检索结果-内蒙古大学图书馆

International Conference on machine learning and Cybernetics

作者： He, Qing Li, Ning Shi, Zhong-Zhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Hebei University Baoding 071002 Hebei China Graduate University of Chinese Academy of Sciences Hebei University Baoding 071002 Hebei China Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 Hebei China

ISBN: (纸本)9781424465262

Support Vector machine (SVM) is a classification technique of machine learning based on statistical learning theory. A quadratic optimization problem needs to be solved in the algorithm, and with the increase of the samples, the time complexity will also increase. So it is necessary to shrink training sets to reduce the time complexity. A sample selection method for SVM is proposed in this paper. It is inspired from the Hyper surface classification (HSC), which is a universal classification method based on Jordan Curve Theorem, and there is no need for mapping from lower-dimensional space to higher-dimensional space. The experiments show that the algorithm shrinks training sets keeping the accuracy for unseen vectors high. © 2010 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

AN INSTANCE SELECTION ALGORITHM BASED ON CONTRIBUTION

AN INSTANCE SELECTION ALGORITHM BASED ON CONTRIBUTION

引用

2008 International Conference on machine learning and Cybernetics(2008机器学习与控制论国际会议)

作者： XI-ZHAO WANG NING ZHANG TAO XIAO Key Lab.for Machine Learning and Computational Intelligence College of Mathematics and Computer Sci College of Science Agricultural University of Hebei Baoding 071002 China

This paper presents an approach to instance selection for the nearest neighbor rule which aims to obtain a condensed set with high condensing rate and prediction accuracy. By making an improvement on MCS algorithm and allowing certain error rate on the training set, a condensed set with high condensing rate and satisfying prediction accuracy is obtained. The condensed set is order-independent of the training instances and insensitive to noise. Comparative experiments have been conducted on real data sets, and the results show its superiority to MCS and FCNN in terms of condensing rate and prediction accuracy.

关键词： Instance selection nearest neighbor rule condensed set MCS FCNN

来源：评论

学校读者我要写书评

暂无评论

Refining Width Parameter of Gaussian Kernel Functionfor Tuning Coherent Point Drift(CPD) Registration

Refining Width Parameter of Gaussian Kernel Functionfor Tuni...

引用

作者： Junfen CHEN Qiang HE Yan LI Key Lab of Machine Learning and Computational Intelligence College of Mathematics and Information Sciences Hebei University School of Sciences Beijing University of Civil Engineering and Architecture

Coherent point drift(CPD), a sophistic non-rigid point sets registration method, is successfully applied in computer vision, medical image analysis, to name a few. Its registration error, however, is affected greatly by three free parameters. One of them, width parameter of Gaussian kernel function, is studied in this paper to tune registration error of the CPD method. Before computing width parameter by a heuristic algorithm, the given data is regulated using minmax and standard normalization in effort to remove heterogeneity among the features of the data. Several experiments are designed on the available six datasets to examine the effectiveness of CPD based on the refined width parameter. Experimental comparison indicated that the refined width parameter from the normalized data can reduce registration error of the CPD method, e.g., by 13.76% on bat dataset.

关键词： Normalization Gaussian kernel Width parameter Coherent point drift(CPD) Registration error(MSE)

来源：评论

学校读者我要写书评

暂无评论

A deep web interface integration approach based on domain knowledge and submitting queries

引用

Journal of Information and computational Science 2009年第3期6卷 1103-1111页

作者： Yuan, Fang Liu, Hongfei Wei, Yonggang Yao, Zengli College of Mathematics and Computer Science Hebei University Hebei Baoding 071002 China Key Lab. in Machine Learning and Computational Intelligence of Hebei Province Hebei Baoding 071002 China

Deep Web can provide us a great amount of high quality information. In order to make full use of the information, it is becoming urgent to establish Deep Web data integration system, in which Deep Web interface integration is an important component. This paper proposes a deep web interface integration method based on domain knowledge and submitting queries for certain domains. Before application this method, we categorize Deep Web interfaces according to their structures and introduce the concept of interface element, which be used to represent the interface. This approach first selects the required attributes, and then matches these attributes in each interface element, after that integrates each interface element which matches the same attribute to generate the global interface. This method includes interface template matching, domain knowledge-based interface elements matching and submitting queries-based interface elements matching, etc. Experimental results show that the proposed method has higher matching accuracy and lower dependency on preparatory work. 1548-7741/ Copyright © 2009 Binary Information Press.

关键词： Domain Knowledge

来源：评论

学校读者我要写书评

暂无评论

Core Set Extreme learning machine

Core Set Extreme Learning Machine

引用

作者： Shuxia Lu Bin Liu Caihong Jiao Key Lab.In Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University School of Mechanical and Vehicular Engineering Beijing Institute of Technology

A core set extreme learning machine(CSELM) approach is proposed in order to deal with large datasets classification problem. In the first stage, the core set can be obtained efficiently by using the generalized core vector machine(GCVM) algorithm. For the second stage, the extreme learning machine(ELM) can be used to implement classification for much larger datasets. Experiments show that the CSELM has comparable performance with SVM and ELM implementations, but is faster on large datasets.

关键词： Core vector machine Extreme learning machine Support vector machine Core set

来源：评论

学校读者我要写书评

暂无评论

Knowledge Updating Method Based On Approximate Reduction Under Dominance Relations

Knowledge Updating Method Based On Approximate Reduction Und...

引用

International Conference on machine learning and Cybernetics (ICMLC)

作者： Yan Li Li Zhang Ting Ting Wu Jun Fen Chen School of Applied Mathematics Beijing Normal University Zhuhai Zhuhai City Key Lab of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding

ISBN: (纸本)9781538652152

Rough set approach based on dominance- equivalence relation can be used to handle classification problems with preference ordered conditional attributes. It firstly extracts the most important information to the decisions, and then approximates target concepts and finally form the decision-making knowledge. In this paper, we study the issue of updating knowledge in classification problems under dynamic environments. When some samples are inserted or deleted, the update principle of dominating sets is given and the approximate reduction algorithm based on sample selection is developed. The proposed method only needs to individually consider the impact of changing samples on knowledge reduction, and therefore it can obviously reduce the storage space. More importantly, since it can utilize previous calculation results, the time cost of subsequent calculations is thus significantly reduced. Ten UCI data sets are selected in our experiments. The results show the effectiveness and efficiency of the proposed method.

关键词： Rough sets Approximation algorithms Information systems Heuristic algorithms Ducts Classification algorithms

来源：评论

学校读者我要写书评

暂无评论

A new instance selection algorithm based on contribution for nearest neighbour classification

A new instance selection algorithm based on contribution for...

引用

International Conference on machine learning and Cybernetics

作者： Cai, Yong-Hua Wu, Bo He, Yu-Lin Zhang, Ye Department of Mathematics and Computer Science Hebei Normal University for Nationalities Chengde067000 Hebei China Automation Department Chengde Iron and Steel Branch Hebei Iron and Steel Group Co. Ltd. Chengde 067000 Hebei China Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding 071002 Hebei China

ISBN: (纸本)9781424465262

Nearest Neighbor Classifier is one of the most classical lazy learning schemes. The basic nearest neighbor classifiers suffer from the common problem that the instances used to train the classifier are all stored indiscriminately, and as a result, the required memory storage is huge and response time becomes slow with a large database. In this paper, a new Instances Selection algorithm based on Classification Contribution Function shortly named ISCC is presented. In this algorithm, a function is introduced to evaluate the classification ability of the instances. For each instance, the function considers its contribution to the neighbor instances not only with same class but also with different class. Then an instance with the highest value of Classification Contribution Function is added to the condensed subset and the instances which can be classified correctly are deleted in each iteration. This process is repeated until the subset is no longer getting larger. The time complexity of ISCC is Ο (in2). The experimental results on two artificial databases and some real databases demonstrate the effectiveness and the feasibility of the proposed algorithm. Compared to traditional methods, such as MCS, ICF and ENN, the condensed sets obtained by ISCC is superior in storage and classification accuracy. © 2010 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Efficient image representation for object recognition via pivots selection

引用

Frontiers of Computer Science 2014年

作者： Xie, Bojun Liu, Yi Zhang, Hui Yu, Jian Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Key Lab of Machine Learning and Computational Intelligence College of Mathematics and Computer Science Hebei University Baoding071000 China

Patch-level features are essential for achieving good performance in computer vision tasks. Besides well-known pre-defined patch-level descriptors such as scaleinvariant feature transform (SIFT) and histogram of oriented gradient (HOG), the kernel descriptor (KD) method [1] offers a new way to "grow-up" features from a match-kernel defined over image patch pairs using kernel principal component analysis (KPCA) and yields impressive *** this paper, we present efficient kernel descriptor (EKD) and efficient hierarchical kernel descriptor (EHKD), which are built upon incomplete Cholesky decomposition. EKD automatically selects a small number of pivot features for generating patch-level features to achieve better computational efficiency. EHKD recursively applies EKD to form image-level features layer-by-layer. Perhaps due to parsimony, we find surprisingly that the EKD and EHKD approaches achieved competitive results on several public datasets compared with other state-of-the-art methods, at an improved efficiency over KD. © 2014 Higher Education Press and Springer-Verlag Berlin Heidelberg

关键词： Object recognition

来源：评论

学校读者我要写书评

暂无评论

NC-ALG: Graph-Based Active learning under Noisy Crowd 40

NC-ALG: Graph-Based Active Learning under Noisy Crowd

引用

40th IEEE International Conference on Data Engineering, ICDE 2024

作者： Zhang, Wentao Wang, Yexin You, Zhenbang Li, Yang Cao, Gang Yang, Zhi Cui, Bin Center for Machine Learning Research Peking University China Key Lab of High Confidence Software Technologies Peking University China Institute of Advanced Algorithms Research Shanghai China Institute of Computational Social Science Peking University Qingdao China National Engineering Labratory for Big Data Analytics and Applications China TEG Tencent Inc. Department of Data Platform China Beijing Academy of Artificial Intelligence China

ISBN: (纸本)9798350317152

Graph Neural Networks (GNNs) have achieved great success in various data mining tasks but they heavily rely on a large number of annotated nodes, requiring considerable human efforts. Despite the effectiveness of existing GNN-based Active learning (AL) methods, they assume that the annotated labels are always correct, which is contradictory to the error-prone labeling process in a practical crowdsourcing environment. Besides, due to this impractical assumption, existing works only focus on optimizing the node selection in AL but neglect optimizing the labeling process. Therefore, we present NC-ALG, the first GNN-based AL framework that optimizes both the node selection and node labeling process under a noisy crowd. For node selection, NC-ALG introduces a new measurement to model influence reliability and an effective influence maximization objective to select nodes. For node labeling, NC-ALG significantly reduces the labeling cost by considering the model-predicted labels and the labels of mirror nodes. To the best of our knowledge, this is the first attempt to consider GNN-based AL under the practical noisy crowd. Empirical studies on public datasets demonstrate that NC-ALG significantly outperforms existing methods in terms labeling efficiency. Notably, it only takes NC-ALG one-third of the labeling budget that the competitive baseline GRAIN needs to achieve an accuracy of 70.7 % on PubMed. © 2024 IEEE.

关键词： Crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

Selection of deep web database based on query relevance

引用

Journal of Information and computational Science 2009年第3期6卷 1113-1120页

作者： Yuan, Fang Fan, Jingchuan Liu, Shuang Zhang, Ming College of Mathematics and Computer Science Hebei University Hebei Baoding 071002 China Key Lab. in Machine Learning and Computational Intelligence of Hebei Province Hebei Baoding 071002 China College of Quality Technology Supervision Hebei University Hebei Baoding 071000 China

During recent years, there are more and more high-quality information in the Web database. Thus, it is becoming more and more important to find the most relevant Web database to user's query. In this paper, we propose a method to calculate the relevance of Web database with respect to user's query. The method submits frequent query to Web database, classifies the obtained results from the Web database by their characteristic, and calculates the relevance between the query and each type of obtained results together with the proportion of each type of the obtained result occupying all the results from all Web database. Meanwhile, the relevance between the query and the Web database is obtained through the weighted sum of the foresaid relevance and proportion. Experimental results on several actual Web databases demonstrate the effectiveness of the proposed method in evaluating the Web database's supporting power with specific queries. 1548-7741/ Copyright © 2009 Binary Information Press.

关键词： Query languages

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：