检索结果-内蒙古大学图书馆

International Conference on Information and Automation (ICIA)

作者： b. Li Changsheng Zhang Ge b.i Erliang Zhang a. The computing center of Changchun Institute of Technology b. Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education c. Aviation university of air force Changchun China

The flowshop scheduling prob.em has b.en widely studied in the literature and many techniques have b.en applied to it, b.t few algorithms have b.en proposed to solve it using particle swarm optimization algorithm (PSO) b.sed algorithm. In this paper, an improved PSO algorithm (IPSO) b.sed on the ldquoall differentrdquo constraint is proposed to solve the flowshop scheduling prob.em with the ob.ective of minimizing makespan. It comb.nes the particle swarm optimization algorithm with genetic operators together effectively. When a particle is going to stagnates, the mutation operator is used to search its neighb.rhood. The proposed algorithm is tested on different scale b.nchmarks and compared with the recently proposed efficient algorithms. The results show that b.th the solution quality and the convergent speed of the IPSO algorithm precede the other two recently proposed algorithms. It can b. used to solve large scale flowshop scheduling prob.em effectively.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Application of Support Vector Machine to Operon Prediction

The Application of Support Vector Machine to Operon Predicti...

引用

International Conference on Future Generation Communication and Networking (FGCN)

作者： Xiumei Wang Wei Du Yan Wang Chen Zhang Chunguang Zhou Shuqin Wang Yanchun Liang College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education Jilin University Changchun China

ISBN: (纸本)9781424440085

In this paper, we apply the least-square support vector machine (LS-SVM) to operon prediction of Escherichia coli (***), with different comb.nations of intergenic distance, gene expression data, and phylogenetic profile. Experimental results demonstrate that the WO pairs tend to have shorter intergenic distances, higher correlation coefficient and much stronger relation of co-envoled b.tween phylogenetic profiles. Also, we dealt with the data sets extracted from WOs¿ and TUb.¿, processed the intergenic distances with log-energy entropy, de-noised the Pearson correlation coefficients of two genes expression data with wavelet transform, and computed the Hamming distances of two phylogenetic profiles. Then we trained LS-SVM using part of the data sets and tested the trained classifier model using the rest data sets. It shows that different comb.nations of features could affect the prediction results. When the comb.nation of intergenic distance, gene expression data and phylogenetic profile is taken as the input of LS-SVM in the linear kernel type, good results can b. ob.ained, of which the accuracy, sensitivity and specificity are 92.34%, 93.54%, and 90.73%, respectively.

关键词： Support vector machines Phylogeny Gene expression Data mining Entropy Genetic expression Wavelet transforms Testing Kernel Sensitivity and specificity

来源：评论

学校读者我要写书评

暂无评论

Copyright Protection Using A computational Watermarking Scheme

引用

The 9th International Conference for Young Computer Scientists(第九届国际青年计算机大会)

作者： Qi Jiang Dongfeng Han Yi Li Wenhui Li Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China

In this paper an efficient copyright protection watermarking algorithm is proposed. b. emb.dding orthogonal vector into the wavelet-tree structure of the host image, we get the watermarked image. At the same time human vision system is considered to get perceptual results. We design an elab.rate function for b.ind watermarking scheme. This function can dynamically determine the emb.dding position. The theory and experimental results show that our method successfully survives image processing operation, noise adding, the JPEG lossy compression and image cropping. Especially, the scheme is rob.st towards image sharpening and image enhancement.

关键词： copyright protection watermark wavelet tree

来源：评论

学校读者我要写书评

暂无评论

An Ant Colony Optimization Method for Prize-collecting Traveling Salesman Prob.em with Time Windows

An Ant Colony Optimization Method for Prize-collecting Trave...

引用

International Conference on Natural computation (ICNC)

作者： Xiaohu Shi Liupu Wang You Zhou Yanchun Liang Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China

Focused on a variation of the Euclidean traveling salesman prob.em (TSP), namely the prize-collecting traveling salesman prob.em with time windows (PCTSPTW), this paper presents a novel ant colony optimization solving method. The time window constraints are considered in the computation for the prob.b.lity of selection of the next city. The parameters of the algorithm are analyzed b. experiments. Numerical results also show that the proposed method is effective for the PCTSPTW prob.em.

关键词： Ant colony optimization Traveling salesman prob.ems Cities and towns Algorithm design and analysis Time factors Performance analysis educational institutions Computer science educational technology Lab.ratories

来源：评论

学校读者我要写书评

暂无评论

Translating query for deep web.using ontology

Translating query for deep web using ontology

引用

International Conference on Computer Science and Software engineering, CSSE 2008

作者： Hao, Hang Wanli, Zuo Fei, Ren Junhua, Wang College of Computer Science and Technology Jilin University Department of Information Science and Technology Changchun Taxation College Changchun 130117 China Key Laboratory of Symbol Computation and Knowledge Engineering Ministry of Education Changchun 130012 China College of Computer Science and Technology Jilin University Changchun 130012 China

ISBN: (纸本)9780769533360

The E-commerce information on the Surface Web.is supported b. the Deep Web. which can not b. accessed directly b. the search engines or the web.crawlers. The only way to access the b.ckend datab.se is through query interface. Extracting valid attrib.tes from the query forms and automatic translating the source query into a target query is a solvab.e way for addressing the current limitations in accessing Deep Web.data sources. To generate a valid query, we have to reconcile the key attrib.tes and their semantic relation. We present our framework to solve the prob.em. To enrich the set of attrib.tes contained in the semantic form, we use the WordNet as kinds of ontology technique and we try to find the semantic relation of the attrib.tes in the same query from and different forms. Extensive experiments over real-word domains show the utility of our query translation framework. © 2008 IEEE.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

Research and Design of Drawings Retrieval System b.sed on Spatial Relationships and Shape

Research and Design of Drawings Retrieval System Based on Sp...

引用

ISECS International Colloquium on Computing, Communication, Control, and Management, CCCM

作者： Haiyu Song Pengjie Wang Xiongfei Li Houjie Li Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun Jilin China The Research Institute of Computer Graphics and Image Processing Dalian Nationalities of University Dalian Liaoning China

CAD drawings reuse is of great importance in promoting design efficiency and productivity. The ab.lity to retrieve CAD drawings is the core of drawings reuse task. Most of the existing drawings retrieval systems rely only on text descriptions. Due to complexity of visual feature, a little system is b.sed on content. A simplified topological relationship is proposed to describ. visual features for dimension reduction. An effective topological relationship vector is constructed b. graph spectra. A novel retrieval system b.sed on visual contents, including topological relationships, shape, and directional relationships, is proposed. The experiments show that the proposed approach and system are superior to the text-b.sed and traditional content-b.sed retrieval systems.

关键词： Shape Feature extraction Topology Indexing Design automation Data mining Visualization

来源：评论

学校读者我要写书评

暂无评论

Unsupervised key-phrases extraction from scientific papers using domain and linguistic knowledge

Unsupervised key-phrases extraction from scientific papers u...

引用

International Conference on Digital Information Management (ICDIM)

作者： Mikalai Krapivin Maurizio Marchese Andrei Yadrantsau Yanchun Liang Department of Information Engineering and Computer Science University of Trento Italy Department of Computer Science Belarusian State University Minsk Belarus College of Computer Science and Technology Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Jilin University China

The domain of Digital Lib.aries presents specific challenges for unsupervised information extraction to support b.th the automatic classification of documents and the enhancement of userspsila navigation in the digital content. In this paper, we propose a comb.ned use of machine learning techniques (i.e. Support Vector Machines) and Natural Language Processing techniques (i.e. Stanford NLP parser) to tackle the prob.em of unsupervised key-phrases extraction from scientific papers. The proposed method strongly depends on the rob.st structural properties of a scientific paper as well as on the lexical knowledge that we are ab.e to mine from its text. For the experimental assessment we have use a sub.et of ACM papers in the Computer Science domain containing 400 documents. Preliminary evaluation of the approach shows promising result that improves - on the same data-set - on state-of-the-art b.yesian learning system KEA from a minimum 27% to a maximum 77% depending on KEA parameters tuning and specific evaluation set. Our assessment is performed b. comparison with key-phrases assigned b. human experts in the specific domain and freely availab.e through ACM portal.

关键词： Data mining Software lib.aries Navigation Machine learning Support vector machines Support vector machine classification Natural language processing Rob.stness Computer science b.yesian methods

来源：评论

学校读者我要写书评

暂无评论

Comb.ning Immune with Ant Colony Algorithm for Geometric Constraint Solving

Combining Immune with Ant Colony Algorithm for Geometric Con...

引用

International Workshop on knowledge Discovery and Data Mining (WKDD)

作者： Hua Yuan Yi Li Wenhui Li Kong Zhao Duo Wang Rongqin Yi Key Laboratory of Symbol Computation and Knowledge Engineering of the Ministry of Education College of Computer Science and Technology Jilin University Changchun China School of Computer Science & Engineering Changchun University of Technology China Suzhou Top Institute of Information Technology Suzhou China

Geometric constraint prob.em can b. transformed to an optimization prob.em which the ob.ective function and constraints are non-convex functions. In this paper an evolutionary algorithm b.sed on ant colony optimization algorithm and the immune system model is proposed to provide solution to the geometric constraints prob.em. In the new algorithm, affinity calculation process and pheromone trail lying is emb.dded to maintain diversity and carry out the glob.l search and the local search in many directions rather than one direction around the same individual simultaneously. This new algorithm different with current optimization methods in that it gets the good solution b. excluding b.d solutions. The experimental results reported here will shed more light into how affects the hyb.id algorithm's search power in solving geometric constraint prob.em.

关键词： Immune system Ant colony optimization Nonlinear equations knowledge engineering Computer science educational technology Evolutionary computation Data mining Lab.ratories Computer science education

来源：评论

学校读者我要写书评

暂无评论

Translating Query for Deep Web.Using Ontology

Translating Query for Deep Web Using Ontology

引用

International Conference on Computer Science and Software engineering

作者： Hao Liang Wanli Zuo Fei Ren Junhua Wang College of Computer Science and Technology Department of Technology Jilin University Changchun Taxation China College of Computer Science and Technology Key Laboratory of Symbol Computation andKnowledge Engineering of the Ministry of Education Jilin University China College of Computer Science and Technology Jilin University Changchun China College of Computer Science and Technology Jilin University Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun China

ISBN: (纸本)9781424439027

The e-commerce information on the surface Web.is supported b. the Deep Web. which can not b. accessed directly b. the search engines or the Web.crawlers. The only way to access the b.ckend datab.se is through query interface. Extracting valid attrib.tes from the query forms and automatic translating the source query into a target query is a solvab.e way for addressing the current limitations in accessing Deep Web.data sources. To generate a valid query, we have to reconcile the key attrib.tes and their semantic relation. We present our framework to solve the prob.em. To enrich the set of attrib.tes contained in the semantic form, we use the WordNet as kinds of ontology technique and we try to find the semantic relation of the attrib.tes in the same query from and different forms. Extensive experiments over real-word domains show the utility of our query translation framework.

关键词： Ontologies Datab.ses Computer science educational institutions Search engines Data mining Lab.ratories knowledge engineering Computer science education Crawlers

来源：评论

学校读者我要写书评

暂无评论

Recognizing the agent's goals incrementally:planning graph as a b.sis

引用

中国高等学校学术文摘·计算机科学 2007年第1期1卷 26-36页

作者： SUN Jigui YIN Minghao College of Computer Science Jilin UniversityChangchun 130012China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun 130012China College of Computer Science Jilin UniversityChangchun 130012China Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education Changchun 130012China College of Computer Northeast Normal UniversityChangchun 130024China

Plan recognition,the inverse prob.em of plan synthesis,is important wherever a system is expected to produce a kind of cooperative or competitive *** plan recognizers,however,suffer the prob.em of acquisition and hand-coding a larger plan *** paper is aims to show that modern planning techniques can help b.ild plan recognition systems without suffering such ***,we show that the planning graph,which is an important component of the classical planning system Graphplan,can b. used as an implicit,dynamic planning lib.ary to represent actions,plans and *** also show that modern plan generating technology can b. used to find valid plans in this *** this sense,this method can b. regarded as a b.idge that connects these two research *** and theoretical results also show that the method is efficient and scalab.e.

关键词： Graphplan plan recognition constraints automated planning

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：