检索结果-内蒙古大学图书馆

International Conference on Computational Intelligence and Applications (ICCIA)

作者： Kecan Cai Hongyun Zhang Duoqian Miao Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

ISBN: (数字)9798350352214

ISBN: (纸本)9798350352221

Current semi-supervised learning-based sample selection methods for noisy label image classification typically utilize all clean and noisy samples for model training. However, not all noisy samples contribute positively to model training. This paper introduces a novel semi-supervised image data granulation method that employs adaptively generated granular noisy sample subsets in place of the original noisy samples to enhance classification efficiency. The granular data generated retain the essential features of the original data, thereby improving efficiency without compromising classification accuracy. The quality of the granular data is assessed using coverage and specificity criteria, standard metrics for evaluating information granules. The proposed method consists of three main components: (i)selecting clean and noisy samples through network co-training, (ii)calculating granular noisy sample subsets by adaptive granulation, and (iii)optimizing the network model using a semi-supervised strategy. Experimental results on benchmark datasets with varying noise rates demonstrate that our method significantly improves the efficiency of noisy label image classification while maintaining accuracy.

关键词： Training Adaptation models Accuracy Computational modeling Noise Benchmark testing Noise measurement Standards Image classification Noise level

来源：评论

学校读者我要写书评

暂无评论

EEG hidden information mining using hierarchical feature extraction and classification

EEG hidden information mining using hierarchical feature ext...

引用

IEEE International Conference on Cognitive Informatics

作者： Deng Wang Duoqian Miao Chen Xie Hongyun Zhang Key Laboratory of Embedded System & Service Computing Ministry of Education of China University of Tongji Shanghai China Tongji University Shanghai Shanghai CN

This paper presents a hierarchical feature extraction and classification method for electroencephalogram (EEG) hidden information mining. It consists of supervised learning for fewer features, hierarchical knowledge base (HKB) construction and classification test. First, the discriminative rules and the corresponding background conditions are extracted by using autoregressive method in combination with the nonparametric weighted feature extraction (NWFE) and k-nearest neighbor. Second, through ranking the discriminative rules according to validation test correct rate, a hierarchical knowledge base HKB is constructed. Third, given an EEG sequence, it chooses one or several discriminative rules from the HKB using the up-bottom search strategy and calculates classification accuracy. The experiments are carried out upon real electroencephalogram (EEG) recordings from five subjects and the results show the better performance of our method.

关键词： Feature extraction Electroencephalography Accuracy Classification algorithms Runtime Knowledge based systems Brain modeling

来源：评论

学校读者我要写书评

暂无评论

Hierarchical attention generative adversarial networks for cross-domain sentiment classification

arXiv

引用

arXiv 2019年

作者： Zhang, Yuebing Miao, Duoqian Wang, Jiaqi Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain data. In recent years, many researchers have used deep neural network models for cross-domain sentiment classification task, many of which use Gradient Reversal Layer (GRL) to design an adversarial network structure to train a domain-shared sentiment classifier. Different from those methods, we proposed Hierarchical Attention Generative Adversarial Networks (HAGAN) which alternately trains a generator and a discriminator in order to produce a document representation which is sentimentdistinguishable but domain-indistinguishable. Besides, the HAGAN model applies Bidirectional Gated Recurrent Unit (Bi-GRU) to encode the contextual information of a word and a sentence into the document representation. In addition, the HAGAN model use hierarchical attention mechanism to optimize the document representation and automatically capture the pivots and non-pivots. The experiments on Amazon review dataset show the effectiveness of HAGAN. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Clustering and Analysis of Household Power Load Based on HMM and Multi-factors

Clustering and Analysis of Household Power Load Based on HMM...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Hao Fang Yue Zhang Min Liu Weiming Shen School of Electronic and Information Engineering Tongji University Shanghai China The Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China

With the advance of the information and communication technology, smart grid, and smart metering, residential electricity usage data are available for analyzing household usage pattern. However, most such usage pattern analyses have been based on smart meter data. Geographical location and environment factors have not been well considered. In order to have a better understanding of residential electricity usage pattern, this paper studies the usage pattern based on both environment data and smart meter data. A Hidden Markov Model (HMM) is applied to learn the consumption dynamic behavior under the corresponding environments and a clustering method is applied to discover the typical usage patterns. The environmental adaptation which indicates the household reaction to the environment during the electricity consumption is revealed.

关键词： Hidden Markov models Clustering algorithms Smart meters Meteorology Pattern analysis Analytical models Biological system modeling

来源：评论

学校读者我要写书评

暂无评论

Consensus in Second-Order Discrete-Time MAS With Distinct and Multiple Coupling Matrices

Consensus in Second-Order Discrete-Time MAS With Distinct an...

引用

International Conference on systems and Informatics (ICSAI)

作者： Chenggong Sun Xiwei Liu Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

ISBN: (数字)9798331510138

ISBN: (纸本)9798331510145

In this paper, we explore and establish several necessary and sufficient conditions that are instrumental in achieving consensus within second-order discrete-time multi-agent systems (SDMAS). Different with previous research, this study addresses the more intricate scenario where the velocity coupling matrix is distinct from the position coupling matrix. We introduce a novel eigenvector condition tailored to this challenge. Furthermore, in response to the burgeoning interest in multiweighted networks, this study is extended to SDMAS with multiple weights. We employ a technique, that rearranges the order of variables, to effectively simplify the analysis of multiweighted networks by transforming them into single-weighted equivalents. The efficacy of our method is substantiated through three numerical examples, which illustrate the practical value in elucidating consensus dynamics within SDMAS featuring diverse coupling matrices.

关键词： Couplings Sufficient conditions Instruments Numerical simulation Trajectory Numerical models Multiaccess communication Informatics Pragmatics Multi-agent systems

来源：评论

学校读者我要写书评

暂无评论

A Distributed Link Prediction Algorithm Based on Clustering in Dynamic Social Networks

A Distributed Link Prediction Algorithm Based on Clustering ...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Han Yuan Yunlong Ma Feng Zhang Min Liu Weiming Shen Tongji University School of Electronic and Information Engineering Shanghai China Tongji University The Key Laboratory of Embedded System and Service Computing Shanghai China

ISBN: (纸本)9781479986989

Link prediction in network attempts to predict the exist-yet-unknown links or future links in accordance with the node properties and the network typology. It has been used in many domains such as social network, biology experiment, and criminal investigations. Classical methods are based on graph topology structure and path features but few consider clustering information. Actually, clustering information plays an important role in link prediction, it connects the sparse nodes and other communities to form intensive communities. Besides the application of clustering, the MapReduce-based method is used to improve the efficiency. The validity of algorithm is verified by real-world datasets. The experimental results show that the proposed algorithm has a higher prediction accuracy and lower time complexity, and is more scalable than traditional methods executed by a single machine.

关键词： Prediction algorithms Clustering algorithms Indexes Prediction methods Algorithm design and analysis Heuristic algorithms Social network services

来源：评论

学校读者我要写书评

暂无评论

A Stable and Distributed Community Detection Algorithm Based on Maximal Cliques

A Stable and Distributed Community Detection Algorithm Based...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Feng Gui Yunlong Ma Feng Zhang Min Liu Rong Yin Weiming Shen Tongji University School of Electronic and Information Engineering Shanghai China Tongji University The Key Laboratory of Embedded System and Service Computing Shanghai China

ISBN: (纸本)9781479986989

In the research area of community detection which aims at detecting some highly cohesive vertex subsets in social network, there mainly exist some problems, such as the algorithms with comparatively excellent quality of the final partitioning usually have high time complexity and some other fast algorithms often result in low quality of partitioning or other disadvantages. Nowadays, the increasing demands for community detection in large-scale social networks necessitate the use of distributed and scalable methods to detect communities in an effective and efficient manner. Label propagation algorithm (LPA), whose time complexity is O (m) on a network with m edges, is a near linear time algorithm to detect community effectively. Besides, owing to having good scalability, the parallel version of LPA (DLPA) is suitable for community detection in large-scale social networks. However, DLPA synchronously updates the vertices labels, which usually brings about label oscillations and results in low quality of partitioning. In this paper, we analyze the drawbacks of DLPA and propose a novel method C-DLPA, which combines DLPA with the notion of maximal cliques and at the same time utilizes a new updating mechanism that updating each node' label by probability of its adjacent nodes, to make final partitioning become more accurate and to avoid oscillations effectively. The experimental results show that C-DLPA has better performance is not only low time cost by as much to avoid oscillations but its community detection accuracy compared with DLPA.

关键词： Oscillators Image edge detection Time complexity Partitioning algorithms Algorithm design and analysis Social network services Transforms

来源：评论

学校读者我要写书评

暂无评论

Genetic Fuzzy + PI Path Tracking Control of a Nonholonomic Mobile Robot*

引用

Chinese Journal of Electronics 2023年第1期20卷 31-34页

作者： Zhengcai Cao Yingtao Zhao Qidi Wu College of Information Science and Technology Beijing University of Chemical Technology Beijing China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

A mobile robot is one of the well-known nonholonomic systems. The genetic fuzzy + PI path tracking control applied to a mobile robot is presented. The proposed controller composes of two fuzzy + PI controllers which are employed to control the angular velocity together, and one fuzzy + PI controller that is utilized to adjust the speed of mobile robot solely. Moreover, the fuzzy controller is designed to track reference path in approaching phase and PI controller is operated to diminish the tracking error in stable phase. In order to obtain better tracking performance, Genetic algorithm (GA) is used to optimize controller parameters. Finally, computer simulation results are given to illustrate the effectiveness of the proposed control scheme.

关键词： PI control Computer simulation Genetics Angular velocity Mobile robots Tuning Optimization

来源：评论

学校读者我要写书评

暂无评论

A comparative study of redundant feature detection based feature selection methods

A comparative study of redundant feature detection based fea...

引用

International Conference on Computer, Information and Telecommunication systems (CITS)

作者： Xue-Qiang Zeng Qian-Sheng Chen Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China Computer Center Nanchang University Nanchang China

As a high dimensional problem, analysis of largescale data sets is a challenging task, where many weakly relevant or redundant features hurt generalization performance of classification models. In order to solve this problem, many effective feature selection methods have proposed to eliminate redundant features in recent years. However, the comparative performances of these redundant feature detection based methods have not been reported yet, which makes the choice of feature selection method relatively difficult for many real applications. The paper presents a novel comparative study of redundant feature detection based feature selection methods. Experiments on several benchmark data sets demonstrate the comparative performances of some state-of-the-arts methods. Based on the extensive empirical results, the minimum Redundancy-Maximum Relevance (mRMR) method has been found to be the best one among all compared feature selection models.

关键词： Breast Colon Lungs Redundancy

来源：评论

学校读者我要写书评

暂无评论

A method to calculate recommendation trust of web services

Journal of Software Engineering

引用

Journal of Software Engineering 2014年第2期8卷 108-115页

作者： Liu, Wei Du, Yu-Yue Yan, Chun Sha, Jing College of Information Science and Engineering Shandong University of Science and Technology Qingdao China The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai China

Web services are widely accepted and used in the e-commerce. Trust plays an important role in selecting one Web service for application among many services satisfying the demand of requesters and trust for Web services is a hot topic in research fields. This study proposes a method to calculate recommendation trust of Web services and the weight of every recommender is confirmed by norm grey correlation analysis method. The detailed process of the given method is revealed by a specific instance. The method avoids the vicious recommendation and improves the reliability of selected services. © 2014 Academic Journals Inc.

关键词： Web services

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：