accuracy instructions was robust over training and generalized across untrained stimulus features. Emphasizing decision accuracy rather than speed was associated with increased boundary separation, drift rate and non-decision time at the beginning of training. However, after training, an emphasis on decision accuracy was only associated with increased boundary separation. In addition, faster and more accurate decisions after learning were due to a gradual decrease in boundary separation and an increase in drift rate. The results suggest that speed-accuracy instructions and learning differentially shape decision-making processes at different time scales.

Sample-Based Extreme Learning Machine with Missing Data

Directory of Open Access Journals (Sweden)

Hang Gao

2015-01-01

Full Text Available Extreme learning machine (ELM has been extensively studied in machine learning community during the last few decades due to its high efficiency and the unification of classification, regression, and so forth. Though bearing such merits, existing ELM algorithms cannot efficiently handle the issue of missing data, which is relatively common in practical applications. The problem of missing data is commonly handled by imputation (i.e., replacing missing values with substituted values according to available information. However, imputation methods are not always effective. In this paper, we propose a sample-based learning framework to address this issue. Based on this framework, we develop two sample-based ELM algorithms for classification and regression, respectively. Comprehensive experiments have been conducted in synthetic data sets, UCI benchmark data sets, and a real world fingerprint image data set. As indicated, without introducing extra computational complexity, the proposed algorithms do more accurate and stable learning than other state-of-the-art ones, especially in the case of higher missing ratio.

Application of Deep Learning Architectures for Accurate and Rapid Detection of Internal Mechanical Damage of Blueberry Using Hyperspectral Transmittance Data

Directory of Open Access Journals (Sweden)

Zhaodi Wang

2018-04-01

Full Text Available Deep learning has become a widely used powerful tool in many research fields, although not much so yet in agriculture technologies. In this work, two deep convolutional neural networks (CNN, viz. Residual Network (ResNet and its improved version named ResNeXt, are used to detect internal mechanical damage of blueberries using hyperspectral transmittance data. The original structure and size of hypercubes are adapted for the deep CNN training. To ensure that the models are applicable to hypercube, we adjust the number of filters in the convolutional layers. Moreover, a total of 5 traditional machine learning algorithms, viz. Sequential Minimal Optimization (SMO, Linear Regression (LR, Random Forest (RF, Bagging and Multilayer Perceptron (MLP, are performed as the comparison experiments. In terms of model assessment, k-fold cross validation is used to indicate that the model performance does not vary with the different combination of dataset. In real-world application, selling damaged berries will lead to greater interest loss than discarding the sound ones. Thus, precision, recall, and F1-score are also used as the evaluation indicators alongside accuracy to quantify the false positive rate. The first three indicators are seldom used by investigators in the agricultural engineering domain. Furthermore, ROC curves and Precision-Recall curves are plotted to visualize the performance of classifiers. The fine-tuned ResNet/ResNeXt achieve average accuracy and F1-score of 0.8844/0.8784 and 0.8952/0.8905, respectively. Classifiers SMO/ LR/RF/Bagging/MLP obtain average accuracy and F1-score of 0.8082/0.7606/0.7314/0.7113/0.7827 and 0.8268/0.7796/0.7529/0.7339/0.7971, respectively. Two deep learning models achieve better classification performance than the traditional machine learning methods. Classification for each testing sample only takes 5.2 ms and 6.5 ms respectively for ResNet and ResNeXt, indicating that the deep learning framework has great

Application of Deep Learning Architectures for Accurate and Rapid Detection of Internal Mechanical Damage of Blueberry Using Hyperspectral Transmittance Data

Science.gov (United States)

Hu, Menghan; Zhai, Guangtao

2018-01-01

Deep learning has become a widely used powerful tool in many research fields, although not much so yet in agriculture technologies. In this work, two deep convolutional neural networks (CNN), viz. Residual Network (ResNet) and its improved version named ResNeXt, are used to detect internal mechanical damage of blueberries using hyperspectral transmittance data. The original structure and size of hypercubes are adapted for the deep CNN training. To ensure that the models are applicable to hypercube, we adjust the number of filters in the convolutional layers. Moreover, a total of 5 traditional machine learning algorithms, viz. Sequential Minimal Optimization (SMO), Linear Regression (LR), Random Forest (RF), Bagging and Multilayer Perceptron (MLP), are performed as the comparison experiments. In terms of model assessment, k-fold cross validation is used to indicate that the model performance does not vary with the different combination of dataset. In real-world application, selling damaged berries will lead to greater interest loss than discarding the sound ones. Thus, precision, recall, and F1-score are also used as the evaluation indicators alongside accuracy to quantify the false positive rate. The first three indicators are seldom used by investigators in the agricultural engineering domain. Furthermore, ROC curves and Precision-Recall curves are plotted to visualize the performance of classifiers. The fine-tuned ResNet/ResNeXt achieve average accuracy and F1-score of 0.8844/0.8784 and 0.8952/0.8905, respectively. Classifiers SMO/ LR/RF/Bagging/MLP obtain average accuracy and F1-score of 0.8082/0.7606/0.7314/0.7113/0.7827 and 0.8268/0.7796/0.7529/0.7339/0.7971, respectively. Two deep learning models achieve better classification performance than the traditional machine learning methods. Classification for each testing sample only takes 5.2 ms and 6.5 ms respectively for ResNet and ResNeXt, indicating that the deep learning framework has great potential for

Application of Deep Learning Architectures for Accurate and Rapid Detection of Internal Mechanical Damage of Blueberry Using Hyperspectral Transmittance Data.

Science.gov (United States)

Wang, Zhaodi; Hu, Menghan; Zhai, Guangtao

2018-04-07

Deep learning has become a widely used powerful tool in many research fields, although not much so yet in agriculture technologies. In this work, two deep convolutional neural networks (CNN), viz. Residual Network (ResNet) and its improved version named ResNeXt, are used to detect internal mechanical damage of blueberries using hyperspectral transmittance data. The original structure and size of hypercubes are adapted for the deep CNN training. To ensure that the models are applicable to hypercube, we adjust the number of filters in the convolutional layers. Moreover, a total of 5 traditional machine learning algorithms, viz. Sequential Minimal Optimization (SMO), Linear Regression (LR), Random Forest (RF), Bagging and Multilayer Perceptron (MLP), are performed as the comparison experiments. In terms of model assessment, k-fold cross validation is used to indicate that the model performance does not vary with the different combination of dataset. In real-world application, selling damaged berries will lead to greater interest loss than discarding the sound ones. Thus, precision, recall, and F1-score are also used as the evaluation indicators alongside accuracy to quantify the false positive rate. The first three indicators are seldom used by investigators in the agricultural engineering domain. Furthermore, ROC curves and Precision-Recall curves are plotted to visualize the performance of classifiers. The fine-tuned ResNet/ResNeXt achieve average accuracy and F1-score of 0.8844/0.8784 and 0.8952/0.8905, respectively. Classifiers SMO/ LR/RF/Bagging/MLP obtain average accuracy and F1-score of 0.8082/0.7606/0.7314/0.7113/0.7827 and 0.8268/0.7796/0.7529/0.7339/0.7971, respectively. Two deep learning models achieve better classification performance than the traditional machine learning methods. Classification for each testing sample only takes 5.2 ms and 6.5 ms respectively for ResNet and ResNeXt, indicating that the deep learning framework has great potential for

Assessing and comparison of different machine learning methods in parent-offspring trios for genotype imputation.

Science.gov (United States)

Mikhchi, Abbas; Honarvar, Mahmood; Kashan, Nasser Emam Jomeh; Aminafshar, Mehdi

2016-06-21

Genotype imputation is an important tool for prediction of unknown genotypes for both unrelated individuals and parent-offspring trios. Several imputation methods are available and can either employ universal machine learning methods, or deploy algorithms dedicated to infer missing genotypes. In this research the performance of eight machine learning methods: Support Vector Machine, K-Nearest Neighbors, Extreme Learning Machine, Radial Basis Function, Random Forest, AdaBoost, LogitBoost, and TotalBoost compared in terms of the imputation accuracy, computation time and the factors affecting imputation accuracy. The methods employed using real and simulated datasets to impute the un-typed SNPs in parent-offspring trios. The tested methods show that imputation of parent-offspring trios can be accurate. The Random Forest and Support Vector Machine were more accurate than the other machine learning methods. The TotalBoost performed slightly worse than the other methods.The running times were different between methods. The ELM was always most fast algorithm. In case of increasing the sample size, the RBF requires long imputation time.The tested methods in this research can be an alternative for imputation of un-typed SNPs in low missing rate of data. However, it is recommended that other machine learning methods to be used for imputation. Copyright © 2016 Elsevier Ltd. All rights reserved.

Automatic labeling of MR brain images through extensible learning and atlas forests.

Science.gov (United States)

Xu, Lijun; Liu, Hong; Song, Enmin; Yan, Meng; Jin, Renchao; Hung, Chih-Cheng

2017-12-01

Multiatlas-based method is extensively used in MR brain images segmentation because of its simplicity and robustness. This method provides excellent accuracy although it is time consuming and limited in terms of obtaining information about new atlases. In this study, an automatic labeling of MR brain images through extensible learning and atlas forest is presented to address these limitations. We propose an extensible learning model which allows the multiatlas-based framework capable of managing the datasets with numerous atlases or dynamic atlas datasets and simultaneously ensure the accuracy of automatic labeling. Two new strategies are used to reduce the time and space complexity and improve the efficiency of the automatic labeling of brain MR images. First, atlases are encoded to atlas forests through random forest technology to reduce the time consumed for cross-registration between atlases and target image, and a scatter spatial vector is designed to eliminate errors caused by inaccurate registration. Second, an atlas selection method based on the extensible learning model is used to select atlases for target image without traversing the entire dataset and then obtain the accurate labeling. The labeling results of the proposed method were evaluated in three public datasets, namely, IBSR, LONI LPBA40, and ADNI. With the proposed method, the dice coefficient metric values on the three datasets were 84.17 ± 4.61%, 83.25 ± 4.29%, and 81.88 ± 4.53% which were 5% higher than those of the conventional method, respectively. The efficiency of the extensible learning model was evaluated by state-of-the-art methods for labeling of MR brain images. Experimental results showed that the proposed method could achieve accurate labeling for MR brain images without traversing the entire datasets. In the proposed multiatlas-based method, extensible learning and atlas forests were applied to control the automatic labeling of brain anatomies on large atlas datasets or dynamic

Fast and accurate methods for phylogenomic analyses

Directory of Open Access Journals (Sweden)

Warnow Tandy

2011-10-01

Full Text Available Abstract Background Species phylogenies are not estimated directly, but rather through phylogenetic analyses of different gene datasets. However, true gene trees can differ from the true species tree (and hence from one another due to biological processes such as horizontal gene transfer, incomplete lineage sorting, and gene duplication and loss, so that no single gene tree is a reliable estimate of the species tree. Several methods have been developed to estimate species trees from estimated gene trees, differing according to the specific algorithmic technique used and the biological model used to explain differences between species and gene trees. Relatively little is known about the relative performance of these methods. Results We report on a study evaluating several different methods for estimating species trees from sequence datasets, simulating sequence evolution under a complex model including indels (insertions and deletions, substitutions, and incomplete lineage sorting. The most important finding of our study is that some fast and simple methods are nearly as accurate as the most accurate methods, which employ sophisticated statistical methods and are computationally quite intensive. We also observe that methods that explicitly consider errors in the estimated gene trees produce more accurate trees than methods that assume the estimated gene trees are correct. Conclusions Our study shows that highly accurate estimations of species trees are achievable, even when gene trees differ from each other and from the species tree, and that these estimations can be obtained using fairly simple and computationally tractable methods.

Ensemble Network Architecture for Deep Reinforcement Learning

Directory of Open Access Journals (Sweden)

Xi-liang Chen

2018-01-01

Full Text Available The popular deep Q learning algorithm is known to be instability because of the Q-value’s shake and overestimation action values under certain conditions. These issues tend to adversely affect their performance. In this paper, we develop the ensemble network architecture for deep reinforcement learning which is based on value function approximation. The temporal ensemble stabilizes the training process by reducing the variance of target approximation error and the ensemble of target values reduces the overestimate and makes better performance by estimating more accurate Q-value. Our results show that this architecture leads to statistically significant better value evaluation and more stable and better performance on several classical control tasks at OpenAI Gym environment.

Accurate x-ray spectroscopy

International Nuclear Information System (INIS)

Deslattes, R.D.

1987-01-01

Heavy ion accelerators are the most flexible and readily accessible sources of highly charged ions. These having only one or two remaining electrons have spectra whose accurate measurement is of considerable theoretical significance. Certain features of ion production by accelerators tend to limit the accuracy which can be realized in measurement of these spectra. This report aims to provide background about spectroscopic limitations and discuss how accelerator operations may be selected to permit attaining intrinsically limited data

Surgical resident learning styles: faculty and resident accuracy at identification of preferences and impact on ABSITE scores.

Science.gov (United States)

Kim, Roger H; Gilbert, Timothy; Ristig, Kyle; Chu, Quyen D

2013-09-01

accurately 41% of the time; more experienced faculty were better than less experienced ones (R(2) = 0.703, P = 0.018). Residents had similar accuracy to faculty in identifying their peers' learning styles. Chief residents were more accurate than junior residents (44% versus 28%, P = 0.009). Most general surgery residents have a multimodal learning preference. Faculty members are relatively inaccurate at identifying residents' preferred learning styles; however, there is a strong correlation between years of faculty experience and accuracy. Chief residents are more accurate than junior residents at learning style identification. Higher mean ABSITE scores may be a reflection of a dominant read/write learning style. Copyright © 2013 Elsevier Inc. All rights reserved.

Writing Strengthens Orthography and Alphabetic-Coding Strengthens Phonology in Learning to Read Chinese

NARCIS (Netherlands)

Guan, C.Q.; Liu, Y.; Chan, D.H.L.; Ye, F.F.; Perfetti, C.A.

2011-01-01

Learning to write words may strengthen orthographic representations and thus support word-specific recognition processes. This hypothesis applies especially to Chinese because its writing system encourages character-specific recognition that depends on accurate representation of orthographic form.

Deep Learning in Gastrointestinal Endoscopy.

Science.gov (United States)

Patel, Vivek; Armstrong, David; Ganguli, Malika; Roopra, Sandeep; Kantipudi, Neha; Albashir, Siwar; Kamath, Markad V

2016-01-01

Gastrointestinal (GI) endoscopy is used to inspect the lumen or interior of the GI tract for several purposes, including, (1) making a clinical diagnosis, in real time, based on the visual appearances; (2) taking targeted tissue samples for subsequent histopathological examination; and (3) in some cases, performing therapeutic interventions targeted at specific lesions. GI endoscopy is therefore predicated on the assumption that the operator-the endoscopist-is able to identify and characterize abnormalities or lesions accurately and reproducibly. However, as in other areas of clinical medicine, such as histopathology and radiology, many studies have documented marked interobserver and intraobserver variability in lesion recognition. Thus, there is a clear need and opportunity for techniques or methodologies that will enhance the quality of lesion recognition and diagnosis and improve the outcomes of GI endoscopy. Deep learning models provide a basis to make better clinical decisions in medical image analysis. Biomedical image segmentation, classification, and registration can be improved with deep learning. Recent evidence suggests that the application of deep learning methods to medical image analysis can contribute significantly to computer-aided diagnosis. Deep learning models are usually considered to be more flexible and provide reliable solutions for image analysis problems compared to conventional computer vision models. The use of fast computers offers the possibility of real-time support that is important for endoscopic diagnosis, which has to be made in real time. Advanced graphics processing units and cloud computing have also favored the use of machine learning, and more particularly, deep learning for patient care. This paper reviews the rapidly evolving literature on the feasibility of applying deep learning algorithms to endoscopic imaging.

A Developmental Perspective in Learning the Mirror-Drawing Task

Directory of Open Access Journals (Sweden)

Mona Sharon Julius

2016-03-01

Full Text Available Is there late maturation of skill learning? This notion has been raised to explain an adult advantage in learning a variety of tasks, such as auditory temporal-interval discrimination, locomotion adaptation, and drawing visually-distorted spatial patterns (mirror-drawing. Here, we test this assertion by following the practice of the mirror-drawing task in two 5 min daily sessions separated by a 10 min break, over the course of two days, in 5–6-year-old kindergarten children, 7–8-year-old second-graders, and young adults. In the mirror-drawing task, participants were required to trace a square while looking at their hand only as a reflection in a mirror. Kindergarteners did not show learning of the visual-motor mapping, and on average, did not produce even one full side of a square correctly. Second-graders showed increased online movement control with longer strokes, and robust learning of the visual-motor mapping, resulting in a between-day increase in the number of correctly drawn sides with no loss in accuracy. Overall, kindergarteners and second-graders producing at least one correct polygon-side on Day 1 were more likely to improve their performance between days. Adults showed better performance with greater improvements in the number of correctly drawn sides between- and within-days, and in accuracy between days. It has been suggested that 5-year-olds cannot learn the task due to their inability to detect and encapsulate previously produced accurate movements. Our findings suggest, instead, that these children did not have initial, accurate performance that could be enhanced through training. Recently, it has been shown that in a simple grapho-motor task the three age-groups improved their speed of performance within a session and between-days, while maintaining accuracy scores. Taken together, these data suggest that children's motor skill learning depends on the task’s characteristics and their adopting an efficient performance

A Machine Learning Approach for Hot-Spot Detection at Protein-Protein Interfaces

NARCIS (Netherlands)

Melo, Rita; Fieldhouse, Robert; Melo, André; Correia, João D G; Cordeiro, Maria Natália D S; Gümüş, Zeynep H; Costa, Joaquim; Bonvin, Alexandre M J J; de Sousa Moreira, Irina

2016-01-01

Understanding protein-protein interactions is a key challenge in biochemistry. In this work, we describe a more accurate methodology to predict Hot-Spots (HS) in protein-protein interfaces from their native complex structure compared to previous published Machine Learning (ML) techniques. Our model

SnapAnatomy, a computer-based interactive tool for independent learning of human anatomy.

Science.gov (United States)

Yip, George W; Rajendran, Kanagasuntheram

2008-06-01

Computer-aided instruction materials are becoming increasing popular in medical education and particularly in the teaching of human anatomy. This paper describes SnapAnatomy, a new interactive program that the authors designed for independent learning of anatomy. SnapAnatomy is primarily tailored for the beginner student to encourage the learning of anatomy by developing a three-dimensional visualization of human structure that is essential to applications in clinical practice and the understanding of function. The program allows the student to take apart and to accurately put together body components in an interactive, self-paced and variable manner to achieve the learning outcome.

Gaussian Multiple Instance Learning Approach for Mapping the Slums of the World Using Very High Resolution Imagery

Energy Technology Data Exchange (ETDEWEB)

Vatsavai, Raju [ORNL

2013-01-01

In this paper, we present a computationally efficient algo- rithm based on multiple instance learning for mapping infor- mal settlements (slums) using very high-resolution remote sensing imagery. From remote sensing perspective, infor- mal settlements share unique spatial characteristics that dis- tinguish them from other urban structures like industrial, commercial, and formal residential settlements. However, regular pattern recognition and machine learning methods, which are predominantly single-instance or per-pixel classi- fiers, often fail to accurately map the informal settlements as they do not capture the complex spatial patterns. To overcome these limitations we employed a multiple instance based machine learning approach, where groups of contigu- ous pixels (image patches) are modeled as generated by a Gaussian distribution. We have conducted several experi- ments on very high-resolution satellite imagery, represent- ing four unique geographic regions across the world. Our method showed consistent improvement in accurately iden- tifying informal settlements.

Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach.

Science.gov (United States)

Ramakrishnan, Raghunathan; Dral, Pavlo O; Rupp, Matthias; von Lilienfeld, O Anatole

2015-05-12

Chemically accurate and comprehensive studies of the virtual space of all possible molecules are severely limited by the computational cost of quantum chemistry. We introduce a composite strategy that adds machine learning corrections to computationally inexpensive approximate legacy quantum methods. After training, highly accurate predictions of enthalpies, free energies, entropies, and electron correlation energies are possible, for significantly larger molecular sets than used for training. For thermochemical properties of up to 16k isomers of C7H10O2 we present numerical evidence that chemical accuracy can be reached. We also predict electron correlation energy in post Hartree-Fock methods, at the computational cost of Hartree-Fock, and we establish a qualitative relationship between molecular entropy and electron correlation. The transferability of our approach is demonstrated, using semiempirical quantum chemistry and machine learning models trained on 1 and 10% of 134k organic molecules, to reproduce enthalpies of all remaining molecules at density functional theory level of accuracy.

Height and Weight Estimation From Anthropometric Measurements Using Machine Learning Regressions.

Science.gov (United States)

Rativa, Diego; Fernandes, Bruno J T; Roque, Alexandre

2018-01-01

Height and weight are measurements explored to tracking nutritional diseases, energy expenditure, clinical conditions, drug dosages, and infusion rates. Many patients are not ambulant or may be unable to communicate, and a sequence of these factors may not allow accurate estimation or measurements; in those cases, it can be estimated approximately by anthropometric means. Different groups have proposed different linear or non-linear equations which coefficients are obtained by using single or multiple linear regressions. In this paper, we present a complete study of the application of different learning models to estimate height and weight from anthropometric measurements: support vector regression, Gaussian process, and artificial neural networks. The predicted values are significantly more accurate than that obtained with conventional linear regressions. In all the cases, the predictions are non-sensitive to ethnicity, and to gender, if more than two anthropometric parameters are analyzed. The learning model analysis creates new opportunities for anthropometric applications in industry, textile technology, security, and health care.

Medical subdomain classification of clinical notes using a machine learning-based natural language processing approach

OpenAIRE

Weng, Wei-Hung; Wagholikar, Kavishwar B.; McCray, Alexa T.; Szolovits, Peter; Chueh, Henry C.

2017-01-01

Background The medical subdomain of a clinical note, such as cardiology or neurology, is useful content-derived metadata for developing machine learning downstream applications. To classify the medical subdomain of a note accurately, we have constructed a machine learning-based natural language processing (NLP) pipeline and developed medical subdomain classifiers based on the content of the note. Methods We constructed the pipeline using the clinical ...

Accurately bearing measurement in non-cooperative passive location system

International Nuclear Information System (INIS)

Liu Zhiqiang; Ma Hongguang; Yang Lifeng

2007-01-01

The system of non-cooperative passive location based on array is proposed. In the system, target is detected by beamforming and Doppler matched filtering; and bearing is measured by a long-base-ling interferometer which is composed of long distance sub-arrays. For the interferometer with long-base-line, the bearing is measured accurately but ambiguously. To realize unambiguous accurately bearing measurement, beam width and multiple constraint adoptive beamforming technique is used to resolve azimuth ambiguous. Theory and simulation result shows this method is effective to realize accurately bearing measurement in no-cooperate passive location system. (authors)

Accurate radiotherapy positioning system investigation based on video

International Nuclear Information System (INIS)

Tao Shengxiang; Wu Yican

2006-01-01

This paper introduces the newest research production on patient positioning method in accurate radiotherapy brought by Accurate Radiotherapy Treating System (ARTS) research team of Institute of Plasma Physics of Chinese Academy of Sciences, such as the positioning system based on binocular vision, the position-measuring system based on contour matching and the breath gate controlling system for positioning. Their basic principle, the application occasion and the prospects are briefly depicted. (authors)

The Diagnostic Accuracy of the Luria-Nebraska Neuropsychological Battery-Children's Revision for 9- to 12-Year-Old Learning Disabled Children.

Science.gov (United States)

Gerry, David C.; And Others

1984-01-01

Two groups (learning disabled and normal) of 15 children were administered the Luria-Nebraska Neuropsychological Battery-Children's Revision and the Wechsler Intelligence Scale for Children-Revised. Considering abnormal or borderline profiles as indicative of learning disability was 93.3 percent accurate in discriminating between groups.…

Toward Automating HIV Identification: Machine Learning for Rapid Identification of HIV-Related Social Media Data.

Science.gov (United States)

Young, Sean D; Yu, Wenchao; Wang, Wei

2017-02-01

"Social big data" from technologies such as social media, wearable devices, and online searches continue to grow and can be used as tools for HIV research. Although researchers can uncover patterns and insights associated with HIV trends and transmission, the review process is time consuming and resource intensive. Machine learning methods derived from computer science might be used to assist HIV domain experts by learning how to rapidly and accurately identify patterns associated with HIV from a large set of social data. Using an existing social media data set that was associated with HIV and coded by an HIV domain expert, we tested whether 4 commonly used machine learning methods could learn the patterns associated with HIV risk behavior. We used the 10-fold cross-validation method to examine the speed and accuracy of these models in applying that knowledge to detect HIV content in social media data. Logistic regression and random forest resulted in the highest accuracy in detecting HIV-related social data (85.3%), whereas the Ridge Regression Classifier resulted in the lowest accuracy. Logistic regression yielded the fastest processing time (16.98 seconds). Machine learning can enable social big data to become a new and important tool in HIV research, helping to create a new field of "digital HIV epidemiology." If a domain expert can identify patterns in social data associated with HIV risk or HIV transmission, machine learning models could quickly and accurately learn those associations and identify potential HIV patterns in large social data sets.

Peripheral vision benefits spatial learning by guiding eye movements.

Science.gov (United States)

Yamamoto, Naohide; Philbeck, John W

2013-01-01

The loss of peripheral vision impairs spatial learning and navigation. However, the mechanisms underlying these impairments remain poorly understood. One advantage of having peripheral vision is that objects in an environment are easily detected and readily foveated via eye movements. The present study examined this potential benefit of peripheral vision by investigating whether competent performance in spatial learning requires effective eye movements. In Experiment 1, participants learned room-sized spatial layouts with or without restriction on direct eye movements to objects. Eye movements were restricted by having participants view the objects through small apertures in front of their eyes. Results showed that impeding effective eye movements made subsequent retrieval of spatial memory slower and less accurate. The small apertures also occluded much of the environmental surroundings, but the importance of this kind of occlusion was ruled out in Experiment 2 by showing that participants exhibited intact learning of the same spatial layouts when luminescent objects were viewed in an otherwise dark room. Together, these findings suggest that one of the roles of peripheral vision in spatial learning is to guide eye movements, highlighting the importance of spatial information derived from eye movements for learning environmental layouts.

Accurate determination of light elements by charged particle activation analysis

International Nuclear Information System (INIS)

Shikano, K.; Shigematsu, T.

1989-01-01

To develop accurate determination of light elements by CPAA, accurate and practical standardization methods and uniform chemical etching are studied based on determination of carbon in gallium arsenide using the 12 C(d,n) 13 N reaction and the following results are obtained: (1)Average stopping power method with thick target yield is useful as an accurate and practical standardization method. (2)Front surface of sample has to be etched for accurate estimate of incident energy. (3)CPAA is utilized for calibration of light element analysis by physical method. (4)Calibration factor of carbon analysis in gallium arsenide using the IR method is determined to be (9.2±0.3) x 10 15 cm -1 . (author)

Accurate 3D Mapping Algorithm for Flexible Antennas

Directory of Open Access Journals (Sweden)

Saed Asaly

2018-01-01

Full Text Available This work addresses the problem of performing an accurate 3D mapping of a flexible antenna surface. Consider a high-gain satellite flexible antenna; even a submillimeter change in the antenna surface may lead to a considerable loss in the antenna gain. Using a robotic subreflector, such changes can be compensated for. Yet, in order to perform such tuning, an accurate 3D mapping of the main antenna is required. This paper presents a general method for performing an accurate 3D mapping of marked surfaces such as satellite dish antennas. Motivated by the novel technology for nanosatellites with flexible high-gain antennas, we propose a new accurate mapping framework which requires a small-sized monocamera and known patterns on the antenna surface. The experimental result shows that the presented mapping method can detect changes up to 0.1-millimeter accuracy, while the camera is located 1 meter away from the dish, allowing an RF antenna optimization for Ka and Ku frequencies. Such optimization process can improve the gain of the flexible antennas and allow an adaptive beam shaping. The presented method is currently being implemented on a nanosatellite which is scheduled to be launched at the end of 2018.

West German Rearmament: From Enemy to Ally in Ten Short Years

Science.gov (United States)

1988-01-01

1%5. Foerster, Roland G.; Greiner , Christian; Meyer, Georg; Rautenberg, Hans-Jurgen: and Wiggershaus, Norbert. Anfange estdeuscher Sicherhei4oolink...New York: Simon and Schuster, 1972. Noelle, Elisabeth and Neumann, Erich Peter, eds. The Germans: Public Opinion Polls 1947 - 1966. Trans. Gerard...Norton and Company, Incorporated. 1962 Noelle, Elisabeth and Neumann, Erich Peter, eds. labrfuch der OffenBt/ichen MeinunvA 17- 19M Trans. Gerard Finan

Mosaic model for sensorimotor learning and control.

Science.gov (United States)

Haruno, M; Wolpert, D M; Kawato, M

2001-10-01

Humans demonstrate a remarkable ability to generate accurate and appropriate motor behavior under many different and often uncertain environmental conditions. We previously proposed a new modular architecture, the modular selection and identification for control (MOSAIC) model, for motor learning and control based on multiple pairs of forward (predictor) and inverse (controller) models. The architecture simultaneously learns the multiple inverse models necessary for control as well as how to select the set of inverse models appropriate for a given environment. It combines both feedforward and feedback sensorimotor information so that the controllers can be selected both prior to movement and subsequently during movement. This article extends and evaluates the MOSAIC architecture in the following respects. The learning in the architecture was implemented by both the original gradient-descent method and the expectation-maximization (EM) algorithm. Unlike gradient descent, the newly derived EM algorithm is robust to the initial starting conditions and learning parameters. Second, simulations of an object manipulation task prove that the architecture can learn to manipulate multiple objects and switch between them appropriately. Moreover, after learning, the model shows generalization to novel objects whose dynamics lie within the polyhedra of already learned dynamics. Finally, when each of the dynamics is associated with a particular object shape, the model is able to select the appropriate controller before movement execution. When presented with a novel shape-dynamic pairing, inappropriate activation of modules is observed followed by on-line correction.

Mental models accurately predict emotion transitions.

Science.gov (United States)

Thornton, Mark A; Tamir, Diana I

2017-06-06

Successful social interactions depend on people's ability to predict others' future actions and emotions. People possess many mechanisms for perceiving others' current emotional states, but how might they use this information to predict others' future states? We hypothesized that people might capitalize on an overlooked aspect of affective experience: current emotions predict future emotions. By attending to regularities in emotion transitions, perceivers might develop accurate mental models of others' emotional dynamics. People could then use these mental models of emotion transitions to predict others' future emotions from currently observable emotions. To test this hypothesis, studies 1-3 used data from three extant experience-sampling datasets to establish the actual rates of emotional transitions. We then collected three parallel datasets in which participants rated the transition likelihoods between the same set of emotions. Participants' ratings of emotion transitions predicted others' experienced transitional likelihoods with high accuracy. Study 4 demonstrated that four conceptual dimensions of mental state representation-valence, social impact, rationality, and human mind-inform participants' mental models. Study 5 used 2 million emotion reports on the Experience Project to replicate both of these findings: again people reported accurate models of emotion transitions, and these models were informed by the same four conceptual dimensions. Importantly, neither these conceptual dimensions nor holistic similarity could fully explain participants' accuracy, suggesting that their mental models contain accurate information about emotion dynamics above and beyond what might be predicted by static emotion knowledge alone.

Mental models accurately predict emotion transitions

Science.gov (United States)

Thornton, Mark A.; Tamir, Diana I.

2017-01-01

Successful social interactions depend on people’s ability to predict others’ future actions and emotions. People possess many mechanisms for perceiving others’ current emotional states, but how might they use this information to predict others’ future states? We hypothesized that people might capitalize on an overlooked aspect of affective experience: current emotions predict future emotions. By attending to regularities in emotion transitions, perceivers might develop accurate mental models of others’ emotional dynamics. People could then use these mental models of emotion transitions to predict others’ future emotions from currently observable emotions. To test this hypothesis, studies 1–3 used data from three extant experience-sampling datasets to establish the actual rates of emotional transitions. We then collected three parallel datasets in which participants rated the transition likelihoods between the same set of emotions. Participants’ ratings of emotion transitions predicted others’ experienced transitional likelihoods with high accuracy. Study 4 demonstrated that four conceptual dimensions of mental state representation—valence, social impact, rationality, and human mind—inform participants’ mental models. Study 5 used 2 million emotion reports on the Experience Project to replicate both of these findings: again people reported accurate models of emotion transitions, and these models were informed by the same four conceptual dimensions. Importantly, neither these conceptual dimensions nor holistic similarity could fully explain participants’ accuracy, suggesting that their mental models contain accurate information about emotion dynamics above and beyond what might be predicted by static emotion knowledge alone. PMID:28533373

Nicotine facilitates memory consolidation in perceptual learning.

Science.gov (United States)

Beer, Anton L; Vartak, Devavrat; Greenlee, Mark W

2013-01-01

Perceptual learning is a special type of non-declarative learning that involves experience-dependent plasticity in sensory cortices. The cholinergic system is known to modulate declarative learning. In particular, reduced levels or efficacy of the neurotransmitter acetylcholine were found to facilitate declarative memory consolidation. However, little is known about the role of the cholinergic system in memory consolidation of non-declarative learning. Here we compared two groups of non-smoking men who learned a visual texture discrimination task (TDT). One group received chewing tobacco containing nicotine for 1 h directly following the TDT training. The other group received a similar tasting control substance without nicotine. Electroencephalographic recordings during substance consumption showed reduced alpha activity and P300 latencies in the nicotine group compared to the control group. When re-tested on the TDT the following day, both groups responded more accurately and more rapidly than during training. These improvements were specific to the retinal location and orientation of the texture elements of the TDT suggesting that learning involved early visual cortex. A group comparison showed that learning effects were more pronounced in the nicotine group than in the control group. These findings suggest that oral consumption of nicotine enhances the efficacy of nicotinic acetylcholine receptors. Our findings further suggest that enhanced efficacy of the cholinergic system facilitates memory consolidation in perceptual learning (and possibly other types of non-declarative learning). In that regard acetylcholine seems to affect consolidation processes in perceptual learning in a different manner than in declarative learning. Alternatively, our findings might reflect dose-dependent cholinergic modulation of memory consolidation. This article is part of a Special Issue entitled 'Cognitive Enhancers'. Copyright © 2012 Elsevier Ltd. All rights reserved.

Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning.

Science.gov (United States)

Wang, Guan; Sun, Yu; Wang, Jianxin

2017-01-01

Automatic and accurate estimation of disease severity is essential for food security, disease management, and yield loss prediction. Deep learning, the latest breakthrough in computer vision, is promising for fine-grained disease severity classification, as the method avoids the labor-intensive feature engineering and threshold-based segmentation. Using the apple black rot images in the PlantVillage dataset, which are further annotated by botanists with four severity stages as ground truth, a series of deep convolutional neural networks are trained to diagnose the severity of the disease. The performances of shallow networks trained from scratch and deep models fine-tuned by transfer learning are evaluated systemically in this paper. The best model is the deep VGG16 model trained with transfer learning, which yields an overall accuracy of 90.4% on the hold-out test set. The proposed deep learning model may have great potential in disease control for modern agriculture.

Sensorimotor learning biases choice behavior: a learning neural field model for decision making.

Directory of Open Access Journals (Sweden)

Christian Klaes

Full Text Available According to a prominent view of sensorimotor processing in primates, selection and specification of possible actions are not sequential operations. Rather, a decision for an action emerges from competition between different movement plans, which are specified and selected in parallel. For action choices which are based on ambiguous sensory input, the frontoparietal sensorimotor areas are considered part of the common underlying neural substrate for selection and specification of action. These areas have been shown capable of encoding alternative spatial motor goals in parallel during movement planning, and show signatures of competitive value-based selection among these goals. Since the same network is also involved in learning sensorimotor associations, competitive action selection (decision making should not only be driven by the sensory evidence and expected reward in favor of either action, but also by the subject's learning history of different sensorimotor associations. Previous computational models of competitive neural decision making used predefined associations between sensory input and corresponding motor output. Such hard-wiring does not allow modeling of how decisions are influenced by sensorimotor learning or by changing reward contingencies. We present a dynamic neural field model which learns arbitrary sensorimotor associations with a reward-driven Hebbian learning algorithm. We show that the model accurately simulates the dynamics of action selection with different reward contingencies, as observed in monkey cortical recordings, and that it correctly predicted the pattern of choice errors in a control experiment. With our adaptive model we demonstrate how network plasticity, which is required for association learning and adaptation to new reward contingencies, can influence choice behavior. The field model provides an integrated and dynamic account for the operations of sensorimotor integration, working memory and action

DNA barcode data accurately assign higher spider taxa

Directory of Open Access Journals (Sweden)

Jonathan A. Coddington

2016-07-01

Full Text Available The use of unique DNA sequences as a method for taxonomic identification is no longer fundamentally controversial, even though debate continues on the best markers, methods, and technology to use. Although both existing databanks such as GenBank and BOLD, as well as reference taxonomies, are imperfect, in best case scenarios “barcodes” (whether single or multiple, organelle or nuclear, loci clearly are an increasingly fast and inexpensive method of identification, especially as compared to manual identification of unknowns by increasingly rare expert taxonomists. Because most species on Earth are undescribed, a complete reference database at the species level is impractical in the near term. The question therefore arises whether unidentified species can, using DNA barcodes, be accurately assigned to more inclusive groups such as genera and families—taxonomic ranks of putatively monophyletic groups for which the global inventory is more complete and stable. We used a carefully chosen test library of CO1 sequences from 49 families, 313 genera, and 816 species of spiders to assess the accuracy of genus and family-level assignment. We used BLAST queries of each sequence against the entire library and got the top ten hits. The percent sequence identity was reported from these hits (PIdent, range 75–100%. Accurate assignment of higher taxa (PIdent above which errors totaled less than 5% occurred for genera at PIdent values >95 and families at PIdent values ≥ 91, suggesting these as heuristic thresholds for accurate generic and familial identifications in spiders. Accuracy of identification increases with numbers of species/genus and genera/family in the library; above five genera per family and fifteen species per genus all higher taxon assignments were correct. We propose that using percent sequence identity between conventional barcode sequences may be a feasible and reasonably accurate method to identify animals to family/genus. However

Applying machine learning techniques for forecasting flexibility of virtual power plants

DEFF Research Database (Denmark)

MacDougall, Pamela; Kosek, Anna Magdalena; Bindner, Henrik W.

2016-01-01

network as well as the multi-variant linear regression. It is found that it is possible to estimate the longevity of flexibility with machine learning. The linear regression algorithm is, on average, able to estimate the longevity with a 15% error. However, there was a significant improvement with the ANN...... approach to investigating the longevity of aggregated response of a virtual power plant using historic bidding and aggregated behaviour with machine learning techniques. The two supervised machine learning techniques investigated and compared in this paper are, multivariate linear regression and single...... algorithm achieving, on average, a 5.3% error. This is lowered 2.4% when learning for the same virtual power plant. With this information it would be possible to accurately offer residential VPP flexibility for market operations to safely avoid causing further imbalances and financial penalties....

Data-driven methods towards learning the highly nonlinear inverse kinematics of tendon-driven surgical manipulators.

Science.gov (United States)

Xu, Wenjun; Chen, Jie; Lau, Henry Y K; Ren, Hongliang

2017-09-01

Accurate motion control of flexible surgical manipulators is crucial in tissue manipulation tasks. The tendon-driven serpentine manipulator (TSM) is one of the most widely adopted flexible mechanisms in minimally invasive surgery because of its enhanced maneuverability in torturous environments. TSM, however, exhibits high nonlinearities and conventional analytical kinematics model is insufficient to achieve high accuracy. To account for the system nonlinearities, we applied a data driven approach to encode the system inverse kinematics. Three regression methods: extreme learning machine (ELM), Gaussian mixture regression (GMR) and K-nearest neighbors regression (KNNR) were implemented to learn a nonlinear mapping from the robot 3D position states to the control inputs. The performance of the three algorithms was evaluated both in simulation and physical trajectory tracking experiments. KNNR performed the best in the tracking experiments, with the lowest RMSE of 2.1275 mm. The proposed inverse kinematics learning methods provide an alternative and efficient way to accurately model the tendon driven flexible manipulator. Copyright © 2016 John Wiley & Sons, Ltd.

Accurate overlaying for mobile augmented reality

NARCIS (Netherlands)

Pasman, W; van der Schaaf, A; Lagendijk, RL; Jansen, F.W.

1999-01-01

Mobile augmented reality requires accurate alignment of virtual information with objects visible in the real world. We describe a system for mobile communications to be developed to meet these strict alignment criteria using a combination of computer vision. inertial tracking and low-latency

Improved method for rapid and accurate isolation and identification of Streptococcus mutans and Streptococcus sobrinus from human plaque samples.

Science.gov (United States)

Villhauer, Alissa L; Lynch, David J; Drake, David R

2017-08-01

Mutans streptococci (MS), specifically Streptococcus mutans (SM) and Streptococcus sobrinus (SS), are bacterial species frequently targeted for investigation due to their role in the etiology of dental caries. Differentiation of S. mutans and S. sobrinus is an essential part of exploring the role of these organisms in disease progression and the impact of the presence of either/both on a subject's caries experience. Of vital importance to the study of these organisms is an identification protocol that allows us to distinguish between the two species in an easy, accurate, and timely manner. While conducting a 5-year birth cohort study in a Northern Plains American Indian tribe, the need for a more rapid procedure for isolating and identifying high volumes of MS was recognized. We report here on the development of an accurate and rapid method for MS identification. Accuracy, ease of use, and material and time requirements for morphological differentiation on selective agar, biochemical tests, and various combinations of PCR primers were compared. The final protocol included preliminary identification based on colony morphology followed by PCR confirmation of species identification using primers targeting regions of the glucosyltransferase (gtf) genes of SM and SS. This method of isolation and identification was found to be highly accurate, more rapid than the previous methodology used, and easily learned. It resulted in more efficient use of both time and material resources. Copyright © 2017 Elsevier B.V. All rights reserved.

Why Don't We Learn to Accurately Forecast Feelings? How Misremembering Our Predictions Blinds Us to Past Forecasting Errors

Science.gov (United States)

Meyvis, Tom; Ratner, Rebecca K.; Levav, Jonathan

2010-01-01

Why do affective forecasting errors persist in the face of repeated disconfirming evidence? Five studies demonstrate that people misremember their forecasts as consistent with their experience and thus fail to perceive the extent of their forecasting error. As a result, people do not learn from past forecasting errors and fail to adjust subsequent…

Accurate formulas for the penalty caused by interferometric crosstalk

DEFF Research Database (Denmark)

Rasmussen, Christian Jørgen; Liu, Fenghai; Jeppesen, Palle

2000-01-01

New simple formulas for the penalty caused by interferometric crosstalk in PIN receiver systems and optically preamplified receiver systems are presented. They are more accurate than existing formulas.......New simple formulas for the penalty caused by interferometric crosstalk in PIN receiver systems and optically preamplified receiver systems are presented. They are more accurate than existing formulas....

Accurate Compton scattering measurements for N{sub 2} molecules

Energy Technology Data Exchange (ETDEWEB)

Kobayashi, Kohjiro [Advanced Technology Research Center, Gunma University, 1-5-1 Tenjin-cho, Kiryu, Gunma 376-8515 (Japan); Itou, Masayoshi; Tsuji, Naruki; Sakurai, Yoshiharu [Japan Synchrotron Radiation Research Institute (JASRI), 1-1-1 Kouto, Sayo-cho, Sayo-gun, Hyogo 679-5198 (Japan); Hosoya, Tetsuo; Sakurai, Hiroshi, E-mail: sakuraih@gunma-u.ac.jp [Department of Production Science and Technology, Gunma University, 29-1 Hon-cho, Ota, Gunma 373-0057 (Japan)

2011-06-14

The accurate Compton profiles of N{sub 2} gas were measured using 121.7 keV synchrotron x-rays. The present accurate measurement proves the better agreement of the CI (configuration interaction) calculation than the Hartree-Fock calculation and suggests the importance of multi-excitation in the CI calculations for the accuracy of wavefunctions in ground states.

Learning, memory, and the role of neural network architecture.

Directory of Open Access Journals (Sweden)

Ann M Hermundstad

2011-06-01

Full Text Available The performance of information processing systems, from artificial neural networks to natural neuronal ensembles, depends heavily on the underlying system architecture. In this study, we compare the performance of parallel and layered network architectures during sequential tasks that require both acquisition and retention of information, thereby identifying tradeoffs between learning and memory processes. During the task of supervised, sequential function approximation, networks produce and adapt representations of external information. Performance is evaluated by statistically analyzing the error in these representations while varying the initial network state, the structure of the external information, and the time given to learn the information. We link performance to complexity in network architecture by characterizing local error landscape curvature. We find that variations in error landscape structure give rise to tradeoffs in performance; these include the ability of the network to maximize accuracy versus minimize inaccuracy and produce specific versus generalizable representations of information. Parallel networks generate smooth error landscapes with deep, narrow minima, enabling them to find highly specific representations given sufficient time. While accurate, however, these representations are difficult to generalize. In contrast, layered networks generate rough error landscapes with a variety of local minima, allowing them to quickly find coarse representations. Although less accurate, these representations are easily adaptable. The presence of measurable performance tradeoffs in both layered and parallel networks has implications for understanding the behavior of a wide variety of natural and artificial learning systems.

More Limitations to Monolingualism: Bilinguals Outperform Monolinguals in Implicit Word Learning.

Science.gov (United States)

Escudero, Paola; Mulak, Karen E; Fu, Charlene S L; Singh, Leher

2016-01-01

To succeed at cross-situational word learning, learners must infer word-object mappings by attending to the statistical co-occurrences of novel objects and labels across multiple encounters. While past studies have investigated this as a learning mechanism for infants and monolingual adults, bilinguals' cross-situational word learning abilities have yet to be tested. Here, we compared monolinguals' and bilinguals' performance on a cross-situational word learning paradigm that featured phonologically distinct word pairs (e.g., BON-DEET) and phonologically similar word pairs that varied by a single consonant or vowel segment (e.g., BON-TON, DEET-DIT, respectively). Both groups learned the novel word-referent mappings, providing evidence that cross-situational word learning is a learning strategy also available to bilingual adults. Furthermore, bilinguals were overall more accurate than monolinguals. This supports that bilingualism fosters a wide range of cognitive advantages that may benefit implicit word learning. Additionally, response patterns to the different trial types revealed a relative difficulty for vowel minimal pairs than consonant minimal pairs, replicating the pattern found in monolinguals by Escudero et al. (2016) in a different English accent. Specifically, all participants failed to learn vowel contrasts differentiated by vowel height. We discuss evidence for this bilingual advantage as a language-specific or general advantage.

Studying depression using imaging and machine learning methods

OpenAIRE

Patel, Meenal J.; Khalaf, Alexander; Aizenstein, Howard J.

2015-01-01

Depression is a complex clinical entity that can pose challenges for clinicians regarding both accurate diagnosis and effective timely treatment. These challenges have prompted the development of multiple machine learning methods to help improve the management of this disease. These methods utilize anatomical and physiological data acquired from neuroimaging to create models that can identify depressed patients vs. non-depressed patients and predict treatment outcomes. This article (1) presen...

SchNet - A deep learning architecture for molecules and materials

Science.gov (United States)

Schütt, K. T.; Sauceda, H. E.; Kindermans, P.-J.; Tkatchenko, A.; Müller, K.-R.

2018-06-01

Deep learning has led to a paradigm shift in artificial intelligence, including web, text, and image search, speech recognition, as well as bioinformatics, with growing impact in chemical physics. Machine learning, in general, and deep learning, in particular, are ideally suitable for representing quantum-mechanical interactions, enabling us to model nonlinear potential-energy surfaces or enhancing the exploration of chemical compound space. Here we present the deep learning architecture SchNet that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers. We demonstrate the capabilities of SchNet by accurately predicting a range of properties across chemical space for molecules and materials, where our model learns chemically plausible embeddings of atom types across the periodic table. Finally, we employ SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules and perform an exemplary study on the quantum-mechanical properties of C20-fullerene that would have been infeasible with regular ab initio molecular dynamics.

Machine Learning Techniques for Prediction of Early Childhood Obesity.

Science.gov (United States)

Dugan, T M; Mukhopadhyay, S; Carroll, A; Downs, S

2015-01-01

This paper aims to predict childhood obesity after age two, using only data collected prior to the second birthday by a clinical decision support system called CHICA. Analyses of six different machine learning methods: RandomTree, RandomForest, J48, ID3, Naïve Bayes, and Bayes trained on CHICA data show that an accurate, sensitive model can be created. Of the methods analyzed, the ID3 model trained on the CHICA dataset proved the best overall performance with accuracy of 85% and sensitivity of 89%. Additionally, the ID3 model had a positive predictive value of 84% and a negative predictive value of 88%. The structure of the tree also gives insight into the strongest predictors of future obesity in children. Many of the strongest predictors seen in the ID3 modeling of the CHICA dataset have been independently validated in the literature as correlated with obesity, thereby supporting the validity of the model. This study demonstrated that data from a production clinical decision support system can be used to build an accurate machine learning model to predict obesity in children after age two.

Bio-inspired adaptive feedback error learning architecture for motor control.

Science.gov (United States)

Tolu, Silvia; Vanegas, Mauricio; Luque, Niceto R; Garrido, Jesús A; Ros, Eduardo

2012-10-01

This study proposes an adaptive control architecture based on an accurate regression method called Locally Weighted Projection Regression (LWPR) and on a bio-inspired module, such as a cerebellar-like engine. This hybrid architecture takes full advantage of the machine learning module (LWPR kernel) to abstract an optimized representation of the sensorimotor space while the cerebellar component integrates this to generate corrective terms in the framework of a control task. Furthermore, we illustrate how the use of a simple adaptive error feedback term allows to use the proposed architecture even in the absence of an accurate analytic reference model. The presented approach achieves an accurate control with low gain corrective terms (for compliant control schemes). We evaluate the contribution of the different components of the proposed scheme comparing the obtained performance with alternative approaches. Then, we show that the presented architecture can be used for accurate manipulation of different objects when their physical properties are not directly known by the controller. We evaluate how the scheme scales for simulated plants of high Degrees of Freedom (7-DOFs).

Accurate quantum chemical calculations

Science.gov (United States)

Bauschlicher, Charles W., Jr.; Langhoff, Stephen R.; Taylor, Peter R.

1989-01-01

An important goal of quantum chemical calculations is to provide an understanding of chemical bonding and molecular electronic structure. A second goal, the prediction of energy differences to chemical accuracy, has been much harder to attain. First, the computational resources required to achieve such accuracy are very large, and second, it is not straightforward to demonstrate that an apparently accurate result, in terms of agreement with experiment, does not result from a cancellation of errors. Recent advances in electronic structure methodology, coupled with the power of vector supercomputers, have made it possible to solve a number of electronic structure problems exactly using the full configuration interaction (FCI) method within a subspace of the complete Hilbert space. These exact results can be used to benchmark approximate techniques that are applicable to a wider range of chemical and physical problems. The methodology of many-electron quantum chemistry is reviewed. Methods are considered in detail for performing FCI calculations. The application of FCI methods to several three-electron problems in molecular physics are discussed. A number of benchmark applications of FCI wave functions are described. Atomic basis sets and the development of improved methods for handling very large basis sets are discussed: these are then applied to a number of chemical and spectroscopic problems; to transition metals; and to problems involving potential energy surfaces. Although the experiences described give considerable grounds for optimism about the general ability to perform accurate calculations, there are several problems that have proved less tractable, at least with current computer resources, and these and possible solutions are discussed.

The Effect of Visual Variability on the Learning of Academic Concepts.

Science.gov (United States)

Bourgoyne, Ashley; Alt, Mary

2017-06-10

The purpose of this study was to identify effects of variability of visual input on development of conceptual representations of academic concepts for college-age students with normal language (NL) and those with language-learning disabilities (LLD). Students with NL (n = 11) and LLD (n = 11) participated in a computer-based training for introductory biology course concepts. Participants were trained on half the concepts under a low-variability condition and half under a high-variability condition. Participants completed a posttest in which they were asked to identify and rate the accuracy of novel and trained visual representations of the concepts. We performed separate repeated measures analyses of variance to examine the accuracy of identification and ratings. Participants were equally accurate on trained and novel items in the high-variability condition, but were less accurate on novel items only in the low-variability condition. The LLD group showed the same pattern as the NL group; they were just less accurate. Results indicated that high-variability visual input may facilitate the acquisition of academic concepts in college students with NL and LLD. High-variability visual input may be especially beneficial for generalization to novel representations of concepts. Implicit learning methods may be harnessed by college courses to provide students with basic conceptual knowledge when they are entering courses or beginning new units.

Formation Learning Control of Multiple Autonomous Underwater Vehicles With Heterogeneous Nonlinear Uncertain Dynamics.

Science.gov (United States)

Yuan, Chengzhi; Licht, Stephen; He, Haibo

2017-09-26

In this paper, a new concept of formation learning control is introduced to the field of formation control of multiple autonomous underwater vehicles (AUVs), which specifies a joint objective of distributed formation tracking control and learning/identification of nonlinear uncertain AUV dynamics. A novel two-layer distributed formation learning control scheme is proposed, which consists of an upper-layer distributed adaptive observer and a lower-layer decentralized deterministic learning controller. This new formation learning control scheme advances existing techniques in three important ways: 1) the multi-AUV system under consideration has heterogeneous nonlinear uncertain dynamics; 2) the formation learning control protocol can be designed and implemented by each local AUV agent in a fully distributed fashion without using any global information; and 3) in addition to the formation control performance, the distributed control protocol is also capable of accurately identifying the AUVs' heterogeneous nonlinear uncertain dynamics and utilizing experiences to improve formation control performance. Extensive simulations have been conducted to demonstrate the effectiveness of the proposed results.

Large-scale Exploration of Neuronal Morphologies Using Deep Learning and Augmented Reality.

Science.gov (United States)

Li, Zhongyu; Butler, Erik; Li, Kang; Lu, Aidong; Ji, Shuiwang; Zhang, Shaoting

2018-02-12

Recently released large-scale neuron morphological data has greatly facilitated the research in neuroinformatics. However, the sheer volume and complexity of these data pose significant challenges for efficient and accurate neuron exploration. In this paper, we propose an effective retrieval framework to address these problems, based on frontier techniques of deep learning and binary coding. For the first time, we develop a deep learning based feature representation method for the neuron morphological data, where the 3D neurons are first projected into binary images and then learned features using an unsupervised deep neural network, i.e., stacked convolutional autoencoders (SCAEs). The deep features are subsequently fused with the hand-crafted features for more accurate representation. Considering the exhaustive search is usually very time-consuming in large-scale databases, we employ a novel binary coding method to compress feature vectors into short binary codes. Our framework is validated on a public data set including 58,000 neurons, showing promising retrieval precision and efficiency compared with state-of-the-art methods. In addition, we develop a novel neuron visualization program based on the techniques of augmented reality (AR), which can help users take a deep exploration of neuron morphologies in an interactive and immersive manner.

An investigation of the role of background music in IVWs for learning

Directory of Open Access Journals (Sweden)

Debbie Richards

2008-12-01

Full Text Available Empirical evidence is needed to corroborate the intuitions of gamers and game developers in understanding the benefits of Immersive Virtual Worlds (IVWs as a learning environment and the role that music plays within these environments. We report an investigation to determine if background music of the genre typically found in computer-based role-playing games has an effect on learning in a computer-animated history lesson about the Macquarie Lighthouse within an IVW. In Experiment 1, music stimuli were created from four different computer game soundtracks. Seventy-two undergraduate students watched the presentation and completed a survey including biographical details, questions on the historical material presented and questions relating to their perceived level of immersion. While the tempo and pitch of the music was unrelated to learning, music conditions resulted in a higher number of accurately remembered facts than the no music condition. One soundtrack showed a statistically significant improvement in memorisation of facts over other music conditions. Also an interaction between the levels of perceived immersion and ability to accurately remember facts was observed. Experiment 2, involving 48 undergraduate students, further investigated the effect of music, sense of immersion and how different display systems affect memory for facts.

Seeing the Errors You Feel Enhances Locomotor Performance but Not Learning.

Science.gov (United States)

Roemmich, Ryan T; Long, Andrew W; Bastian, Amy J

2016-10-24

In human motor learning, it is thought that the more information we have about our errors, the faster we learn. Here, we show that additional error information can lead to improved motor performance without any concomitant improvement in learning. We studied split-belt treadmill walking that drives people to learn a new gait pattern using sensory prediction errors detected by proprioceptive feedback. When we also provided visual error feedback, participants acquired the new walking pattern far more rapidly and showed accelerated restoration of the normal walking pattern during washout. However, when the visual error feedback was removed during either learning or washout, errors reappeared with performance immediately returning to the level expected based on proprioceptive learning alone. These findings support a model with two mechanisms: a dual-rate adaptation process that learns invariantly from sensory prediction error detected by proprioception and a visual-feedback-dependent process that monitors learning and corrects residual errors but shows no learning itself. We show that our voluntary correction model accurately predicted behavior in multiple situations where visual feedback was used to change acquisition of new walking patterns while the underlying learning was unaffected. The computational and behavioral framework proposed here suggests that parallel learning and error correction systems allow us to rapidly satisfy task demands without necessarily committing to learning, as the relative permanence of learning may be inappropriate or inefficient when facing environments that are liable to change. Copyright © 2016 Elsevier Ltd. All rights reserved.

Effects of incidental pictorial and verbal adjuncts on text learning.

Science.gov (United States)

Terry, W S; Howe, D C

1988-01-01

In this study, college students read and studied texts on historical figures in psychology, which were supplemented by drawings and/or brief biographies of these persons. In Experiment 1, a 2 x 2 between-groups design was conducted in which students received one adjunct with each text, both adjuncts, or neither. In Experiment 2, a single group of students received a within-subjects manipulation of the same adjunct conditions. In the between-groups comparison, students receiving biographies learned less of the target text passages, with the group receiving illustrations and biographies performing least accurately. In the within-subject conditions, texts accompanied by an illustration were better learned, with these students doing best on the text with both picture and biography. The results suggest that adjuncts may emphasize some texts, at the expense of learning from the other texts, but that too much adjunct material interferes with the learning of the target passages.

Automatic Image-Based Plant Disease Severity Estimation Using Deep Learning

Directory of Open Access Journals (Sweden)

Guan Wang

2017-01-01

Full Text Available Automatic and accurate estimation of disease severity is essential for food security, disease management, and yield loss prediction. Deep learning, the latest breakthrough in computer vision, is promising for fine-grained disease severity classification, as the method avoids the labor-intensive feature engineering and threshold-based segmentation. Using the apple black rot images in the PlantVillage dataset, which are further annotated by botanists with four severity stages as ground truth, a series of deep convolutional neural networks are trained to diagnose the severity of the disease. The performances of shallow networks trained from scratch and deep models fine-tuned by transfer learning are evaluated systemically in this paper. The best model is the deep VGG16 model trained with transfer learning, which yields an overall accuracy of 90.4% on the hold-out test set. The proposed deep learning model may have great potential in disease control for modern agriculture.

PBODL : Parallel Bayesian Online Deep Learning for Click-Through Rate Prediction in Tencent Advertising System

OpenAIRE

Liu, Xun; Xue, Wei; Xiao, Lei; Zhang, Bo

2017-01-01

We describe a parallel bayesian online deep learning framework (PBODL) for click-through rate (CTR) prediction within today's Tencent advertising system, which provides quick and accurate learning of user preferences. We first explain the framework with a deep probit regression model, which is trained with probabilistic back-propagation in the mode of assumed Gaussian density filtering. Then we extend the model family to a variety of bayesian online models with increasing feature embedding ca...

Toward accurate and fast iris segmentation for iris biometrics.

Science.gov (United States)

He, Zhaofeng; Tan, Tieniu; Sun, Zhenan; Qiu, Xianchao

2009-09-01

Iris segmentation is an essential module in iris recognition because it defines the effective image region used for subsequent processing such as feature extraction. Traditional iris segmentation methods often involve an exhaustive search of a large parameter space, which is time consuming and sensitive to noise. To address these problems, this paper presents a novel algorithm for accurate and fast iris segmentation. After efficient reflection removal, an Adaboost-cascade iris detector is first built to extract a rough position of the iris center. Edge points of iris boundaries are then detected, and an elastic model named pulling and pushing is established. Under this model, the center and radius of the circular iris boundaries are iteratively refined in a way driven by the restoring forces of Hooke's law. Furthermore, a smoothing spline-based edge fitting scheme is presented to deal with noncircular iris boundaries. After that, eyelids are localized via edge detection followed by curve fitting. The novelty here is the adoption of a rank filter for noise elimination and a histogram filter for tackling the shape irregularity of eyelids. Finally, eyelashes and shadows are detected via a learned prediction model. This model provides an adaptive threshold for eyelash and shadow detection by analyzing the intensity distributions of different iris regions. Experimental results on three challenging iris image databases demonstrate that the proposed algorithm outperforms state-of-the-art methods in both accuracy and speed.

Simultaneous Vascular Targeting and Tumor Targeting of Cerebral Breast Cancer Metastases Using a T-Cell Receptor Mimic Antibody

Science.gov (United States)

2014-05-01

in May 2013, the difference between nude mice (which lack T- cells , but still have a partially functional adaptive and innate immune system) and NSG...Mangada J, Greiner DL, Handgretinger R. Human lymphoid and myeloid cell development in NOD/LtSz-scid IL2R gamma null mice engrafted with mobilized human...Targeting of Cerebral Breast Cancer Metastases Using a T- Cell Receptor Mimic Antibody PRINCIPAL INVESTIGATOR: Ulrich Bickel

Integrative Lifecourse and Genetic Analysis of Military Working Dogs

Science.gov (United States)

2015-12-01

Multhoff, Technische Universitaet Muenchen, GERMANY Received: July 22, 2015 Accepted: October 15, 2015 Published: November 11, 2015 Copyright: © 2015...MO) were used. For the monolayer model, cells were plated in 96-well black flat-clear bottom plates (Greiner Bio-One GmbH, Frickenhausen, Germany ...and oncogenic determinants of metastasis have been reported and appear to be similar in both species. Comparative analysis of deregulated gene sets or

An Interpretable Machine Learning Model for Accurate Prediction of Sepsis in the ICU.

Science.gov (United States)

Nemati, Shamim; Holder, Andre; Razmi, Fereshteh; Stanley, Matthew D; Clifford, Gari D; Buchman, Timothy G

2018-04-01

Sepsis is among the leading causes of morbidity, mortality, and cost overruns in critically ill patients. Early intervention with antibiotics improves survival in septic patients. However, no clinically validated system exists for real-time prediction of sepsis onset. We aimed to develop and validate an Artificial Intelligence Sepsis Expert algorithm for early prediction of sepsis. Observational cohort study. Academic medical center from January 2013 to December 2015. Over 31,000 admissions to the ICUs at two Emory University hospitals (development cohort), in addition to over 52,000 ICU patients from the publicly available Medical Information Mart for Intensive Care-III ICU database (validation cohort). Patients who met the Third International Consensus Definitions for Sepsis (Sepsis-3) prior to or within 4 hours of their ICU admission were excluded, resulting in roughly 27,000 and 42,000 patients within our development and validation cohorts, respectively. None. High-resolution vital signs time series and electronic medical record data were extracted. A set of 65 features (variables) were calculated on hourly basis and passed to the Artificial Intelligence Sepsis Expert algorithm to predict onset of sepsis in the proceeding T hours (where T = 12, 8, 6, or 4). Artificial Intelligence Sepsis Expert was used to predict onset of sepsis in the proceeding T hours and to produce a list of the most significant contributing factors. For the 12-, 8-, 6-, and 4-hour ahead prediction of sepsis, Artificial Intelligence Sepsis Expert achieved area under the receiver operating characteristic in the range of 0.83-0.85. Performance of the Artificial Intelligence Sepsis Expert on the development and validation cohorts was indistinguishable. Using data available in the ICU in real-time, Artificial Intelligence Sepsis Expert can accurately predict the onset of sepsis in an ICU patient 4-12 hours prior to clinical recognition. A prospective study is necessary to determine the

Monitoring and regulation of learning in medical education: the need for predictive cues.

Science.gov (United States)

de Bruin, Anique B H; Dunlosky, John; Cavalcanti, Rodrigo B

2017-06-01

Being able to accurately monitor learning activities is a key element in self-regulated learning in all settings, including medical schools. Yet students' ability to monitor their progress is often limited, leading to inefficient use of study time. Interventions that improve the accuracy of students' monitoring can optimise self-regulated learning, leading to higher achievement. This paper reviews findings from cognitive psychology and explores potential applications in medical education, as well as areas for future research. Effective monitoring depends on students' ability to generate information ('cues') that accurately reflects their knowledge and skills. The ability of these 'cues' to predict achievement is referred to as 'cue diagnosticity'. Interventions that improve the ability of students to elicit predictive cues typically fall into two categories: (i) self-generation of cues and (ii) generation of cues that is delayed after self-study. Providing feedback and support is useful when cues are predictive but may be too complex to be readily used. Limited evidence exists about interventions to improve the accuracy of self-monitoring among medical students or trainees. Developing interventions that foster use of predictive cues can enhance the accuracy of self-monitoring, thereby improving self-study and clinical reasoning. First, insight should be gained into the characteristics of predictive cues used by medical students and trainees. Next, predictive cue prompts should be designed and tested to improve monitoring and regulation of learning. Finally, the use of predictive cues should be explored in relation to teaching and learning clinical reasoning. Improving self-regulated learning is important to help medical students and trainees efficiently acquire knowledge and skills necessary for clinical practice. Interventions that help students generate and use predictive cues hold the promise of improved self-regulated learning and achievement. This framework is

Learning and coding in biological neural networks

Science.gov (United States)

Fiete, Ila Rani

How can large groups of neurons that locally modify their activities learn to collectively perform a desired task? Do studies of learning in small networks tell us anything about learning in the fantastically large collection of neurons that make up a vertebrate brain? What factors do neurons optimize by encoding sensory inputs or motor commands in the way they do? In this thesis I present a collection of four theoretical works: each of the projects was motivated by specific constraints and complexities of biological neural networks, as revealed by experimental studies; together, they aim to partially address some of the central questions of neuroscience posed above. We first study the role of sparse neural activity, as seen in the coding of sequential commands in a premotor area responsible for birdsong. We show that the sparse coding of temporal sequences in the songbird brain can, in a network where the feedforward plastic weights must translate the sparse sequential code into a time-varying muscle code, facilitate learning by minimizing synaptic interference. Next, we propose a biologically plausible synaptic plasticity rule that can perform goal-directed learning in recurrent networks of voltage-based spiking neurons that interact through conductances. Learning is based on the correlation of noisy local activity with a global reward signal; we prove that this rule performs stochastic gradient ascent on the reward. Thus, if the reward signal quantifies network performance on some desired task, the plasticity rule provably drives goal-directed learning in the network. To assess the convergence properties of the learning rule, we compare it with a known example of learning in the brain. Song-learning in finches is a clear example of a learned behavior, with detailed available neurophysiological data. With our learning rule, we train an anatomically accurate model birdsong network that drives a sound source to mimic an actual zebrafinch song. Simulation and

Medication adherence as a learning process: insights from cognitive psychology.

Science.gov (United States)

Rottman, Benjamin Margolin; Marcum, Zachary A; Thorpe, Carolyn T; Gellad, Walid F

2017-03-01

Non-adherence to medications is one of the largest contributors to sub-optimal health outcomes. Many theories of adherence include a 'value-expectancy' component in which a patient decides to take a medication partly based on expectations about whether it is effective, necessary, and tolerable. We propose reconceptualising this common theme as a kind of 'causal learning' - the patient learns whether a medication is effective, necessary, and tolerable, from experience with the medication. We apply cognitive psychology theories of how people learn cause-effect relations to elaborate this causal-learning challenge. First, expectations and impressions about a medication and beliefs about how a medication works, such as delay of onset, can shape a patient's perceived experience with the medication. Second, beliefs about medications propagate both 'top-down' and 'bottom-up', from experiences with specific medications to general beliefs about medications and vice versa. Third, non-adherence can interfere with learning about a medication, because beliefs, adherence, and experience with a medication are connected in a cyclic learning problem. We propose that by conceptualising non-adherence as a causal-learning process, clinicians can more effectively address a patient's misconceptions and biases, helping the patient develop more accurate impressions of the medication.

Traffic Flow Prediction with Rainfall Impact Using a Deep Learning Method

Directory of Open Access Journals (Sweden)

Yuhan Jia

2017-01-01

Full Text Available Accurate traffic flow prediction is increasingly essential for successful traffic modeling, operation, and management. Traditional data driven traffic flow prediction approaches have largely assumed restrictive (shallow model architectures and do not leverage the large amount of environmental data available. Inspired by deep learning methods with more complex model architectures and effective data mining capabilities, this paper introduces the deep belief network (DBN and long short-term memory (LSTM to predict urban traffic flow considering the impact of rainfall. The rainfall-integrated DBN and LSTM can learn the features of traffic flow under various rainfall scenarios. Experimental results indicate that, with the consideration of additional rainfall factor, the deep learning predictors have better accuracy than existing predictors and also yield improvements over the original deep learning models without rainfall input. Furthermore, the LSTM can outperform the DBN to capture the time series characteristics of traffic flow data.

Improving galaxy morphologies for SDSS with Deep Learning

Science.gov (United States)

Domínguez Sánchez, H.; Huertas-Company, M.; Bernardi, M.; Tuccillo, D.; Fischer, J. L.

2018-05-01

We present a morphological catalogue for ˜670 000 galaxies in the Sloan Digital Sky Survey in two flavours: T-type, related to the Hubble sequence, and Galaxy Zoo 2 (GZ2 hereafter) classification scheme. By combining accurate existing visual classification catalogues with machine learning, we provide the largest and most accurate morphological catalogue up to date. The classifications are obtained with Deep Learning algorithms using Convolutional Neural Networks (CNNs). We use two visual classification catalogues, GZ2 and Nair & Abraham (2010), for training CNNs with colour images in order to obtain T-types and a series of GZ2 type questions (disc/features, edge-on galaxies, bar signature, bulge prominence, roundness, and mergers). We also provide an additional probability enabling a separation between pure elliptical (E) from S0, where the T-type model is not so efficient. For the T-type, our results show smaller offset and scatter than previous models trained with support vector machines. For the GZ2 type questions, our models have large accuracy (>97 per cent), precision and recall values (>90 per cent), when applied to a test sample with the same characteristics as the one used for training. The catalogue is publicly released with the paper.

The Relationships among Verbal Short-Term Memory, Phonological Awareness, and New Word Learning: Evidence from Typical Development and Down Syndrome

Science.gov (United States)

Jarrold, Christopher; Thorn, Annabel S. C.; Stephens, Emma

2009-01-01

This study examined the correlates of new word learning in a sample of 64 typically developing children between 5 and 8 years of age and a group of 22 teenagers and young adults with Down syndrome. Verbal short-term memory and phonological awareness skills were assessed to determine whether learning new words involved accurately representing…

Structural damage detection using deep learning of ultrasonic guided waves

Science.gov (United States)

Melville, Joseph; Alguri, K. Supreet; Deemer, Chris; Harley, Joel B.

2018-04-01

Structural health monitoring using ultrasonic guided waves relies on accurate interpretation of guided wave propagation to distinguish damage state indicators. However, traditional physics based models do not provide an accurate representation, and classic data driven techniques, such as a support vector machine, are too simplistic to capture the complex nature of ultrasonic guide waves. To address this challenge, this paper uses a deep learning interpretation of ultrasonic guided waves to achieve fast, accurate, and automated structural damaged detection. To achieve this, full wavefield scans of thin metal plates are used, half from the undamaged state and half from the damaged state. This data is used to train our deep network to predict the damage state of a plate with 99.98% accuracy given signals from just 10 spatial locations on the plate, as compared to that of a support vector machine (SVM), which achieved a 62% accuracy.

Fast Low-Rank Shared Dictionary Learning for Image Classification.

Science.gov (United States)

Tiep Huu Vu; Monga, Vishal

2017-11-01

Despite the fact that different objects possess distinct class-specific features, they also usually share common patterns. This observation has been exploited partially in a recently proposed dictionary learning framework by separating the particularity and the commonality (COPAR). Inspired by this, we propose a novel method to explicitly and simultaneously learn a set of common patterns as well as class-specific features for classification with more intuitive constraints. Our dictionary learning framework is hence characterized by both a shared dictionary and particular (class-specific) dictionaries. For the shared dictionary, we enforce a low-rank constraint, i.e., claim that its spanning subspace should have low dimension and the coefficients corresponding to this dictionary should be similar. For the particular dictionaries, we impose on them the well-known constraints stated in the Fisher discrimination dictionary learning (FDDL). Furthermore, we develop new fast and accurate algorithms to solve the subproblems in the learning step, accelerating its convergence. The said algorithms could also be applied to FDDL and its extensions. The efficiencies of these algorithms are theoretically and experimentally verified by comparing their complexities and running time with those of other well-known dictionary learning methods. Experimental results on widely used image data sets establish the advantages of our method over the state-of-the-art dictionary learning methods.

Accurate forced-choice recognition without awareness of memory retrieval

OpenAIRE

Voss, Joel L.; Baym, Carol L.; Paller, Ken A.

2008-01-01

Recognition confidence and the explicit awareness of memory retrieval commonly accompany accurate responding in recognition tests. Memory performance in recognition tests is widely assumed to measure explicit memory, but the generality of this assumption is questionable. Indeed, whether recognition in nonhumans is always supported by explicit memory is highly controversial. Here we identified circumstances wherein highly accurate recognition was unaccompanied by hallmark features of explicit ...

Learning and exploration in action-perception loops.

Science.gov (United States)

Little, Daniel Y; Sommer, Friedrich T

2013-01-01

Discovering the structure underlying observed data is a recurring problem in machine learning with important applications in neuroscience. It is also a primary function of the brain. When data can be actively collected in the context of a closed action-perception loop, behavior becomes a critical determinant of learning efficiency. Psychologists studying exploration and curiosity in humans and animals have long argued that learning itself is a primary motivator of behavior. However, the theoretical basis of learning-driven behavior is not well understood. Previous computational studies of behavior have largely focused on the control problem of maximizing acquisition of rewards and have treated learning the structure of data as a secondary objective. Here, we study exploration in the absence of external reward feedback. Instead, we take the quality of an agent's learned internal model to be the primary objective. In a simple probabilistic framework, we derive a Bayesian estimate for the amount of information about the environment an agent can expect to receive by taking an action, a measure we term the predicted information gain (PIG). We develop exploration strategies that approximately maximize PIG. One strategy based on value-iteration consistently learns faster than previously developed reward-free exploration strategies across a diverse range of environments. Psychologists believe the evolutionary advantage of learning-driven exploration lies in the generalized utility of an accurate internal model. Consistent with this hypothesis, we demonstrate that agents which learn more efficiently during exploration are later better able to accomplish a range of goal-directed tasks. We will conclude by discussing how our work elucidates the explorative behaviors of animals and humans, its relationship to other computational models of behavior, and its potential application to experimental design, such as in closed-loop neurophysiology studies.

Learning and exploration in action-perception loops

Directory of Open Access Journals (Sweden)

Daniel Ying-Jeh Little

2013-03-01

Full Text Available Discovering the structure underlying observed data is a recurring problem in machine learning with important applications in neuroscience. It is also a primary function of the brain. When data can be actively collected in the context of a closed action-perception loop, behavior becomes a critical determinant of learning efficiency. Psychologists studying exploration and curiosity in humans and animals have long argued that learning itself is a primary motivator of behavior. However, the theoretical basis of learning-driven behavior is not well understood. Previous computational studies of behavior have largely focused on the control problem of maximizing acquisition of rewards and have treated learning the structure of data as a secondary objective. Here, we study exploration in the absence of external reward feedback. Instead, we take the quality of an agent's learned internal model to be the primary objective. In a simple probabilistic framework, we derive a Bayesian estimate for the amount of information about the environment an agent can expect to receive by taking an action, a measure we term the predicted information gain (PIG. We develop exploration strategies that approximately maximize PIG. One strategy based on value-iteration consistently learns faster, across a diverse range of environments, than previously developed reward-free exploration strategies. Psychologists believe the evolutionary advantage of learning-driven exploration lies in the generalized utility of an accurate internal model. Consistent with this hypothesis, we demonstrate that agents which learn more efficiently during exploration are later better able to accomplish a range of goal-directed tasks. We will conclude by discussing how our work elucidates the explorative behaviors of animals and humans, its relationship to other computational models of behavior, and its potential application to experimental design, such as in closed-loop neurophysiology studies.

Organization of students’ knowledge control in the process of distance learning

Directory of Open Access Journals (Sweden)

Miklashevich N. V.

2016-07-01

Full Text Available the article observes the main problems of organizing and carrying out the educational diagnosis in distance learning. Studying different approaches to monitoring showed that such control types as routine control and self-control are more efficient and effective. There is a difficulty of carrying out the control in distance learning: the need for accurate identification of the learner's personality. Despite existing technologies and recent developments in this area, the problem of preventing the test results from falsification is not fully resolved. According to the authors, the basic type of routine control when educating distantly remains the student obligatory attendance.

The Accurate Particle Tracer Code

OpenAIRE

Wang, Yulei; Liu, Jian; Qin, Hong; Yu, Zhi

2016-01-01

The Accurate Particle Tracer (APT) code is designed for large-scale particle simulations on dynamical systems. Based on a large variety of advanced geometric algorithms, APT possesses long-term numerical accuracy and stability, which are critical for solving multi-scale and non-linear problems. Under the well-designed integrated and modularized framework, APT serves as a universal platform for researchers from different fields, such as plasma physics, accelerator physics, space science, fusio...

Unsupervised Learning and Pattern Recognition of Biological Data Structures with Density Functional Theory and Machine Learning.

Science.gov (United States)

Chen, Chien-Chang; Juan, Hung-Hui; Tsai, Meng-Yuan; Lu, Henry Horng-Shing

2018-01-11

By introducing the methods of machine learning into the density functional theory, we made a detour for the construction of the most probable density function, which can be estimated by learning relevant features from the system of interest. Using the properties of universal functional, the vital core of density functional theory, the most probable cluster numbers and the corresponding cluster boundaries in a studying system can be simultaneously and automatically determined and the plausibility is erected on the Hohenberg-Kohn theorems. For the method validation and pragmatic applications, interdisciplinary problems from physical to biological systems were enumerated. The amalgamation of uncharged atomic clusters validated the unsupervised searching process of the cluster numbers and the corresponding cluster boundaries were exhibited likewise. High accurate clustering results of the Fisher's iris dataset showed the feasibility and the flexibility of the proposed scheme. Brain tumor detections from low-dimensional magnetic resonance imaging datasets and segmentations of high-dimensional neural network imageries in the Brainbow system were also used to inspect the method practicality. The experimental results exhibit the successful connection between the physical theory and the machine learning methods and will benefit the clinical diagnoses.

Collaborative Filtering for Expansion of Learner's Background Knowledge in Online Language Learning: Does "Top-Down" Processing Improve Vocabulary Proficiency?

Science.gov (United States)

Yamada, Masanori; Kitamura, Satoshi; Matsukawa, Hideya; Misono, Tadashi; Kitani, Noriko; Yamauchi, Yuhei

2014-01-01

In recent years, collaborative filtering, a recommendation algorithm that incorporates a user's data such as interest, has received worldwide attention as an advanced learning support system. However, accurate recommendations along with a user's interest cannot be ideal as an effective learning environment. This study aims to develop and…

Ship localization in Santa Barbara Channel using machine learning classifiers.

Science.gov (United States)

Niu, Haiqiang; Ozanich, Emma; Gerstoft, Peter

2017-11-01

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

Interaction between age and perceptual similarity in olfactory discrimination learning in F344 rats: relationships with spatial learning

Science.gov (United States)

Yoder, Wendy M.; Gaynor, Leslie S.; Burke, Sara N.; Setlow, Barry; Smith, David W.; Bizon, Jennifer L.

2017-01-01

Emerging evidence suggests that aging is associated with a reduced ability to distinguish perceptually similar stimuli in one’s environment. As the ability to accurately perceive and encode sensory information is foundational for explicit memory, understanding the neurobiological underpinnings of discrimination impairments that emerge with advancing age could help elucidate the mechanisms of mnemonic decline. To this end, there is a need for preclinical approaches that robustly and reliably model age-associated perceptual discrimination deficits. Taking advantage of rodents’ exceptional olfactory abilities, the present study applied rigorous psychophysical techniques to the evaluation of discrimination learning in young and aged F344 rats. Aging did not influence odor detection thresholds or the ability to discriminate between perceptually distinct odorants. In contrast, aged rats were disproportionately impaired relative to young on problems that required discriminations between perceptually similar olfactory stimuli. Importantly, these disproportionate impairments in discrimination learning did not simply reflect a global learning impairment in aged rats, as they performed other types of difficult discriminations on par with young rats. Among aged rats, discrimination deficits were strongly associated with spatial learning deficits. These findings reveal a new, sensitive behavioral approach for elucidating the neural mechanisms of cognitive decline associated with normal aging. PMID:28259065

Predicting Market Impact Costs Using Nonparametric Machine Learning Models.

Science.gov (United States)

Park, Saerom; Lee, Jaewook; Son, Youngdoo

2016-01-01

Market impact cost is the most significant portion of implicit transaction costs that can reduce the overall transaction cost, although it cannot be measured directly. In this paper, we employed the state-of-the-art nonparametric machine learning models: neural networks, Bayesian neural network, Gaussian process, and support vector regression, to predict market impact cost accurately and to provide the predictive model that is versatile in the number of variables. We collected a large amount of real single transaction data of US stock market from Bloomberg Terminal and generated three independent input variables. As a result, most nonparametric machine learning models outperformed a-state-of-the-art benchmark parametric model such as I-star model in four error measures. Although these models encounter certain difficulties in separating the permanent and temporary cost directly, nonparametric machine learning models can be good alternatives in reducing transaction costs by considerably improving in prediction performance.

Accurate estimation of short read mapping quality for next-generation genome sequencing

Science.gov (United States)

Ruffalo, Matthew; Koyutürk, Mehmet; Ray, Soumya; LaFramboise, Thomas

2012-01-01

Motivation: Several software tools specialize in the alignment of short next-generation sequencing reads to a reference sequence. Some of these tools report a mapping quality score for each alignment—in principle, this quality score tells researchers the likelihood that the alignment is correct. However, the reported mapping quality often correlates weakly with actual accuracy and the qualities of many mappings are underestimated, encouraging the researchers to discard correct mappings. Further, these low-quality mappings tend to correlate with variations in the genome (both single nucleotide and structural), and such mappings are important in accurately identifying genomic variants. Approach: We develop a machine learning tool, LoQuM (LOgistic regression tool for calibrating the Quality of short read mappings, to assign reliable mapping quality scores to mappings of Illumina reads returned by any alignment tool. LoQuM uses statistics on the read (base quality scores reported by the sequencer) and the alignment (number of matches, mismatches and deletions, mapping quality score returned by the alignment tool, if available, and number of mappings) as features for classification and uses simulated reads to learn a logistic regression model that relates these features to actual mapping quality. Results: We test the predictions of LoQuM on an independent dataset generated by the ART short read simulation software and observe that LoQuM can ‘resurrect’ many mappings that are assigned zero quality scores by the alignment tools and are therefore likely to be discarded by researchers. We also observe that the recalibration of mapping quality scores greatly enhances the precision of called single nucleotide polymorphisms. Availability: LoQuM is available as open source at http://compbio.case.edu/loqum/. Contact: matthew.ruffalo@case.edu. PMID:22962451

Smart and accurate state-of-charge indication in portable applications

NARCIS (Netherlands)

Pop, V.; Bergveld, H.J.; Notten, P.H.L.; Regtien, P.P.L.

2005-01-01

Accurate state-of-charge (SoC) and remaining run-time indication for portable devices is important for the user-convenience and to prolong the lifetime of batteries. However, the known methods of SoC indication in portable applications are not accurate enough under all practical conditions. The

Smart and accurate State-of-Charge indication in Portable Applications

NARCIS (Netherlands)

Pop, V.; Bergveld, H.J.; Notten, P.H.L.; Regtien, Paulus P.L.

2006-01-01

Accurate state-of-charge (SoC) and remaining run-time indication for portable devices is important for the user-convenience and to prolong the lifetime of batteries. However, the known methods of SoC indication in portable applications are not accurate enough under all practical conditions. The

Patient learning of treatment contents in cognitive therapy.

Science.gov (United States)

Gumport, Nicole B; Dong, Lu; Lee, Jason Y; Harvey, Allison G

2018-03-01

Research has demonstrated that both memory and learning for treatment contents are poor, and that both are associated with worse treatment outcome. The Memory Support Intervention has been shown to improve memory for treatment, but it has not yet been established if this intervention can also improve learning of treatment contents. This study was designed to document the number of times participants exhibited each of the indices of learning, to examine the indices of learning and their relationship to recall of treatment points, and to investigate the association between the indices of learning and depression outcome. Adults diagnosed with major depressive disorder (N = 48) were randomly assigned to 14 sessions of cognitive therapy-as-usual (CT-as-usual) or cognitive therapy plus the Memory Support Intervention (CT + Memory Support). Measures of learning, memory, and depressive symptomatology were taken at mid-treatment, post-treatment, and at 6-month follow-up. Relative to the CT-as-usual group, participants in the CT + Memory Support group reported more accurate thoughts and applications of treatment points at mid-treatment, post-treatment, and 6-month follow-up. Patient recall was significantly correlated with application and cognitive generalization. Thoughts and application at mid-treatment were associated with increased odds of treatment response at post-treatment. The learning measure for this study has not yet been psychometrically validated. The results are based on a small sample. Learning during treatment is poor, but modifiable via the Memory Support Intervention. These results provide encouraging data that improving learning of treatment contents can reduce symptoms during and following treatment. Copyright © 2017 Elsevier Ltd. All rights reserved.

Machine learning approaches for integrating clinical and imaging features in late-life depression classification and response prediction.

Science.gov (United States)

Patel, Meenal J; Andreescu, Carmen; Price, Julie C; Edelman, Kathryn L; Reynolds, Charles F; Aizenstein, Howard J

2015-10-01

Currently, depression diagnosis relies primarily on behavioral symptoms and signs, and treatment is guided by trial and error instead of evaluating associated underlying brain characteristics. Unlike past studies, we attempted to estimate accurate prediction models for late-life depression diagnosis and treatment response using multiple machine learning methods with inputs of multi-modal imaging and non-imaging whole brain and network-based features. Late-life depression patients (medicated post-recruitment) (n = 33) and older non-depressed individuals (n = 35) were recruited. Their demographics and cognitive ability scores were recorded, and brain characteristics were acquired using multi-modal magnetic resonance imaging pretreatment. Linear and nonlinear learning methods were tested for estimating accurate prediction models. A learning method called alternating decision trees estimated the most accurate prediction models for late-life depression diagnosis (87.27% accuracy) and treatment response (89.47% accuracy). The diagnosis model included measures of age, Mini-mental state examination score, and structural imaging (e.g. whole brain atrophy and global white mater hyperintensity burden). The treatment response model included measures of structural and functional connectivity. Combinations of multi-modal imaging and/or non-imaging measures may help better predict late-life depression diagnosis and treatment response. As a preliminary observation, we speculate that the results may also suggest that different underlying brain characteristics defined by multi-modal imaging measures-rather than region-based differences-are associated with depression versus depression recovery because to our knowledge this is the first depression study to accurately predict both using the same approach. These findings may help better understand late-life depression and identify preliminary steps toward personalized late-life depression treatment. Copyright © 2015 John Wiley

Deep Learning in Radiology.

Science.gov (United States)

McBee, Morgan P; Awan, Omer A; Colucci, Andrew T; Ghobadi, Comeron W; Kadom, Nadja; Kansagra, Akash P; Tridandapani, Srini; Auffermann, William F

2018-03-29

As radiology is inherently a data-driven specialty, it is especially conducive to utilizing data processing techniques. One such technique, deep learning (DL), has become a remarkably powerful tool for image processing in recent years. In this work, the Association of University Radiologists Radiology Research Alliance Task Force on Deep Learning provides an overview of DL for the radiologist. This article aims to present an overview of DL in a manner that is understandable to radiologists; to examine past, present, and future applications; as well as to evaluate how radiologists may benefit from this remarkable new tool. We describe several areas within radiology in which DL techniques are having the most significant impact: lesion or disease detection, classification, quantification, and segmentation. The legal and ethical hurdles to implementation are also discussed. By taking advantage of this powerful tool, radiologists can become increasingly more accurate in their interpretations with fewer errors and spend more time to focus on patient care. Copyright © 2018 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved.

The e-Learning Needs Analysis in Graduate Programs of Universitas Negeri Makassar

Directory of Open Access Journals (Sweden)

Nurhikmah Hasyim

2017-12-01

Full Text Available This research aims to develop learning materials and tutorial videos e-learning for students of PPs UNM. Accurately, this research will produce learning materials, video tutorials, and scholarly articles. Product development refers to the ADDIE model (Analysis-Design-Develop-Implement-Evaluate developed by Reiser and Mollenda in 1990. The research subject is graduate PPs UNM and the data gathering methods are documentation, interview, questionnaire, and tests, then analyzed by the descriptive qualitative method. In the first stage of research conducted analysis, i.e., identifying characteristics or profiles of prospective participants learn, identify gaps, and the identification of needs. The result shows, 1 characteristic of participants, i.e., in the range 25-35 years adult category, the respondent's gender dominated by women and respondents are dominated by kindergarten teacher/PAUD until lecturer, and they have a very high motivation to learn the program; 2 Some gap identify based on question form given to the respondents, i.e., they strongly agree with the application of e-learning-based lesson at school and University, but abilities and skills related to the program is still very limited; and 3 needed learning materials in the form of video tutorials that can help them to learn independently and master the lesson of e-learning based program.

Exploring the relationship between sequence similarity and accurate phylogenetic trees.

Science.gov (United States)

Cantarel, Brandi L; Morrison, Hilary G; Pearson, William

2006-11-01

We have characterized the relationship between accurate phylogenetic reconstruction and sequence similarity, testing whether high levels of sequence similarity can consistently produce accurate evolutionary trees. We generated protein families with known phylogenies using a modified version of the PAML/EVOLVER program that produces insertions and deletions as well as substitutions. Protein families were evolved over a range of 100-400 point accepted mutations; at these distances 63% of the families shared significant sequence similarity. Protein families were evolved using balanced and unbalanced trees, with ancient or recent radiations. In families sharing statistically significant similarity, about 60% of multiple sequence alignments were 95% identical to true alignments. To compare recovered topologies with true topologies, we used a score that reflects the fraction of clades that were correctly clustered. As expected, the accuracy of the phylogenies was greatest in the least divergent families. About 88% of phylogenies clustered over 80% of clades in families that shared significant sequence similarity, using Bayesian, parsimony, distance, and maximum likelihood methods. However, for protein families with short ancient branches (ancient radiation), only 30% of the most divergent (but statistically significant) families produced accurate phylogenies, and only about 70% of the second most highly conserved families, with median expectation values better than 10(-60), produced accurate trees. These values represent upper bounds on expected tree accuracy for sequences with a simple divergence history; proteins from 700 Giardia families, with a similar range of sequence similarities but considerably more gaps, produced much less accurate trees. For our simulated insertions and deletions, correct multiple sequence alignments did not perform much better than those produced by T-COFFEE, and including sequences with expressed sequence tag-like sequencing errors did not

Deep learning for studies of galaxy morphology

Science.gov (United States)

Tuccillo, D.; Huertas-Company, M.; Decencière, E.; Velasco-Forero, S.

2017-06-01

Establishing accurate morphological measurements of galaxies in a reasonable amount of time for future big-data surveys such as EUCLID, the Large Synoptic Survey Telescope or the Wide Field Infrared Survey Telescope is a challenge. Because of its high level of abstraction with little human intervention, deep learning appears to be a promising approach. Deep learning is a rapidly growing discipline that models high-level patterns in data as complex multilayered networks. In this work we test the ability of deep convolutional networks to provide parametric properties of Hubble Space Telescope like galaxies (half-light radii, Sérsic indices, total flux etc..). We simulate a set of galaxies including point spread function and realistic noise from the CANDELS survey and try to recover the main galaxy parameters using deep-learning. We compare the results with the ones obtained with the commonly used profile fitting based software GALFIT. This way showing that with our method we obtain results at least equally good as the ones obtained with GALFIT but, once trained, with a factor 5 hundred time faster.

Learning Spatial Object Localization from Vision on a Humanoid Robot

Directory of Open Access Journals (Sweden)

Jürgen Leitner

2012-12-01

Full Text Available We present a combined machine learning and computer vision approach for robots to localize objects. It allows our iCub humanoid to quickly learn to provide accurate 3D position estimates (in the centimetre range of objects seen. Biologically inspired approaches, such as Artificial Neural Networks (ANN and Genetic Programming (GP, are trained to provide these position estimates using the two cameras and the joint encoder readings. No camera calibration or explicit knowledge of the robot's kinematic model is needed. We find that ANN and GP are not just faster and have lower complexity than traditional techniques, but also learn without the need for extensive calibration procedures. In addition, the approach is localizing objects robustly, when placed in the robot's workspace at arbitrary positions, even while the robot is moving its torso, head and eyes.

Fast and accurate computation of projected two-point functions

Science.gov (United States)

Grasshorn Gebhardt, Henry S.; Jeong, Donghui

2018-01-01

We present the two-point function from the fast and accurate spherical Bessel transformation (2-FAST) algorithm1Our code is available at https://github.com/hsgg/twoFAST. for a fast and accurate computation of integrals involving one or two spherical Bessel functions. These types of integrals occur when projecting the galaxy power spectrum P (k ) onto the configuration space, ξℓν(r ), or spherical harmonic space, Cℓ(χ ,χ'). First, we employ the FFTLog transformation of the power spectrum to divide the calculation into P (k )-dependent coefficients and P (k )-independent integrations of basis functions multiplied by spherical Bessel functions. We find analytical expressions for the latter integrals in terms of special functions, for which recursion provides a fast and accurate evaluation. The algorithm, therefore, circumvents direct integration of highly oscillating spherical Bessel functions.

Explanation-based learning in infancy.

Science.gov (United States)

Baillargeon, Renée; DeJong, Gerald F

2017-10-01

In explanation-based learning (EBL), domain knowledge is leveraged in order to learn general rules from few examples. An explanation is constructed for initial exemplars and is then generalized into a candidate rule that uses only the relevant features specified in the explanation; if the rule proves accurate for a few additional exemplars, it is adopted. EBL is thus highly efficient because it combines both analytic and empirical evidence. EBL has been proposed as one of the mechanisms that help infants acquire and revise their physical rules. To evaluate this proposal, 11- and 12-month-olds (n = 260) were taught to replace their current support rule (that an object is stable when half or more of its bottom surface is supported) with a more sophisticated rule (that an object is stable when half or more of the entire object is supported). Infants saw teaching events in which asymmetrical objects were placed on a base, followed by static test displays involving a novel asymmetrical object and a novel base. When the teaching events were designed to facilitate EBL, infants learned the new rule with as few as two (12-month-olds) or three (11-month-olds) exemplars. When the teaching events were designed to impede EBL, however, infants failed to learn the rule. Together, these results demonstrate that even infants, with their limited knowledge about the world, benefit from the knowledge-based approach of EBL.

Focus group discussion in mathematical physics learning

Science.gov (United States)

Ellianawati; Rudiana, D.; Sabandar, J.; Subali, B.

2018-03-01

The Focus Group Discussion (FGD) activity in Mathematical Physics learning has helped students perform the stages of problem solving reflectively. The FGD implementation was conducted to explore the problems and find the right strategy to improve the students' ability to solve the problem accurately which is one of reflective thinking component that has been difficult to improve. The research method used is descriptive qualitative by using single subject response in Physics student. During the FGD process, one student was observed of her reflective thinking development in solving the physics problem. The strategy chosen in the discussion activity was the Cognitive Apprenticeship-Instruction (CA-I) syntax. Based on the results of this study, it is obtained the information that after going through a series of stages of discussion, the students' reflective thinking skills is increased significantly. The scaffolding stage in the CA-I model plays an important role in the process of solving physics problems accurately. Students are able to recognize and formulate problems by describing problem sketches, identifying the variables involved, applying mathematical equations that accord to physics concepts, executing accurately, and applying evaluation by explaining the solution to various contexts.

Accuracy of deep learning, a machine-learning technology, using ultra-wide-field fundus ophthalmoscopy for detecting rhegmatogenous retinal detachment.

Science.gov (United States)

Ohsugi, Hideharu; Tabuchi, Hitoshi; Enno, Hiroki; Ishitobi, Naofumi

2017-08-25

Rhegmatogenous retinal detachment (RRD) is a serious condition that can lead to blindness; however, it is highly treatable with timely and appropriate treatment. Thus, early diagnosis and treatment of RRD is crucial. In this study, we applied deep learning, a machine-learning technology, to detect RRD using ultra-wide-field fundus images and investigated its performance. In total, 411 images (329 for training and 82 for grading) from 407 RRD patients and 420 images (336 for training and 84 for grading) from 238 non-RRD patients were used in this study. The deep learning model demonstrated a high sensitivity of 97.6% [95% confidence interval (CI), 94.2-100%] and a high specificity of 96.5% (95% CI, 90.2-100%), and the area under the curve was 0.988 (95% CI, 0.981-0.995). This model can improve medical care in remote areas where eye clinics are not available by using ultra-wide-field fundus ophthalmoscopy for the accurate diagnosis of RRD. Early diagnosis of RRD can prevent blindness.

Pileup Subtraction and Jet Energy Prediction Using Machine Learning

OpenAIRE

Kong, Vein S; Li, Jiakun; Zhang, Yujia

2015-01-01

In the Large Hardron Collider (LHC), multiple proton-proton collisions cause pileup in reconstructing energy information for a single primary collision (jet). This project aims to select the most important features and create a model to accurately estimate jet energy. Different machine learning methods were explored, including linear regression, support vector regression and decision tree. The best result is obtained by linear regression with predictive features and the performance is improve...

Instance Selection for Classifier Performance Estimation in Meta Learning

OpenAIRE

Marcin Blachnik

2017-01-01

Building an accurate prediction model is challenging and requires appropriate model selection. This process is very time consuming but can be accelerated with meta-learning–automatic model recommendation by estimating the performances of given prediction models without training them. Meta-learning utilizes metadata extracted from the dataset to effectively estimate the accuracy of the model in question. To achieve that goal, metadata descriptors must be gathered efficiently and must be inform...

Upscaling of Surface Soil Moisture Using a Deep Learning Model with VIIRS RDR

Directory of Open Access Journals (Sweden)

Dongying Zhang

2017-04-01

Full Text Available In current upscaling of in situ surface soil moisture practices, commonly used novel statistical or machine learning-based regression models combined with remote sensing data show some advantages in accurately capturing the satellite footprint scale of specific local or regional surface soil moisture. However, the performance of most models is largely determined by the size of the training data and the limited generalization ability to accomplish correlation extraction in regression models, which are unsuitable for larger scale practices. In this paper, a deep learning model was proposed to estimate soil moisture on a national scale. The deep learning model has the advantage of representing nonlinearities and modeling complex relationships from large-scale data. To illustrate the deep learning model for soil moisture estimation, the croplands of China were selected as the study area, and four years of Visible Infrared Imaging Radiometer Suite (VIIRS raw data records (RDR were used as input parameters, then the models were trained and soil moisture estimates were obtained. Results demonstrate that the estimated models captured the complex relationship between the remote sensing variables and in situ surface soil moisture with an adjusted coefficient of determination of R ¯ 2 = 0.9875 and a root mean square error (RMSE of 0.0084 in China. These results were more accurate than the Soil Moisture Active Passive (SMAP active radar soil moisture products and the Global Land data assimilation system (GLDAS 0–10 cm depth soil moisture data. Our study suggests that deep learning model have potential for operational applications of upscaling in situ surface soil moisture data at the national scale.

A system for learning statistical motion patterns.

Science.gov (United States)

Hu, Weiming; Xiao, Xuejuan; Fu, Zhouyu; Xie, Dan; Tan, Tieniu; Maybank, Steve

2006-09-01

Analysis of motion patterns is an effective approach for anomaly detection and behavior prediction. Current approaches for the analysis of motion patterns depend on known scenes, where objects move in predefined ways. It is highly desirable to automatically construct object motion patterns which reflect the knowledge of the scene. In this paper, we present a system for automatically learning motion patterns for anomaly detection and behavior prediction based on a proposed algorithm for robustly tracking multiple objects. In the tracking algorithm, foreground pixels are clustered using a fast accurate fuzzy K-means algorithm. Growing and prediction of the cluster centroids of foreground pixels ensure that each cluster centroid is associated with a moving object in the scene. In the algorithm for learning motion patterns, trajectories are clustered hierarchically using spatial and temporal information and then each motion pattern is represented with a chain of Gaussian distributions. Based on the learned statistical motion patterns, statistical methods are used to detect anomalies and predict behaviors. Our system is tested using image sequences acquired, respectively, from a crowded real traffic scene and a model traffic scene. Experimental results show the robustness of the tracking algorithm, the efficiency of the algorithm for learning motion patterns, and the encouraging performance of algorithms for anomaly detection and behavior prediction.

Accurate bearing remaining useful life prediction based on Weibull distribution and artificial neural network

Science.gov (United States)

Ben Ali, Jaouher; Chebel-Morello, Brigitte; Saidi, Lotfi; Malinowski, Simon; Fnaiech, Farhat

2015-05-01

Accurate remaining useful life (RUL) prediction of critical assets is an important challenge in condition based maintenance to improve reliability and decrease machine's breakdown and maintenance's cost. Bearing is one of the most important components in industries which need to be monitored and the user should predict its RUL. The challenge of this study is to propose an original feature able to evaluate the health state of bearings and to estimate their RUL by Prognostics and Health Management (PHM) techniques. In this paper, the proposed method is based on the data-driven prognostic approach. The combination of Simplified Fuzzy Adaptive Resonance Theory Map (SFAM) neural network and Weibull distribution (WD) is explored. WD is used just in the training phase to fit measurement and to avoid areas of fluctuation in the time domain. SFAM training process is based on fitted measurements at present and previous inspection time points as input. However, the SFAM testing process is based on real measurements at present and previous inspections. Thanks to the fuzzy learning process, SFAM has an important ability and a good performance to learn nonlinear time series. As output, seven classes are defined; healthy bearing and six states for bearing degradation. In order to find the optimal RUL prediction, a smoothing phase is proposed in this paper. Experimental results show that the proposed method can reliably predict the RUL of rolling element bearings (REBs) based on vibration signals. The proposed prediction approach can be applied to prognostic other various mechanical assets.

E-learning and education in radiology

International Nuclear Information System (INIS)

Pinto, Antonio; Brunese, Luca; Pinto, Fabio; Acampora, Ciro; Romano, Luigia

2011-01-01

Purpose: To evaluate current applications of e-learning in radiology. Material and methods: A Medline search was performed using PubMed (National Library of Medicine, Bethesda, MD) for publications discussing the applications of e-learning in radiology. The search strategy employed a single combination of the following terms: (1) e-learning, and (2) education and (3) radiology. This review was limited to human studies and to English-language literature. We reviewed all the titles and subsequent the abstract of 29 articles that appeared pertinent. Additional articles were identified by reviewing the reference lists of relevant papers. Finally, the full text of 38 selected articles was reviewed. Results: Literature data shows that with the constant development of technology and global spread of computer networks, in particular of the Internet, the integration of multimedia and interactivity introduced into electronic publishing has allowed the creation of multimedia applications that provide valuable support for medical teaching and continuing medical education, specifically for radiology. Such technologies are valuable tools for collaboration, interactivity, simulation, and self-testing. However, not everything on the World Wide Web is useful, accurate, or beneficial: the quality and veracity of medical information on the World Wide Web is variable and much time can be wasted as many websites do not meet basic publication standards. Conclusion: E-learning will become an important source of education in radiology.

E-learning and education in radiology.

Science.gov (United States)

Pinto, Antonio; Brunese, Luca; Pinto, Fabio; Acampora, Ciro; Romano, Luigia

2011-06-01

To evaluate current applications of e-learning in radiology. A Medline search was performed using PubMed (National Library of Medicine, Bethesda, MD) for publications discussing the applications of e-learning in radiology. The search strategy employed a single combination of the following terms: (1) e-learning, and (2) education and (3) radiology. This review was limited to human studies and to English-language literature. We reviewed all the titles and subsequent the abstract of 29 articles that appeared pertinent. Additional articles were identified by reviewing the reference lists of relevant papers. Finally, the full text of 38 selected articles was reviewed. Literature data shows that with the constant development of technology and global spread of computer networks, in particular of the Internet, the integration of multimedia and interactivity introduced into electronic publishing has allowed the creation of multimedia applications that provide valuable support for medical teaching and continuing medical education, specifically for radiology. Such technologies are valuable tools for collaboration, interactivity, simulation, and self-testing. However, not everything on the World Wide Web is useful, accurate, or beneficial: the quality and veracity of medical information on the World Wide Web is variable and much time can be wasted as many websites do not meet basic publication standards. E-learning will become an important source of education in radiology. Copyright © 2010 Elsevier Ireland Ltd. All rights reserved.

E-learning and education in radiology

Energy Technology Data Exchange (ETDEWEB)

Pinto, Antonio, E-mail: antopin1968@libero.it [Department of Diagnostic Imaging, A. Cardarelli Hospital, I-80131 Naples (Italy); Brunese, Luca, E-mail: lucabrunese@libero.it [Department of Health Science, Faculty of Medicine and Surgery, University of Molise, I-86100 Campobasso (Italy); Pinto, Fabio, E-mail: fpinto1966@libero.it [Department of Diagnostic Imaging, A. Cardarelli Hospital, I-80131 Naples (Italy); Acampora, Ciro, E-mail: itrasente@libero.it [Department of Diagnostic Imaging, A. Cardarelli Hospital, I-80131 Naples (Italy); Romano, Luigia, E-mail: luigia.romano@fastwebnet.it [Department of Diagnostic Imaging, A. Cardarelli Hospital, I-80131 Naples (Italy)

2011-06-15

Purpose: To evaluate current applications of e-learning in radiology. Material and methods: A Medline search was performed using PubMed (National Library of Medicine, Bethesda, MD) for publications discussing the applications of e-learning in radiology. The search strategy employed a single combination of the following terms: (1) e-learning, and (2) education and (3) radiology. This review was limited to human studies and to English-language literature. We reviewed all the titles and subsequent the abstract of 29 articles that appeared pertinent. Additional articles were identified by reviewing the reference lists of relevant papers. Finally, the full text of 38 selected articles was reviewed. Results: Literature data shows that with the constant development of technology and global spread of computer networks, in particular of the Internet, the integration of multimedia and interactivity introduced into electronic publishing has allowed the creation of multimedia applications that provide valuable support for medical teaching and continuing medical education, specifically for radiology. Such technologies are valuable tools for collaboration, interactivity, simulation, and self-testing. However, not everything on the World Wide Web is useful, accurate, or beneficial: the quality and veracity of medical information on the World Wide Web is variable and much time can be wasted as many websites do not meet basic publication standards. Conclusion: E-learning will become an important source of education in radiology.

Classroom Preschool Science Learning: The Learner, Instructional Tools, and Peer-Learning Assignments

Science.gov (United States)

Reuter, Jamie M.

accurately recall initial predictions, as well as discriminate between the outcome of a scientific manipulation and their original predictions (i.e., to determine whether one's predictions were confirmed). Finally, this dissertation also explores the social context of learning science with peers in the preschool classroom. Due to little prior research in this area, it is currently unclear whether and how preschool children may benefit from working with peers on science activities in the classroom. This work aims to examine preschoolers' collaboration on a science learning activity, as well as the developmental function for such collaborative skills over the preschool years.

Comparing SVM and ANN based Machine Learning Methods for Species Identification of Food Contaminating Beetles.

Science.gov (United States)

Bisgin, Halil; Bera, Tanmay; Ding, Hongjian; Semey, Howard G; Wu, Leihong; Liu, Zhichao; Barnes, Amy E; Langley, Darryl A; Pava-Ripoll, Monica; Vyas, Himansu J; Tong, Weida; Xu, Joshua

2018-04-25

Insect pests, such as pantry beetles, are often associated with food contaminations and public health risks. Machine learning has the potential to provide a more accurate and efficient solution in detecting their presence in food products, which is currently done manually. In our previous research, we demonstrated such feasibility where Artificial Neural Network (ANN) based pattern recognition techniques could be implemented for species identification in the context of food safety. In this study, we present a Support Vector Machine (SVM) model which improved the average accuracy up to 85%. Contrary to this, the ANN method yielded ~80% accuracy after extensive parameter optimization. Both methods showed excellent genus level identification, but SVM showed slightly better accuracy  for most species. Highly accurate species level identification remains a challenge, especially in distinguishing between species from the same genus which may require improvements in both imaging and machine learning techniques. In summary, our work does illustrate a new SVM based technique and provides a good comparison with the ANN model in our context. We believe such insights will pave better way forward for the application of machine learning towards species identification and food safety.

Learning by observation: insights from Williams syndrome.

Science.gov (United States)

Foti, Francesca; Menghini, Deny; Mandolesi, Laura; Federico, Francesca; Vicari, Stefano; Petrosini, Laura

2013-01-01

Observing another person performing a complex action accelerates the observer's acquisition of the same action and limits the time-consuming process of learning by trial and error. Observational learning makes an interesting and potentially important topic in the developmental domain, especially when disorders are considered. The implications of studies aimed at clarifying whether and how this form of learning is spared by pathology are manifold. We focused on a specific population with learning and intellectual disabilities, the individuals with Williams syndrome. The performance of twenty-eight individuals with Williams syndrome was compared with that of mental age- and gender-matched thirty-two typically developing children on tasks of learning of a visuo-motor sequence by observation or by trial and error. Regardless of the learning modality, acquiring the correct sequence involved three main phases: a detection phase, in which participants discovered the correct sequence and learned how to perform the task; an exercise phase, in which they reproduced the sequence until performance was error-free; an automatization phase, in which by repeating the error-free sequence they became accurate and speedy. Participants with Williams syndrome beneficiated of observational training (in which they observed an actor detecting the visuo-motor sequence) in the detection phase, while they performed worse than typically developing children in the exercise and automatization phases. Thus, by exploiting competencies learned by observation, individuals with Williams syndrome detected the visuo-motor sequence, putting into action the appropriate procedural strategies. Conversely, their impaired performances in the exercise phases appeared linked to impaired spatial working memory, while their deficits in automatization phases to deficits in processes increasing efficiency and speed of the response. Overall, observational experience was advantageous for acquiring competencies

Learning by observation: insights from Williams syndrome.

Directory of Open Access Journals (Sweden)

Francesca Foti

Full Text Available Observing another person performing a complex action accelerates the observer's acquisition of the same action and limits the time-consuming process of learning by trial and error. Observational learning makes an interesting and potentially important topic in the developmental domain, especially when disorders are considered. The implications of studies aimed at clarifying whether and how this form of learning is spared by pathology are manifold. We focused on a specific population with learning and intellectual disabilities, the individuals with Williams syndrome. The performance of twenty-eight individuals with Williams syndrome was compared with that of mental age- and gender-matched thirty-two typically developing children on tasks of learning of a visuo-motor sequence by observation or by trial and error. Regardless of the learning modality, acquiring the correct sequence involved three main phases: a detection phase, in which participants discovered the correct sequence and learned how to perform the task; an exercise phase, in which they reproduced the sequence until performance was error-free; an automatization phase, in which by repeating the error-free sequence they became accurate and speedy. Participants with Williams syndrome beneficiated of observational training (in which they observed an actor detecting the visuo-motor sequence in the detection phase, while they performed worse than typically developing children in the exercise and automatization phases. Thus, by exploiting competencies learned by observation, individuals with Williams syndrome detected the visuo-motor sequence, putting into action the appropriate procedural strategies. Conversely, their impaired performances in the exercise phases appeared linked to impaired spatial working memory, while their deficits in automatization phases to deficits in processes increasing efficiency and speed of the response. Overall, observational experience was advantageous for

Defining the Undefinable: Operationalization of Methods to Identify Specific Learning Disabilities among Practicing School Psychologists

Science.gov (United States)

Cottrell, Joseph M.; Barrett, Courtenay A.

2016-01-01

Accurate and consistent identification of students with specific learning disabilities (SLDs) is crucial; however, state and district guidelines regarding identification methods lack operationalization and are inconsistent throughout the United States. In the current study, the authors surveyed 471 school psychologists about "school" SLD…

Equipment upgrade - Accurate positioning of ion chambers

International Nuclear Information System (INIS)

Doane, Harry J.; Nelson, George W.

1990-01-01

Five adjustable clamps were made to firmly support and accurately position the ion Chambers, that provide signals to the power channels for the University of Arizona TRIGA reactor. The design requirements, fabrication procedure and installation are described

Support patient search on pathology reports with interactive online learning based data extraction.

Science.gov (United States)

Zheng, Shuai; Lu, James J; Appin, Christina; Brat, Daniel; Wang, Fusheng

2015-01-01

more accurate knowledge to support biomedical research and clinical diagnosis. IDEAL-X provides a bridge that takes advantage of online machine learning based data extraction and the knowledge from human's feedback. By combining iterative online learning and adaptive controlled vocabularies, IDEAL-X can deliver highly adaptive and accurate data extraction to support patient search.

The drift diffusion model as the choice rule in reinforcement learning.

Science.gov (United States)

Pedersen, Mads Lund; Frank, Michael J; Biele, Guido

2017-08-01

Current reinforcement-learning models often assume simplified decision processes that do not fully reflect the dynamic complexities of choice processes. Conversely, sequential-sampling models of decision making account for both choice accuracy and response time, but assume that decisions are based on static decision values. To combine these two computational models of decision making and learning, we implemented reinforcement-learning models in which the drift diffusion model describes the choice process, thereby capturing both within- and across-trial dynamics. To exemplify the utility of this approach, we quantitatively fit data from a common reinforcement-learning paradigm using hierarchical Bayesian parameter estimation, and compared model variants to determine whether they could capture the effects of stimulant medication in adult patients with attention-deficit hyperactivity disorder (ADHD). The model with the best relative fit provided a good description of the learning process, choices, and response times. A parameter recovery experiment showed that the hierarchical Bayesian modeling approach enabled accurate estimation of the model parameters. The model approach described here, using simultaneous estimation of reinforcement-learning and drift diffusion model parameters, shows promise for revealing new insights into the cognitive and neural mechanisms of learning and decision making, as well as the alteration of such processes in clinical groups.

Enhanced Quality Control in Pharmaceutical Applications by Combining Raman Spectroscopy and Machine Learning Techniques

Science.gov (United States)

Martinez, J. C.; Guzmán-Sepúlveda, J. R.; Bolañoz Evia, G. R.; Córdova, T.; Guzmán-Cabrera, R.

2018-06-01

In this work, we applied machine learning techniques to Raman spectra for the characterization and classification of manufactured pharmaceutical products. Our measurements were taken with commercial equipment, for accurate assessment of variations with respect to one calibrated control sample. Unlike the typical use of Raman spectroscopy in pharmaceutical applications, in our approach the principal components of the Raman spectrum are used concurrently as attributes in machine learning algorithms. This permits an efficient comparison and classification of the spectra measured from the samples under study. This also allows for accurate quality control as all relevant spectral components are considered simultaneously. We demonstrate our approach with respect to the specific case of acetaminophen, which is one of the most widely used analgesics in the market. In the experiments, commercial samples from thirteen different laboratories were analyzed and compared against a control sample. The raw data were analyzed based on an arithmetic difference between the nominal active substance and the measured values in each commercial sample. The principal component analysis was applied to the data for quantitative verification (i.e., without considering the actual concentration of the active substance) of the difference in the calibrated sample. Our results show that by following this approach adulterations in pharmaceutical compositions can be clearly identified and accurately quantified.

ROLAIDS-CPM: A code for accurate resonance absorption calculations

International Nuclear Information System (INIS)

Kruijf, W.J.M. de.

1993-08-01

ROLAIDS is used to calculate group-averaged cross sections for specific zones in a one-dimensional geometry. This report describes ROLAIDS-CPM which is an extended version of ROLAIDS. The main extension in ROLAIDS-CPM is the possibility to use the collision probability method for a slab- or cylinder-geometry instead of the less accurate interface-currents method. In this way accurate resonance absorption calculations can be performed with ROLAIDS-CPM. ROLAIDS-CPM has been developed at ECN. (orig.)

Neuropsychological Test Selection for Cognitive Impairment Classification: A Machine Learning Approach

Science.gov (United States)

Williams, Jennifer A.; Schmitter-Edgecombe, Maureen; Cook, Diane J.

2016-01-01

Introduction Reducing the amount of testing required to accurately detect cognitive impairment is clinically relevant. The aim of this research was to determine the fewest number of clinical measures required to accurately classify participants as healthy older adult, mild cognitive impairment (MCI) or dementia using a suite of classification techniques. Methods Two variable selection machine learning models (i.e., naive Bayes, decision tree), a logistic regression, and two participant datasets (i.e., clinical diagnosis, clinical dementia rating; CDR) were explored. Participants classified using clinical diagnosis criteria included 52 individuals with dementia, 97 with MCI, and 161 cognitively healthy older adults. Participants classified using CDR included 154 individuals CDR = 0, 93 individuals with CDR = 0.5, and 25 individuals with CDR = 1.0+. Twenty-seven demographic, psychological, and neuropsychological variables were available for variable selection. Results No significant difference was observed between naive Bayes, decision tree, and logistic regression models for classification of both clinical diagnosis and CDR datasets. Participant classification (70.0 – 99.1%), geometric mean (60.9 – 98.1%), sensitivity (44.2 – 100%), and specificity (52.7 – 100%) were generally satisfactory. Unsurprisingly, the MCI/CDR = 0.5 participant group was the most challenging to classify. Through variable selection only 2 – 9 variables were required for classification and varied between datasets in a clinically meaningful way. Conclusions The current study results reveal that machine learning techniques can accurately classifying cognitive impairment and reduce the number of measures required for diagnosis. PMID:26332171

Model-based iterative learning control of Parkinsonian state in thalamic relay neuron

Science.gov (United States)

Liu, Chen; Wang, Jiang; Li, Huiyan; Xue, Zhiqin; Deng, Bin; Wei, Xile

2014-09-01

Although the beneficial effects of chronic deep brain stimulation on Parkinson's disease motor symptoms are now largely confirmed, the underlying mechanisms behind deep brain stimulation remain unclear and under debate. Hence, the selection of stimulation parameters is full of challenges. Additionally, due to the complexity of neural system, together with omnipresent noises, the accurate model of thalamic relay neuron is unknown. Thus, the iterative learning control of the thalamic relay neuron's Parkinsonian state based on various variables is presented. Combining the iterative learning control with typical proportional-integral control algorithm, a novel and efficient control strategy is proposed, which does not require any particular knowledge on the detailed physiological characteristics of cortico-basal ganglia-thalamocortical loop and can automatically adjust the stimulation parameters. Simulation results demonstrate the feasibility of the proposed control strategy to restore the fidelity of thalamic relay in the Parkinsonian condition. Furthermore, through changing the important parameter—the maximum ionic conductance densities of low-threshold calcium current, the dominant characteristic of the proposed method which is independent of the accurate model can be further verified.

A Combination Tissue Engineering Strategy for Schwann Cell-Induced Spinal Cord Repair

Science.gov (United States)

2016-10-01

and Biopharmaceutics, 2005. 61(3): p. 171-180. 6. Sellers, D.L., et al., Poly (lactic-co-glycolic) acid microspheres encapsulated in Pluronic F- 127...described (Greiner and Wendorff, 2007; Lee et al., 2011; Weber et al., 2010). 15% (w/v) of poly (vinylidene fluoride trifluoroethylene) (65/35) (PVDF...UK) was administrated twice a day for 3 days immediately after surgery to reduce pain . Gentamycin (APP Pharmaceuticals, LLC, Schaumburg, IL, 40 mg

Bio-Inspired Controllable Adhesive

Science.gov (United States)

2008-12-01

pad of the tarsus – which act as a sort of hydraulic suspension. The lamellae contain rows of thin slender fibers , called setae, approximately 130 µm...in length and 20 µm in diameter (Hildebrand, 1988), Fig.1. The terminus of each seta branches into thousands of smaller fibers , or spatular stalks...ADHESION TESTING The structures were characterized (Northen et al., 2008) using a home-built adhesion test apparatus ( Basalt - II) with C. Greiner

Amp: A modular approach to machine learning in atomistic simulations

Science.gov (United States)

Khorshidi, Alireza; Peterson, Andrew A.

2016-10-01

Electronic structure calculations, such as those employing Kohn-Sham density functional theory or ab initio wavefunction theories, have allowed for atomistic-level understandings of a wide variety of phenomena and properties of matter at small scales. However, the computational cost of electronic structure methods drastically increases with length and time scales, which makes these methods difficult for long time-scale molecular dynamics simulations or large-sized systems. Machine-learning techniques can provide accurate potentials that can match the quality of electronic structure calculations, provided sufficient training data. These potentials can then be used to rapidly simulate large and long time-scale phenomena at similar quality to the parent electronic structure approach. Machine-learning potentials usually take a bias-free mathematical form and can be readily developed for a wide variety of systems. Electronic structure calculations have favorable properties-namely that they are noiseless and targeted training data can be produced on-demand-that make them particularly well-suited for machine learning. This paper discusses our modular approach to atomistic machine learning through the development of the open-source Atomistic Machine-learning Package (Amp), which allows for representations of both the total and atom-centered potential energy surface, in both periodic and non-periodic systems. Potentials developed through the atom-centered approach are simultaneously applicable for systems with various sizes. Interpolation can be enhanced by introducing custom descriptors of the local environment. We demonstrate this in the current work for Gaussian-type, bispectrum, and Zernike-type descriptors. Amp has an intuitive and modular structure with an interface through the python scripting language yet has parallelizable fortran components for demanding tasks; it is designed to integrate closely with the widely used Atomic Simulation Environment (ASE), which

MR PROSTATE SEGMENTATION VIA DISTRIBUTED DISCRIMINATIVE DICTIONARY (DDD) LEARNING.

Science.gov (United States)

Guo, Yanrong; Zhan, Yiqiang; Gao, Yaozong; Jiang, Jianguo; Shen, Dinggang

2013-01-01

Segmenting prostate from MR images is important yet challenging. Due to non-Gaussian distribution of prostate appearances in MR images, the popular active appearance model (AAM) has its limited performance. Although the newly developed sparse dictionary learning method[1, 2] can model the image appearance in a non-parametric fashion, the learned dictionaries still lack the discriminative power between prostate and non-prostate tissues, which is critical for accurate prostate segmentation. In this paper, we propose to integrate deformable model with a novel learning scheme, namely the Distributed Discriminative Dictionary ( DDD ) learning, which can capture image appearance in a non-parametric and discriminative fashion. In particular, three strategies are designed to boost the tissue discriminative power of DDD. First , minimum Redundancy Maximum Relevance (mRMR) feature selection is performed to constrain the dictionary learning in a discriminative feature space. Second , linear discriminant analysis (LDA) is employed to assemble residuals from different dictionaries for optimal separation between prostate and non-prostate tissues. Third , instead of learning the global dictionaries, we learn a set of local dictionaries for the local regions (each with small appearance variations) along prostate boundary, thus achieving better tissue differentiation locally. In the application stage, DDDs will provide the appearance cues to robustly drive the deformable model onto the prostate boundary. Experiments on 50 MR prostate images show that our method can yield a Dice Ratio of 88% compared to the manual segmentations, and have 7% improvement over the conventional AAM.

Predicting Market Impact Costs Using Nonparametric Machine Learning Models.

Directory of Open Access Journals (Sweden)

Saerom Park

Full Text Available Market impact cost is the most significant portion of implicit transaction costs that can reduce the overall transaction cost, although it cannot be measured directly. In this paper, we employed the state-of-the-art nonparametric machine learning models: neural networks, Bayesian neural network, Gaussian process, and support vector regression, to predict market impact cost accurately and to provide the predictive model that is versatile in the number of variables. We collected a large amount of real single transaction data of US stock market from Bloomberg Terminal and generated three independent input variables. As a result, most nonparametric machine learning models outperformed a-state-of-the-art benchmark parametric model such as I-star model in four error measures. Although these models encounter certain difficulties in separating the permanent and temporary cost directly, nonparametric machine learning models can be good alternatives in reducing transaction costs by considerably improving in prediction performance.

An accurate metric for the spacetime around neutron stars

OpenAIRE

Pappas, George

2016-01-01

The problem of having an accurate description of the spacetime around neutron stars is of great astrophysical interest. For astrophysical applications, one needs to have a metric that captures all the properties of the spacetime around a neutron star. Furthermore, an accurate appropriately parameterised metric, i.e., a metric that is given in terms of parameters that are directly related to the physical structure of the neutron star, could be used to solve the inverse problem, which is to inf...

Evaluating the diagnostic utility of applying a machine learning algorithm to diffusion tensor MRI measures in individuals with major depressive disorder.

Science.gov (United States)

Schnyer, David M; Clasen, Peter C; Gonzalez, Christopher; Beevers, Christopher G

2017-06-30

Using MRI to diagnose mental disorders has been a long-term goal. Despite this, the vast majority of prior neuroimaging work has been descriptive rather than predictive. The current study applies support vector machine (SVM) learning to MRI measures of brain white matter to classify adults with Major Depressive Disorder (MDD) and healthy controls. In a precisely matched group of individuals with MDD (n =25) and healthy controls (n =25), SVM learning accurately (74%) classified patients and controls across a brain map of white matter fractional anisotropy values (FA). The study revealed three main findings: 1) SVM applied to DTI derived FA maps can accurately classify MDD vs. healthy controls; 2) prediction is strongest when only right hemisphere white matter is examined; and 3) removing FA values from a region identified by univariate contrast as significantly different between MDD and healthy controls does not change the SVM accuracy. These results indicate that SVM learning applied to neuroimaging data can classify the presence versus absence of MDD and that predictive information is distributed across brain networks rather than being highly localized. Finally, MDD group differences revealed through typical univariate contrasts do not necessarily reveal patterns that provide accurate predictive information. Copyright © 2017 Elsevier Ireland Ltd. All rights reserved.

Machine learning and predictive data analytics enabling metrology and process control in IC fabrication

Science.gov (United States)

Rana, Narender; Zhang, Yunlin; Wall, Donald; Dirahoui, Bachir; Bailey, Todd C.

2015-03-01

Integrate circuit (IC) technology is going through multiple changes in terms of patterning techniques (multiple patterning, EUV and DSA), device architectures (FinFET, nanowire, graphene) and patterning scale (few nanometers). These changes require tight controls on processes and measurements to achieve the required device performance, and challenge the metrology and process control in terms of capability and quality. Multivariate data with complex nonlinear trends and correlations generally cannot be described well by mathematical or parametric models but can be relatively easily learned by computing machines and used to predict or extrapolate. This paper introduces the predictive metrology approach which has been applied to three different applications. Machine learning and predictive analytics have been leveraged to accurately predict dimensions of EUV resist patterns down to 18 nm half pitch leveraging resist shrinkage patterns. These patterns could not be directly and accurately measured due to metrology tool limitations. Machine learning has also been applied to predict the electrical performance early in the process pipeline for deep trench capacitance and metal line resistance. As the wafer goes through various processes its associated cost multiplies. It may take days to weeks to get the electrical performance readout. Predicting the electrical performance early on can be very valuable in enabling timely actionable decision such as rework, scrap, feedforward, feedback predicted information or information derived from prediction to improve or monitor processes. This paper provides a general overview of machine learning and advanced analytics application in the advanced semiconductor development and manufacturing.

From rapid place learning to behavioral performance: a key role for the intermediate hippocampus.

Directory of Open Access Journals (Sweden)

Tobias Bast

2009-04-01

Full Text Available Rapid place encoding by hippocampal neurons, as reflected by place-related firing, has been intensely studied, whereas the substrates that translate hippocampal place codes into behavior have received little attention. A key point relevant to this translation is that hippocampal organization is characterized by functional-anatomical gradients along the septotemporal axis: Whereas the ability of hippocampal neurons to encode accurate place information declines from the septal to temporal end, hippocampal connectivity to prefrontal and subcortical sites that might relate such place information to behavioral-control processes shows an opposite gradient. We examined in rats the impact of selective lesions to relevant parts of the hippocampus on behavioral tests requiring place learning (watermaze procedures and on in vivo electrophysiological models of hippocampal encoding (long-term potentiation [LTP], place cells. We found that the intermediate hippocampus is necessary and largely sufficient for behavioral performance based on rapid place learning. In contrast, a residual septal pole of the hippocampus, although displaying intact electrophysiological indices of rapid information encoding (LTP, precise place-related firing, and rapid remapping, failed to sustain watermaze performance based on rapid place learning. These data highlight the important distinction between hippocampal encoding and the behavioral performance based on such encoding, and suggest that the intermediate hippocampus, where substrates of rapid accurate place encoding converge with links to behavioral control, is critical to translate rapid (one-trial place learning into navigational performance.

Machine learning for predicting soil classes in three semi-arid landscapes

Science.gov (United States)

Brungard, Colby W.; Boettinger, Janis L.; Duniway, Michael C.; Wills, Skye A.; Edwards, Thomas C.

2015-01-01

Mapping the spatial distribution of soil taxonomic classes is important for informing soil use and management decisions. Digital soil mapping (DSM) can quantitatively predict the spatial distribution of soil taxonomic classes. Key components of DSM are the method and the set of environmental covariates used to predict soil classes. Machine learning is a general term for a broad set of statistical modeling techniques. Many different machine learning models have been applied in the literature and there are different approaches for selecting covariates for DSM. However, there is little guidance as to which, if any, machine learning model and covariate set might be optimal for predicting soil classes across different landscapes. Our objective was to compare multiple machine learning models and covariate sets for predicting soil taxonomic classes at three geographically distinct areas in the semi-arid western United States of America (southern New Mexico, southwestern Utah, and northeastern Wyoming). All three areas were the focus of digital soil mapping studies. Sampling sites at each study area were selected using conditioned Latin hypercube sampling (cLHS). We compared models that had been used in other DSM studies, including clustering algorithms, discriminant analysis, multinomial logistic regression, neural networks, tree based methods, and support vector machine classifiers. Tested machine learning models were divided into three groups based on model complexity: simple, moderate, and complex. We also compared environmental covariates derived from digital elevation models and Landsat imagery that were divided into three different sets: 1) covariates selected a priori by soil scientists familiar with each area and used as input into cLHS, 2) the covariates in set 1 plus 113 additional covariates, and 3) covariates selected using recursive feature elimination. Overall, complex models were consistently more accurate than simple or moderately complex models. Random

Moving virtuality into reality: A comparison study of the effectiveness of traditional and alternative assessments of learning in a multisensory, fully immersive physics program

Science.gov (United States)

Gamor, Keysha Ingram

This paper contains a research study that investigated the relative efficacy of using both a traditional paper-and-pencil assessment instrument and an alternative, virtual reality (VR) assessment instrument to assist educators and/or instructional designers in measuring learning in a virtual reality learning environment. To this end, this research study investigated assessment in VR, with the goal of analyzing aspects of student learning in VR that are feasible to access or capture by traditional assessments and alternative assessments. The researcher also examined what additional types of learning alternative assessments may offer. More specifically, this study compared the effectiveness of a traditional method with an alternative (performance-based) method of assessment that was used to examine the ability of the tools to accurately evidence the levels of students' understanding and learning. The domain area was electrostatics, a complex, abstract multidimensional concept, with which students often experience difficulty. Outcomes of the study suggest that, in the evaluation of learning in an immersive VR learning environment, assessments would most accurately manifest student learning if the assessment measure matched the learning environment itself. In this study, learning and assessing in the VR environment yielded higher final test scores than learning in VR and testing with traditional paper-and-pencil. Being able to transfer knowledge from a VR environment to other situations is critical in demonstrating the overall level of understanding of a concept. For this reason, the researcher recommends a combination of testing measures to enhance understanding of complex, abstract concepts.

Efficient Learning for the Poor: New Insights into Literacy Acquisition for Children

Science.gov (United States)

Abadzi, Helen

2008-01-01

Reading depends on the speed of visual recognition and capacity of short-term memory. To understand a sentence, the mind must read it fast enough to capture it within the limits of the short-term memory. This means that children must attain a minimum speed of fairly accurate reading to understand a passage. Learning to read involves "tricking" the…

Symmetry-Adapted Machine Learning for Tensorial Properties of Atomistic Systems.

Science.gov (United States)

Grisafi, Andrea; Wilkins, David M; Csányi, Gábor; Ceriotti, Michele

2018-01-19

Statistical learning methods show great promise in providing an accurate prediction of materials and molecular properties, while minimizing the need for computationally demanding electronic structure calculations. The accuracy and transferability of these models are increased significantly by encoding into the learning procedure the fundamental symmetries of rotational and permutational invariance of scalar properties. However, the prediction of tensorial properties requires that the model respects the appropriate geometric transformations, rather than invariance, when the reference frame is rotated. We introduce a formalism that extends existing schemes and makes it possible to perform machine learning of tensorial properties of arbitrary rank, and for general molecular geometries. To demonstrate it, we derive a tensor kernel adapted to rotational symmetry, which is the natural generalization of the smooth overlap of atomic positions kernel commonly used for the prediction of scalar properties at the atomic scale. The performance and generality of the approach is demonstrated by learning the instantaneous response to an external electric field of water oligomers of increasing complexity, from the isolated molecule to the condensed phase.

Automated analysis of high-content microscopy data with deep learning.

Science.gov (United States)

Kraus, Oren Z; Grys, Ben T; Ba, Jimmy; Chong, Yolanda; Frey, Brendan J; Boone, Charles; Andrews, Brenda J

2017-04-18

Existing computational pipelines for quantitative analysis of high-content microscopy data rely on traditional machine learning approaches that fail to accurately classify more than a single dataset without substantial tuning and training, requiring extensive analysis. Here, we demonstrate that the application of deep learning to biological image data can overcome the pitfalls associated with conventional machine learning classifiers. Using a deep convolutional neural network (DeepLoc) to analyze yeast cell images, we show improved performance over traditional approaches in the automated classification of protein subcellular localization. We also demonstrate the ability of DeepLoc to classify highly divergent image sets, including images of pheromone-arrested cells with abnormal cellular morphology, as well as images generated in different genetic backgrounds and in different laboratories. We offer an open-source implementation that enables updating DeepLoc on new microscopy datasets. This study highlights deep learning as an important tool for the expedited analysis of high-content microscopy data. © 2017 The Authors. Published under the terms of the CC BY 4.0 license.

Learning Orthographic Structure With Sequential Generative Neural Networks.

Science.gov (United States)

Testolin, Alberto; Stoianov, Ivilin; Sperduti, Alessandro; Zorzi, Marco

2016-04-01

Learning the structure of event sequences is a ubiquitous problem in cognition and particularly in language. One possible solution is to learn a probabilistic generative model of sequences that allows making predictions about upcoming events. Though appealing from a neurobiological standpoint, this approach is typically not pursued in connectionist modeling. Here, we investigated a sequential version of the restricted Boltzmann machine (RBM), a stochastic recurrent neural network that extracts high-order structure from sensory data through unsupervised generative learning and can encode contextual information in the form of internal, distributed representations. We assessed whether this type of network can extract the orthographic structure of English monosyllables by learning a generative model of the letter sequences forming a word training corpus. We show that the network learned an accurate probabilistic model of English graphotactics, which can be used to make predictions about the letter following a given context as well as to autonomously generate high-quality pseudowords. The model was compared to an extended version of simple recurrent networks, augmented with a stochastic process that allows autonomous generation of sequences, and to non-connectionist probabilistic models (n-grams and hidden Markov models). We conclude that sequential RBMs and stochastic simple recurrent networks are promising candidates for modeling cognition in the temporal domain. Copyright © 2015 Cognitive Science Society, Inc.

Discovery and Use of Online Learning Resources: Case Study Findings

Directory of Open Access Journals (Sweden)

Laurie Miller Nelson

2004-04-01

Full Text Available Much recent research and funding have focused on building Internet-based repositories that contain collections of high-quality learning resources, often called ‘learning objects.’ Yet little is known about how non-specialist users, in particular teachers, find, access, and use digital learning resources. To address this gap, this article describes a case study of mathematics and science teachers’ practices and desires surrounding the discovery, selection, and use of digital library resources for instructional purposes. Findings suggest that the teacher participants used a broad range of search strategies in order to find resources that they deemed were age-appropriate, current, and accurate. They intended to include these resources with little modifications into planned instructional activities. The article concludes with a discussion of the implications of the findings for improving the design of educational digital library systems, including tools supporting resource reuse.

Impacts of visuomotor sequence learning methods on speed and accuracy: Starting over from the beginning or from the point of error.

Science.gov (United States)

Tanaka, Kanji; Watanabe, Katsumi

2016-02-01

The present study examined whether sequence learning led to more accurate and shorter performance time if people who are learning a sequence start over from the beginning when they make an error (i.e., practice the whole sequence) or only from the point of error (i.e., practice a part of the sequence). We used a visuomotor sequence learning paradigm with a trial-and-error procedure. In Experiment 1, we found fewer errors, and shorter performance time for those who restarted their performance from the beginning of the sequence as compared to those who restarted from the point at which an error occurred, indicating better learning of spatial and motor representations of the sequence. This might be because the learned elements were repeated when the next performance started over from the beginning. In subsequent experiments, we increased the occasions for the repetitions of learned elements by modulating the number of fresh start points in the sequence after errors. The results showed that fewer fresh start points were likely to lead to fewer errors and shorter performance time, indicating that the repetitions of learned elements enabled participants to develop stronger spatial and motor representations of the sequence. Thus, a single or two fresh start points in the sequence (i.e., starting over only from the beginning or from the beginning or midpoint of the sequence after errors) is likely to lead to more accurate and faster performance. Copyright © 2016 Elsevier B.V. All rights reserved.

Brain networks for confidence weighting and hierarchical inference during probabilistic learning.

Science.gov (United States)

Meyniel, Florent; Dehaene, Stanislas

2017-05-09

Learning is difficult when the world fluctuates randomly and ceaselessly. Classical learning algorithms, such as the delta rule with constant learning rate, are not optimal. Mathematically, the optimal learning rule requires weighting prior knowledge and incoming evidence according to their respective reliabilities. This "confidence weighting" implies the maintenance of an accurate estimate of the reliability of what has been learned. Here, using fMRI and an ideal-observer analysis, we demonstrate that the brain's learning algorithm relies on confidence weighting. While in the fMRI scanner, human adults attempted to learn the transition probabilities underlying an auditory or visual sequence, and reported their confidence in those estimates. They knew that these transition probabilities could change simultaneously at unpredicted moments, and therefore that the learning problem was inherently hierarchical. Subjective confidence reports tightly followed the predictions derived from the ideal observer. In particular, subjects managed to attach distinct levels of confidence to each learned transition probability, as required by Bayes-optimal inference. Distinct brain areas tracked the likelihood of new observations given current predictions, and the confidence in those predictions. Both signals were combined in the right inferior frontal gyrus, where they operated in agreement with the confidence-weighting model. This brain region also presented signatures of a hierarchical process that disentangles distinct sources of uncertainty. Together, our results provide evidence that the sense of confidence is an essential ingredient of probabilistic learning in the human brain, and that the right inferior frontal gyrus hosts a confidence-based statistical learning algorithm for auditory and visual sequences.

Brain networks for confidence weighting and hierarchical inference during probabilistic learning

Science.gov (United States)

Meyniel, Florent; Dehaene, Stanislas

2017-01-01

Learning is difficult when the world fluctuates randomly and ceaselessly. Classical learning algorithms, such as the delta rule with constant learning rate, are not optimal. Mathematically, the optimal learning rule requires weighting prior knowledge and incoming evidence according to their respective reliabilities. This “confidence weighting” implies the maintenance of an accurate estimate of the reliability of what has been learned. Here, using fMRI and an ideal-observer analysis, we demonstrate that the brain’s learning algorithm relies on confidence weighting. While in the fMRI scanner, human adults attempted to learn the transition probabilities underlying an auditory or visual sequence, and reported their confidence in those estimates. They knew that these transition probabilities could change simultaneously at unpredicted moments, and therefore that the learning problem was inherently hierarchical. Subjective confidence reports tightly followed the predictions derived from the ideal observer. In particular, subjects managed to attach distinct levels of confidence to each learned transition probability, as required by Bayes-optimal inference. Distinct brain areas tracked the likelihood of new observations given current predictions, and the confidence in those predictions. Both signals were combined in the right inferior frontal gyrus, where they operated in agreement with the confidence-weighting model. This brain region also presented signatures of a hierarchical process that disentangles distinct sources of uncertainty. Together, our results provide evidence that the sense of confidence is an essential ingredient of probabilistic learning in the human brain, and that the right inferior frontal gyrus hosts a confidence-based statistical learning algorithm for auditory and visual sequences. PMID:28439014

Caudate nucleus reactivity predicts perceptual learning rate for visual feature conjunctions.

Science.gov (United States)

Reavis, Eric A; Frank, Sebastian M; Tse, Peter U

2015-04-15

Useful information in the visual environment is often contained in specific conjunctions of visual features (e.g., color and shape). The ability to quickly and accurately process such conjunctions can be learned. However, the neural mechanisms responsible for such learning remain largely unknown. It has been suggested that some forms of visual learning might involve the dopaminergic neuromodulatory system (Roelfsema et al., 2010; Seitz and Watanabe, 2005), but this hypothesis has not yet been directly tested. Here we test the hypothesis that learning visual feature conjunctions involves the dopaminergic system, using functional neuroimaging, genetic assays, and behavioral testing techniques. We use a correlative approach to evaluate potential associations between individual differences in visual feature conjunction learning rate and individual differences in dopaminergic function as indexed by neuroimaging and genetic markers. We find a significant correlation between activity in the caudate nucleus (a component of the dopaminergic system connected to visual areas of the brain) and visual feature conjunction learning rate. Specifically, individuals who showed a larger difference in activity between positive and negative feedback on an unrelated cognitive task, indicative of a more reactive dopaminergic system, learned visual feature conjunctions more quickly than those who showed a smaller activity difference. This finding supports the hypothesis that the dopaminergic system is involved in visual learning, and suggests that visual feature conjunction learning could be closely related to associative learning. However, no significant, reliable correlations were found between feature conjunction learning and genotype or dopaminergic activity in any other regions of interest. Copyright © 2015 Elsevier Inc. All rights reserved.

A fully automated Drosophila olfactory classical conditioning and testing system for behavioral learning and memory assessment.

Science.gov (United States)

Jiang, Hui; Hanna, Eriny; Gatto, Cheryl L; Page, Terry L; Bhuva, Bharat; Broadie, Kendal

2016-03-01

Aversive olfactory classical conditioning has been the standard method to assess Drosophila learning and memory behavior for decades, yet training and testing are conducted manually under exceedingly labor-intensive conditions. To overcome this severe limitation, a fully automated, inexpensive system has been developed, which allows accurate and efficient Pavlovian associative learning/memory analyses for high-throughput pharmacological and genetic studies. The automated system employs a linear actuator coupled to an odorant T-maze with airflow-mediated transfer of animals between training and testing stages. Odorant, airflow and electrical shock delivery are automatically administered and monitored during training trials. Control software allows operator-input variables to define parameters of Drosophila learning, short-term memory and long-term memory assays. The approach allows accurate learning/memory determinations with operational fail-safes. Automated learning indices (immediately post-training) and memory indices (after 24h) are comparable to traditional manual experiments, while minimizing experimenter involvement. The automated system provides vast improvements over labor-intensive manual approaches with no experimenter involvement required during either training or testing phases. It provides quality control tracking of airflow rates, odorant delivery and electrical shock treatments, and an expanded platform for high-throughput studies of combinational drug tests and genetic screens. The design uses inexpensive hardware and software for a total cost of ∼$500US, making it affordable to a wide range of investigators. This study demonstrates the design, construction and testing of a fully automated Drosophila olfactory classical association apparatus to provide low-labor, high-fidelity, quality-monitored, high-throughput and inexpensive learning and memory behavioral assays. Copyright © 2015 Elsevier B.V. All rights reserved.

Sub-processes of motor learning revealed by a robotic manipulandum for rodents.

Science.gov (United States)

Lambercy, O; Schubring-Giese, M; Vigaru, B; Gassert, R; Luft, A R; Hosp, J A

2015-02-01

Rodent models are widely used to investigate neural changes in response to motor learning. Usually, the behavioral readout of motor learning tasks used for this purpose is restricted to a binary measure of performance (i.e. "successful" movement vs. "failure"). Thus, the assignability of research in rodents to concepts gained in human research - implying diverse internal models that constitute motor learning - is still limited. To solve this problem, we recently introduced a three-degree-of-freedom robotic platform designed for rats (the ETH-Pattus) that combines an accurate behavioral readout (in the form of kinematics) with the possibility to invasively assess learning related changes within the brain (e.g. by performing immunohistochemistry or electrophysiology in acute slice preparations). Here, we validate this platform as a tool to study motor learning by establishing two forelimb-reaching paradigms that differ in degree of skill. Both conditions can be precisely differentiated in terms of their temporal pattern and performance levels. Based on behavioral data, we hypothesize the presence of several sub-processes contributing to motor learning. These share close similarities with concepts gained in humans or primates. Copyright © 2014 Elsevier B.V. All rights reserved.

Assessing patient risk of central line-associated bacteremia via machine learning.

Science.gov (United States)

Beeler, Cole; Dbeibo, Lana; Kelley, Kristen; Thatcher, Levi; Webb, Douglas; Bah, Amadou; Monahan, Patrick; Fowler, Nicole R; Nicol, Spencer; Judy-Malcolm, Alisa; Azar, Jose

2018-04-13

Central line-associated bloodstream infections (CLABSIs) contribute to increased morbidity, length of hospital stay, and cost. Despite progress in understanding the risk factors, there remains a need to accurately predict the risk of CLABSIs and, in real time, prevent them from occurring. A predictive model was developed using retrospective data from a large academic healthcare system. Models were developed with machine learning via construction of random forests using validated input variables. Fifteen variables accounted for the most significant effect on CLABSI prediction based on a retrospective study of 70,218 unique patient encounters between January 1, 2013, and May 31, 2016. The area under the receiver operating characteristic curve for the best-performing model was 0.82 in production. This model has multiple applications for resource allocation for CLABSI prevention, including serving as a tool to target patients at highest risk for potentially cost-effective but otherwise time-limited interventions. Machine learning can be used to develop accurate models to predict the risk of CLABSI in real time prior to the development of infection. Copyright © 2018 Association for Professionals in Infection Control and Epidemiology, Inc. Published by Elsevier Inc. All rights reserved.

Classifying smoking urges via machine learning.

Science.gov (United States)

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

2016-12-01

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

Validating Machine Learning Algorithms for Twitter Data Against Established Measures of Suicidality.

Science.gov (United States)

Braithwaite, Scott R; Giraud-Carrier, Christophe; West, Josh; Barnes, Michael D; Hanson, Carl Lee

2016-05-16

One of the leading causes of death in the United States (US) is suicide and new methods of assessment are needed to track its risk in real time. Our objective is to validate the use of machine learning algorithms for Twitter data against empirically validated measures of suicidality in the US population. Using a machine learning algorithm, the Twitter feeds of 135 Mechanical Turk (MTurk) participants were compared with validated, self-report measures of suicide risk. Our findings show that people who are at high suicidal risk can be easily differentiated from those who are not by machine learning algorithms, which accurately identify the clinically significant suicidal rate in 92% of cases (sensitivity: 53%, specificity: 97%, positive predictive value: 75%, negative predictive value: 93%). Machine learning algorithms are efficient in differentiating people who are at a suicidal risk from those who are not. Evidence for suicidality can be measured in nonclinical populations using social media data.

Accurate activity recognition in a home setting

NARCIS (Netherlands)

van Kasteren, T.; Noulas, A.; Englebienne, G.; Kröse, B.

2008-01-01

A sensor system capable of automatically recognizing activities would allow many potential ubiquitous applications. In this paper, we present an easy to install sensor network and an accurate but inexpensive annotation method. A recorded dataset consisting of 28 days of sensor data and its

Use of Machine Learning to Identify Children with Autism and Their Motor Abnormalities

Science.gov (United States)

Crippa, Alessandro; Salvatore, Christian; Perego, Paolo; Forti, Sara; Nobile, Maria; Molteni, Massimo; Castiglioni, Isabella

2015-01-01

In the present work, we have undertaken a proof-of-concept study to determine whether a simple upper-limb movement could be useful to accurately classify low-functioning children with autism spectrum disorder (ASD) aged 2-4. To answer this question, we developed a supervised machine-learning method to correctly discriminate 15 preschool children…

External Prior Guided Internal Prior Learning for Real-World Noisy Image Denoising

Science.gov (United States)

Xu, Jun; Zhang, Lei; Zhang, David

2018-06-01

Most of existing image denoising methods learn image priors from either external data or the noisy image itself to remove noise. However, priors learned from external data may not be adaptive to the image to be denoised, while priors learned from the given noisy image may not be accurate due to the interference of corrupted noise. Meanwhile, the noise in real-world noisy images is very complex, which is hard to be described by simple distributions such as Gaussian distribution, making real noisy image denoising a very challenging problem. We propose to exploit the information in both external data and the given noisy image, and develop an external prior guided internal prior learning method for real noisy image denoising. We first learn external priors from an independent set of clean natural images. With the aid of learned external priors, we then learn internal priors from the given noisy image to refine the prior model. The external and internal priors are formulated as a set of orthogonal dictionaries to efficiently reconstruct the desired image. Extensive experiments are performed on several real noisy image datasets. The proposed method demonstrates highly competitive denoising performance, outperforming state-of-the-art denoising methods including those designed for real noisy images.

Machine learning for the New York City power grid.

Science.gov (United States)

Rudin, Cynthia; Waltz, David; Anderson, Roger N; Boulanger, Albert; Salleb-Aouissi, Ansaf; Chow, Maggie; Dutta, Haimonti; Gross, Philip N; Huang, Bert; Ierome, Steve; Isaac, Delfina F; Kressner, Arthur; Passonneau, Rebecca J; Radeva, Axinia; Wu, Leon

2012-02-01

Power companies can benefit from the use of knowledge discovery methods and statistical machine learning for preventive maintenance. We introduce a general process for transforming historical electrical grid data into models that aim to predict the risk of failures for components and systems. These models can be used directly by power companies to assist with prioritization of maintenance and repair work. Specialized versions of this process are used to produce 1) feeder failure rankings, 2) cable, joint, terminator, and transformer rankings, 3) feeder Mean Time Between Failure (MTBF) estimates, and 4) manhole events vulnerability rankings. The process in its most general form can handle diverse, noisy, sources that are historical (static), semi-real-time, or realtime, incorporates state-of-the-art machine learning algorithms for prioritization (supervised ranking or MTBF), and includes an evaluation of results via cross-validation and blind test. Above and beyond the ranked lists and MTBF estimates are business management interfaces that allow the prediction capability to be integrated directly into corporate planning and decision support; such interfaces rely on several important properties of our general modeling approach: that machine learning features are meaningful to domain experts, that the processing of data is transparent, and that prediction results are accurate enough to support sound decision making. We discuss the challenges in working with historical electrical grid data that were not designed for predictive purposes. The “rawness” of these data contrasts with the accuracy of the statistical models that can be obtained from the process; these models are sufficiently accurate to assist in maintaining New York City’s electrical grid.

Technology learning in a small open economy-The systems, modelling and exploiting the learning effect

International Nuclear Information System (INIS)

Martinsen, Thomas

2011-01-01

This paper reviews the characteristics of technology learning and discusses its application in energy system modelling in a global-local perspective. Its influence on the national energy system, exemplified by Norway, is investigated using a global and national Markal model. The dynamic nature of the learning system boundary and coupling between the national energy system and the global development and manufacturing system is elaborated. Some criteria important for modelling of spillover are suggested. Particularly, to ensure balance in global energy demand and supply and accurately reflect alternative global pathways spillover for all technologies as well as energy carrier cost/prices should be estimated under the same global scenario. The technology composition, CO 2 emissions and system cost in Norway up to 2050 exhibit sensitivity to spillover. Moreover, spillover may reduce both CO 2 emissions and total system cost. National energy system analysis of low carbon society should therefore consider technology development paths in global policy scenarios. Without the spillover from international deployment a domestic technology relies only on endogenous national learning. However, with high but realistic learning rates offshore floating wind may become cost-efficient even if initially deployed only in Norwegian niche markets. - Research highlights: → Spillover for all technologies should emanate from the same global scenario. → A global model is called for to estimate spillover.→ Spillover may reduce CO 2 emissions and the total system cost in a small open economy. → Off-shore floating wind may become cost-efficient in a national niche market.

Informatics and machine learning to define the phenotype.

Science.gov (United States)

Basile, Anna Okula; Ritchie, Marylyn DeRiggi

2018-03-01

For the past decade, the focus of complex disease research has been the genotype. From technological advancements to the development of analysis methods, great progress has been made. However, advances in our definition of the phenotype have remained stagnant. Phenotype characterization has recently emerged as an exciting area of informatics and machine learning. The copious amounts of diverse biomedical data that have been collected may be leveraged with data-driven approaches to elucidate trait-related features and patterns. Areas covered: In this review, the authors discuss the phenotype in traditional genetic associations and the challenges this has imposed.Approaches for phenotype refinement that can aid in more accurate characterization of traits are also discussed. Further, the authors highlight promising machine learning approaches for establishing a phenotype and the challenges of electronic health record (EHR)-derived data. Expert commentary: The authors hypothesize that through unsupervised machine learning, data-driven approaches can be used to define phenotypes rather than relying on expert clinician knowledge. Through the use of machine learning and an unbiased set of features extracted from clinical repositories, researchers will have the potential to further understand complex traits and identify patient subgroups. This knowledge may lead to more preventative and precise clinical care.

Let's start learning radiation. Supplementary material on radiation for secondary school students

International Nuclear Information System (INIS)

Watanabe, Yoko; Yamashita, Kiyonobu; Shimada, Mayuka

2015-01-01

The Japan Atomic Energy Agency has been organizing training programs for engineers in Asian countries introducing nuclear technology. In 2012, we launched a course ‘Basic Radiation Knowledge for School Education’ as we thought disseminating accurate knowledge on radiation to school students and public would also be important in those countries after Fukushima-Daiichi nuclear power station accident. Ministry of Education, Culture, Sports, Science and Technology - Japan published supplemental learning material on radiation for secondary school students and teachers in Japanese in October 2011. Since the learning material is designed to give a clear explanation of radiation and covers various topics, we thought it would also be beneficial for young students in the world if a learning material in English was available. Therefore, we made a new learning material in English using the topics covered in supplemental learning material on radiation in Japanese as a reference. This learning material has been favourably evaluated by the International Atomic Energy Agency (IAEA) and will be widely used as a practical educational tool in many countries around the world through the IAEA. (author)

Relationships Between the External and Internal Training Load in Professional Soccer: What Can We Learn From Machine Learning?

Science.gov (United States)

Jaspers, Arne; Beéck, Tim Op De; Brink, Michel S; Frencken, Wouter G P; Staes, Filip; Davis, Jesse J; Helsen, Werner F

2017-12-28

Machine learning may contribute to understanding the relationship between the external load and internal load in professional soccer. Therefore, the relationship between external load indicators and the rating of perceived exertion (RPE) was examined using machine learning techniques on a group and individual level. Training data were collected from 38 professional soccer players over two seasons. The external load was measured using global positioning system technology and accelerometry. The internal load was obtained using the RPE. Predictive models were constructed using two machine learning techniques, artificial neural networks (ANNs) and least absolute shrinkage and selection operator (LASSO), and one naive baseline method. The predictions were based on a large set of external load indicators. Using each technique, one group model involving all players and one individual model for each player was constructed. These models' performance on predicting the reported RPE values for future training sessions was compared to the naive baseline's performance. Both the ANN and LASSO models outperformed the baseline. Additionally, the LASSO model made more accurate predictions for the RPE than the ANN model. Furthermore, decelerations were identified as important external load indicators. Regardless of the applied machine learning technique, the group models resulted in equivalent or better predictions for the reported RPE values than the individual models. Machine learning techniques may have added value in predicting the RPE for future sessions to optimize training design and evaluation. Additionally, these techniques may be used in conjunction with expert knowledge to select key external load indicators for load monitoring.

Accurate guitar tuning by cochlear implant musicians.

Directory of Open Access Journals (Sweden)

Thomas Lu

Full Text Available Modern cochlear implant (CI users understand speech but find difficulty in music appreciation due to poor pitch perception. Still, some deaf musicians continue to perform with their CI. Here we show unexpected results that CI musicians can reliably tune a guitar by CI alone and, under controlled conditions, match simultaneously presented tones to <0.5 Hz. One subject had normal contralateral hearing and produced more accurate tuning with CI than his normal ear. To understand these counterintuitive findings, we presented tones sequentially and found that tuning error was larger at ∼ 30 Hz for both subjects. A third subject, a non-musician CI user with normal contralateral hearing, showed similar trends in performance between CI and normal hearing ears but with less precision. This difference, along with electric analysis, showed that accurate tuning was achieved by listening to beats rather than discriminating pitch, effectively turning a spectral task into a temporal discrimination task.

Seeing and Being Seen: Predictors of Accurate Perceptions about Classmates’ Relationships

Science.gov (United States)

Neal, Jennifer Watling; Neal, Zachary P.; Cappella, Elise

2015-01-01

This study examines predictors of observer accuracy (i.e. seeing) and target accuracy (i.e. being seen) in perceptions of classmates’ relationships in a predominantly African American sample of 420 second through fourth graders (ages 7 – 11). Girls, children in higher grades, and children in smaller classrooms were more accurate observers. Targets (i.e. pairs of children) were more accurately observed when they occurred in smaller classrooms of higher grades and involved same-sex, high-popularity, and similar-popularity children. Moreover, relationships between pairs of girls were more accurately observed than relationships between pairs of boys. As a set, these findings suggest the importance of both observer and target characteristics for children’s accurate perceptions of classroom relationships. Moreover, the substantial variation in observer accuracy and target accuracy has methodological implications for both peer-reported assessments of classroom relationships and the use of stochastic actor-based models to understand peer selection and socialization processes. PMID:26347582

Word learning in adults with second language experience: Effects of phonological and referent familiarity

Science.gov (United States)

Kaushanskaya, Margarita; Yoo, Jeewon; Van Hecke, Stephanie

2014-01-01

Purpose The goal of this research was to examine whether phonological familiarity exerts different effects on novel word learning for familiar vs. unfamiliar referents, and whether successful word-learning is associated with increased second-language experience. Method Eighty-one adult native English speakers with various levels of Spanish knowledge learned phonologically-familiar novel words (constructed using English sounds) or phonologically-unfamiliar novel words (constructed using non-English and non-Spanish sounds) in association with either familiar or unfamiliar referents. Retention was tested via a forced-choice recognition-task. A median-split procedure identified high-ability and low-ability word-learners in each condition, and the two groups were compared on measures of second-language experience. Results Findings suggest that the ability to accurately match newly-learned novel names to their appropriate referents is facilitated by phonological familiarity only for familiar referents but not for unfamiliar referents. Moreover, more extensive second-language learning experience characterized superior learners primarily in one word-learning condition: Where phonologically-unfamiliar novel words were paired with familiar referents. Conclusions Together, these findings indicate that phonological familiarity facilitates novel word learning only for familiar referents, and that experience with learning a second language may have a specific impact on novel vocabulary learning in adults. PMID:22992709

On accurate determination of contact angle

Science.gov (United States)

Concus, P.; Finn, R.

1992-01-01

Methods are proposed that exploit a microgravity environment to obtain highly accurate measurement of contact angle. These methods, which are based on our earlier mathematical results, do not require detailed measurement of a liquid free-surface, as they incorporate discontinuous or nearly-discontinuous behavior of the liquid bulk in certain container geometries. Physical testing is planned in the forthcoming IML-2 space flight and in related preparatory ground-based experiments.

Physics of steam generators and visit of Saint-Marcel plant; La physique des generateurs de vapeur et la visite de l'Usine de Saint-Marcel

Energy Technology Data Exchange (ETDEWEB)

Gillet, N.; Gloaguen, C.; Holcblat, A. [FRAMATOME ANP, 92 - Paris La Defence (France); Borsoi, L. [CEA Saclay (SEMT/DYN), 91 - Gif sur yvette (France); Adobes, A.; David, F. [Electricite de France (EDF/RD), 75 - Paris (France); Greiner, E. [Electricite de France (EDF CIPN-CM), 13 - Marseille (France); Pascal-Ribot, S. [CEA Cadarache, 13 - Saint Paul lez Durance (France); Gauchet, J.P. [Electricite de France (EDF/UTO/GVD), 93 - Noisy le Grand (France); Mercier, L. [Electricite de France (EDF/CAPE/GMC), 93 - Saint enis (France); Leomy, F. [FRAMATOME ANP, 71 - Chalon (France)

2004-07-01

This document gathers the transparencies presented at the 6. technical session of the French nuclear energy society (SFEN) in June 2004. The main topic was the physics of steam generators: 1 - description (G. Paudroux, J.Y. Guena, M. Petit); 2 - thermo-hydraulics (A. Holcblat, F. David, S. Pascal-Ribot); 3 - mechanics (N. Gillet, L. Borsoi, A. Adobes); 4 - monitoring and maintenance means (J.P. Gauchet, L. Mercier, F. Leomy); 5 - replacement (C. Gloaguen, E. Greiner). (J.S.)

Physics of steam generators and visit of Saint-Marcel plant

International Nuclear Information System (INIS)

Gillet, N.; Gloaguen, C.; Holcblat, A.; Borsoi, L.; Adobes, A.; David, F.; Greiner, E.; Pascal-Ribot, S.; Gauchet, J.P.; Mercier, L.; Leomy, F.

2004-01-01

This document gathers the transparencies presented at the 6. technical session of the French nuclear energy society (SFEN) in June 2004. The main topic was the physics of steam generators: 1 - description (G. Paudroux, J.Y. Guena, M. Petit); 2 - thermo-hydraulics (A. Holcblat, F. David, S. Pascal-Ribot); 3 - mechanics (N. Gillet, L. Borsoi, A. Adobes); 4 - monitoring and maintenance means (J.P. Gauchet, L. Mercier, F. Leomy); 5 - replacement (C. Gloaguen, E. Greiner). (J.S.)

Accurate thermoelastic tensor and acoustic velocities of NaCl

Energy Technology Data Exchange (ETDEWEB)

Marcondes, Michel L., E-mail: michel@if.usp.br [Physics Institute, University of Sao Paulo, Sao Paulo, 05508-090 (Brazil); Chemical Engineering and Material Science, University of Minnesota, Minneapolis, 55455 (United States); Shukla, Gaurav, E-mail: shukla@physics.umn.edu [School of Physics and Astronomy, University of Minnesota, Minneapolis, 55455 (United States); Minnesota supercomputer Institute, University of Minnesota, Minneapolis, 55455 (United States); Silveira, Pedro da [Chemical Engineering and Material Science, University of Minnesota, Minneapolis, 55455 (United States); Wentzcovitch, Renata M., E-mail: wentz002@umn.edu [Chemical Engineering and Material Science, University of Minnesota, Minneapolis, 55455 (United States); Minnesota supercomputer Institute, University of Minnesota, Minneapolis, 55455 (United States)

2015-12-15

Despite the importance of thermoelastic properties of minerals in geology and geophysics, their measurement at high pressures and temperatures are still challenging. Thus, ab initio calculations are an essential tool for predicting these properties at extreme conditions. Owing to the approximate description of the exchange-correlation energy, approximations used in calculations of vibrational effects, and numerical/methodological approximations, these methods produce systematic deviations. Hybrid schemes combining experimental data and theoretical results have emerged as a way to reconcile available information and offer more reliable predictions at experimentally inaccessible thermodynamics conditions. Here we introduce a method to improve the calculated thermoelastic tensor by using highly accurate thermal equation of state (EoS). The corrective scheme is general, applicable to crystalline solids with any symmetry, and can produce accurate results at conditions where experimental data may not exist. We apply it to rock-salt-type NaCl, a material whose structural properties have been challenging to describe accurately by standard ab initio methods and whose acoustic/seismic properties are important for the gas and oil industry.

Relations among Metamemory, Rehearsal Activity and Word Recall of Learning Disabled and Non-Disabled Readers.

Science.gov (United States)

Swanson, H.L.

1983-01-01

In free recall of word lists involving different rehearsal strategies, more words were recalled by older (as against younger) children and by nondisabled (as against learning disabled) readers. Disabled readers tended to be nonstrategic recallers and less accurate estimators of their memory capacity. Recall differences were attributed to semantic…

A Model for Considering the Financial Sustainability of Learning and Teaching Programs: Concepts and Challenges

Science.gov (United States)

De Bellis, David

2012-01-01

The expansion of tertiary education, an intensity of focus on accountability and performance, and the emergence of new governance and management structures drives an economic fiscal perspective of the value of learning and teaching. Accurate and meaningful models defining financial sustainability are therefore proposed as an imperative for…

Honeybees in a virtual reality environment learn unique combinations of colour and shape.

Science.gov (United States)

Rusch, Claire; Roth, Eatai; Vinauger, Clément; Riffell, Jeffrey A

2017-10-01

Honeybees are well-known models for the study of visual learning and memory. Whereas most of our knowledge of learned responses comes from experiments using free-flying bees, a tethered preparation would allow fine-scale control of the visual stimuli as well as accurate characterization of the learned responses. Unfortunately, conditioning procedures using visual stimuli in tethered bees have been limited in their efficacy. In this study, using a novel virtual reality environment and a differential training protocol in tethered walking bees, we show that the majority of honeybees learn visual stimuli, and need only six paired training trials to learn the stimulus. We found that bees readily learn visual stimuli that differ in both shape and colour. However, bees learn certain components over others (colour versus shape), and visual stimuli are learned in a non-additive manner with the interaction of specific colour and shape combinations being crucial for learned responses. To better understand which components of the visual stimuli the bees learned, the shape-colour association of the stimuli was reversed either during or after training. Results showed that maintaining the visual stimuli in training and testing phases was necessary to elicit visual learning, suggesting that bees learn multiple components of the visual stimuli. Together, our results demonstrate a protocol for visual learning in restrained bees that provides a powerful tool for understanding how components of a visual stimulus elicit learned responses as well as elucidating how visual information is processed in the honeybee brain. © 2017. Published by The Company of Biologists Ltd.

Accurate modeling and maximum power point detection of ...

African Journals Online (AJOL)

Accurate modeling and maximum power point detection of photovoltaic ... Determination of MPP enables the PV system to deliver maximum available power. ..... adaptive artificial neural network: Proposition for a new sizing procedure.

Six to Ten Digits Multiplication Fun Learning Using Puppet Prototype

Science.gov (United States)

Islamiah Rosli, D.'oria; Ali, Azita; Peng, Lim Soo; Sujardi, Imam; Usodo, Budi; Adie Perdana, Fengky

2017-01-01

Logic and technical subjects require students to understand basic knowledge in mathematic. For instance, addition, minus, division and multiplication operations need to be mastered by students due to mathematic complexity as the learning mathematic grows higher. Weak foundation in mathematic also contribute to high failure rate in mathematic subjects in schools. In fact, students in primary schools are struggling to learn mathematic because they need to memorize formulas, multiplication or division operations. To date, this study will develop a puppet prototyping for learning mathematic for six to ten digits multiplication. Ten participants involved in the process of developing the prototype in this study. Students involved in the study were those from the intermediate class students whilst teachers were selected based on their vast knowledge and experiences and have more than five years of experience in teaching mathematic. Close participatory analysis will be used in the prototyping process as to fulfil the requirements of the students and teachers whom will use the puppet in learning six to ten digit multiplication in mathematic. Findings showed that, the students had a great time and fun learning experience in learning multiplication and they able to understand the concept of multiplication using puppet. Colour and materials of the puppet also help to attract student attention during learning. Additionally, students able to visualized and able to calculate accurate multiplication value and the puppet help them to recall in multiplying and adding the digits accordingly.

Parallelization of learning problems by artificial neural networks. Application in external radiotherapy; Parallelisation de problemes d'apprentissage par des reseaux neuronaux artificiels. Application en radiotherapie externe

Energy Technology Data Exchange (ETDEWEB)

Sauget, M

2007-12-15

This research is about the application of neural networks used in the external radiotherapy domain. The goal is to elaborate a new evaluating system for the radiation dose distributions in heterogeneous environments. The al objective of this work is to build a complete tool kit to evaluate the optimal treatment planning. My st research point is about the conception of an incremental learning algorithm. The interest of my work is to combine different optimizations specialized in the function interpolation and to propose a new algorithm allowing to change the neural network architecture during the learning phase. This algorithm allows to minimise the al size of the neural network while keeping a good accuracy. The second part of my research is to parallelize the previous incremental learning algorithm. The goal of that work is to increase the speed of the learning step as well as the size of the learned dataset needed in a clinical case. For that, our incremental learning algorithm presents an original data decomposition with overlapping, together with a fault tolerance mechanism. My last research point is about a fast and accurate algorithm computing the radiation dose deposit in any heterogeneous environment. At the present time, the existing solutions used are not optimal. The fast solution are not accurate and do not give an optimal treatment planning. On the other hand, the accurate solutions are far too slow to be used in a clinical context. Our algorithm answers to this problem by bringing rapidity and accuracy. The concept is to use a neural network adequately learned together with a mechanism taking into account the environment changes. The advantages of this algorithm is to avoid the use of a complex physical code while keeping a good accuracy and reasonable computation times. (author)

Predicting brain age with deep learning from raw imaging data results in a reliable and heritable biomarker

NARCIS (Netherlands)

Cole, James H.; Poudel, Rudra P. K.; Tsagkrasoulis, Dimosthenis; Caan, Matthan W. A.; Steves, Claire; Spector, Tim D.; Montana, Giovanni

2017-01-01

Machine learning analysis of neuroimaging data can accurately predict chronological age in healthy people. Deviations from healthy brain ageing have been associated with cognitive impairment and disease. Here we sought to further establish the credentials of 'brain-predicted age' as a biomarker of

Machine vision systems using machine learning for industrial product inspection

Science.gov (United States)

Lu, Yi; Chen, Tie Q.; Chen, Jie; Zhang, Jian; Tisler, Anthony

2002-02-01

Machine vision inspection requires efficient processing time and accurate results. In this paper, we present a machine vision inspection architecture, SMV (Smart Machine Vision). SMV decomposes a machine vision inspection problem into two stages, Learning Inspection Features (LIF), and On-Line Inspection (OLI). The LIF is designed to learn visual inspection features from design data and/or from inspection products. During the OLI stage, the inspection system uses the knowledge learnt by the LIF component to inspect the visual features of products. In this paper we will present two machine vision inspection systems developed under the SMV architecture for two different types of products, Printed Circuit Board (PCB) and Vacuum Florescent Displaying (VFD) boards. In the VFD board inspection system, the LIF component learns inspection features from a VFD board and its displaying patterns. In the PCB board inspection system, the LIF learns the inspection features from the CAD file of a PCB board. In both systems, the LIF component also incorporates interactive learning to make the inspection system more powerful and efficient. The VFD system has been deployed successfully in three different manufacturing companies and the PCB inspection system is the process of being deployed in a manufacturing plant.

Accuracy of latent-variable estimation in Bayesian semi-supervised learning.

Science.gov (United States)

Yamazaki, Keisuke

2015-09-01

Hierarchical probabilistic models, such as Gaussian mixture models, are widely used for unsupervised learning tasks. These models consist of observable and latent variables, which represent the observable data and the underlying data-generation process, respectively. Unsupervised learning tasks, such as cluster analysis, are regarded as estimations of latent variables based on the observable ones. The estimation of latent variables in semi-supervised learning, where some labels are observed, will be more precise than that in unsupervised, and one of the concerns is to clarify the effect of the labeled data. However, there has not been sufficient theoretical analysis of the accuracy of the estimation of latent variables. In a previous study, a distribution-based error function was formulated, and its asymptotic form was calculated for unsupervised learning with generative models. It has been shown that, for the estimation of latent variables, the Bayes method is more accurate than the maximum-likelihood method. The present paper reveals the asymptotic forms of the error function in Bayesian semi-supervised learning for both discriminative and generative models. The results show that the generative model, which uses all of the given data, performs better when the model is well specified. Copyright © 2015 Elsevier Ltd. All rights reserved.

Scaling up graph-based semisupervised learning via prototype vector machines.

Science.gov (United States)

Zhang, Kai; Lan, Liang; Kwok, James T; Vucetic, Slobodan; Parvin, Bahram

2015-03-01

When the amount of labeled data are limited, semisupervised learning can improve the learner's performance by also using the often easily available unlabeled data. In particular, a popular approach requires the learned function to be smooth on the underlying data manifold. By approximating this manifold as a weighted graph, such graph-based techniques can often achieve state-of-the-art performance. However, their high time and space complexities make them less attractive on large data sets. In this paper, we propose to scale up graph-based semisupervised learning using a set of sparse prototypes derived from the data. These prototypes serve as a small set of data representatives, which can be used to approximate the graph-based regularizer and to control model complexity. Consequently, both training and testing become much more efficient. Moreover, when the Gaussian kernel is used to define the graph affinity, a simple and principled method to select the prototypes can be obtained. Experiments on a number of real-world data sets demonstrate encouraging performance and scaling properties of the proposed approach. It also compares favorably with models learned via l1 -regularization at the same level of model sparsity. These results demonstrate the efficacy of the proposed approach in producing highly parsimonious and accurate models for semisupervised learning.

Testing students' e-learning via Facebook through Bayesian structural equation modeling.

Science.gov (United States)

Salarzadeh Jenatabadi, Hashem; Moghavvemi, Sedigheh; Wan Mohamed Radzi, Che Wan Jasimah Bt; Babashamsi, Parastoo; Arashi, Mohammad

2017-01-01

Learning is an intentional activity, with several factors affecting students' intention to use new learning technology. Researchers have investigated technology acceptance in different contexts by developing various theories/models and testing them by a number of means. Although most theories/models developed have been examined through regression or structural equation modeling, Bayesian analysis offers more accurate data analysis results. To address this gap, the unified theory of acceptance and technology use in the context of e-learning via Facebook are re-examined in this study using Bayesian analysis. The data (S1 Data) were collected from 170 students enrolled in a business statistics course at University of Malaya, Malaysia, and tested with the maximum likelihood and Bayesian approaches. The difference between the two methods' results indicates that performance expectancy and hedonic motivation are the strongest factors influencing the intention to use e-learning via Facebook. The Bayesian estimation model exhibited better data fit than the maximum likelihood estimator model. The results of the Bayesian and maximum likelihood estimator approaches are compared and the reasons for the result discrepancy are deliberated.

Testing students' e-learning via Facebook through Bayesian structural equation modeling.

Directory of Open Access Journals (Sweden)

Hashem Salarzadeh Jenatabadi

Full Text Available Learning is an intentional activity, with several factors affecting students' intention to use new learning technology. Researchers have investigated technology acceptance in different contexts by developing various theories/models and testing them by a number of means. Although most theories/models developed have been examined through regression or structural equation modeling, Bayesian analysis offers more accurate data analysis results. To address this gap, the unified theory of acceptance and technology use in the context of e-learning via Facebook are re-examined in this study using Bayesian analysis. The data (S1 Data were collected from 170 students enrolled in a business statistics course at University of Malaya, Malaysia, and tested with the maximum likelihood and Bayesian approaches. The difference between the two methods' results indicates that performance expectancy and hedonic motivation are the strongest factors influencing the intention to use e-learning via Facebook. The Bayesian estimation model exhibited better data fit than the maximum likelihood estimator model. The results of the Bayesian and maximum likelihood estimator approaches are compared and the reasons for the result discrepancy are deliberated.

Accurate determination of antenna directivity

DEFF Research Database (Denmark)

Dich, Mikael

1997-01-01

The derivation of a formula for accurate estimation of the total radiated power from a transmitting antenna for which the radiated power density is known in a finite number of points on the far-field sphere is presented. The main application of the formula is determination of directivity from power......-pattern measurements. The derivation is based on the theory of spherical wave expansion of electromagnetic fields, which also establishes a simple criterion for the required number of samples of the power density. An array antenna consisting of Hertzian dipoles is used to test the accuracy and rate of convergence...

Daily Discharge Estimation in Talar River Using Lazy Learning Model

Directory of Open Access Journals (Sweden)

Zahra Abdollahi

2017-03-01

Full Text Available Introduction: River discharge as one of the most important hydrology factors has a vital role in physical, ecological, social and economic processes. So, accurate and reliable prediction and estimation of river discharge have been widely considered by many researchers in different fields such as surface water management, design of hydraulic structures, flood control and ecological studies in spetialand temporal scale. Therefore, in last decades different techniques for short-term and long-term estimation of hourly, daily, monthly and annual discharge have been developed for many years. However, short-term estimation models are less sophisticated and more accurate.Various global and local algorithms have been widely used to estimate hydrologic variables. The current study effort to use Lazy Learning approach to evaluate the adequacy of input data in order to follow the variation of discharge and also simulate next-day discharge in Talar River in KasilianBasinwhere is located in north of Iran with an area of 66.75 km2. Lazy learning is a local linear modelling approach in which generalization beyond the training data is delayed until a query is made to the system, as opposed to in eager learning, where the system tries to generalize the training data before receiving queries Materials and Methods: The current study was conducted in Kasilian Basin, where is located in north of Iran with an area of 66.75 km2. The main river of this basin joins to Talar River near Valicbon village and then exit from the watershed. Hydrometric station located near Valicbon village is equipped with Parshall flume and Limnogragh which can record river discharge of about 20 cubic meters per second.In this study, daily data of discharge recorded in Valicbon station related to 2002 to 2012 was used to estimate the discharge of 19 September 2012. The mean annual discharge of considered river was also calculated by using available data about 0.441 cubic meters per second. To

Accurate shear measurement with faint sources

International Nuclear Information System (INIS)

Zhang, Jun; Foucaud, Sebastien; Luo, Wentao

2015-01-01

For cosmic shear to become an accurate cosmological probe, systematic errors in the shear measurement method must be unambiguously identified and corrected for. Previous work of this series has demonstrated that cosmic shears can be measured accurately in Fourier space in the presence of background noise and finite pixel size, without assumptions on the morphologies of galaxy and PSF. The remaining major source of error is source Poisson noise, due to the finiteness of source photon number. This problem is particularly important for faint galaxies in space-based weak lensing measurements, and for ground-based images of short exposure times. In this work, we propose a simple and rigorous way of removing the shear bias from the source Poisson noise. Our noise treatment can be generalized for images made of multiple exposures through MultiDrizzle. This is demonstrated with the SDSS and COSMOS/ACS data. With a large ensemble of mock galaxy images of unrestricted morphologies, we show that our shear measurement method can achieve sub-percent level accuracy even for images of signal-to-noise ratio less than 5 in general, making it the most promising technique for cosmic shear measurement in the ongoing and upcoming large scale galaxy surveys

A Neural Network Model to Learn Multiple Tasks under Dynamic Environments

Science.gov (United States)

Tsumori, Kenji; Ozawa, Seiichi

When environments are dynamically changed for agents, the knowledge acquired in an environment might be useless in future. In such dynamic environments, agents should be able to not only acquire new knowledge but also modify old knowledge in learning. However, modifying all knowledge acquired before is not efficient because the knowledge once acquired may be useful again when similar environment reappears and some knowledge can be shared among different environments. To learn efficiently in such environments, we propose a neural network model that consists of the following modules: resource allocating network, long-term & short-term memory, and environment change detector. We evaluate the model under a class of dynamic environments where multiple function approximation tasks are sequentially given. The experimental results demonstrate that the proposed model possesses stable incremental learning, accurate environmental change detection, proper association and recall of old knowledge, and efficient knowledge transfer.

Using Deep Learning to Analyze the Voices of Stars.

Science.gov (United States)

Boudreaux, Thomas Macaulay

2018-01-01

With several new large-scale surveys on the horizon, including LSST, TESS, ZTF, and Evryscope, faster and more accurate analysis methods will be required to adequately process the enormous amount of data produced. Deep learning, used in industry for years now, allows for advanced feature detection in minimally prepared datasets at very high speeds; however, despite the advantages of this method, its application to astrophysics has not yet been extensively explored. This dearth may be due to a lack of training data available to researchers. Here we generate synthetic data loosely mimicking the properties of acoustic mode pulsating stars and compare the performance of different deep learning algorithms, including Artifical Neural Netoworks, and Convolutional Neural Networks, in classifing these synthetic data sets as either pulsators, or not observed to vary stars.

Sunspot drawings handwritten character recognition method based on deep learning

Science.gov (United States)

Zheng, Sheng; Zeng, Xiangyun; Lin, Ganghua; Zhao, Cui; Feng, Yongli; Tao, Jinping; Zhu, Daoyuan; Xiong, Li

2016-05-01

High accuracy scanned sunspot drawings handwritten characters recognition is an issue of critical importance to analyze sunspots movement and store them in the database. This paper presents a robust deep learning method for scanned sunspot drawings handwritten characters recognition. The convolution neural network (CNN) is one algorithm of deep learning which is truly successful in training of multi-layer network structure. CNN is used to train recognition model of handwritten character images which are extracted from the original sunspot drawings. We demonstrate the advantages of the proposed method on sunspot drawings provided by Chinese Academy Yunnan Observatory and obtain the daily full-disc sunspot numbers and sunspot areas from the sunspot drawings. The experimental results show that the proposed method achieves a high recognition accurate rate.

Multi-task learning with group information for human action recognition

Science.gov (United States)

Qian, Li; Wu, Song; Pu, Nan; Xu, Shulin; Xiao, Guoqiang

2018-04-01

Human action recognition is an important and challenging task in computer vision research, due to the variations in human motion performance, interpersonal differences and recording settings. In this paper, we propose a novel multi-task learning framework with group information (MTL-GI) for accurate and efficient human action recognition. Specifically, we firstly obtain group information through calculating the mutual information according to the latent relationship between Gaussian components and action categories, and clustering similar action categories into the same group by affinity propagation clustering. Additionally, in order to explore the relationships of related tasks, we incorporate group information into multi-task learning. Experimental results evaluated on two popular benchmarks (UCF50 and HMDB51 datasets) demonstrate the superiority of our proposed MTL-GI framework.

High accurate time system of the Low Latitude Meridian Circle.

Science.gov (United States)

Yang, Jing; Wang, Feng; Li, Zhiming

In order to obtain the high accurate time signal for the Low Latitude Meridian Circle (LLMC), a new GPS accurate time system is developed which include GPS, 1 MC frequency source and self-made clock system. The second signal of GPS is synchronously used in the clock system and information can be collected by a computer automatically. The difficulty of the cancellation of the time keeper can be overcomed by using this system.

Prediction of Employee Turnover in Organizations using Machine Learning Algorithms

OpenAIRE

Rohit Punnoose; Pankaj Ajit

2016-01-01

Employee turnover has been identified as a key issue for organizations because of its adverse impact on work place productivity and long term growth strategies. To solve this problem, organizations use machine learning techniques to predict employee turnover. Accurate predictions enable organizations to take action for retention or succession planning of employees. However, the data for this modeling problem comes from HR Information Systems (HRIS); these are typically under-funded compared t...

Learning to Predict Demand in a Transport-Resource Sharing Task

Science.gov (United States)

2015-09-01

to make a more accurate prediction. Each tree is constructed using a bootstrapped sample of the training set (i.e., a sample that is the same size as...Belissent, J., Mines, C., Radcliffe, E. & Darashkevich, Y. (2010). Getting clever about smart cities: New opportunities require new business models...Require+New+ Business +Models/fulltext/-/E-RES56701 Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. doi: 10.1023/A:1010933404324

Neural network representation and learning of mappings and their derivatives

Science.gov (United States)

White, Halbert; Hornik, Kurt; Stinchcombe, Maxwell; Gallant, A. Ronald

1991-01-01

Discussed here are recent theorems proving that artificial neural networks are capable of approximating an arbitrary mapping and its derivatives as accurately as desired. This fact forms the basis for further results establishing the learnability of the desired approximations, using results from non-parametric statistics. These results have potential applications in robotics, chaotic dynamics, control, and sensitivity analysis. An example involving learning the transfer function and its derivatives for a chaotic map is discussed.

Stacking Ensemble Learning for Short-Term Electricity Consumption Forecasting

Directory of Open Access Journals (Sweden)

Federico Divina

2018-04-01

Full Text Available The ability to predict short-term electric energy demand would provide several benefits, both at the economic and environmental level. For example, it would allow for an efficient use of resources in order to face the actual demand, reducing the costs associated to the production as well as the emission of CO 2 . To this aim, in this paper we propose a strategy based on ensemble learning in order to tackle the short-term load forecasting problem. In particular, our approach is based on a stacking ensemble learning scheme, where the predictions produced by three base learning methods are used by a top level method in order to produce final predictions. We tested the proposed scheme on a dataset reporting the energy consumption in Spain over more than nine years. The obtained experimental results show that an approach for short-term electricity consumption forecasting based on ensemble learning can help in combining predictions produced by weaker learning methods in order to obtain superior results. In particular, the system produces a lower error with respect to the existing state-of-the art techniques used on the same dataset. More importantly, this case study has shown that using an ensemble scheme can achieve very accurate predictions, and thus that it is a suitable approach for addressing the short-term load forecasting problem.

Visual recognition and inference using dynamic overcomplete sparse learning.

Science.gov (United States)

Murray, Joseph F; Kreutz-Delgado, Kenneth

2007-09-01

We present a hierarchical architecture and learning algorithm for visual recognition and other visual inference tasks such as imagination, reconstruction of occluded images, and expectation-driven segmentation. Using properties of biological vision for guidance, we posit a stochastic generative world model and from it develop a simplified world model (SWM) based on a tractable variational approximation that is designed to enforce sparse coding. Recent developments in computational methods for learning overcomplete representations (Lewicki & Sejnowski, 2000; Teh, Welling, Osindero, & Hinton, 2003) suggest that overcompleteness can be useful for visual tasks, and we use an overcomplete dictionary learning algorithm (Kreutz-Delgado, et al., 2003) as a preprocessing stage to produce accurate, sparse codings of images. Inference is performed by constructing a dynamic multilayer network with feedforward, feedback, and lateral connections, which is trained to approximate the SWM. Learning is done with a variant of the back-propagation-through-time algorithm, which encourages convergence to desired states within a fixed number of iterations. Vision tasks require large networks, and to make learning efficient, we take advantage of the sparsity of each layer to update only a small subset of elements in a large weight matrix at each iteration. Experiments on a set of rotated objects demonstrate various types of visual inference and show that increasing the degree of overcompleteness improves recognition performance in difficult scenes with occluded objects in clutter.

Saliency U-Net: A regional saliency map-driven hybrid deep learning network for anomaly segmentation

Science.gov (United States)

Karargyros, Alex; Syeda-Mahmood, Tanveer

2018-02-01

Deep learning networks are gaining popularity in many medical image analysis tasks due to their generalized ability to automatically extract relevant features from raw images. However, this can make the learning problem unnecessarily harder requiring network architectures of high complexity. In case of anomaly detection, in particular, there is often sufficient regional difference between the anomaly and the surrounding parenchyma that could be easily highlighted through bottom-up saliency operators. In this paper we propose a new hybrid deep learning network using a combination of raw image and such regional maps to more accurately learn the anomalies using simpler network architectures. Specifically, we modify a deep learning network called U-Net using both the raw and pre-segmented images as input to produce joint encoding (contraction) and expansion paths (decoding) in the U-Net. We present results of successfully delineating subdural and epidural hematomas in brain CT imaging and liver hemangioma in abdominal CT images using such network.

Probabilistic forecasting of wind power generation using extreme learning machine

DEFF Research Database (Denmark)

Wan, Can; Xu, Zhao; Pinson, Pierre

2014-01-01

an extreme learning machine (ELM)-based probabilistic forecasting method for wind power generation. To account for the uncertainties in the forecasting results, several bootstrapmethods have been compared for modeling the regression uncertainty, based on which the pairs bootstrap method is identified......Accurate and reliable forecast of wind power is essential to power system operation and control. However, due to the nonstationarity of wind power series, traditional point forecasting can hardly be accurate, leading to increased uncertainties and risks for system operation. This paper proposes...... with the best performance. Consequently, a new method for prediction intervals formulation based on theELMand the pairs bootstrap is developed.Wind power forecasting has been conducted in different seasons using the proposed approach with the historical wind power time series as the inputs alone. The results...

Instance Selection for Classifier Performance Estimation in Meta Learning

Directory of Open Access Journals (Sweden)

Marcin Blachnik

2017-11-01

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

The importance of accurate meteorological input fields and accurate planetary boundary layer parameterizations, tested against ETEX-1

International Nuclear Information System (INIS)

Brandt, J.; Ebel, A.; Elbern, H.; Jakobs, H.; Memmesheimer, M.; Mikkelsen, T.; Thykier-Nielsen, S.; Zlatev, Z.

1997-01-01

Atmospheric transport of air pollutants is, in principle, a well understood process. If information about the state of the atmosphere is given in all details (infinitely accurate information about wind speed, etc.) and infinitely fast computers are available then the advection equation could in principle be solved exactly. This is, however, not the case: discretization of the equations and input data introduces some uncertainties and errors in the results. Therefore many different issues have to be carefully studied in order to diminish these uncertainties and to develop an accurate transport model. Some of these are e.g. the numerical treatment of the transport equation, accuracy of the mean meteorological input fields and parameterizations of sub-grid scale phenomena (as e.g. parameterizations of the 2 nd and higher order turbulence terms in order to reach closure in the perturbation equation). A tracer model for studying transport and dispersion of air pollution caused by a single but strong source is under development. The model simulations from the first ETEX release illustrate the differences caused by using various analyzed fields directly in the tracer model or using a meteorological driver. Also different parameterizations of the mixing height and the vertical exchange are compared. (author)

Support patient search on pathology reports with interactive online learning based data extraction

Directory of Open Access Journals (Sweden)

Shuai Zheng

2015-01-01

tests. Conclusions: Extracting data from pathology reports could enable more accurate knowledge to support biomedical research and clinical diagnosis. IDEAL-X provides a bridge that takes advantage of online machine learning based data extraction and the knowledge from human′s feedback. By combining iterative online learning and adaptive controlled vocabularies, IDEAL-X can deliver highly adaptive and accurate data extraction to support patient search.

Accurate Alignment of Plasma Channels Based on Laser Centroid Oscillations

International Nuclear Information System (INIS)

Gonsalves, Anthony; Nakamura, Kei; Lin, Chen; Osterhoff, Jens; Shiraishi, Satomi; Schroeder, Carl; Geddes, Cameron; Toth, Csaba; Esarey, Eric; Leemans, Wim

2011-01-01

A technique has been developed to accurately align a laser beam through a plasma channel by minimizing the shift in laser centroid and angle at the channel outptut. If only the shift in centroid or angle is measured, then accurate alignment is provided by minimizing laser centroid motion at the channel exit as the channel properties are scanned. The improvement in alignment accuracy provided by this technique is important for minimizing electron beam pointing errors in laser plasma accelerators.

Ego-Motion and Tracking for Continuous Object Learning: A Brief Survey

Science.gov (United States)

2017-09-01

past research related to the tasks of ego-motion estimation and object tracking from the viewpoint of their role in continuous object learning...in visual object tracking, competitions are held each year to identify the most accurate and robust tracking implementations. Over recent competitions...information should they share) or vice versa? These are just some of the questions that must be addressed in future research toward continuous object

Is Attribute-Based Zero-Shot Learning an Ill-Posed Strategy?

KAUST Repository

Alabdulmohsin, Ibrahim; Cisse, Moustapha; Zhang, Xiangliang

2016-01-01

One transfer learning approach that has gained a wide popularity lately is attribute-based zero-shot learning. Its goal is to learn novel classes that were never seen during the training stage. The classical route towards realizing this goal is to incorporate a prior knowledge, in the form of a semantic embedding of classes, and to learn to predict classes indirectly via their semantic attributes. Despite the amount of research devoted to this subject lately, no known algorithm has yet reported a predictive accuracy that could exceed the accuracy of supervised learning with very few training examples. For instance, the direct attribute prediction (DAP) algorithm, which forms a standard baseline for the task, is known to be as accurate as supervised learning when as few as two examples from each hidden class are used for training on some popular benchmark datasets! In this paper, we argue that this lack of significant results in the literature is not a coincidence; attribute-based zero-shot learning is fundamentally an ill-posed strategy. The key insight is the observation that the mechanical task of predicting an attribute is, in fact, quite different from the epistemological task of learning the “correct meaning” of the attribute itself. This renders attribute-based zero-shot learning fundamentally ill-posed. In more precise mathematical terms, attribute-based zero-shot learning is equivalent to the mirage goal of learning with respect to one distribution of instances, with the hope of being able to predict with respect to any arbitrary distribution. We demonstrate this overlooked fact on some synthetic and real datasets. The data and software related to this paper are available at https://mine. kaust.edu.sa/Pages/zero-shot-learning.aspx. © Springer International Publishing AG 2016.

Is Attribute-Based Zero-Shot Learning an Ill-Posed Strategy?

KAUST Repository

Alabdulmohsin, Ibrahim

2016-09-03

One transfer learning approach that has gained a wide popularity lately is attribute-based zero-shot learning. Its goal is to learn novel classes that were never seen during the training stage. The classical route towards realizing this goal is to incorporate a prior knowledge, in the form of a semantic embedding of classes, and to learn to predict classes indirectly via their semantic attributes. Despite the amount of research devoted to this subject lately, no known algorithm has yet reported a predictive accuracy that could exceed the accuracy of supervised learning with very few training examples. For instance, the direct attribute prediction (DAP) algorithm, which forms a standard baseline for the task, is known to be as accurate as supervised learning when as few as two examples from each hidden class are used for training on some popular benchmark datasets! In this paper, we argue that this lack of significant results in the literature is not a coincidence; attribute-based zero-shot learning is fundamentally an ill-posed strategy. The key insight is the observation that the mechanical task of predicting an attribute is, in fact, quite different from the epistemological task of learning the “correct meaning” of the attribute itself. This renders attribute-based zero-shot learning fundamentally ill-posed. In more precise mathematical terms, attribute-based zero-shot learning is equivalent to the mirage goal of learning with respect to one distribution of instances, with the hope of being able to predict with respect to any arbitrary distribution. We demonstrate this overlooked fact on some synthetic and real datasets. The data and software related to this paper are available at https://mine. kaust.edu.sa/Pages/zero-shot-learning.aspx. © Springer International Publishing AG 2016.

Accurate 3d Textured Models of Vessels for the Improvement of the Educational Tools of a Museum

Science.gov (United States)

Soile, S.; Adam, K.; Ioannidis, C.; Georgopoulos, A.

2013-02-01

Besides the demonstration of the findings, modern museums organize educational programs which aim to experience and knowledge sharing combined with entertainment rather than to pure learning. Toward that effort, 2D and 3D digital representations are gradually replacing the traditional recording of the findings through photos or drawings. The present paper refers to a project that aims to create 3D textured models of two lekythoi that are exhibited in the National Archaeological Museum of Athens in Greece; on the surfaces of these lekythoi scenes of the adventures of Odysseus are depicted. The project is expected to support the production of an educational movie and some other relevant interactive educational programs for the museum. The creation of accurate developments of the paintings and of accurate 3D models is the basis for the visualization of the adventures of the mythical hero. The data collection was made by using a structured light scanner consisting of two machine vision cameras that are used for the determination of geometry of the object, a high resolution camera for the recording of the texture, and a DLP projector. The creation of the final accurate 3D textured model is a complicated and tiring procedure which includes the collection of geometric data, the creation of the surface, the noise filtering, the merging of individual surfaces, the creation of a c-mesh, the creation of the UV map, the provision of the texture and, finally, the general processing of the 3D textured object. For a better result a combination of commercial and in-house software made for the automation of various steps of the procedure was used. The results derived from the above procedure were especially satisfactory in terms of accuracy and quality of the model. However, the procedure was proved to be time consuming while the use of various software packages presumes the services of a specialist.

Accurate thickness measurement of graphene

International Nuclear Information System (INIS)

Shearer, Cameron J; Slattery, Ashley D; Stapleton, Andrew J; Shapter, Joseph G; Gibson, Christopher T

2016-01-01

Graphene has emerged as a material with a vast variety of applications. The electronic, optical and mechanical properties of graphene are strongly influenced by the number of layers present in a sample. As a result, the dimensional characterization of graphene films is crucial, especially with the continued development of new synthesis methods and applications. A number of techniques exist to determine the thickness of graphene films including optical contrast, Raman scattering and scanning probe microscopy techniques. Atomic force microscopy (AFM), in particular, is used extensively since it provides three-dimensional images that enable the measurement of the lateral dimensions of graphene films as well as the thickness, and by extension the number of layers present. However, in the literature AFM has proven to be inaccurate with a wide range of measured values for single layer graphene thickness reported (between 0.4 and 1.7 nm). This discrepancy has been attributed to tip-surface interactions, image feedback settings and surface chemistry. In this work, we use standard and carbon nanotube modified AFM probes and a relatively new AFM imaging mode known as PeakForce tapping mode to establish a protocol that will allow users to accurately determine the thickness of graphene films. In particular, the error in measuring the first layer is reduced from 0.1–1.3 nm to 0.1–0.3 nm. Furthermore, in the process we establish that the graphene-substrate adsorbate layer and imaging force, in particular the pressure the tip exerts on the surface, are crucial components in the accurate measurement of graphene using AFM. These findings can be applied to other 2D materials. (paper)

Due Process in Dual Process: Model-Recovery Simulations of Decision-Bound Strategy Analysis in Category Learning

Science.gov (United States)

Edmunds, Charlotte E. R.; Milton, Fraser; Wills, Andy J.

2018-01-01

Behavioral evidence for the COVIS dual-process model of category learning has been widely reported in over a hundred publications (Ashby & Valentin, 2016). It is generally accepted that the validity of such evidence depends on the accurate identification of individual participants' categorization strategies, a task that usually falls to…

Orthographic learning in children with isolated and combined reading and spelling deficits.

Science.gov (United States)

Mehlhase, Heike; Bakos, Sarolta; Landerl, Karin; Schulte-Körne, Gerd; Moll, Kristina

2018-05-07

Dissociations between reading and spelling problems are likely to be associated with different underlying cognitive deficits, and with different deficits in orthographic learning. In order to understand these differences, the current study examined orthographic learning using a printed-word learning paradigm. Children (4th grade) with isolated reading, isolated spelling and combined reading and spelling problems were compared to children with age appropriate reading and spelling skills on their performance during learning novel words and symbols (non-verbal control condition), and during immediate and delayed reading and spelling recall tasks. No group differences occurred in the non-verbal control condition. In the verbal condition, initial learning was intact in all groups, but differences occurred during recall tasks. Children with reading fluency deficits showed slower reading times, while children with spelling deficits were less accurate, both in reading and spelling recall. Children with isolated spelling problems showed no difficulties in immediate spelling recall, but had problems in remembering the spellings 2 hours later. The results suggest that different orthographic learning deficits underlie reading fluency and spelling problems: Children with isolated reading fluency deficits have no difficulties in building-up orthographic representations, but access to these representations is slowed down while children with isolated spelling deficits have problems in storing precise orthographic representations in long-term memory.

Cancer survival analysis using semi-supervised learning method based on Cox and AFT models with L1/2 regularization.

Science.gov (United States)

Liang, Yong; Chai, Hua; Liu, Xiao-Ying; Xu, Zong-Ben; Zhang, Hai; Leung, Kwong-Sak

2016-03-01

One of the most important objectives of the clinical cancer research is to diagnose cancer more accurately based on the patients' gene expression profiles. Both Cox proportional hazards model (Cox) and accelerated failure time model (AFT) have been widely adopted to the high risk and low risk classification or survival time prediction for the patients' clinical treatment. Nevertheless, two main dilemmas limit the accuracy of these prediction methods. One is that the small sample size and censored data remain a bottleneck for training robust and accurate Cox classification model. In addition to that, similar phenotype tumours and prognoses are actually completely different diseases at the genotype and molecular level. Thus, the utility of the AFT model for the survival time prediction is limited when such biological differences of the diseases have not been previously identified. To try to overcome these two main dilemmas, we proposed a novel semi-supervised learning method based on the Cox and AFT models to accurately predict the treatment risk and the survival time of the patients. Moreover, we adopted the efficient L1/2 regularization approach in the semi-supervised learning method to select the relevant genes, which are significantly associated with the disease. The results of the simulation experiments show that the semi-supervised learning model can significant improve the predictive performance of Cox and AFT models in survival analysis. The proposed procedures have been successfully applied to four real microarray gene expression and artificial evaluation datasets. The advantages of our proposed semi-supervised learning method include: 1) significantly increase the available training samples from censored data; 2) high capability for identifying the survival risk classes of patient in Cox model; 3) high predictive accuracy for patients' survival time in AFT model; 4) strong capability of the relevant biomarker selection. Consequently, our proposed semi

The use of machine learning and nonlinear statistical tools for ADME prediction.

Science.gov (United States)

Sakiyama, Yojiro

2009-02-01

Absorption, distribution, metabolism and excretion (ADME)-related failure of drug candidates is a major issue for the pharmaceutical industry today. Prediction of ADME by in silico tools has now become an inevitable paradigm to reduce cost and enhance efficiency in pharmaceutical research. Recently, machine learning as well as nonlinear statistical tools has been widely applied to predict routine ADME end points. To achieve accurate and reliable predictions, it would be a prerequisite to understand the concepts, mechanisms and limitations of these tools. Here, we have devised a small synthetic nonlinear data set to help understand the mechanism of machine learning by 2D-visualisation. We applied six new machine learning methods to four different data sets. The methods include Naive Bayes classifier, classification and regression tree, random forest, Gaussian process, support vector machine and k nearest neighbour. The results demonstrated that ensemble learning and kernel machine displayed greater accuracy of prediction than classical methods irrespective of the data set size. The importance of interaction with the engineering field is also addressed. The results described here provide insights into the mechanism of machine learning, which will enable appropriate usage in the future.

CORRELATION BETWEEN METACOGNITIVE STRATEGY, FOREIGN LANGUAGE APTITUDE AND MOTIVATIONS IN LANGUAGE LEARNING

Directory of Open Access Journals (Sweden)

Novia Tri Febriani

2017-11-01

Full Text Available Language learning belief and language learning strategies are two essential predictors that have significant effect toward students’ language proficiency. Learners’ belief is dealing with what comes from inside the learners in learning the language, such as foreign language aptitude; difficulty of language learning; nature of language learning; learning and communication strategies; and motivation. Meanwhile, language learning strategies are learners’ plan in achieving certain goals or mastering the target language. A preliminary research was conducted in order to find what strategy mostly used by the learners. It turned out that the strategy mostly used by them was metacognitive strategies. Thus, this study aims to investigate about the correlation between metacognitive strategies and certain belief’ variables in students’ language learning which are foreign language aptitude and motivation. Moreover, twenty postgraduate students of English education department participated in this study. This study used correlational research, in which the BALLI (Beliefs about Language Learning Inventory and SILL (Strategies Inventory for Language Learners questionnaires were adopted as the instruments in collecting the data. The findings of this study indicated that there is negative linear correlation between metacognitive strategy and foreign language aptitude (rXY = -0,049 while there is significant positive linear correlation between metacognitive and motivation (rXY =+0,79 in students’ language learning. Furthermore, this study also provide some recommendations, which is it is expected that there will be more researches use studies using different respondents with various contexts. Secondly, the further research will use both of quantitative and qualitative data relating to this issue in order to make a more accurate data.

Accurate isotope ratio mass spectrometry. Some problems and possibilities

International Nuclear Information System (INIS)

Bievre, P. de

1978-01-01

The review includes reference to 190 papers, mainly published during the last 10 years. It covers the following: important factors in accurate isotope ratio measurements (precision and accuracy of isotope ratio measurements -exemplified by determinations of 235 U/ 238 U and of other elements including 239 Pu/ 240 Pu; isotope fractionation -exemplified by curves for Rb, U); applications (atomic weights); the Oklo natural nuclear reactor (discovered by UF 6 mass spectrometry at Pierrelatte); nuclear and other constants; isotope ratio measurements in nuclear geology and isotope cosmology - accurate age determination; isotope ratio measurements on very small samples - archaeometry; isotope dilution; miscellaneous applications; and future prospects. (U.K.)

Learning How to Learn

DEFF Research Database (Denmark)

Lauridsen, Karen M.; Lauridsen, Ole

Ole Lauridsen, Aarhus School of Business and Social Sciences, Aarhus University, Denmark Karen M. Lauridsen, Aarhus School of Business and Social Sciences, Aarhus University, Denmark Learning Styles in Higher Education – Learning How to Learn Applying learning styles (LS) in higher education...... by Constructivist learning theory and current basic knowledge of how the brain learns. The LS concept will thus be placed in a broader learning theoretical context as a strong learning and teaching tool. Participants will be offered the opportunity to have their own LS preferences established before...... teaching leads to positive results and enhanced student learning. However, learning styles should not only be considered a didactic matter for the teacher, but also a tool for the individual students to improve their learning capabilities – not least in contexts where information is not necessarily...

Novel real-time tumor-contouring method using deep learning to prevent mistracking in X-ray fluoroscopy.

Science.gov (United States)

Terunuma, Toshiyuki; Tokui, Aoi; Sakae, Takeji

2018-03-01

Robustness to obstacles is the most important factor necessary to achieve accurate tumor tracking without fiducial markers. Some high-density structures, such as bone, are enhanced on X-ray fluoroscopic images, which cause tumor mistracking. Tumor tracking should be performed by controlling "importance recognition": the understanding that soft-tissue is an important tracking feature and bone structure is unimportant. We propose a new real-time tumor-contouring method that uses deep learning with importance recognition control. The novelty of the proposed method is the combination of the devised random overlay method and supervised deep learning to induce the recognition of structures in tumor contouring as important or unimportant. This method can be used for tumor contouring because it uses deep learning to perform image segmentation. Our results from a simulated fluoroscopy model showed accurate tracking of a low-visibility tumor with an error of approximately 1 mm, even if enhanced bone structure acted as an obstacle. A high similarity of approximately 0.95 on the Jaccard index was observed between the segmented and ground truth tumor regions. A short processing time of 25 ms was achieved. The results of this simulated fluoroscopy model support the feasibility of robust real-time tumor contouring with fluoroscopy. Further studies using clinical fluoroscopy are highly anticipated.

Discrete sensors distribution for accurate plantar pressure analyses.

Science.gov (United States)

Claverie, Laetitia; Ille, Anne; Moretto, Pierre

2016-12-01

The aim of this study was to determine the distribution of discrete sensors under the footprint for accurate plantar pressure analyses. For this purpose, two different sensor layouts have been tested and compared, to determine which was the most accurate to monitor plantar pressure with wireless devices in research and/or clinical practice. Ten healthy volunteers participated in the study (age range: 23-58 years). The barycenter of pressures (BoP) determined from the plantar pressure system (W-inshoe®) was compared to the center of pressures (CoP) determined from a force platform (AMTI) in the medial-lateral (ML) and anterior-posterior (AP) directions. Then, the vertical ground reaction force (vGRF) obtained from both W-inshoe® and force platform was compared for both layouts for each subject. The BoP and vGRF determined from the plantar pressure system data showed good correlation (SCC) with those determined from the force platform data, notably for the second sensor organization (ML SCC= 0.95; AP SCC=0.99; vGRF SCC=0.91). The study demonstrates that an adjusted placement of removable sensors is key to accurate plantar pressure analyses. These results are promising for a plantar pressure recording outside clinical or laboratory settings, for long time monitoring, real time feedback or for whatever activity requiring a low-cost system. Copyright © 2016 IPEM. Published by Elsevier Ltd. All rights reserved.

More accurate picture of human body organs

International Nuclear Information System (INIS)

Kolar, J.

1985-01-01

Computerized tomography and nucler magnetic resonance tomography (NMRT) are revolutionary contributions to radiodiagnosis because they allow to obtain a more accurate image of human body organs. The principles are described of both methods. Attention is mainly devoted to NMRT which has clinically only been used for three years. It does not burden the organism with ionizing radiation. (Ha)

Supervised learning of probability distributions by neural networks

Science.gov (United States)

Baum, Eric B.; Wilczek, Frank

1988-01-01

Supervised learning algorithms for feedforward neural networks are investigated analytically. The back-propagation algorithm described by Werbos (1974), Parker (1985), and Rumelhart et al. (1986) is generalized by redefining the values of the input and output neurons as probabilities. The synaptic weights are then varied to follow gradients in the logarithm of likelihood rather than in the error. This modification is shown to provide a more rigorous theoretical basis for the algorithm and to permit more accurate predictions. A typical application involving a medical-diagnosis expert system is discussed.

Effectiveness of an e-Learning Platform for Image Interpretation Education of Medical Staff and Students.

Science.gov (United States)

Ogura, Akio; Hayashi, Norio; Negishi, Tohru; Watanabe, Haruyuki

2018-05-09

Medical staff must be able to perform accurate initial interpretations of radiography to prevent diagnostic errors. Education in medical image interpretation is an ongoing need that is addressed by text-based and e-learning platforms. The effectiveness of these methods has been previously reported. Here, we describe the effectiveness of an e-learning platform used for medical image interpretation education. Ten third-year medical students without previous experience in chest radiography interpretation were provided with e-learning instructions. Accuracy of diagnosis using chest radiography was provided before and after e-learning education. We measured detection accuracy for two image groups: nodular shadow and ground-glass shadow. We also distributed the e-learning system to the two groups and analyzed the effectiveness of education for both types of image shadow. The mean correct answer rate after the 2-week e-learning period increased from 34.5 to 72.7%. Diagnosis of the ground glass shadow improved significantly more than that of the mass shadow. Education using the e-leaning platform is effective for interpretation of chest radiography results. E-learning is particularly effective for the interpretation of chest radiography images containing ground glass shadow.

CAT-PUMA: CME Arrival Time Prediction Using Machine learning Algorithms

Science.gov (United States)

Liu, Jiajia; Ye, Yudong; Shen, Chenglong; Wang, Yuming; Erdélyi, Robert

2018-04-01

CAT-PUMA (CME Arrival Time Prediction Using Machine learning Algorithms) quickly and accurately predicts the arrival of Coronal Mass Ejections (CMEs) of CME arrival time. The software was trained via detailed analysis of CME features and solar wind parameters using 182 previously observed geo-effective partial-/full-halo CMEs and uses algorithms of the Support Vector Machine (SVM) to make its predictions, which can be made within minutes of providing the necessary input parameters of a CME.

Delayed Treatment of Ebola Virus Infection with Plant-Derived Monoclonal Antibodies Provides Protection in Rhesus Macaques

Science.gov (United States)

2012-10-15

filtration (Mustang Q membrane ; Pall). The final polishing column for c13C6 and c6D8 was a CHT, Type I 40-μm (Bio-Rad) column. The columnwas...monkey chow, primate treats, fruits, and vegetables throughout the course of the study. Animals were observed at least once daily to monitor overall...Coulter Act 10 (Beckman Coulter) on samples collected in EDTA plasma vacuette tubes (Greiner Bio-One). Blood was collected in 2-mL serum vacuette tubes

Screening for autistic spectrum disorder at the 18-month developmental assessment: a population-based study

OpenAIRE

VanDenHeuvel, A.; Fitzgerald, M.; Greiner, Birgit A.; Perry, Ivan J.

2007-01-01

VanDenHeuvel A, Fitzgerald M, Greiner B, Perry IJ. Screening for autistic spectrum disorder at the 18-month developmental assessment: a population-based study. Ir Med J. 2007;100(8):565-7. The objectives of this study were to assess the feasibility of administering the CHecklist for Autism in Toddlers (CHAT) at the 18-month developmental check, estimate the prevalence of screening positive for autism at the first and second administrations of the CHAT and estimate the prevalence of diagnos...

Finding faults: analogical comparison supports spatial concept learning in geoscience.

Science.gov (United States)

Jee, Benjamin D; Uttal, David H; Gentner, Dedre; Manduca, Cathy; Shipley, Thomas F; Sageman, Bradley

2013-05-01

A central issue in education is how to support the spatial thinking involved in learning science, technology, engineering, and mathematics (STEM). We investigated whether and how the cognitive process of analogical comparison supports learning of a basic spatial concept in geoscience, fault. Because of the high variability in the appearance of faults, it may be difficult for students to learn the category-relevant spatial structure. There is abundant evidence that comparing analogous examples can help students gain insight into important category-defining features (Gentner in Cogn Sci 34(5):752-775, 2010). Further, comparing high-similarity pairs can be especially effective at revealing key differences (Sagi et al. 2012). Across three experiments, we tested whether comparison of visually similar contrasting examples would help students learn the fault concept. Our main findings were that participants performed better at identifying faults when they (1) compared contrasting (fault/no fault) cases versus viewing each case separately (Experiment 1), (2) compared similar as opposed to dissimilar contrasting cases early in learning (Experiment 2), and (3) viewed a contrasting pair of schematic block diagrams as opposed to a single block diagram of a fault as part of an instructional text (Experiment 3). These results suggest that comparison of visually similar contrasting cases helped distinguish category-relevant from category-irrelevant features for participants. When such comparisons occurred early in learning, participants were more likely to form an accurate conceptual representation. Thus, analogical comparison of images may provide one powerful way to enhance spatial learning in geoscience and other STEM disciplines.

COGNITIVE LOAD MEASUREMENT WITHIN THE RESEARCH OF EFFICIENT USAGE OF LEARNING SOFTWARE

Directory of Open Access Journals (Sweden)

Tetiana M. Derkach

2011-05-01

Full Text Available The methods of cognitive load measurement are described within the research of efficient usage of learning Software. Their classification is given, main advantages and disadvantages are analyzed, as well as area of use of these methods is defined. The article presents an overview of modern Software and Hardware that can be used for cognitive load measurement while studying with information technologies and practical examples of such methods. The use of the secondary task method is reasoned to be the most optimal for cognitive load measurement as well as for detection of optimal conditions for student work with different learning materials. This method allows to receive objective quantification of cognitive load and to investigate its dynamics accurately.

Bi-directional effect of increasing doses of baclofen on reinforcement learning

Directory of Open Access Journals (Sweden)

Jean eTerrier

2011-07-01

Full Text Available In rodents as well as in humans, efficient reinforcement learning depends on dopamine (DA released from ventral tegmental area (VTA neurons. It has been shown that in brain slices of mice, GABAB-receptor agonists at low concentrations increase the firing frequency of VTA-DA neurons, while high concentrations reduce the firing frequency. It remains however elusive whether baclofen can modulate reinforcement learning. Here, in a double blind study in 34 healthy human volunteers, we tested the effects of a low and a high concentration of oral baclofen in a gambling task associated with monetary reward. A low (20 mg dose of baclofen increased the efficiency of reward-associated learning but had no effect on the avoidance of monetary loss. A high (50 mg dose of baclofen on the other hand did not affect the learning curve. At the end of the task, subjects who received 20 mg baclofen p.o. were more accurate in choosing the symbol linked to the highest probability of earning money compared to the control group (89.55±1.39% vs 81.07±1.55%, p=0.002. Our results support a model where baclofen, at low concentrations, causes a disinhibition of DA neurons, increases DA levels and thus facilitates reinforcement learning.

Constrained Bayesian Active Learning of Interference Channels in Cognitive Radio Networks

Science.gov (United States)

Tsakmalis, Anestis; Chatzinotas, Symeon; Ottersten, Bjorn

2018-02-01

In this paper, a sequential probing method for interference constraint learning is proposed to allow a centralized Cognitive Radio Network (CRN) accessing the frequency band of a Primary User (PU) in an underlay cognitive scenario with a designed PU protection specification. The main idea is that the CRN probes the PU and subsequently eavesdrops the reverse PU link to acquire the binary ACK/NACK packet. This feedback indicates whether the probing-induced interference is harmful or not and can be used to learn the PU interference constraint. The cognitive part of this sequential probing process is the selection of the power levels of the Secondary Users (SUs) which aims to learn the PU interference constraint with a minimum number of probing attempts while setting a limit on the number of harmful probing-induced interference events or equivalently of NACK packet observations over a time window. This constrained design problem is studied within the Active Learning (AL) framework and an optimal solution is derived and implemented with a sophisticated, accurate and fast Bayesian Learning method, the Expectation Propagation (EP). The performance of this solution is also demonstrated through numerical simulations and compared with modified versions of AL techniques we developed in earlier work.

Second-order accurate volume-of-fluid algorithms for tracking material interfaces

International Nuclear Information System (INIS)

Pilliod, James Edward; Puckett, Elbridge Gerry

2004-01-01

We introduce two new volume-of-fluid interface reconstruction algorithms and compare the accuracy of these algorithms to four other widely used volume-of-fluid interface reconstruction algorithms. We find that when the interface is smooth (e.g., continuous with two continuous derivatives) the new methods are second-order accurate and the other algorithms are first-order accurate. We propose a design criteria for a volume-of-fluid interface reconstruction algorithm to be second-order accurate. Namely, that it reproduce lines in two space dimensions or planes in three space dimensions exactly. We also introduce a second-order, unsplit, volume-of-fluid advection algorithm that is based on a second-order, finite difference method for scalar conservation laws due to Bell, Dawson and Shubin. We test this advection algorithm by modeling several different interface shapes propagating in two simple incompressible flows and compare the results with the standard second-order, operator-split advection algorithm. Although both methods are second-order accurate when the interface is smooth, we find that the unsplit algorithm exhibits noticeably better resolution in regions where the interface has discontinuous derivatives, such as at corners

Learning to Learn.

Science.gov (United States)

Weiss, Helen; Weiss, Martin

1988-01-01

The article reviews theories of learning (e.g., stimulus-response, trial and error, operant conditioning, cognitive), considers the role of motivation, and summarizes nine research-supported rules of effective learning. Suggestions are applied to teaching learning strategies to learning-disabled students. (DB)

Keeping conceptual boundaries distinct between decision making and learning is necessary to understand social influence.

Science.gov (United States)

Le Mens, Gaël

2014-02-01

Bentley et al. make the deliberate choice to blur the distinction between learning and decision making. This obscures the social influence mechanisms that operate in the various empirical settings that their map aims to categorize. Useful policy prescriptions, however, require an accurate understanding of the social influence mechanisms that underlie the dynamics of popularity.

Leg mass characteristics of accurate and inaccurate kickers--an Australian football perspective.

Science.gov (United States)

Hart, Nicolas H; Nimphius, Sophia; Cochrane, Jodie L; Newton, Robert U

2013-01-01

Athletic profiling provides valuable information to sport scientists, assisting in the optimal design of strength and conditioning programmes. Understanding the influence these physical characteristics may have on the generation of kicking accuracy is advantageous. The aim of this study was to profile and compare the lower limb mass characteristics of accurate and inaccurate Australian footballers. Thirty-one players were recruited from the Western Australian Football League to perform ten drop punt kicks over 20 metres to a player target. Players were separated into accurate (n = 15) and inaccurate (n = 16) groups, with leg mass characteristics assessed using whole body dual energy x-ray absorptiometry (DXA) scans. Accurate kickers demonstrated significantly greater relative lean mass (P ≤ 0.004) and significantly lower relative fat mass (P ≤ 0.024) across all segments of the kicking and support limbs, while also exhibiting significantly higher intra-limb lean-to-fat mass ratios for all segments across both limbs (P ≤ 0.009). Inaccurate kickers also produced significantly larger asymmetries between limbs than accurate kickers (P ≤ 0.028), showing considerably lower lean mass in their support leg. These results illustrate a difference in leg mass characteristics between accurate and inaccurate kickers, highlighting the potential influence these may have on technical proficiency of the drop punt.

Neuronal integration of dynamic sources: Bayesian learning and Bayesian inference.

Science.gov (United States)

Siegelmann, Hava T; Holzman, Lars E

2010-09-01

One of the brain's most basic functions is integrating sensory data from diverse sources. This ability causes us to question whether the neural system is computationally capable of intelligently integrating data, not only when sources have known, fixed relative dependencies but also when it must determine such relative weightings based on dynamic conditions, and then use these learned weightings to accurately infer information about the world. We suggest that the brain is, in fact, fully capable of computing this parallel task in a single network and describe a neural inspired circuit with this property. Our implementation suggests the possibility that evidence learning requires a more complex organization of the network than was previously assumed, where neurons have different specialties, whose emergence brings the desired adaptivity seen in human online inference.

A comparative study of machine learning models for ethnicity classification

Science.gov (United States)

Trivedi, Advait; Bessie Amali, D. Geraldine

2017-11-01

This paper endeavours to adopt a machine learning approach to solve the problem of ethnicity recognition. Ethnicity identification is an important vision problem with its use cases being extended to various domains. Despite the multitude of complexity involved, ethnicity identification comes naturally to humans. This meta information can be leveraged to make several decisions, be it in target marketing or security. With the recent development of intelligent systems a sub module to efficiently capture ethnicity would be useful in several use cases. Several attempts to identify an ideal learning model to represent a multi-ethnic dataset have been recorded. A comparative study of classifiers such as support vector machines, logistic regression has been documented. Experimental results indicate that the logical classifier provides a much accurate classification than the support vector machine.

[Connectionist models of social learning: a case of learning by observing a simple task].

Science.gov (United States)

Paignon, A; Desrichard, O; Bollon, T

2004-03-01

alone is not sufficient to ensure accurate reproduction and must be made functional through the production phase (Deakin & Proteau, 2000). Results obtained through a second simulation replicate those produced by Bandura & Jeffery (1973), who observed that the individual tested following the retention phase recalled recorded information better than he realized in the production phase. The outcome of a third simulation shows that, when performing the transfer task, agents performed the task all the more effectively when they were required to learn a simple path which facilitated knowledge transfer to an adjacent situation. New explanatory assumptions of the mechanics of learning through observation may be produced through OLEANNet. Thus, observed deterioration between memorization and production is caused by successive approximations which occur in the acquisition phase then in the production phase. Further, depending on the type of learning undergone by agents, use of representation as a production guide induces a more or less stringent constraint in the approximation of actual behaviour. This results, during the transfer task, in the ability to effectively generalize acquired knowledge where such knowledge is not specifically related to the task at hand. In conclusion, connectionist model architecture appears valid for modeling learning through observation as defined by Bandura (1977). However, certain limitations appear during implementation, especially in terms of the observed behaviour's availability and the planning of produced behaviours that future developments are liable to counter.

How Accurate are Government Forecast of Economic Fundamentals?

NARCIS (Netherlands)

C-L. Chang (Chia-Lin); Ph.H.B.F. Franses (Philip Hans); M.J. McAleer (Michael)

2009-01-01

textabstractA government’s ability to forecast key economic fundamentals accurately can affect business confidence, consumer sentiment, and foreign direct investment, among others. A government forecast based on an econometric model is replicable, whereas one that is not fully based on an

Novel multi-beam radiometers for accurate ocean surveillance

DEFF Research Database (Denmark)

Cappellin, C.; Pontoppidan, K.; Nielsen, P. H.

2014-01-01

Novel antenna architectures for real aperture multi-beam radiometers providing high resolution and high sensitivity for accurate sea surface temperature (SST) and ocean vector wind (OVW) measurements are investigated. On the basis of the radiometer requirements set for future SST/OVW missions...

Machine learning of the reactor core loading pattern critical parameters

International Nuclear Information System (INIS)

Trontl, K.; Pevec, D.; Smuc, T.

2007-01-01

The usual approach to loading pattern optimization involves high degree of engineering judgment, a set of heuristic rules, an optimization algorithm and a computer code used for evaluating proposed loading patterns. The speed of the optimization process is highly dependent on the computer code used for the evaluation. In this paper we investigate the applicability of a machine learning model which could be used for fast loading pattern evaluation. We employed a recently introduced machine learning technique, Support Vector Regression (SVR), which has a strong theoretical background in statistical learning theory. Superior empirical performance of the method has been reported on difficult regression problems in different fields of science and technology. SVR is a data driven, kernel based, nonlinear modelling paradigm, in which model parameters are automatically determined by solving a quadratic optimization problem. The main objective of the work reported in this paper was to evaluate the possibility of applying SVR method for reactor core loading pattern modelling. The starting set of experimental data for training and testing of the machine learning algorithm was obtained using a two-dimensional diffusion theory reactor physics computer code. We illustrate the performance of the solution and discuss its applicability, i.e., complexity, speed and accuracy, with a projection to a more realistic scenario involving machine learning from the results of more accurate and time consuming three-dimensional core modelling code. (author)

Spatiotemporal neural characterization of prediction error valence and surprise during reward learning in humans.

Science.gov (United States)

Fouragnan, Elsa; Queirazza, Filippo; Retzler, Chris; Mullinger, Karen J; Philiastides, Marios G

2017-07-06

Reward learning depends on accurate reward associations with potential choices. These associations can be attained with reinforcement learning mechanisms using a reward prediction error (RPE) signal (the difference between actual and expected rewards) for updating future reward expectations. Despite an extensive body of literature on the influence of RPE on learning, little has been done to investigate the potentially separate contributions of RPE valence (positive or negative) and surprise (absolute degree of deviation from expectations). Here, we coupled single-trial electroencephalography with simultaneously acquired fMRI, during a probabilistic reversal-learning task, to offer evidence of temporally overlapping but largely distinct spatial representations of RPE valence and surprise. Electrophysiological variability in RPE valence correlated with activity in regions of the human reward network promoting approach or avoidance learning. Electrophysiological variability in RPE surprise correlated primarily with activity in regions of the human attentional network controlling the speed of learning. Crucially, despite the largely separate spatial extend of these representations our EEG-informed fMRI approach uniquely revealed a linear superposition of the two RPE components in a smaller network encompassing visuo-mnemonic and reward areas. Activity in this network was further predictive of stimulus value updating indicating a comparable contribution of both signals to reward learning.

Machine learning strategies for systems with invariance properties

Science.gov (United States)

Ling, Julia; Jones, Reese; Templeton, Jeremy

2016-08-01

In many scientific fields, empirical models are employed to facilitate computational simulations of engineering systems. For example, in fluid mechanics, empirical Reynolds stress closures enable computationally-efficient Reynolds Averaged Navier Stokes simulations. Likewise, in solid mechanics, constitutive relations between the stress and strain in a material are required in deformation analysis. Traditional methods for developing and tuning empirical models usually combine physical intuition with simple regression techniques on limited data sets. The rise of high performance computing has led to a growing availability of high fidelity simulation data. These data open up the possibility of using machine learning algorithms, such as random forests or neural networks, to develop more accurate and general empirical models. A key question when using data-driven algorithms to develop these empirical models is how domain knowledge should be incorporated into the machine learning process. This paper will specifically address physical systems that possess symmetry or invariance properties. Two different methods for teaching a machine learning model an invariance property are compared. In the first method, a basis of invariant inputs is constructed, and the machine learning model is trained upon this basis, thereby embedding the invariance into the model. In the second method, the algorithm is trained on multiple transformations of the raw input data until the model learns invariance to that transformation. Results are discussed for two case studies: one in turbulence modeling and one in crystal elasticity. It is shown that in both cases embedding the invariance property into the input features yields higher performance at significantly reduced computational training costs.

Prevalence of accurate nursing documentation in patient records

NARCIS (Netherlands)

Paans, Wolter; Sermeus, Walter; Nieweg, Roos; van der Schans, Cees

2010-01-01

AIM: This paper is a report of a study conducted to describe the accuracy of nursing documentation in patient records in hospitals. Background.  Accurate nursing documentation enables nurses to systematically review the nursing process and to evaluate the quality of care. Assessing nurses' reports

Dynamic weighing for accurate fertilizer application and monitoring

NARCIS (Netherlands)

Bergeijk, van J.; Goense, D.; Willigenburg, van L.G.; Speelman, L.

2001-01-01

The mass flow of fertilizer spreaders must be calibrated for the different types of fertilizers used. To obtain accurate fertilizer application manual calibration of actual mass flow must be repeated frequently. Automatic calibration is possible by measurement of the actual mass flow, based on

Laser guided automated calibrating system for accurate bracket ...

African Journals Online (AJOL)

It is widely recognized that accurate bracket placement is of critical importance in the efficient application of biomechanics and in realizing the full potential of a preadjusted edgewise appliance. Aim: The purpose of ... placement. Keywords: Hough transforms, Indirect bonding technique, Laser, Orthodontic bracket placement ...

Procedural Memory: Computer Learning in Control Subjects and in Parkinson’s Disease Patients

Directory of Open Access Journals (Sweden)

C. Thomas-Antérion

1996-01-01

Full Text Available We used perceptual motor tasks involving the learning of mouse control by looking at a Macintosh computer screen. We studied 90 control subjects aged between sixteen and seventy-five years. There was a significant time difference between the scales of age but improvement was the same for all subjects. We also studied 24 patients with Parkinson's disease (PD. We observed an influence of age and also of educational levels. The PD patients had difficulties of learning in all tests but they did not show differences in time when compared to the control group in the first learning session (Student's t-test. They learned two or four and a half times less well than the control group. In the first test, they had some difficulty in initiating the procedure and learned eight times less well than the control group. Performances seemed to be heterogeneous: patients with only tremor (seven and patients without treatment (five performed better than others but learned less. Success in procedural tasks for the PD group seemed to depend on the capacity to initiate the response and not on the development of an accurate strategy. Many questions still remain unanswered, and we have to study different kinds of implicit memory tasks to differentiate performance in control and basal ganglia groups.

Machine learning: a useful radiological adjunct in determination of a newly diagnosed glioma's grade and IDH status.

Science.gov (United States)

De Looze, Céline; Beausang, Alan; Cryan, Jane; Loftus, Teresa; Buckley, Patrick G; Farrell, Michael; Looby, Seamus; Reilly, Richard; Brett, Francesca; Kearney, Hugh

2018-05-16

Machine learning methods have been introduced as a computer aided diagnostic tool, with applications to glioma characterisation on MRI. Such an algorithmic approach may provide a useful adjunct for a rapid and accurate diagnosis of a glioma. The aim of this study is to devise a machine learning algorithm that may be used by radiologists in routine practice to aid diagnosis of both: WHO grade and IDH mutation status in de novo gliomas. To evaluate the status quo, we interrogated the accuracy of neuroradiology reports in relation to WHO grade: grade II 96.49% (95% confidence intervals [CI] 0.88, 0.99); III 36.51% (95% CI 0.24, 0.50); IV 72.9% (95% CI 0.67, 0.78). We derived five MRI parameters from the same diagnostic brain scans, in under two minutes per case, and then supplied these data to a random forest algorithm. Machine learning resulted in a high level of accuracy in prediction of tumour grade: grade II/III; area under the receiver operating characteristic curve (AUC) = 98%, sensitivity = 0.82, specificity = 0.94; grade II/IV; AUC = 100%, sensitivity = 1.0, specificity = 1.0; grade III/IV; AUC = 97%, sensitivity = 0.83, specificity = 0.97. Furthermore, machine learning also facilitated the discrimination of IDH status: AUC of 88%, sensitivity = 0.81, specificity = 0.77. These data demonstrate the ability of machine learning to accurately classify diffuse gliomas by both WHO grade and IDH status from routine MRI alone-without significant image processing, which may facilitate usage as a diagnostic adjunct in clinical practice.

Enhancing performance expectancies through visual illusions facilitates motor learning in children.

Science.gov (United States)

Bahmani, Moslem; Wulf, Gabriele; Ghadiri, Farhad; Karimi, Saeed; Lewthwaite, Rebecca

2017-10-01

In a recent study by Chauvel, Wulf, and Maquestiaux (2015), golf putting performance was found to be affected by the Ebbinghaus illusion. Specifically, adult participants demonstrated more effective learning when they practiced with a hole that was surrounded by small circles, making it look larger, than when the hole was surrounded by large circles, making it look smaller. The present study examined whether this learning advantage would generalize to children who are assumed to be less sensitive to the visual illusion. Two groups of 10-year olds practiced putting golf balls from a distance of 2m, with perceived larger or smaller holes resulting from the visual illusion. Self-efficacy was increased in the group with the perceived larger hole. The latter group also demonstrated more accurate putting performance during practice. Importantly, learning (i.e., delayed retention performance without the illusion) was enhanced in the group that practiced with the perceived larger hole. The findings replicate previous results with adult learners and are in line with the notion that enhanced performance expectancies are key to optimal motor learning (Wulf & Lewthwaite, 2016). Copyright © 2017 Elsevier B.V. All rights reserved.

The Role of Consulting a Dictionary in Reading and Vocabulary Learning

Directory of Open Access Journals (Sweden)

Carol A. Fraser

1999-12-01

Full Text Available Abstract This article reviews recent research on consulting a dictionary in L2 reading and vocabulary learning. From the perspective of cognitive learning theory, the author re-evaluates the limited role that has often been accorded to dictionary consulting. It is noted that, among the three available lexical processing strategies (inferencing, consulting and ignoring, learners tend to use consulting infrequently and selectively and also to differ among each other in their strategy use. Consulting in combination with inferencing is shown to have the greatest positive effect on performance in L2 reading and vocabulary learning, although consulting is found to slow down task completion. Excerpts from think-aloud protocols illustrate the potential contribution of strategic dictionary use to the cognitive processes required for vocabulary acquisition: attention to form-meaning connections, rehearsal of words for storage in long-term memory and elaboration of associations with other knowledge. Among the pedagogical implications of these findings is the need for training in lexical processing strategies in order to help learners use the dictionary effectively and accurately in L2 reading comprehension and vocabulary learning.

Real-time tumor motion estimation using respiratory surrogate via memory-based learning

International Nuclear Information System (INIS)

Li Ruijiang; Xing Lei; Lewis, John H; Berbeco, Ross I

2012-01-01

Respiratory tumor motion is a major challenge in radiation therapy for thoracic and abdominal cancers. Effective motion management requires an accurate knowledge of the real-time tumor motion. External respiration monitoring devices (optical, etc) provide a noninvasive, non-ionizing, low-cost and practical approach to obtain the respiratory signal. Due to the highly complex and nonlinear relations between tumor and surrogate motion, its ultimate success hinges on the ability to accurately infer the tumor motion from respiratory surrogates. Given their widespread use in the clinic, such a method is critically needed. We propose to use a powerful memory-based learning method to find the complex relations between tumor motion and respiratory surrogates. The method first stores the training data in memory and then finds relevant data to answer a particular query. Nearby data points are assigned high relevance (or weights) and conversely distant data are assigned low relevance. By fitting relatively simple models to local patches instead of fitting one single global model, it is able to capture highly nonlinear and complex relations between the internal tumor motion and external surrogates accurately. Due to the local nature of weighting functions, the method is inherently robust to outliers in the training data. Moreover, both training and adapting to new data are performed almost instantaneously with memory-based learning, making it suitable for dynamically following variable internal/external relations. We evaluated the method using respiratory motion data from 11 patients. The data set consists of simultaneous measurement of 3D tumor motion and 1D abdominal surface (used as the surrogate signal in this study). There are a total of 171 respiratory traces, with an average peak-to-peak amplitude of ∼15 mm and average duration of ∼115 s per trace. Given only 5 s (roughly one breath) pretreatment training data, the method achieved an average 3D error of 1.5 mm and 95

Real-time tumor motion estimation using respiratory surrogate via memory-based learning

Science.gov (United States)

Li, Ruijiang; Lewis, John H.; Berbeco, Ross I.; Xing, Lei

2012-08-01

Respiratory tumor motion is a major challenge in radiation therapy for thoracic and abdominal cancers. Effective motion management requires an accurate knowledge of the real-time tumor motion. External respiration monitoring devices (optical, etc) provide a noninvasive, non-ionizing, low-cost and practical approach to obtain the respiratory signal. Due to the highly complex and nonlinear relations between tumor and surrogate motion, its ultimate success hinges on the ability to accurately infer the tumor motion from respiratory surrogates. Given their widespread use in the clinic, such a method is critically needed. We propose to use a powerful memory-based learning method to find the complex relations between tumor motion and respiratory surrogates. The method first stores the training data in memory and then finds relevant data to answer a particular query. Nearby data points are assigned high relevance (or weights) and conversely distant data are assigned low relevance. By fitting relatively simple models to local patches instead of fitting one single global model, it is able to capture highly nonlinear and complex relations between the internal tumor motion and external surrogates accurately. Due to the local nature of weighting functions, the method is inherently robust to outliers in the training data. Moreover, both training and adapting to new data are performed almost instantaneously with memory-based learning, making it suitable for dynamically following variable internal/external relations. We evaluated the method using respiratory motion data from 11 patients. The data set consists of simultaneous measurement of 3D tumor motion and 1D abdominal surface (used as the surrogate signal in this study). There are a total of 171 respiratory traces, with an average peak-to-peak amplitude of ∼15 mm and average duration of ∼115 s per trace. Given only 5 s (roughly one breath) pretreatment training data, the method achieved an average 3D error of 1.5 mm and 95

The digital Dalton Plan: Progressive education as integral part of web-based learning environments

Directory of Open Access Journals (Sweden)

Georg Weichhart

2018-03-01

Full Text Available e-Learning systems increasingly support learning management and self-organized learning processes. Since the latter have been studied in the field of progressive education extensively, it is worthwhile to consider them for developing digital learning environments to support self-regulated learning processes. In this paper we aim at transforming one of the most prominent and sustainable approaches to self-organized learning, the “Dalton Plan” as proposed by Helen Parkhurst. Its assignment structure supports learners when managing their learning tasks, thus triggering self-organized acquisition of knowledge, and its feedback graphs enable transparent learning processes. Since e-learning environments have become common use, rather than creating another system, we propose a modular approach that can be used for extending existing e-learning environments. In order to design a respective component, we interviewed experts in self-organized e-learning. Their input facilitated integrating the Dalton Plan with existing features of e-learning environments. After representing each interview in concept maps, we were able to aggregate them for deriving e-learning requirements conform to the Dalton Plan instruments. In the course of implementing them, particular attention had to be paid to the asynchrony of interaction during runtime. Java Server Faces technology enable the Dalton Plan component to be migrated into existing web 2.0 e-learning platforms. The result was evaluated based on the acquired concept maps, as they also captured the transformation process of the Dalton Plan to e-learning features. The findings encourage embodying further progressive education approaches in this way, since the structured (concept mapping of the Dalton Plan to e-learning features turned out to be accurate. The experts were able to recognize the potential of the approach both in terms of structuring the knowledge acquisition process, and in terms of developing

Training self-assessment and task-selection skills to foster self-regulated learning: Do trained skills transfer across domains?

Science.gov (United States)

Raaijmakers, Steven F; Baars, Martine; Paas, Fred; van Merriënboer, Jeroen J G; van Gog, Tamara

2018-01-01

Students' ability to accurately self-assess their performance and select a suitable subsequent learning task in response is imperative for effective self-regulated learning. Video modeling examples have proven effective for training self-assessment and task-selection skills, and-importantly-such training fostered self-regulated learning outcomes. It is unclear, however, whether trained skills would transfer across domains. We investigated whether skills acquired from training with either a specific, algorithmic task-selection rule or a more general heuristic task-selection rule in biology would transfer to self-regulated learning in math. A manipulation check performed after the training confirmed that both algorithmic and heuristic training improved task-selection skills on the biology problems compared with the control condition. However, we found no evidence that students subsequently applied the acquired skills during self-regulated learning in math. Future research should investigate how to support transfer of task-selection skills across domains.

Influences of Formal Learning, Personal Learning Orientation, and Supportive Learning Environment on Informal Learning

Science.gov (United States)

Choi, Woojae; Jacobs, Ronald L.

2011-01-01

While workplace learning includes formal and informal learning, the relationship between the two has been overlooked, because they have been viewed as separate entities. This study investigated the effects of formal learning, personal learning orientation, and supportive learning environment on informal learning among 203 middle managers in Korean…

An Improved Brain-Inspired Emotional Learning Algorithm for Fast Classification

Directory of Open Access Journals (Sweden)

Ying Mei

2017-06-01

Full Text Available Classification is an important task of machine intelligence in the field of information. The artificial neural network (ANN is widely used for classification. However, the traditional ANN shows slow training speed, and it is hard to meet the real-time requirement for large-scale applications. In this paper, an improved brain-inspired emotional learning (BEL algorithm is proposed for fast classification. The BEL algorithm was put forward to mimic the high speed of the emotional learning mechanism in mammalian brain, which has the superior features of fast learning and low computational complexity. To improve the accuracy of BEL in classification, the genetic algorithm (GA is adopted for optimally tuning the weights and biases of amygdala and orbitofrontal cortex in the BEL neural network. The combinational algorithm named as GA-BEL has been tested on eight University of California at Irvine (UCI datasets and two well-known databases (Japanese Female Facial Expression, Cohn–Kanade. The comparisons of experiments indicate that the proposed GA-BEL is more accurate than the original BEL algorithm, and it is much faster than the traditional algorithm.

Autonomous learning in gesture recognition by using lobe component analysis

Science.gov (United States)

Lu, Jian; Weng, Juyang

2007-02-01

Gesture recognition is a new human-machine interface method implemented by pattern recognition(PR).In order to assure robot safety when gesture is used in robot control, it is required to implement the interface reliably and accurately. Similar with other PR applications, 1) feature selection (or model establishment) and 2) training from samples, affect the performance of gesture recognition largely. For 1), a simple model with 6 feature points at shoulders, elbows, and hands, is established. The gestures to be recognized are restricted to still arm gestures, and the movement of arms is not considered. These restrictions are to reduce the misrecognition, but are not so unreasonable. For 2), a new biological network method, called lobe component analysis(LCA), is used in unsupervised learning. Lobe components, corresponding to high-concentrations in probability of the neuronal input, are orientation selective cells follow Hebbian rule and lateral inhibition. Due to the advantage of LCA method for balanced learning between global and local features, large amount of samples can be used in learning efficiently.

Orthographic learning and the role of text-to-speech software in Dutch disabled readers.

Science.gov (United States)

Staels, Eva; Van den Broeck, Wim

2015-01-01

In this study, we examined whether orthographic learning can be demonstrated in disabled readers learning to read in a transparent orthography (Dutch). In addition, we tested the effect of the use of text-to-speech software, a new form of direct instruction, on orthographic learning. Both research goals were investigated by replicating Share's self-teaching paradigm. A total of 65 disabled Dutch readers were asked to read eight stories containing embedded homophonic pseudoword targets (e.g., Blot/Blod), with or without the support of text-to-speech software. The amount of orthographic learning was assessed 3 or 7 days later by three measures of orthographic learning. First, the results supported the presence of orthographic learning during independent silent reading by demonstrating that target spellings were correctly identified more often, named more quickly, and spelled more accurately than their homophone foils. Our results support the hypothesis that all readers, even poor readers of transparent orthographies, are capable of developing word-specific knowledge. Second, a negative effect of text-to-speech software on orthographic learning was demonstrated in this study. This negative effect was interpreted as the consequence of passively listening to the auditory presentation of the text. We clarify how these results can be interpreted within current theoretical accounts of orthographic learning and briefly discuss implications for remedial interventions. © Hammill Institute on Disabilities 2013.

Can cancer researchers accurately judge whether preclinical reports will reproduce?

Directory of Open Access Journals (Sweden)

Daniel Benjamin

2017-06-01

Full Text Available There is vigorous debate about the reproducibility of research findings in cancer biology. Whether scientists can accurately assess which experiments will reproduce original findings is important to determining the pace at which science self-corrects. We collected forecasts from basic and preclinical cancer researchers on the first 6 replication studies conducted by the Reproducibility Project: Cancer Biology (RP:CB to assess the accuracy of expert judgments on specific replication outcomes. On average, researchers forecasted a 75% probability of replicating the statistical significance and a 50% probability of replicating the effect size, yet none of these studies successfully replicated on either criterion (for the 5 studies with results reported. Accuracy was related to expertise: experts with higher h-indices were more accurate, whereas experts with more topic-specific expertise were less accurate. Our findings suggest that experts, especially those with specialized knowledge, were overconfident about the RP:CB replicating individual experiments within published reports; researcher optimism likely reflects a combination of overestimating the validity of original studies and underestimating the difficulties of repeating their methodologies.

Accurate and approximate thermal rate constants for polyatomic chemical reactions

International Nuclear Information System (INIS)

Nyman, Gunnar

2007-01-01

In favourable cases it is possible to calculate thermal rate constants for polyatomic reactions to high accuracy from first principles. Here, we discuss the use of flux correlation functions combined with the multi-configurational time-dependent Hartree (MCTDH) approach to efficiently calculate cumulative reaction probabilities and thermal rate constants for polyatomic chemical reactions. Three isotopic variants of the H 2 + CH 3 → CH 4 + H reaction are used to illustrate the theory. There is good agreement with experimental results although the experimental rates generally are larger than the calculated ones, which are believed to be at least as accurate as the experimental rates. Approximations allowing evaluation of the thermal rate constant above 400 K are treated. It is also noted that for the treated reactions, transition state theory (TST) gives accurate rate constants above 500 K. TST theory also gives accurate results for kinetic isotope effects in cases where the mass of the transfered atom is unchanged. Due to neglect of tunnelling, TST however fails below 400 K if the mass of the transferred atom changes between the isotopic reactions

A multiple regression analysis for accurate background subtraction in 99Tcm-DTPA renography

International Nuclear Information System (INIS)

Middleton, G.W.; Thomson, W.H.; Davies, I.H.; Morgan, A.

1989-01-01

A technique for accurate background subtraction in 99 Tc m -DTPA renography is described. The technique is based on a multiple regression analysis of the renal curves and separate heart and soft tissue curves which together represent background activity. It is compared, in over 100 renograms, with a previously described linear regression technique. Results show that the method provides accurate background subtraction, even in very poorly functioning kidneys, thus enabling relative renal filtration and excretion to be accurately estimated. (author)

A machine learning approach to the accurate prediction of multi-leaf collimator positional errors

Science.gov (United States)

Carlson, Joel N. K.; Park, Jong Min; Park, So-Yeon; In Park, Jong; Choi, Yunseok; Ye, Sung-Joon

2016-03-01

Discrepancies between planned and delivered movements of multi-leaf collimators (MLCs) are an important source of errors in dose distributions during radiotherapy. In this work we used machine learning techniques to train models to predict these discrepancies, assessed the accuracy of the model predictions, and examined the impact these errors have on quality assurance (QA) procedures and dosimetry. Predictive leaf motion parameters for the models were calculated from the plan files, such as leaf position and velocity, whether the leaf was moving towards or away from the isocenter of the MLC, and many others. Differences in positions between synchronized DICOM-RT planning files and DynaLog files reported during QA delivery were used as a target response for training of the models. The final model is capable of predicting MLC positions during delivery to a high degree of accuracy. For moving MLC leaves, predicted positions were shown to be significantly closer to delivered positions than were planned positions. By incorporating predicted positions into dose calculations in the TPS, increases were shown in gamma passing rates against measured dose distributions recorded during QA delivery. For instance, head and neck plans with 1%/2 mm gamma criteria had an average increase in passing rate of 4.17% (SD  =  1.54%). This indicates that the inclusion of predictions during dose calculation leads to a more realistic representation of plan delivery. To assess impact on the patient, dose volumetric histograms (DVH) using delivered positions were calculated for comparison with planned and predicted DVHs. In all cases, predicted dose volumetric parameters were in closer agreement to the delivered parameters than were the planned parameters, particularly for organs at risk on the periphery of the treatment area. By incorporating the predicted positions into the TPS, the treatment planner is given a more realistic view of the dose distribution as it will truly be

Accurate automatic tuning circuit for bipolar integrated filters

NARCIS (Netherlands)

de Heij, Wim J.A.; de Heij, W.J.A.; Hoen, Klaas; Hoen, Klaas; Seevinck, Evert; Seevinck, E.

1990-01-01

An accurate automatic tuning circuit for tuning the cutoff frequency and Q-factor of high-frequency bipolar filters is presented. The circuit is based on a voltage controlled quadrature oscillator (VCO). The frequency and the RMS (root mean square) amplitude of the oscillator output signal are

Accurate Charge Densities from Powder Diffraction

DEFF Research Database (Denmark)

Bindzus, Niels; Wahlberg, Nanna; Becker, Jacob

Synchrotron powder X-ray diffraction has in recent years advanced to a level, where it has become realistic to probe extremely subtle electronic features. Compared to single-crystal diffraction, it may be superior for simple, high-symmetry crystals owing to negligible extinction effects and minimal...... peak overlap. Additionally, it offers the opportunity for collecting data on a single scale. For charge densities studies, the critical task is to recover accurate and bias-free structure factors from the diffraction pattern. This is the focal point of the present study, scrutinizing the performance...

Importance of molecular diagnosis in the accurate diagnosis of ...

Indian Academy of Sciences (India)

1Department of Health and Environmental Sciences, Kyoto University Graduate School of Medicine, Yoshida Konoecho, ... of molecular diagnosis in the accurate diagnosis of systemic carnitine deficiency. .... 'affecting protein function' by SIFT.

Exploring the knowledge behind predictions in everyday cognition: an iterated learning study.

Science.gov (United States)

Stephens, Rachel G; Dunn, John C; Rao, Li-Lin; Li, Shu

2015-10-01

Making accurate predictions about events is an important but difficult task. Recent work suggests that people are adept at this task, making predictions that reflect surprisingly accurate knowledge of the distributions of real quantities. Across three experiments, we used an iterated learning procedure to explore the basis of this knowledge: to what extent is domain experience critical to accurate predictions and how accurate are people when faced with unfamiliar domains? In Experiment 1, two groups of participants, one resident in Australia, the other in China, predicted the values of quantities familiar to both (movie run-times), unfamiliar to both (the lengths of Pharaoh reigns), and familiar to one but unfamiliar to the other (cake baking durations and the lengths of Beijing bus routes). While predictions from both groups were reasonably accurate overall, predictions were inaccurate in the selectively unfamiliar domains and, surprisingly, predictions by the China-resident group were also inaccurate for a highly familiar domain: local bus route lengths. Focusing on bus routes, two follow-up experiments with Australia-resident groups clarified the knowledge and strategies that people draw upon, plus important determinants of accurate predictions. For unfamiliar domains, people appear to rely on extrapolating from (not simply directly applying) related knowledge. However, we show that people's predictions are subject to two sources of error: in the estimation of quantities in a familiar domain and extension to plausible values in an unfamiliar domain. We propose that the key to successful predictions is not simply domain experience itself, but explicit experience of relevant quantities.

Prediction of Bispectral Index during Target-controlled Infusion of Propofol and Remifentanil: A Deep Learning Approach.

Science.gov (United States)

Lee, Hyung-Chul; Ryu, Ho-Geol; Chung, Eun-Jin; Jung, Chul-Woo

2018-03-01

The discrepancy between predicted effect-site concentration and measured bispectral index is problematic during intravenous anesthesia with target-controlled infusion of propofol and remifentanil. We hypothesized that bispectral index during total intravenous anesthesia would be more accurately predicted by a deep learning approach. Long short-term memory and the feed-forward neural network were sequenced to simulate the pharmacokinetic and pharmacodynamic parts of an empirical model, respectively, to predict intraoperative bispectral index during combined use of propofol and remifentanil. Inputs of long short-term memory were infusion histories of propofol and remifentanil, which were retrieved from target-controlled infusion pumps for 1,800 s at 10-s intervals. Inputs of the feed-forward network were the outputs of long short-term memory and demographic data such as age, sex, weight, and height. The final output of the feed-forward network was the bispectral index. The performance of bispectral index prediction was compared between the deep learning model and previously reported response surface model. The model hyperparameters comprised 8 memory cells in the long short-term memory layer and 16 nodes in the hidden layer of the feed-forward network. The model training and testing were performed with separate data sets of 131 and 100 cases. The concordance correlation coefficient (95% CI) were 0.561 (0.560 to 0.562) in the deep learning model, which was significantly larger than that in the response surface model (0.265 [0.263 to 0.266], P deep learning model-predicted bispectral index during target-controlled infusion of propofol and remifentanil more accurately compared to the traditional model. The deep learning approach in anesthetic pharmacology seems promising because of its excellent performance and extensibility.

Accurate evaluation of exchange fields in finite element micromagnetic solvers

Science.gov (United States)

Chang, R.; Escobar, M. A.; Li, S.; Lubarda, M. V.; Lomakin, V.

2012-04-01

Quadratic basis functions (QBFs) are implemented for solving the Landau-Lifshitz-Gilbert equation via the finite element method. This involves the introduction of a set of special testing functions compatible with the QBFs for evaluating the Laplacian operator. The results by using QBFs are significantly more accurate than those via linear basis functions. QBF approach leads to significantly more accurate results than conventionally used approaches based on linear basis functions. Importantly QBFs allow reducing the error of computing the exchange field by increasing the mesh density for structured and unstructured meshes. Numerical examples demonstrate the feasibility of the method.

Sequence-based prediction of protein protein interaction using a deep-learning algorithm.

Science.gov (United States)

Sun, Tanlin; Zhou, Bo; Lai, Luhua; Pei, Jianfeng

2017-05-25

Protein-protein interactions (PPIs) are critical for many biological processes. It is therefore important to develop accurate high-throughput methods for identifying PPI to better understand protein function, disease occurrence, and therapy design. Though various computational methods for predicting PPI have been developed, their robustness for prediction with external datasets is unknown. Deep-learning algorithms have achieved successful results in diverse areas, but their effectiveness for PPI prediction has not been tested. We used a stacked autoencoder, a type of deep-learning algorithm, to study the sequence-based PPI prediction. The best model achieved an average accuracy of 97.19% with 10-fold cross-validation. The prediction accuracies for various external datasets ranged from 87.99% to 99.21%, which are superior to those achieved with previous methods. To our knowledge, this research is the first to apply a deep-learning algorithm to sequence-based PPI prediction, and the results demonstrate its potential in this field.

Opinion Mining in Latvian Text Using Semantic Polarity Analysis and Machine Learning Approach

Directory of Open Access Journals (Sweden)

Gatis Špats

2016-07-01

Full Text Available In this paper we demonstrate approaches for opinion mining in Latvian text. Authors have applied, combined and extended results of several previous studies and public resources to perform opinion mining in Latvian text using two approaches, namely, semantic polarity analysis and machine learning. One of the most significant constraints that make application of opinion mining for written content classification in Latvian text challenging is the limited publicly available text corpora for classifier training. We have joined several sources and created a publically available extended lexicon. Our results are comparable to or outperform current achievements in opinion mining in Latvian. Experiments show that lexicon-based methods provide more accurate opinion mining than the application of Naive Bayes machine learning classifier on Latvian tweets. Methods used during this study could be further extended using human annotators, unsupervised machine learning and bootstrapping to create larger corpora of classified text.

Foresight begins with FMEA. Delivering accurate risk assessments.

Science.gov (United States)

Passey, R D

1999-03-01

If sufficient factors are taken into account and two- or three-stage analysis is employed, failure mode and effect analysis represents an excellent technique for delivering accurate risk assessments for products and processes, and for relating them to legal liability. This article describes a format that facilitates easy interpretation.

Inaccurate Metacognitive Monitoring and Its Effects on Metacognitive Control and Task Outcomes in Self-Regulated L2 Learning

Science.gov (United States)

Ranalli, Jim

2018-01-01

Accurate metacognitive monitoring of one's own knowledge or performance is a precondition for self-regulated learning; monitoring informs metacognitive control, which in turn affects task outcomes. Studies of monitoring accuracy and its connection to knowledge and performance are common in psychology and educational research but rare in instructed…

Deformable MR Prostate Segmentation via Deep Feature Learning and Sparse Patch Matching.

Science.gov (United States)

Guo, Yanrong; Gao, Yaozong; Shen, Dinggang

2016-04-01

Automatic and reliable segmentation of the prostate is an important but difficult task for various clinical applications such as prostate cancer radiotherapy. The main challenges for accurate MR prostate localization lie in two aspects: (1) inhomogeneous and inconsistent appearance around prostate boundary, and (2) the large shape variation across different patients. To tackle these two problems, we propose a new deformable MR prostate segmentation method by unifying deep feature learning with the sparse patch matching. First, instead of directly using handcrafted features, we propose to learn the latent feature representation from prostate MR images by the stacked sparse auto-encoder (SSAE). Since the deep learning algorithm learns the feature hierarchy from the data, the learned features are often more concise and effective than the handcrafted features in describing the underlying data. To improve the discriminability of learned features, we further refine the feature representation in a supervised fashion. Second, based on the learned features, a sparse patch matching method is proposed to infer a prostate likelihood map by transferring the prostate labels from multiple atlases to the new prostate MR image. Finally, a deformable segmentation is used to integrate a sparse shape model with the prostate likelihood map for achieving the final segmentation. The proposed method has been extensively evaluated on the dataset that contains 66 T2-wighted prostate MR images. Experimental results show that the deep-learned features are more effective than the handcrafted features in guiding MR prostate segmentation. Moreover, our method shows superior performance than other state-of-the-art segmentation methods.

Accurate multiplicity scaling in isotopically conjugate reactions

International Nuclear Information System (INIS)

Golokhvastov, A.I.

1989-01-01

The generation of accurate scaling of mutiplicity distributions is presented. The distributions of π - mesons (negative particles) and π + mesons in different nucleon-nucleon interactions (PP, NP and NN) are described by the same universal function Ψ(z) and the same energy dependence of the scale parameter which determines the stretching factor for the unit function Ψ(z) to obtain the desired multiplicity distribution. 29 refs.; 6 figs

Deep-Learning-Based Approach for Prediction of Algal Blooms

Directory of Open Access Journals (Sweden)

Feng Zhang

2016-10-01

Full Text Available Algal blooms have recently become a critical global environmental concern which might put economic development and sustainability at risk. However, the accurate prediction of algal blooms remains a challenging scientific problem. In this study, a novel prediction approach for algal blooms based on deep learning is presented—a powerful tool to represent and predict highly dynamic and complex phenomena. The proposed approach constructs a five-layered model to extract detailed relationships between the density of phytoplankton cells and various environmental parameters. The algal blooms can be predicted by the phytoplankton density obtained from the output layer. A case study is conducted in coastal waters of East China using both our model and a traditional back-propagation neural network for comparison. The results show that the deep-learning-based model yields better generalization and greater accuracy in predicting algal blooms than a traditional shallow neural network does.

The application of language-game theory to the analysis of science learning: Developing an interpretive classroom-level learning framework

Science.gov (United States)

Ahmadibasir, Mohammad

In this study an interpretive learning framework that aims to measure learning on the classroom level is introduced. In order to develop and evaluate the value of the framework, a theoretical/empirical study is designed. The researcher attempted to illustrate how the proposed framework provides insights on the problem of classroom-level learning. The framework is developed by construction of connections between the current literature on science learning and Wittgenstein's language-game theory. In this framework learning is defined as change of classroom language-game or discourse. In the proposed framework, learning is measured by analysis of classroom discourse. The empirical explanation power of the framework is evaluated by applying the framework in the analysis of learning in a fifth-grade science classroom. The researcher attempted to analyze how students' colloquial discourse changed to a discourse that bears more resemblance to science discourse. The results of the empirical part of the investigation are presented in three parts: first, the gap between what students did and what they were supposed to do was reported. The gap showed that students during the classroom inquiry wanted to do simple comparisons by direct observation, while they were supposed to do tool-assisted observation and procedural manipulation for a complete comparison. Second, it was illustrated that the first attempt to connect the colloquial to science discourse was done by what was immediately intelligible for students and then the teacher negotiated with students in order to help them to connect the old to the new language-game more purposefully. The researcher suggested that these two events in the science classroom are critical in discourse change. Third, it was illustrated that through the academic year, the way that students did the act of comparison was improved and by the end of the year more accurate causal inferences were observable in classroom communication. At the end of the

Deep-Learning-Enabled On-Demand Design of Chiral Metamaterials.

Science.gov (United States)

Ma, Wei; Cheng, Feng; Liu, Yongmin

2018-06-11

Deep-learning framework has significantly impelled the development of modern machine learning technology by continuously pushing the limit of traditional recognition and processing of images, speech, and videos. In the meantime, it starts to penetrate other disciplines, such as biology, genetics, materials science, and physics. Here, we report a deep-learning-based model, comprising two bidirectional neural networks assembled by a partial stacking strategy, to automatically design and optimize three-dimensional chiral metamaterials with strong chiroptical responses at predesignated wavelengths. The model can help to discover the intricate, nonintuitive relationship between a metamaterial structure and its optical responses from a number of training examples, which circumvents the time-consuming, case-by-case numerical simulations in conventional metamaterial designs. This approach not only realizes the forward prediction of optical performance much more accurately and efficiently but also enables one to inversely retrieve designs from given requirements. Our results demonstrate that such a data-driven model can be applied as a very powerful tool in studying complicated light-matter interactions and accelerating the on-demand design of nanophotonic devices, systems, and architectures for real world applications.

Compensatory Processing During Rule-Based Category Learning in Older Adults

Science.gov (United States)

Bharani, Krishna L.; Paller, Ken A.; Reber, Paul J.; Weintraub, Sandra; Yanar, Jorge; Morrison, Robert G.

2016-01-01

Healthy older adults typically perform worse than younger adults at rule-based category learning, but better than patients with Alzheimer's or Parkinson's disease. To further investigate aging's effect on rule-based category learning, we monitored event-related potentials (ERPs) while younger and neuropsychologically typical older adults performed a visual category-learning task with a rule-based category structure and trial-by-trial feedback. Using these procedures, we previously identified ERPs sensitive to categorization strategy and accuracy in young participants. In addition, previous studies have demonstrated the importance of neural processing in the prefrontal cortex and the medial temporal lobe for this task. In this study, older adults showed lower accuracy and longer response times than younger adults, but there were two distinct subgroups of older adults. One subgroup showed near-chance performance throughout the procedure, never categorizing accurately. The other subgroup reached asymptotic accuracy that was equivalent to that in younger adults, although they categorized more slowly. These two subgroups were further distinguished via ERPs. Consistent with the compensation theory of cognitive aging, older adults who successfully learned showed larger frontal ERPs when compared with younger adults. Recruitment of prefrontal resources may have improved performance while slowing response times. Additionally, correlations of feedback-locked P300 amplitudes with category-learning accuracy differentiated successful younger and older adults. Overall, the results suggest that the ability to adapt one's behavior in response to feedback during learning varies across older individuals, and that the failure of some to adapt their behavior may reflect inadequate engagement of prefrontal cortex. PMID:26422522

Gene Prediction in Metagenomic Fragments with Deep Learning

Directory of Open Access Journals (Sweden)

Shao-Wu Zhang

2017-01-01

Full Text Available Next generation sequencing technologies used in metagenomics yield numerous sequencing fragments which come from thousands of different species. Accurately identifying genes from metagenomics fragments is one of the most fundamental issues in metagenomics. In this article, by fusing multifeatures (i.e., monocodon usage, monoamino acid usage, ORF length coverage, and Z-curve features and using deep stacking networks learning model, we present a novel method (called Meta-MFDL to predict the metagenomic genes. The results with 10 CV and independent tests show that Meta-MFDL is a powerful tool for identifying genes from metagenomic fragments.

Learning a Weighted Sequence Model of the Nucleosome Core and Linker Yields More Accurate Predictions in Saccharomyces cerevisiae and Homo sapiens

Science.gov (United States)

Reynolds, Sheila M.; Bilmes, Jeff A.; Noble, William Stafford

2010-01-01

DNA in eukaryotes is packaged into a chromatin complex, the most basic element of which is the nucleosome. The precise positioning of the nucleosome cores allows for selective access to the DNA, and the mechanisms that control this positioning are important pieces of the gene expression puzzle. We describe a large-scale nucleosome pattern that jointly characterizes the nucleosome core and the adjacent linkers and is predominantly characterized by long-range oscillations in the mono, di- and tri-nucleotide content of the DNA sequence, and we show that this pattern can be used to predict nucleosome positions in both Homo sapiens and Saccharomyces cerevisiae more accurately than previously published methods. Surprisingly, in both H. sapiens and S. cerevisiae, the most informative individual features are the mono-nucleotide patterns, although the inclusion of di- and tri-nucleotide features results in improved performance. Our approach combines a much longer pattern than has been previously used to predict nucleosome positioning from sequence—301 base pairs, centered at the position to be scored—with a novel discriminative classification approach that selectively weights the contributions from each of the input features. The resulting scores are relatively insensitive to local AT-content and can be used to accurately discriminate putative dyad positions from adjacent linker regions without requiring an additional dynamic programming step and without the attendant edge effects and assumptions about linker length modeling and overall nucleosome density. Our approach produces the best dyad-linker classification results published to date in H. sapiens, and outperforms two recently published models on a large set of S. cerevisiae nucleosome positions. Our results suggest that in both genomes, a comparable and relatively small fraction of nucleosomes are well-positioned and that these positions are predictable based on sequence alone. We believe that the bulk of the

Learning a weighted sequence model of the nucleosome core and linker yields more accurate predictions in Saccharomyces cerevisiae and Homo sapiens.

Directory of Open Access Journals (Sweden)

Sheila M Reynolds

2010-07-01

Full Text Available DNA in eukaryotes is packaged into a chromatin complex, the most basic element of which is the nucleosome. The precise positioning of the nucleosome cores allows for selective access to the DNA, and the mechanisms that control this positioning are important pieces of the gene expression puzzle. We describe a large-scale nucleosome pattern that jointly characterizes the nucleosome core and the adjacent linkers and is predominantly characterized by long-range oscillations in the mono, di- and tri-nucleotide content of the DNA sequence, and we show that this pattern can be used to predict nucleosome positions in both Homo sapiens and Saccharomyces cerevisiae more accurately than previously published methods. Surprisingly, in both H. sapiens and S. cerevisiae, the most informative individual features are the mono-nucleotide patterns, although the inclusion of di- and tri-nucleotide features results in improved performance. Our approach combines a much longer pattern than has been previously used to predict nucleosome positioning from sequence-301 base pairs, centered at the position to be scored-with a novel discriminative classification approach that selectively weights the contributions from each of the input features. The resulting scores are relatively insensitive to local AT-content and can be used to accurately discriminate putative dyad positions from adjacent linker regions without requiring an additional dynamic programming step and without the attendant edge effects and assumptions about linker length modeling and overall nucleosome density. Our approach produces the best dyad-linker classification results published to date in H. sapiens, and outperforms two recently published models on a large set of S. cerevisiae nucleosome positions. Our results suggest that in both genomes, a comparable and relatively small fraction of nucleosomes are well-positioned and that these positions are predictable based on sequence alone. We believe that the

Learning a weighted sequence model of the nucleosome core and linker yields more accurate predictions in Saccharomyces cerevisiae and Homo sapiens.

Science.gov (United States)

Reynolds, Sheila M; Bilmes, Jeff A; Noble, William Stafford

2010-07-08

DNA in eukaryotes is packaged into a chromatin complex, the most basic element of which is the nucleosome. The precise positioning of the nucleosome cores allows for selective access to the DNA, and the mechanisms that control this positioning are important pieces of the gene expression puzzle. We describe a large-scale nucleosome pattern that jointly characterizes the nucleosome core and the adjacent linkers and is predominantly characterized by long-range oscillations in the mono, di- and tri-nucleotide content of the DNA sequence, and we show that this pattern can be used to predict nucleosome positions in both Homo sapiens and Saccharomyces cerevisiae more accurately than previously published methods. Surprisingly, in both H. sapiens and S. cerevisiae, the most informative individual features are the mono-nucleotide patterns, although the inclusion of di- and tri-nucleotide features results in improved performance. Our approach combines a much longer pattern than has been previously used to predict nucleosome positioning from sequence-301 base pairs, centered at the position to be scored-with a novel discriminative classification approach that selectively weights the contributions from each of the input features. The resulting scores are relatively insensitive to local AT-content and can be used to accurately discriminate putative dyad positions from adjacent linker regions without requiring an additional dynamic programming step and without the attendant edge effects and assumptions about linker length modeling and overall nucleosome density. Our approach produces the best dyad-linker classification results published to date in H. sapiens, and outperforms two recently published models on a large set of S. cerevisiae nucleosome positions. Our results suggest that in both genomes, a comparable and relatively small fraction of nucleosomes are well-positioned and that these positions are predictable based on sequence alone. We believe that the bulk of the

An efficient and accurate 3D displacements tracking strategy for digital volume correlation

KAUST Repository

Pan, Bing; Wang, Bo; Wu, Dafang; Lubineau, Gilles

2014-01-01

inverse compositional Gauss-Newton (3D IC-GN) algorithm is introduced to replace existing forward additive algorithms for accurate sub-voxel displacement registration. Second, to ensure the 3D IC-GN algorithm that converges accurately and rapidly and avoid

A highly accurate method for determination of dissolved oxygen: Gravimetric Winkler method

International Nuclear Information System (INIS)

Helm, Irja; Jalukse, Lauri; Leito, Ivo

2012-01-01

Highlights: ► Probably the most accurate method available for dissolved oxygen concentration measurement was developed. ► Careful analysis of uncertainty sources was carried out and the method was optimized for minimizing all uncertainty sources as far as practical. ► This development enables more accurate calibration of dissolved oxygen sensors for routine analysis than has been possible before. - Abstract: A high-accuracy Winkler titration method has been developed for determination of dissolved oxygen concentration. Careful analysis of uncertainty sources relevant to the Winkler method was carried out and the method was optimized for minimizing all uncertainty sources as far as practical. The most important improvements were: gravimetric measurement of all solutions, pre-titration to minimize the effect of iodine volatilization, accurate amperometric end point detection and careful accounting for dissolved oxygen in the reagents. As a result, the developed method is possibly the most accurate method of determination of dissolved oxygen available. Depending on measurement conditions and on the dissolved oxygen concentration the combined standard uncertainties of the method are in the range of 0.012–0.018 mg dm −3 corresponding to the k = 2 expanded uncertainty in the range of 0.023–0.035 mg dm −3 (0.27–0.38%, relative). This development enables more accurate calibration of electrochemical and optical dissolved oxygen sensors for routine analysis than has been possible before.

Deep learning for EEG-Based preference classification

Science.gov (United States)

Teo, Jason; Hou, Chew Lin; Mountstephens, James

2017-10-01

Electroencephalogram (EEG)-based emotion classification is rapidly becoming one of the most intensely studied areas of brain-computer interfacing (BCI). The ability to passively identify yet accurately correlate brainwaves with our immediate emotions opens up truly meaningful and previously unattainable human-computer interactions such as in forensic neuroscience, rehabilitative medicine, affective entertainment and neuro-marketing. One particularly useful yet rarely explored areas of EEG-based emotion classification is preference recognition [1], which is simply the detection of like versus dislike. Within the limited investigations into preference classification, all reported studies were based on musically-induced stimuli except for a single study which used 2D images. The main objective of this study is to apply deep learning, which has been shown to produce state-of-the-art results in diverse hard problems such as in computer vision, natural language processing and audio recognition, to 3D object preference classification over a larger group of test subjects. A cohort of 16 users was shown 60 bracelet-like objects as rotating visual stimuli on a computer display while their preferences and EEGs were recorded. After training a variety of machine learning approaches which included deep neural networks, we then attempted to classify the users' preferences for the 3D visual stimuli based on their EEGs. Here, we show that that deep learning outperforms a variety of other machine learning classifiers for this EEG-based preference classification task particularly in a highly challenging dataset with large inter- and intra-subject variability.

Rapid and accurate evaluation of the quality of commercial organic fertilizers using near infrared spectroscopy.

Directory of Open Access Journals (Sweden)

Chang Wang

Full Text Available The composting industry has been growing rapidly in China because of a boom in the animal industry. Therefore, a rapid and accurate assessment of the quality of commercial organic fertilizers is of the utmost importance. In this study, a novel technique that combines near infrared (NIR spectroscopy with partial least squares (PLS analysis is developed for rapidly and accurately assessing commercial organic fertilizers quality. A total of 104 commercial organic fertilizers were collected from full-scale compost factories in Jiangsu Province, east China. In general, the NIR-PLS technique showed accurate predictions of the total organic matter, water soluble organic nitrogen, pH, and germination index; less accurate results of the moisture, total nitrogen, and electrical conductivity; and the least accurate results for water soluble organic carbon. Our results suggested the combined NIR-PLS technique could be applied as a valuable tool to rapidly and accurately assess the quality of commercial organic fertilizers.

Rapid and accurate evaluation of the quality of commercial organic fertilizers using near infrared spectroscopy.

Science.gov (United States)

Wang, Chang; Huang, Chichao; Qian, Jian; Xiao, Jian; Li, Huan; Wen, Yongli; He, Xinhua; Ran, Wei; Shen, Qirong; Yu, Guanghui

2014-01-01

The composting industry has been growing rapidly in China because of a boom in the animal industry. Therefore, a rapid and accurate assessment of the quality of commercial organic fertilizers is of the utmost importance. In this study, a novel technique that combines near infrared (NIR) spectroscopy with partial least squares (PLS) analysis is developed for rapidly and accurately assessing commercial organic fertilizers quality. A total of 104 commercial organic fertilizers were collected from full-scale compost factories in Jiangsu Province, east China. In general, the NIR-PLS technique showed accurate predictions of the total organic matter, water soluble organic nitrogen, pH, and germination index; less accurate results of the moisture, total nitrogen, and electrical conductivity; and the least accurate results for water soluble organic carbon. Our results suggested the combined NIR-PLS technique could be applied as a valuable tool to rapidly and accurately assess the quality of commercial organic fertilizers.

An Hourly Streamflow Forecasting Model Coupled with an Enforced Learning Strategy

Directory of Open Access Journals (Sweden)

Ming-Chang Wu

2015-10-01

Full Text Available Floods, one of the most significant natural hazards, often result in loss of life and property. Accurate hourly streamflow forecasting is always a key issue in hydrology for flood hazard mitigation. To improve the performance of hourly streamflow forecasting, a methodology concerning the development of neural network (NN based models with an enforced learning strategy is proposed in this paper. Firstly, four different NNs, namely back propagation network (BPN, radial basis function network (RBFN, self-organizing map (SOM, and support vector machine (SVM, are used to construct streamflow forecasting models. Through the cross-validation test, NN-based models with superior performance in streamflow forecasting are detected. Then, an enforced learning strategy is developed to further improve the performance of the superior NN-based models, i.e., SOM and SVM in this study. Finally, the proposed flow forecasting model is obtained. Actual applications are conducted to demonstrate the potential of the proposed model. Moreover, comparison between the NN-based models with and without the enforced learning strategy is performed to evaluate the effect of the enforced learning strategy on model performance. The results indicate that the NN-based models with the enforced learning strategy indeed improve the accuracy of hourly streamflow forecasting. Hence, the presented methodology is expected to be helpful for developing improved NN-based streamflow forecasting models.

Video-Based Surgical Learning: Improving Trainee Education and Preparation for Surgery.

Science.gov (United States)

Mota, Paulo; Carvalho, Nuno; Carvalho-Dias, Emanuel; João Costa, Manuel; Correia-Pinto, Jorge; Lima, Estevão

2017-10-11

Since the end of the XIX century, teaching of surgery has remained practically unaltered until now. With the dawn of video-assisted laparoscopy, surgery has faced new technical and learning challenges. Due to technological advances, from Internet access to portable electronic devices, the use of online resources is part of the educational armamentarium. In this respect, videos have already proven to be effective and useful, however the best way to benefit from these tools is still not clearly defined. To assess the importance of video-based learning, using an electronic questionnaire applied to residents and specialists of different surgical fields. Importance of video-based learning was assessed in a sample of 141 subjects, using a questionnaire distributed by a GoogleDoc online form. We found that 98.6% of the respondents have already used videos to prepare for surgery. When comparing video sources by formation status, residents were found to use Youtube significantly more often than specialists (p learning is currently a hallmark of surgical preparation among residents and specialists working in Portugal. Based on these findings we believe that the creation of quality and scientifically accurate videos, and subsequent compilation in available video-libraries appears to be the future landscape for video-based learning. Copyright © 2017 Association of Program Directors in Surgery. Published by Elsevier Inc. All rights reserved.

THE SELF-CORRECTION OF ENGLISH SPEECH ERRORS IN SECOND LANGUANGE LEARNING

Directory of Open Access Journals (Sweden)

Ketut Santi Indriani

2015-05-01

Full Text Available The process of second language (L2 learning is strongly influenced by the factors of error reconstruction that occur when the language is learned. Errors will definitely appear in the learning process. However, errors can be used as a step to accelerate the process of understanding the language. Doing self-correction (with or without giving cues is one of the examples. In the aspect of speaking, self-correction is done immediately after the error appears. This study is aimed at finding (i what speech errors the L2 speakers are able to identify, (ii of the errors identified, what speech errors the L2 speakers are able to self correct and (iii whether the self-correction of speech error are able to immediately improve the L2 learning. Based on the data analysis, it was found that the majority identified errors are related to noun (plurality, subject-verb agreement, grammatical structure and pronunciation.. B2 speakers tend to correct errors properly. Of the 78% identified speech errors, as much as 66% errors could be self-corrected accurately by the L2 speakers. Based on the analysis, it was also found that self-correction is able to improve L2 learning ability directly. This is evidenced by the absence of repetition of the same error after the error had been corrected.

Is bioelectrical impedance accurate for use in large epidemiological studies?

Directory of Open Access Journals (Sweden)

Merchant Anwar T

2008-09-01

Full Text Available Abstract Percentage of body fat is strongly associated with the risk of several chronic diseases but its accurate measurement is difficult. Bioelectrical impedance analysis (BIA is a relatively simple, quick and non-invasive technique, to measure body composition. It measures body fat accurately in controlled clinical conditions but its performance in the field is inconsistent. In large epidemiologic studies simpler surrogate techniques such as body mass index (BMI, waist circumference, and waist-hip ratio are frequently used instead of BIA to measure body fatness. We reviewed the rationale, theory, and technique of recently developed systems such as foot (or hand-to-foot BIA measurement, and the elements that could influence its results in large epidemiologic studies. BIA results are influenced by factors such as the environment, ethnicity, phase of menstrual cycle, and underlying medical conditions. We concluded that BIA measurements validated for specific ethnic groups, populations and conditions can accurately measure body fat in those populations, but not others and suggest that for large epdiemiological studies with diverse populations BIA may not be the appropriate choice for body composition measurement unless specific calibration equations are developed for different groups participating in the study.

9 CFR 442.3 - Scale requirements for accurate weights, repairs, adjustments, and replacements after inspection.

Science.gov (United States)

2010-01-01

... 9 Animals and Animal Products 2 2010-01-01 2010-01-01 false Scale requirements for accurate... PROCEDURES AND REQUIREMENTS FOR ACCURATE WEIGHTS § 442.3 Scale requirements for accurate weights, repairs, adjustments, and replacements after inspection. (a) All scales used to determine the net weight of meat and...

Systematization of Accurate Discrete Optimization Methods

Directory of Open Access Journals (Sweden)

V. A. Ovchinnikov

2015-01-01

Full Text Available The object of study of this paper is to define accurate methods for solving combinatorial optimization problems of structural synthesis. The aim of the work is to systemize the exact methods of discrete optimization and define their applicability to solve practical problems.The article presents the analysis, generalization and systematization of classical methods and algorithms described in the educational and scientific literature.As a result of research a systematic presentation of combinatorial methods for discrete optimization described in various sources is given, their capabilities are described and properties of the tasks to be solved using the appropriate methods are specified.

Software Estimation: Developing an Accurate, Reliable Method

Science.gov (United States)

2011-08-01

based and size-based estimates is able to accurately plan, launch, and execute on schedule. Bob Sinclair, NAWCWD Chris Rickets , NAWCWD Brad Hodgins...Office by Carnegie Mellon University. SMPSP and SMTSP are service marks of Carnegie Mellon University. 1. Rickets , Chris A, “A TSP Software Maintenance...Life Cycle”, CrossTalk, March, 2005. 2. Koch, Alan S, “TSP Can Be the Building blocks for CMMI”, CrossTalk, March, 2005. 3. Hodgins, Brad, Rickets

Readiness of Adults to Learn Using E-Learning, M-Learning and T-Learning Technologies

Science.gov (United States)

Vilkonis, Rytis; Bakanoviene, Tatjana; Turskiene, Sigita

2013-01-01

The article presents results of the empirical research revealing readiness of adults to participate in the lifelong learning process using e-learning, m-learning and t-learning technologies. The research has been carried out in the framework of the international project eBig3 aiming at development a new distance learning platform blending virtual…

Targeted Memory Reactivation during Sleep Depends on Prior Learning.

Science.gov (United States)

Creery, Jessica D; Oudiette, Delphine; Antony, James W; Paller, Ken A

2015-05-01

When sounds associated with learning are presented again during slow-wave sleep, targeted memory reactivation (TMR) can produce improvements in subsequent location recall. Here we used TMR to investigate memory consolidation during an afternoon nap as a function of prior learning. Twenty healthy individuals (8 male, 19-23 y old). Participants learned to associate each of 50 common objects with a unique screen location. When each object appeared, its characteristic sound was played. After electroencephalography (EEG) electrodes were applied, location recall was assessed for each object, followed by a 90-min interval for sleep. During EEG-verified slow-wave sleep, half of the sounds were quietly presented over white noise. Recall was assessed 3 h after initial learning. A beneficial effect of TMR was found in the form of higher recall accuracy for cued objects compared to uncued objects when pre-sleep accuracy was used as an explanatory variable. An analysis of individual differences revealed that this benefit was greater for participants with higher pre-sleep recall accuracy. In an analysis for individual objects, cueing benefits were apparent as long as initial recall was not highly accurate. Sleep physiology analyses revealed that the cueing benefit correlated with delta power and fast spindle density. These findings substantiate the use of targeted memory reactivation (TMR) methods for manipulating consolidation during sleep. TMR can selectively strengthen memory storage for object-location associations learned prior to sleep, except for those near-perfectly memorized. Neural measures found in conjunction with TMR-induced strengthening provide additional evidence about mechanisms of sleep consolidation. © 2015 Associated Professional Sleep Societies, LLC.

Overall Memory Impairment Identification with Mathematical Modeling of the CVLT-II Learning Curve in Multiple Sclerosis

Directory of Open Access Journals (Sweden)

Igor I. Stepanov

2012-01-01

Full Text Available The CVLT-II provides standardized scores for each of the List A five learning trials, so that the clinician can compare the patient's raw trials 1–5 scores with standardized ones. However, frequently, a patient's raw scores fluctuate making a proper interpretation difficult. The CVLT-II does not offer any other methods for classifying a patient's learning and memory status on the background of the learning curve. The main objective of this research is to illustrate that discriminant analysis provides an accurate assessment of the learning curve, if suitable predictor variables are selected. Normal controls were ninety-eight healthy volunteers (78 females and 20 males. A group of MS patients included 365 patients (266 females and 99 males with clinically defined multiple sclerosis. We show that the best predictor variables are coefficients 3 and 4 of our mathematical model 3∗exp(−2∗(−1+4∗(1−exp(−2∗(−1 because discriminant functions, calculated separately for 3 and 4, allow nearly 100% correct classification. These predictors allow identification of separate impairment of readiness to learn or ability to learn, or both.

Laser Guided Automated Calibrating System for Accurate Bracket ...

African Journals Online (AJOL)

Background: The basic premise of preadjusted bracket system is accurate bracket positioning. ... using MATLAB ver. 7 software (The MathWorks Inc.). These images are in the form of matrices of size 640 × 480. 650 nm (red light) type III diode laser is used as ... motion control and Pitch, Yaw, Roll degrees of freedom (DOF).

Robust representation and recognition of facial emotions using extreme sparse learning.

Science.gov (United States)

Shojaeilangari, Seyedehsamaneh; Yau, Wei-Yun; Nandakumar, Karthik; Li, Jun; Teoh, Eam Khwang

2015-07-01

Recognition of natural emotions from human faces is an interesting topic with a wide range of potential applications, such as human-computer interaction, automated tutoring systems, image and video retrieval, smart environments, and driver warning systems. Traditionally, facial emotion recognition systems have been evaluated on laboratory controlled data, which is not representative of the environment faced in real-world applications. To robustly recognize the facial emotions in real-world natural situations, this paper proposes an approach called extreme sparse learning, which has the ability to jointly learn a dictionary (set of basis) and a nonlinear classification model. The proposed approach combines the discriminative power of extreme learning machine with the reconstruction property of sparse representation to enable accurate classification when presented with noisy signals and imperfect data recorded in natural settings. In addition, this paper presents a new local spatio-temporal descriptor that is distinctive and pose-invariant. The proposed framework is able to achieve the state-of-the-art recognition accuracy on both acted and spontaneous facial emotion databases.

Examining ERP correlates of recognition memory: Evidence of accurate source recognition without recollection

Science.gov (United States)

Addante, Richard, J.; Ranganath, Charan; Yonelinas, Andrew, P.

2012-01-01

Recollection is typically associated with high recognition confidence and accurate source memory. However, subjects sometimes make accurate source memory judgments even for items that are not confidently recognized, and it is not known whether these responses are based on recollection or some other memory process. In the current study, we measured event related potentials (ERPs) while subjects made item and source memory confidence judgments in order to determine whether recollection supported accurate source recognition responses for items that were not confidently recognized. In line with previous studies, we found that recognition memory was associated with two ERP effects: an early on-setting FN400 effect, and a later parietal old-new effect [Late Positive Component (LPC)], which have been associated with familiarity and recollection, respectively. The FN400 increased gradually with item recognition confidence, whereas the LPC was only observed for highly confident recognition responses. The LPC was also related to source accuracy, but only for items that had received a high confidence item recognition response; accurate source judgments to items that were less confidently recognized did not exhibit the typical ERP correlate of recollection or familiarity, but rather showed a late, broadly distributed negative ERP difference. The results indicate that accurate source judgments of episodic context can occur even when recollection fails. PMID:22548808

Automated vehicle identification tags in San Antonio : lessons learned from the metropolitan model deployment initiative : unique method for collecting arterial travel speed information

Science.gov (United States)

2000-10-01

This report demonstrates a unique solution to the challenge of providing accurate, timely estimates of arterial travel times to the motoring public. In particular, it discusses the lessons learned in deploying the Vehicle Tag Project in San Antonio, ...

Indexed variation graphs for efficient and accurate resistome profiling.

Science.gov (United States)

Rowe, Will P M; Winn, Martyn D

2018-05-14

Antimicrobial resistance remains a major threat to global health. Profiling the collective antimicrobial resistance genes within a metagenome (the "resistome") facilitates greater understanding of antimicrobial resistance gene diversity and dynamics. In turn, this can allow for gene surveillance, individualised treatment of bacterial infections and more sustainable use of antimicrobials. However, resistome profiling can be complicated by high similarity between reference genes, as well as the sheer volume of sequencing data and the complexity of analysis workflows. We have developed an efficient and accurate method for resistome profiling that addresses these complications and improves upon currently available tools. Our method combines a variation graph representation of gene sets with an LSH Forest indexing scheme to allow for fast classification of metagenomic sequence reads using similarity-search queries. Subsequent hierarchical local alignment of classified reads against graph traversals enables accurate reconstruction of full-length gene sequences using a scoring scheme. We provide our implementation, GROOT, and show it to be both faster and more accurate than a current reference-dependent tool for resistome profiling. GROOT runs on a laptop and can process a typical 2 gigabyte metagenome in 2 minutes using a single CPU. Our method is not restricted to resistome profiling and has the potential to improve current metagenomic workflows. GROOT is written in Go and is available at https://github.com/will-rowe/groot (MIT license). will.rowe@stfc.ac.uk. Supplementary data are available at Bioinformatics online.

Funnel metadynamics as accurate binding free-energy method

Science.gov (United States)

Limongelli, Vittorio; Bonomi, Massimiliano; Parrinello, Michele

2013-01-01

A detailed description of the events ruling ligand/protein interaction and an accurate estimation of the drug affinity to its target is of great help in speeding drug discovery strategies. We have developed a metadynamics-based approach, named funnel metadynamics, that allows the ligand to enhance the sampling of the target binding sites and its solvated states. This method leads to an efficient characterization of the binding free-energy surface and an accurate calculation of the absolute protein–ligand binding free energy. We illustrate our protocol in two systems, benzamidine/trypsin and SC-558/cyclooxygenase 2. In both cases, the X-ray conformation has been found as the lowest free-energy pose, and the computed protein–ligand binding free energy in good agreement with experiments. Furthermore, funnel metadynamics unveils important information about the binding process, such as the presence of alternative binding modes and the role of waters. The results achieved at an affordable computational cost make funnel metadynamics a valuable method for drug discovery and for dealing with a variety of problems in chemistry, physics, and material science. PMID:23553839