检索结果-内蒙古大学图书馆

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

Imbalanced Data Classification Based on Extreme learning machine Autoencoder

Imbalanced Data Classification Based on Extreme Learning Mac...

引用

International Conference on machine learning and Cybernetics (ICMLC)

作者： Chu Shen Su-Fang Zhang Jun-Hai Zhai Ding-Sheng Luo Jun-Fen Chen Key Lab. of Machine Learning and Computational Intelligence College of Mathematics and Information Science Hebei University Baoding Hebei China Hebei Branch of China Meteorological Administration Training Center China Meteorological Administration Baoding China Key Lab. of Machine Perception (Ministry of Education) School of EECS Peking University Beijing China

ISBN: (纸本)9781538652152

In practice, there are many imbalanced data classification problems, for example, spam filtering, credit card fraud detection and software defect prediction etc. it is important in theory as well as in application for investigating the problem of imbalanced data classification. In order to deal with this problem, based on extreme learning machine autoencoder, this paper proposed an approach for addressing the problem of binary imbalanced data classification. The proposed method includes 3 steps. (1) the positive instances are used as seeds, new samples are generated for increasing the number of positive instances by extreme learning machine autoencoder, the generated new samples are similar with the positive instances but not same. (2) step (1) is repeated several times, and a balanced data set is obtained. (3) a classifier is trained with the balanced data set and used to classify unseen samples. The experimental results demonstrate that the proposed approach is feasible and effective.

关键词： Classification algorithms Glass Training Measurement Data models Support vector machines Decoding

来源：评论

学校读者我要写书评

暂无评论

Robust task and motion planning for long-horizon architectural construction planning

arXiv

引用

arXiv 2020年

作者： Hartmann, Valentin N. Oguz, Ozgur S. Driess, Danny Toussaint, Marc Menges, Achim Machine Learning & Robotics Lab. University of Stuttgart Germany Max Planck Institute for Intelligent Systems Germany Institute for Computational Design and Construction University of Stuttgart Germany

Integrating robotic systems in architectural and construction processes is of core interest to increase the efficiency of the building industry. Automated planning for such systems enables design analysis tools and facilitates faster design iteration cycles for designers and engineers. However, generic task-and-motion planning (TAMP) for long-horizon construction processes is beyond the capabilities of current approaches. In this paper, we develop a multi-agent TAMP framework for long horizon problems such as constructing a full-scale building. To this end we extend the Logic-Geometric Programming framework by sampling-based motion planning, a limited horizon approach, and a task-specific structural stability optimization that allow an effective decomposition of the task. We show that our framework is capable of constructing a large pavilion built from several hundred geometrically unique building elements from start to end autonomously. Copyright © 2020, The Authors. All rights reserved.

关键词： Motion planning

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

A DYNAMIC FUZZY MEASURE FOR MULTIPLE CLASSIFIER FUSION

A DYNAMIC FUZZY MEASURE FOR MULTIPLE CLASSIFIER FUSION

引用

2009 International Conference on machine learning and Cybernetics(2009机器学习与控制论国际会议)

作者： YA-JING ZHANG XUE-FEI LI JUN-FEN CHEN HUI-MIN FENG College of Science Agricultural University of Hebei Baoding 071001 China Key Lab.of Machine Learning and Computational Intelligence College of Mathematics and Computer Scie

It has been shown that the fuzzy integral is an effective tool for the fusion of multiple classifiers. Of primary importance in the development of the system is the choice of the measure which embodies the importance of subsets of classifiers. In this paper we propose a method for a dynamic fuzzy measure which will change following the pattern to be classified (data dependent). This method uses the neural network which has good study ability. Our experiment results show that this method make the classification accurate improve.

关键词： Multiple classifier Fusion Fuzzy measure Fuzzy integral Neural network

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 availab.e 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

Feature Selection for Data Classification based on Binary Brain Storm Optimization

Feature Selection for Data Classification based on Binary Br...

引用

IEEE International Conference on Cloud Computing and Intelligence Systems (CCIS)

作者： Farhad Pourpanah Ran Wang Xizhao Wang College of Mathematics and Statistics Shenzhen University China Shenzhen Key Lab. Of advanced machine learning and applications Shenzhen University China Guangdong Key Lab. of Intelligent Information Processing Shenzhen University China

ISBN: (数字)9781728138633

ISBN: (纸本)9781728138640

Brain Storm Optimization (BSO) is an effective population-based optimization method inspired by human brainstorming process. This paper proposes a new binary BSO algorithm (BBSO) to develop a new feature selection approach in order to reduce the number of selected features and/or improve the classification accuracy. Specifically, a new update rule mechanism for generating new solutions is proposed, which improves the convergence speed and reduces the possibility of immature convergence in the algorithm. Furthermore, a fuzzy ARTMAP (FAM) neural network, which is an incremental learning model, is utilized as a classification approach to evaluate the effectiveness of the selected feature subsets. The performance of the proposed method is compared with those from the original BSO, particle swarm optimization (PSO) and genetic algorithm (GA) on eight commonly used and well-known benchmark problems. The experimental results indicate the superiority of the BBSO as compared with other state-of-the-art feature selection methods.

关键词： Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

USING 2-ADDITIVE FUZZY MEASURE IN MULTIPLE CLASSIFIER SYSTEM

USING 2-ADDITIVE FUZZY MEASURE IN MULTIPLE CLASSIFIER SYSTEM

引用

2009 International Conference on machine learning and Cybernetics(2009机器学习与控制论国际会议)

作者： AI-XIA CHEN GUO-FANG ZHANG NING LI LI ZHAO GUO-QIANG YUAN Key Lab.of Machine Learning and Computational Intelligence College of Mathematics and Computer Scie Department of Basic Courses Hebei College of Finance Baoding 071051 China

Fuzzy measure and integral are widely used in Multiple Classifier System (MCS). But the number of coefficients involved in the fuzzy integral model grows exponentially with the number of classifiers to be aggregated. The main difficulty is to identify all these coefficients. This paper does an attempt Using 2-additrve fuzzy measure in Multiple Classifier System. Our conclusion is that when different interactions exist in different classifiers the complexity of the computation can be significantly reduced by 2-order additive measure.A simple example is included to illustrate the 2-order additive measure.

关键词： Fuzzy measure λ - fuzzy measure 2-additive fuzzy measure Interaction Multiple Classifier System

来源：评论

学校读者我要写书评

暂无评论

THE STUDY OF UNSTABLE CUT-POINT DECISION TREE GENERATION BASED-ON THE PARTITION IMPURITY

THE STUDY OF UNSTABLE CUT-POINT DECISION TREE GENERATION BAS...

引用

2009 International Conference on machine learning and Cybernetics(2009机器学习与控制论国际会议)

作者： XI-ZHAO WANG HUI-QIN ZHAO SHUAI WANG Key Lab.of Machine Learning and Computational Intelligence College of Mathematics and Computer Scie College of Mathematics and Computer Science Hebei University Baoding 071002 China

This paper is to discuss the reduction of computation complexity in decision tree generation for the numerical-valued attributes. The proposed method is based on the partition impurity. The partition impurity minimization is used to select the expanded attribute for generation the sub-node during the tree growth. After inducing the unstable cut-points of numerical-attributes, it is analytically proved that the partition impurity minimization can always be obtained at the unstable cut-points. It implies that the computation on stable cut-points may not be considered during the tree growth. Since the stable cut-points are far more than unstable cut-points, the experimental results show that the proposed method can reduce the computational complexity greatly.

关键词： Numerical-valued attributes decision trees Gini Indez Information entropy Partition impurity Unstable cut-point

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

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：