检索结果-内蒙古大学图书馆

K-local hyperplane distance nearest neighbor classifier oriented local discriminant analysis

INFORMATION SCIENCES 2013年 232卷 11-26页

作者： Xu, Jie Yang, Jian Lai, Zhihui Nanjing Univ Sci & Technol Sch Comp Sci & Technol Nanjing 210094 Jiangsu Peoples R China Shaoguan Univ Sch Math & Informat Sci Shaoguan 512000 Guangdong Peoples R China Harbin Inst Technol Shenzhen Grad Sch Biocomp Res Ctr Shenzhen 518055 Peoples R China

K-local hyperplane distance nearest neighbor (HKNN) classifier is an improved K-nearest neighbor (KNN) algorithm that has been successfully applied to pattern classification. This paper embeds the decision rule of HKNN classifier into the discriminant analysis model to develop a new feature extractor. The obtained feature extractor is called K-local hyperplane distance nearest neighbor classifier oriented local discriminant analysis (HOLDA), in which a regularization item is imposed on the original HKNN algorithm to obtain a more reliable distance metric. Based on this distance metric, the homo-class and hetero-class local scatters are characterized in HOLDA. By maximizing the ratio of the hetero-class local scatter to the homo-class local scatter, we obtain a subspace which is suitable for feature extraction and classification. In general, this paper provides a framework for building a feature extractor from the decision rule of a classifier. By this means, the feature extractor and classifier can be seamlessly integrated. Experimental results on four databases demonstrate that the integrated pattern recognition system is effective. (C) 2013 Elsevier Inc. All rights reserved.

关键词： Regularization HKNN classifier Discriminant analysis pattern recognition system

来源：评论

学校读者我要写书评

暂无评论

Sensory motor imagery EEG classification based on non-dyadic wavelets using dynamic weighted majority ensemble classification

引用

INTELLIGENT DECISION TECHNOLOGIES-NETHERLANDS 2021年第1期15卷 33-43页

作者： Chaudhary, Poonam Agrawal, Rashmi Manav Rachna Int Inst Res & Studies Faridabad India

The classification accuracy has become a significant challenge and an important task in sensory motor imagery (SMI) electroencephalogram (EEG) based Brain Computer interface (BCI) system. This paper compares ensemble classification framework with individual classifiers. The main objective is to reduce the inference of non-stationary and transient information and improves the classification decision in BCI system. The framework comprises the three phases as follows: (1) the EEG signal first decomposes into triadic frequency bands: low pass band, band pass filter and high pass filter to localize alpha, beta and high gamma frequency bands within the EEG signals, (2) Then, Common spatial pattern (CSP) algorithm has been applied on the extracted frequencies in phase Ito heave out the important features of EEG signal, (3) Further, an existing Dynamic Weighted Majiority (DWM) ensemble classification algorithm has been implemented using features extracted in phase II, for final class label decision. J48, Naive Bayes, Support Vector Machine, and K-Nearest Neighbor classifiers used as base classifiers for making a diverse ensemble of classifiers. A comparative study between individual classifiers and ensemble framework has been included in the paper. Experimental evaluation and assessment of the performance of the proposed model is done on the publically available datasets: BCI Competition IV dataset Ha and BCI Competition III dataset IVa. The ensemble based learning method gave the highest accuracy among all. The average sensitivity, specificity, and accuracy of 85.4%, 86.5%, and 85.6% were achieved with a kappa value of 0.59 using DWM classification.

关键词： Sensory motor imagery (SMI) electroencephalogram (EEG) pattern recognition system triadic frequency bands dynamic weighted majiority (DWM) J48 naive Bayes support vector machine k-nearest neighbor classifiers

来源：评论

学校读者我要写书评

暂无评论

PostDOCK: A structural, empirical approach to scoring protein ligand complexes

引用

JOURNAL OF MEDICINAL CHEMISTRY 2005年第22期48卷 6821-6831页

作者： Springer, C Adalsteinsson, H Young, MM Kegelmeyer, PW Roe, DC Sandia Natl Labs Livermore CA 94551 USA

In this work we introduce a postprocessing filter (PostDOCK) that distinguishes true binding ligand-protein complexes from docking artifacts (that are created by DOCK 4.0.1). PostDOCK is a pattern recognition system that relies on (1) a database of complexes, (2) biochemical descriptors of those complexes, and (3) machine learning tools. We use the protein databank (PDB) as the structural database of complexes and create diverse training and validation sets from it based on the "families of structurally similar proteins" (FSSP) hierarchy. For the biochemical descriptors, we consider terms from the DOCK score, empirical scoring, and buried solvent accessible surface area. For the machine-learners, we use a random forest classifier and logistic regression. Our results were obtained on a test set of 44 structurally diverse protein targets. Our highest performing descriptor combinations obtained similar to 19-fold enrichment (39 of 44 binding complexes were correctly identified, while only allowing 2 of 44 decoy complexes), and our best overall accuracy was 92%.

关键词： complexes accessible surface pattern recognition system Descriptors Database

来源：评论

学校读者我要写书评

暂无评论

Dimensionality Reduction for Data Visualization

引用

IEEE SIGNAL PROCESSING MAGAZINE 2011年第2期28卷 100-104页

作者： Kaski, Samuel Peltonen, Jaakko Aalto Univ Dept Informat & Comp Sci Alto Finland

Dimensionality reduction is one of the basic operations in the toolbox of data analysts and designers of machine learning and pattern recognition systems. Given a large set of measured variables but few observations, an obvious idea is to reduce the degrees of freedom in the measurements by representing them with a smaller set of more “condensed” variables. Another reason for reducing the dimensionality is to reduce computational load in further processing. A third reason is visualization.

关键词： tool cases psychoanalyst Visualization Basic Operations dimensionality reduction Machine Learning pattern recognition system Degree of freedom Designers

来源：评论

学校读者我要写书评

暂无评论

Electronic noses - A mini-review

引用

FRESENIUS JOURNAL OF ANALYTICAL CHEMISTRY 1999年第6期364卷 499-505页

作者： Strike, DJ Meijerink, MGH Koudelka-Hep, M Univ Neuchatel Inst Microtechnol CH-2007 Neuchatel Switzerland

Electronic noses are a new class of analytical instruments anticipated to have an impact in many areas. They are based around an array of sensors each having a partial specificity and thus producing an odour fingerprint that can be identified by a pattern recognition system. In this review the technologies involved are discussed, giving particular emphasis to the sensors since these form the heart of the systems. The major sensor technologies are described, indicating both their strengths and their weaknesses. Finally, after a brief discussion of data processing technologies, the review ends with an assessment of the current state of the art and possible future directions.

关键词： Fingerprints arrays New classes Assaying equipment Heart Sensors state of the art Smell Odor Technology Arts sensor technology pattern recognition system Electronic Nose current status

来源：评论

学校读者我要写书评

暂无评论

Spilt bundle detection in polarimetric images of the human retinal nerve fiber layer

引用

METHODS OF INFORMATION IN MEDICINE 2007年第4期46卷 425-431页

作者： Vermeer, K. A. Reus, N. J. Vos, F. M. Lemiil, H. G. Vossepoel, A. M. Rotterdam Eye Hosp Rotterdam Netherlands Delft Univ Technol Quantitat Imaging Grp Delft Netherlands Univ Amsterdam Acad Med Ctr Dept Radiol NL-1105 AZ Amsterdam Netherlands Univ Med Ctr Rotterdam Erasmus MC Biomed Imaging Grp Rotterdam Rotterdam Netherlands

Objectives: One method for assessing pathological retinal nerve fiber layer (NFL) appearance is by comparing the NFL to normative values, derived from healthy subjects. These normative values will be more specific when normal physiological differences are taken into account. One common variation is a split bundle. This paper describes a method to automatically detect these split bundles. Methods. The thickness profile along the NFL bundle is described by a non-split and a split bundle model. Based on these two fits, statistics are derived and used as features for two non-parametric classifiers (Parzen density based and k nearest neighbor). Features were selected by forward feature selection. Three hundred and nine superior and 324 inferior bundles were used to train and test this method. Results: The prevalence of split superior bundles was 68% and the split inferior bundles' prevalence was 13%. The resulting estimated error of the Parzen density-based classifier was 12.5% for the superior bundle and 10.2% for the inferior bundle. The k nearest neighbor classifier errors were 11.7% and 9.2%. Conclusions. The classification error of automated detection of split inferior bundles is not much smaller than its prevalence, thereby limiting the usefulness of separate cut-off values for split and non-split inferior bundles. For superior bundles, however, the classification error was low compared to the prevalence. Application of specific cut-off values, selected by the proposed classification system, may therefore increase the specificity and sensitivity of pathological NFL detection.

关键词： pattern recognition system computer-assisted diagnosis glaucoma retina morphology

来源：评论

学校读者我要写书评

暂无评论

NOD-LIKE RECEPTORS: VERSATILE CYTOSOLIC SENTINELS

引用

PHYSIOLOGICAL REVIEWS 2015年第1期95卷 149-178页

作者： Motta, Vinicius Soares, Fraser Sun, Tian Philpott, Dana J. Univ Toronto Dept Immunol Toronto ON M5S 1A8 Canada Univ Toronto Dept Lab Med & Pathobiol Toronto ON M5S 1A8 Canada

Nucleotide binding oligomerization domain (NOD)-like receptors are cytoplasmic pattern-recognition receptors that together with RIG-I-like receptor (retinoic acid-inducible gene 1), Toll-like receptor (TLR), and C-type lectin families make up the innate pathogen pattern recognition system. There are 22 members of NLRs in humans, 34 in mice, and even a larger number in some invertebrates like sea urchins, which contain more than 200 receptors. Although initially described to respond to intracellular pathogens, NLRs have been shown to play important roles in distinct biological processes ranging from regulation of antigen presentation, sensing metabolic changes in the cell, modulation of inflammation, embryo development, cell death, and differentiation of the adaptive immune response. The diversity among NLR receptors is derived from ligand specificity conferred by the leucine-rich repeats and an NH2-terminal effector domain that triggers the activation of different biological pathways. Here, we describe NLR genes associated with different biological processes and the molecular mechanisms underlying their function. Furthermore, we discuss mutations in NLR genes that have been associated with human diseases.

关键词： Antigen Presentation Biological Process pattern recognition system C-Type Lectins Sea Urchins Receptor noise load ratio

来源：评论

学校读者我要写书评

暂无评论

Computational frameworks for context-aware hybrid sensor fusion

引用

INTERNATIONAL JOURNAL OF IMAGE AND DATA FUSION 2016年第1期7卷 83-102页

作者： Biswas, Pratik K. Moon, Sangwoo Qi, Hairong Dey, Anind K. Ep Sci Spring Lake Hts NJ 07762 USA Univ Tennessee Dept Elect Engn & Comp Sci Knoxville TN 37996 USA Carnegie Mellon Univ Human Comp Interact Inst Pittsburgh PA 15213 USA

This paper proposes inexpensive, specialised, computational frameworks that automate and integrate context-aware sensing, data aggregation, information extraction and understanding and qualitative decision making through intelligent algorithms. Its contributions are spread across context-aware data collection and aggregation, hybrid feature extraction incorporating both supervised and unsupervised approaches, and decision-based information fusion. It provides a toolkit that makes it easier for applications to use context. It presents a hybrid feature extraction framework based on two diverse optimisation problems in aspects of risk and independence to extract features resulting in higher classification performance. It combines a context-aware multi-sensor data collection model and a "Feature Input Feature Output (FeI-FeO)" based fusion model with an intelligent classifier to create a "Feature Input Decision Output (FeI-DeO)" based pattern recognition system, which can classify targets by eliminating redundant contexts. The proposed frameworks achieve context-sensitive information fusion with higher accuracy, less energy consumption and greater fault tolerance in resource-constrained environments with data collected from distributed sensors.

关键词： context context-aware applications context toolkit feature extraction risk minimisation projection independence maximisation classifier pattern recognition system

来源：评论

学校读者我要写书评

暂无评论

A Collaborative Tool for Modelling Multi-stage Attacks 3

A Collaborative Tool for Modelling Multi-stage Attacks

引用

3rd International Conference on Information systems Security and Privacy (ICISSP)

作者： Herwono, Ian El-Moussa, Fadi Ali BT Secur Futures Practice Res & Innovat Ipswich IP5 3RE Suffolk England

ISBN: (纸本)9789897582097

Cyber-attacks that are conducted in multiple stages over short or long periods of time are becoming more common. One approach for detecting such attacks at an early stage is to make use of attack patterns and attack signatures to provide a structure for correlating events collected from various sensors in the network. In this paper, we present our ongoing work on a pattern recognition system that aims to support cyber-defence analysts in sharing their attack knowledge and threat intelligence in the form of attack patterns or scenarios that can later be used to discover potential security breaches in their network. Our main goal is to allow the analysts to associate the attack patterns with their own organisation's security data and thus benefit from the collective attack knowledge without revealing any confidential information. We present the architecture of the system and describe a typical process for modelling multi-stage attacks. We demonstrate how its analytics engine interprets an attack pattern, tasks the data source agents to fetch and correlate relevant security events, and reports the results back for visualisation and further investigation.

关键词： Cyber Security Attack patterns pattern recognition system Knowledge Sharing

来源：评论

学校读者我要写书评

暂无评论

Swarm-wavelet based Extreme Learning Machine for Finger Movement Classification on Transradial Amputees 36

Swarm-wavelet based Extreme Learning Machine for Finger Move...

引用

36th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC)

作者： Anam, Khairul Al-Jumaily, Adel Univ Jember Indonesia Jember Jawa Timur Indonesia Univ Technol Sydney Sch Elect Mech & Mechatron Syst Sydney NSW 2007 Australia

ISBN: (纸本)9781424479290

The use of a small number of surface electromyography (EMG) channels on the transradial amputee in a myoelectric controller is a big challenge. This paper proposes a pattern recognition system using an extreme learning machine (ELM) optimized by particle swarm optimization (PSO). PSO is mutated by wavelet function to avoid trapped in a local minima. The proposed system is used to classify eleven imagined finger motions on five amputees by using only two EMG channels. The optimal performance of wavelet-PSO was compared to a grid-search method and standard PSO. The experimental results show that the proposed system is the most accurate classifier among other tested classifiers. It could classify 11 finger motions with the average accuracy of about 94 % across five amputees.

关键词： Accuracy Electromyography Equations Feature extraction Kernel Thumb Electromyogram Thumb Learning machines Feature extraction Amputees pattern recognition system Kernel Fingers parametric subharmonic oscillator optimum performance

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：