检索结果-内蒙古大学图书馆

Protein sequence classification using feature hashing

PROTEOME SCIENCE 2012年第sup1期10卷 S14-S14页

作者： Caragea, Cornelia Silvescu, Adrian Mitra, Prasenjit Penn State Univ University Pk PA 16802 USA Naviance Inc Oakland CA USA

Recent advances in next-generation sequencing technologies have resulted in an exponential increase in the rate at which protein sequence data are being acquired. The k-gram feature representation, commonly used for protein sequence classification, usually results in prohibitively high dimensional input spaces, for large values of k. Applying data mining algorithms to these input spaces may be intractable due to the large number of dimensions. Hence, using dimensionality reduction techniques can be crucial for the performance and the complexity of the learning algorithms. In this paper, we study the applicability of feature hashing to protein sequence classification, where the original high-dimensional space is "reduced" by hashing the features into a low-dimensional space, using a hash function, i.e., by mapping features into hash keys, where multiple features can be mapped (at random) to the same hash key, and "aggregating" their counts. We compare feature hashing with the "bag of k-grams" approach. Our results show that feature hashing is an effective approach to reducing dimensionality on protein sequence classification tasks.

关键词： Hash Function support vector machine classifier Latent Dirichlet Allocation Average Mutual Information Latent Semantic Indexing

来源：评论

学校读者我要写书评

暂无评论

GO for gene documents

引用

BMC BIOINFORMATICS 2007年第s9期8卷 S3-S3页

作者： Srinivasan, Padmini Qiu, Xin Ying Univ Iowa Sch Lib & Informat Sci Iowa City IA 52242 USA Univ Iowa Dept Management Sci Iowa City IA 52242 USA

Background: Annotating genes and their products with Gene Ontology codes is an important area of research. One approach is to use the information available about these genes in the biomedical literature. The goal in this paper, based on this approach, is to develop automatic annotation methods that can supplement the expensive manual annotation processes currently in place. Results: Using a set of support vector machines (SVM) classifiers we were able to achieve Fscores of 0.49, 0.41 and 0.33 for codes of the molecular function, cellular component and biological process GO hierarchies respectively. We find that alternative term weighting strategies are not different from each other in performance and feature selection strategies reduce performance. The best thresholding strategy is one where a single threshold is picked for each hierarchy. Hierarchy level is important especially for molecular function and biological process. The cellular component hierarchy stands apart from the other two in many respects. This may be due to fundamental differences in link semantics. This research shows that it is possible to beneficially exploit the hierarchical structures by defining and testing a relaxed criteria for classification correctness. Finally it is possible to build classifiers for codes with very few associated documents but as expected a huge penalty is paid in performance. Conclusion: The GO annotation problem is complex. Several key observations have been made as for example about topic drift that may be important to consider in annotation strategies.

关键词： support vector machine Gene Ontology Feature Selection support vector machine classifier Annotation Problem

来源：评论

学校读者我要写书评

暂无评论

Facial Components Extraction and Expression Recognition in Static images 1

Facial Components Extraction and Expression Recognition in S...

引用

International Conference on Green Computing and Internet of Things (ICGCIoT)

作者： Pukhrambam, Mameeta Das, Arundhati Saha, Ashim NIT Agartala CSE Dept Agartala India

ISBN: (纸本)9781467379106

This paper deals with the emotion recognition in static images. Facial feature extraction plays a very important role in recognizing a particular emotion in humans. In this paper, the facial expressions in humans. i.e., happy, anger, sad, neutral and disgust, are recognized with the help support vector machine classifier. First, a static image is taken. Then, skin region is extracted from that image using Hue Saturation Value. After skin region extraction, the right eye, the left eye and the mouth part are extracted as they are the most important part for facial expression recognition. These processes are done for every images collected in the training set. Then, support vector machine classifier is used to classify which image belongs to which class category by comparing the feature vectors of the trained images. This paper produces a model which predicts a set of testing images into which class categories the image belongs to, namely anger, disgust, fear, happy and neutral.

关键词： Facial feature extraction support vector machine classifier Hue Saturation Value

来源：评论

学校读者我要写书评

暂无评论

Improving Speech Emotion Recognition System for a Social Robot with Speaker Recognition 19

Improving Speech Emotion Recognition System for a Social Rob...

引用

19th International Conference on Methods and Models in Automation and Robotics (MMAR)

作者： Juszkiewicz, Lukasz Wroclaw Univ Technol PL-50370 Wroclaw Poland

ISBN: (纸本)9781479950812

This paper presents modification of a speech emotion recognition system for a social robot. Using speaker dependent classifiers with prior speaker identification step was proposed. Emotion recognition is done using global acoustic features of the speech. Six speech signal parameters are computed with the specialised software. The feature extraction is based on calculation of global statistics of those parameters and their derivatives. Correlation based feature selection algorithms are used for reducing feature vector length. For the evaluation of the system three classifiers were used: Bayes Network, Radial Basis Function Network and support vector machine. Six emotions could be recognised by the system. Several experiments were carried out: emotion recognition of the speaker not known to the system, speaker independent recognition of the known speakers, gender dependent classification as well as speaker dependent recognition with prior identification. The results of identification-driven speech emotion recognition show significant improvement compared to the performance of the speaker independent system based on previous research. The use of the tailored speaker dependent recognition system led to increase in the Bayes Network classification accuracy from 74% to 96%, in the support vector machine classification accuracy from 64% to 96% and in the Radial Basis Function Network classification accuracy from 67% to 88%.

关键词： belief networks emotion recognition feature extraction radial basis function networks robots signal classification speaker recognition speech recognition support vector machines Bayes network classifier correlation based feature selection algorithms global acoustic features radial basis function network classifier social robot speaker dependent classifiers speaker identification speech emotion recognition system speech signal parameters support vector machine classifier Accuracy Emotion recognition Feature extraction Robots Speech Speech recognition support vector machines emotion recognition speaker recognition Feature extraction support vector Network Radial basis function networks Robot Speech recognition Bayesian networks Speech speech recognition system signal classification

来源：评论

学校读者我要写书评

暂无评论

Classification of micro-CT images using 3D characterization of bone canal patters in human osteogenesis imperfecta

Classification of micro-CT images using 3D characterization ...

引用

Conference on Medical Imaging - Computer-Aided Diagnosis

作者： Abidin, Anas Z. Jameson, John Molthen, Robert Wismueller, Axel Univ Rochester Dept Biomed Engn Rochester NY 14627 USA Univ Rochester Dept Imaging Sci Rochester NY 14627 USA Ludwig Maximilians Univ Munchen Fac Med Munich Germany Ludwig Maximilians Univ Munchen Inst Clin Radiol Munich Germany Marquette Univ Dept Biomed Engn Milwaukee WI 53233 USA Marquette Univ OREC Milwaukee WI 53233 USA

ISBN: (纸本)9781510607132;9781510607149

Few studies have analyzed the microstructural properties of bone in cases of Osteogenenis Imperfecta (OI), or 'brittle bone disease'. Current approaches mainly focus on bone mineral density measurements as an indirect indicator of bone strength and quality. It has been shown that bone strength would depend not only on composition but also structural organization. This study aims to characterize 3D structure of the cortical bone in high- resolution micro CT images. A total of 40 bone fragments from 28 subjects (13 with OI and 15 healthy controls) were imaged using micro tomography using a synchrotron light source (SR mu CT). Minkowski functionals - volume, surface, curvature, and Euler characteristics - describing the topological organization of the bone were computed from the images. The features were used in a machine learning task to classify between healthy and OI bone. The best classification performance (mean AUC - 0.96) was achieved with a combined 4-dimensional feature of all Minkowski functionals. Individually, the best feature performance was seen using curvature (mean AUC - 0.85), which characterizes the edges within a binary object. These results show that quantitative analysis of cortical bone microstructure, in a computer-aided diagnostics framework, can be used to distinguish between healthy and OI bone with high accuracy.

关键词： Minkowski functionals texture analysis support vector machine classifier bone osteogenesis imperfecta

来源：评论

学校读者我要写书评

暂无评论

Hybrid EEG-EOG System for Intelligent Prosthesis Control based on Common Spatial Pattern Algorithmd

Hybrid EEG-EOG System for Intelligent Prosthesis Control bas...

引用

IEEE International Conference on Information and Automation (ICIA)

作者： Yang, Junyou Su, Xiaoying Bai, Dianchun Jiang, Yinlai Yokoi, Hiroshi Shenyang Univ Technol Dept Elect Engn Shenyang Liaoning Provin Peoples R China Univ Electrocommun Dept Intelligent Robot Chofu Tokyo Japan

ISBN: (纸本)9781509041022

A newly brain computer interaction (BCI) system which combined electrooculography (EOG) with electroencephalography (EEG) was designed and realized to make prosthesis control with multicontrol commands come true. Based on two different imaginary tasks, time-frequency spectrum and brain topographic mapping were used to analyze and validate event related synchronization/desychronization (ERS/ERD). Obviously frequency band of EEG is chosen based on common spatial pattern (CSP) algorithm, and then support vector machine (SVM) were implemented to classify data's characteristics. In order to improve the performance of BCI system, the EOG signals caused by eye movements and EEG signals of ERS/ERD were simultaneously provided as the input of hybrid BCI system. In the lab environment, the proposed system was tested on a multi-functional robotic prosthesis. The robot is light in weight and low in power consumption. Taking advantage of both EOG and EEG, recognition accuracy of entire system reaches 91.1%. The experiments results show that feature information of EEG signal which is evoked by motor imagery have obvious spatial specificity. This hybrid system can recognize different motions of the upper limb, whereas the task can be executed effectively and operator controls the prosthesis easily as their own arm.

关键词： EOG signal EEG signal prosthesis common spatial pattern support vector machine classifier

来源：评论

学校读者我要写书评

暂无评论

Identification of winter land use in temperate agricultural landscapes based on Sentinel-1 and 2 times-series. 38

Identification of winter land use in temperate agricultural ...

引用

38th IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Denize, Julien Hubert-Moy, Laurence Corgne, Samuel Betbeder, Julie Pottier, Eric Univ Rennes Rennes France IETR UMR 6164 Rennes France LETG UMR 6554 Rennes France Cirad UPR 105 Forests & Soc Montpellier France

ISBN: (纸本)9781538671504

Land cover and land use monitoring, particularly during winter season, is still a major environmental and scientific issue in agricultural areas. From an environmental point of view, the presence and type of vegetation cover in winter have an impact on pollutant transport to water bodies. From a methodological point of view, characterizing spatio-temporal dynamics of winter land cover and land use at a field scale remains a challenge due to the diversity of farming strategies and practices. The objective of this study was to evaluate the potential of optical and SAR time-series to improve the monitoring of winter land use in an area of 130 km(2). For that purpose, Sentinel-1 and 2 time-series were classified using SVM and RF algorithms. Winter land use was identified with an overall accuracy of 81% and a kappa index of 0.77 from a combination of Sentinel-1 and 2 images.

关键词： Agricultural monitoring Multi-temporal classifications support vector machine classifier Random Forest classifier Earth observing sensors optical and SAR time series

来源：评论

学校读者我要写书评

暂无评论

Night-time pedestrian classification with histograms of oriented gradients-local binary patterns vectors

Night-time pedestrian classification with histograms of orie...

引用

20th ITS World Congress

作者： Hurney, Patrick Waldron, Peter Morgan, Fearghal Jones, Edward Glavin, Martin Natl Univ Ireland Galway Sch Elect & Elect Engn Coll Engn & Informat Connaught Automot Res Grp Galway City Ireland Intel Shannon Shannon Clare Ireland Natl Univ Ireland Galway Sch Elect & Elect Engn Coll Engn & Informat Galway City Ireland

The use of night vision systems in vehicles is becoming increasingly common, not just in luxury cars but also in the more cost sensitive sectors. Numerous approaches using infrared sensors have been proposed in the literature to detect and classify pedestrians in low visibility situations. However, the performance of these systems is limited by the capability of the classifier. This paper presents a novel method of classifying pedestrians in far-infrared automotive imagery. Regions of interest are segmented from the infrared frame using seeded region growing. A novel method of filtering the region growing results based on the location and size of the bounding box within the frame is described. This results in a smaller number of regions of interest for classification, leading to a reduced false positive rate. Histograms of oriented gradient features and local binary pattern features are extracted from the regions of interest and concatenated to form a feature for classification. Pedestrians are tracked with a Kalman filter to increase detection rates and system robustness. Detection rates of 98%, and false positive rates of 1% have been achieved on a database of 2000 images and streams of video;this is a 3% improvement on previously reported detection rates.

关键词： pedestrians traffic engineering computing feature extraction image classification infrared detectors automobiles support vector machines image segmentation filtering theory night-time pedestrian classification histogram of oriented gradient-local binary pattern vectors night vision systems high end luxury cars low-cost infrared sensors far infrared automotive image streams support vector machine classifier region of interest RoF captured infrared frame seeded region growing filtering method bounding box ROI reduced false positive rate local binary pattern feature extraction histogram of oriented gradient feature extraction Kalman filter detection rates

来源：评论

学校读者我要写书评

暂无评论

IMAGE RECOGNITION BY LEARNED LINEAR SUBSPACE OF COMBINED BAG-OF-FEATURES AND LOW-LEVEL FEATURES

IMAGE RECOGNITION BY LEARNED LINEAR SUBSPACE OF COMBINED BAG...

引用

IEEE International Conference on Image Processing

作者： Han, Xian-Hua Chen, Yen-Wei Ruan, Xiang Ritsumeikan Univ Coll Informat Sci & Engn Kusatsu 5258577 Japan Omron Corp Kyoto Japan

ISBN: (纸本)9781424479948

Image category recognition is important to access visual information on the level of objects and scene types. This paper combines different feature representations of images and learn a compact subspace of different features for the automatic recognition of object and scene classes. Compact visual-words and low-level-features object class subspaces are automatically learned from a set of training images by a Regularized Linear Discriminant analysis (RLDA) algorithm, and the extracted RLDA-domain features are used for support vector machine (SVM) classifier. The main contribution of this paper is two folds: i) Different features (bag-of-features and low-level features) is fused for image representation. ii) The compact feature subspaces (low-dimension features) of different features are learned for rendering to SVM classifier, which is computationally efficient for image category. High classification accuracy is demonstrated on object recognition database (Caltech). We confirm that the proposed strategy cam improve accuracy rate compared with state-of-the-art methods for object recognition databases.

关键词： automatic recognition combined bag-of-features feature extraction image recognition image recognition image representation image representation learned linear subspace low-level features object recognition object recognition databases regularized linear discriminant analysis rendering support vector machine classifier support vector machines training images

来源：评论

学校读者我要写书评

暂无评论

Performance Study of Cyclostationary based Digital Modulation Classification Schemes 9

Performance Study of Cyclostationary based Digital Modulatio...

引用

9th Int Conf Ind Information Syst (ICIIS2014)

作者： Satija, Udit Manikandan, M. S. Ramkumar, Barathram Indian Inst Technol Sch Elect Sci Bhubaneswar Orissa India

ISBN: (纸本)9781479964994

Automatic Modulation Classification (AMC) is a essential component in Cognitive Radio (CR) for recognizing the modulation scheme. Many modulated signals manifest the property of cyclostationarity as a feature so it can be exploited for classification. In this paper, we study the performance of digital modulation classification technique based on the cyclostationary features and different classifiers such as Neural Network, support vector machine, k-Nearest Neighbor, Naive Bayes, Linear Discriminant Analysis and Neuro-Fuzzy classifier. In this study we considered modulations i.e. BPSK, QPSK, FSK and MSK for classification. All classification methods studied using performance matrix including classification accuracy and computational complexity (time). The robustness of these methods are studied with SNR ranging from 0 to 20dB. Based upon the result we found that combining cyclostationary features with Naive Bayes and Linear Discriminant Analysis classifiers leads to provide better classification accuracy with less computational complexity.

关键词： Bayes methods cognitive radio frequency shift keying fuzzy systems neural nets pattern classification phase shift keying signal classification support vector machines telecommunication computing BPSK FSK MSK QPSK automatic modulation classification classification accuracy computational complexity cyclostationary based digital modulation classification cyclostationary feature digital modulation classification technique k-nearest neighbor classifier linear discriminant analysis classifier modulated signal naive Bayes classifier neural network classifier neuro-fuzzy classifier performance matrix support vector machine classifier Binary phase shift keying Computational complexity Frequency shift keying Neural networks support vector machines frequency shift keying Binary phase shift keying support vector Network complexity classes Cognitive radio Neural network minimum shift keying modulated signal Quadrature phase shift keying telecommunication computing Phase shift keying signal classification Bayes methods Pattern recognition Fuzzy systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：