检索结果-内蒙古大学图书馆

learning vector quantization as an interpretable classifier for the detection of SARS-CoV-2 types based on their RNA sequences

引用

NEURAL COMPUTING & APPLICATIONS 2022年第1期34卷 67-78页

作者： Kaden, Marika Bohnsack, Katrin Sophie Weber, Mirko Kudla, Mateusz Gutowska, Kaja Blazewicz, Jacek Villmann, Thomas Univ Appl Sci Mittweida Technikumpl 17 D-09648 Mittweida Germany Saxon Inst Computat Intelligence & Machine Learni Technikumpl 17 D-09648 Mittweida Germany Poznan Univ Tech Inst Comp Sci Piotrowo 2 PL-60965 Poznan Poland Polish Acad Sci Inst Bioorgan Chem Noskowskiego 12-14 PL-61704 Poznan Poland European Ctr Bioinformat & Genom Piotrowo 2 PL-60965 Poznan Poland

We present an approach to discriminate SARS-CoV-2 virus types based on their RNA sequence descriptions avoiding a sequence alignment. For that purpose, sequences are preprocessed by feature extraction and the resulting feature vectors are analyzed by prototype-based classification to remain interpretable. In particular, we propose to use variants of learning vector quantization (LVQ) based on dissimilarity measures for RNA sequence data. The respective matrix LVQ provides additional knowledge about the classification decisions like discriminant feature correlations and, additionally, can be equipped with easy to realize reject options for uncertain data. Those options provide self-controlled evidence, i.e., the model refuses to make a classification decision if the model evidence for the presented data is not sufficient. This model is first trained using a GISAID dataset with given virus types detected according to the molecular differences in coronavirus populations by phylogenetic tree clustering. In a second step, we apply the trained model to another but unlabeled SARS-CoV-2 virus dataset. For these data, we can either assign a virus type to the sequences or reject atypical samples. Those rejected sequences allow to speculate about new virus types with respect to nucleotide base mutations in the viral sequences. Moreover, this rejection analysis improves model robustness. Last but not least, the presented approach has lower computational complexity compared to methods based on (multiple) sequence alignment.

关键词： learning vector quantization Interpretable models Genomic sequence analysis Reject options

来源：评论

学校读者我要写书评

暂无评论

learning vector quantization neural network for surface water extraction from Landsat OLI images

引用

JOURNAL OF APPLIED REMOTE SENSING 2020年第3期14卷

作者： Somasundaram, Deepakrishna Zhang, Fangfang Wang, Shenglei Ye, Huping Zhang, Zongke Zhang, Bing Chinese Acad Sci Inst Remote Sensing & Digital Earth Key Lab Digital Earth Sci Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Peking Univ Inst Remote Sensing & Geog Informat Syst Beijing Peoples R China Chinese Acad Sci Inst Geog Sci & Nat Resources Res State Key Lab Resources & Environm Informat Syst Beijing Peoples R China Chinese Acad Sci China Sri Lanka Joint Res & Demonstrat Ctr Water Beijing Peoples R China Chinese Acad Sci China Sri Lanka Joint Ctr Educ & Res Guangzhou Peoples R China

There is a growing concern over surface water dynamics due to an increased understanding of water availability and management with current climate trends. Remote sensing has now become an effective means of water extraction due to the availability of an enormous amount of data with diverse spatial, spectral, and temporal resolutions. However, water extraction from optical remote sensing data is associated with several major difficulties, such as the applicability of the extraction method over large areas and complex environments;shadow contamination from clouds, buildings, and mountains;and disclosure of shadowed water and exclusion of floating and submerged plants. To address these difficulties, a learning vector quantization (LVQ) neural network-based method was proposed and implemented to extract water using Landsat 8 imageries. This method is capable of separating water from clouds, build-up areas, shadows, and shadowed water by the ideal input of bands 1 to 7 and normalized difference vegetation index. This model learns water across Sri Lanka. Eight OLI scenes were tested, and the performance was compared with five widely used machine learning algorithms: support vector machine, K-nearest neighbor, discriminant analysis, combination of modified normalized difference water index and modified fuzzy clustering method, and K-means clustering methods. This method performed the best, achieving overall accuracies and the kappa coefficients between 97.8% and 99.7% and between 0.96 and 0.99, respectively. Results have demonstrated robustness, consistency, and preciseness in various dark surfaces, noisiest water environments, and highly water scarce scenes. LVQ revealed a good generalizing ability to detect all types of water with less amount of training samples. This method can be easily adaptable for other sensors and global water to support water resource studies. (C) The Authors.

关键词： water extraction water body mapping learning vector quantization neural network machine learning Landsat 8

来源：评论

学校读者我要写书评

暂无评论

learning vector quantization and relevances in complex coefficient space

引用

NEURAL COMPUTING & APPLICATIONS 2020年第24期32卷 18085-18099页

作者： Straat, M. Kaden, M. Gay, M. Villmann, T. Lampe, A. Seiffert, U. Biehl, M. Melchert, F. Univ Groningen POB 407 NL-9700 AK Groningen Netherlands Univ Appl Sci Mittweida Computat Intelligence Grp Tech Pl 17 D-09648 Mittweida Germany Fraunhofer Inst Factory Operat & Automat Sandtorstr 22 D-39106 Magdeburg Germany Fraunhofer Inst Transportat & Infrastruct Syst IV Zeunerstr 38 D-01069 Dresden Germany

In this contribution, we consider the classification of time series and similar functional data which can be represented in complex Fourier and wavelet coefficient space. We apply versions of learning vector quantization (LVQ) which are suitable for complex-valued data, based on the so-called Wirtinger calculus. It allows for the formulation of gradient-based update rules in the framework of cost-function-based generalized matrix relevance LVQ (GMLVQ). Alternatively, we consider the concatenation of real and imaginary parts of Fourier coefficients in a real-valued feature vector and the classification of time-domain representations by means of conventional GMLVQ. In addition, we consider the application of the method in combination with wavelet-space features to heartbeat classification.

关键词： Classification Supervised learning Functional data learning vector quantization Relevance learning Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

learning vector quantization: The dynamics of winner-takes-all algorithms

引用

NEUROCOMPUTING 2006年第7-9期69卷 660-670页

作者： Biehl, M Ghosh, A Hammer, B Univ Groningen NL-9700 AV Groningen Netherlands Tech Univ Clausthal Inst Comp Sci D-98678 Clausthal Zellerfeld Germany

Winner-Takes-All (WTA) prescriptions for learning vector quantization (LVQ) are studied in the framework of a model situation: two competing prototype vectors are updated according to a sequence of example data drawn from a mixture of Gaussialls. The theory of on-line learning allows for an exact mathernatical description of the training dynamics, even if an underlying cost function cannot be identified. We compare the typical behavior of several WTA schemes including basic LVQ and unsupervised vector quantization. The focus is on the learning curves, i.e. the achievable generalization ability as a function of the number of training examples. (c) 2005 Elsevier B.V. All rights reserved.

关键词： learning vector quantization prototype-based classification winner-takes-all algorithms on-line learning competitive learning

来源：评论

学校读者我要写书评

暂无评论

learning vector quantization for variable ordering in constraint satisfaction problems

引用

PATTERN RECOGNITION LETTERS 2013年第4期34卷 423-432页

作者： Carlos Ortiz-Bayliss, Jose Terashima-Marin, Hugo Enrique Conant-Pablos, Santiago Tecnol Monterrey Monterrey 64849 Mexico

A constraint satisfaction problem (CSP) is a generic problem with many applications in different areas of artificial intelligence and operational research. During the search for a solution, the order in which the variables are selected to be instantiated has a tremendous impact in the complexity of the search. Many heuristics exist for ordering these variables, but they are specialized for some types of instances. Hyper-heuristics are methodologies used to choose from a set of heuristics and decide which one to apply given some properties of the instance at hand. In this research, we propose a new type of hyper-heuristic based on a learning vector quantization (LVQ) neural network for variable ordering within CSP. The first part of the investigation describes a methodology to generate LVQ neural networks that are able to map some properties of the instances to one suitable variable ordering heuristic. Later, the networks are created according to such methodology and tested on random and real instances proving that they are a feasible method to improve the performance of search on CSP when compared to single heuristics applied in isolation. (C) 2012 Elsevier B.V. All rights reserved.

关键词： Constraint satisfaction Hyper-heuristics learning vector quantization Variable and value ordering

来源：评论

学校读者我要写书评

暂无评论

learning vector quantization with training count (LVQTC)

引用

NEURAL NETWORKS 1997年第6期10卷 1083-1088页

作者： Odorico, R UNIV BOLOGNA IST NAZL FIS NUCLI-40126 BOLOGNAITALY

Kohonen's learning vector quantization (LVQ) is modified by attributing training counters to each neuron, which record its training statistics. During training, this allows for dynamic self-allocation of the neurons to classes. In the classification stage training counters provide an estimate of the reliability of classification of the single neurons, which can be exploited to obtain a substantially higher purity of classification. The method turns out to be especially valuable in the presence of considerable overlaps among class distributions in the pattern space. The results of a typical application to high energy elementary particle physics are discussed in detail. (C) 1997 Elsevier Science Ltd.

关键词： learning vector quantization neural network architecture training classification high energy physics elementary particle physics

来源：评论

学校读者我要写书评

暂无评论

learning vector quantization for (dis-)similarities

引用

NEUROCOMPUTING 2014年 131卷 43-51页

作者： Hammer, Barbara Hofmann, Daniela Schleif, Frank-Michael Zhu, Xibin Univ Bielefeld CITEC Ctr Excellence Bielefeld Germany

Prototype-based methods often display very intuitive classification and learning rules. However, popular prototype based classifiers such as learning vector quantization (LVQ) are restricted to vectorial data only. In this contribution, we discuss techniques how to extend LVQ algorithms to more general data characterized by pairwise similarities or dissimilarities only. We propose a general framework how the methods can be combined based on the background of a pseudo-Euclidean embedding of the data. This covers the existing approaches kernel generalized relevance LVQ and relational generalized relevance LVQ and it opens the way towards two novel approach, kernel robust soft LVQ and relational robust soft LVQ. Interestingly, also unsupervised prototype based techniques which are based on a cost function can be put into this framework including kernel and relational neural gas and kernel and relational self-organizing maps (based on Heskes' cost function). We demonstrate the performance of the LVQ techniques for similarity or dissimilarity data in several benchmarks, reaching state of the art results. (C) 2013 Elsevier B.V. All rights reserved.

关键词： learning vector quantization Pseudo-Euclidean space Dissimilarity data

来源：评论

学校读者我要写书评

暂无评论

learning vector quantization classifiers for ROC-optimization

引用

COMPUTATIONAL STATISTICS 2018年第3期33卷 1173-1194页

作者： Villmann, T. Kaden, M. Hermann, W. Biehl, M. Univ Appl Sci Mittweida Computat Intelligence Grp Mittweida Germany Paracelsus Klinikum Zwickau Abt Neurol Zwickau Germany Univ Groningen Johann Bernoulli Inst Math & Comp Sci Groningen Netherlands

This paper proposes a variant of the generalized learning vector quantizer (GLVQ) optimizing explicitly the area under the receiver operating characteristics (ROC) curve for binary classification problems instead of the classification accuracy, which is frequently not appropriate for classifier evaluation. This is particularly important in case of overlapping class distributions, when the user has to decide about the trade-off between high true-positive and good false-positive performance. The model keeps the idea of learning vector quantization based on prototypes by stochastic gradient descent learning. For this purpose, a GLVQ-based cost function is presented, which describes the area under the ROC-curve in terms of the sum of local discriminant functions. This cost function reflects the underlying rank statistics in ROC analysis being involved into the design of the prototype based discriminant function. The resulting learning scheme for the prototype vectors uses structured inputs, i.e. ordered pairs of data vectors of both classes.

关键词： learning vector quantization ROC analysis AUC optimization

来源：评论

学校读者我要写书评

暂无评论

learning vector quantization-Based Fuzzy Rules Oversampling Method

引用

Computers, Materials & Continua 2024年第6期79卷 5067-5082页

作者： Jiqiang Chen Ranran Han Dongqing Zhang Litao Ma School of Mathematics and Physics Hebei University of EngineeringHandan056038China

Imbalanced datasets are common in practical applications,and oversampling methods using fuzzy rules have been shown to enhance the classification performance of imbalanced data by taking into account the relationship between data ***,the creation of fuzzy rules typically depends on expert knowledge,which may not fully leverage the label information in training data and may be *** address this issue,a novel fuzzy rule oversampling approach is developed based on the learning vector quantization(LVQ)*** this method,the label information of the training data is utilized to determine the antecedent part of If-Then fuzzy rules by dynamically dividing attribute intervals using ***,fuzzy rules are generated and adjusted to calculate rule *** number of new samples to be synthesized for each rule is then computed,and samples from the minority class are synthesized based on the newly generated fuzzy *** results in the establishment of a fuzzy rule oversampling method based on *** evaluate the effectiveness of this method,comparative experiments are conducted on 12 publicly available imbalance datasets with five other sampling techniques in combination with the support function *** experimental results demonstrate that the proposed method can significantly enhance the classification algorithm across seven performance indicators,including a boost of 2.15%to 12.34%in Accuracy,6.11%to 27.06%in G-mean,and 4.69%to 18.78%in *** show that the proposed method is capable of more efficiently improving the classification performance of imbalanced data.

关键词： Oversampling fuzzy rules learning vector quantization imbalanced data support function machine

来源：评论

学校读者我要写书评

暂无评论

learning vector quantization-Aided Detection for MIMO Systems

引用

IEEE COMMUNICATIONS LETTERS 2021年第3期25卷 874-878页

作者： Wang, Zheng Xu, Xiong Qiang, Xiaodan Li, Kezhi CEMEE State Key Lab Complex Electromagnet Environm Effe Luoyang 471003 Peoples R China Nanjing Univ Aeronaut & Astronaut Minist Ind & Informat Technol Key Lab Dynam Cognit Syst Electromagnet Spectrum Nanjing 211106 Peoples R China MCC Huatian Engn & Technol Corp Nanjing 210000 Peoples R China UCL Inst Hlth Informat London WC1E 6BT England

In this letter, the learning vector quantization (LVQ) from machine learning (ML) is adopted into the large-scale multiple-input multiple-output (MIMO) detection to improve the detection performance. Inspired by the decision region from lattice decoding, the random Gaussian noises are applied in the proposed learning vector quantization-aided detection (LVQD) algorithm for data generation. Then, based on the classification, supervised learning is activated to update the targeted prototype vector iteratively, so as to a better detection performance. Meanwhile, the decoding radius in lattices is also used to serve as a preprocessing for LVQD, which leads to an efficient detection without performance loss. Finally, simulation results confirm that considerable performance gain can be achieved by the proposed LVQD algorithm, which suits well for suboptimal detection schemes.

关键词： learning vector quantization large-scale MIMO detection lattice decoding machine learning

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：