The International Conference on

Advanced Data Mining And Application

ADMA 2009

Final Program

Published By Hosted By

17-19 August, 2009

Beijing, China

http://www.adma2009.org

TABLE OF CONTENTS

Welcome Message ----------------------------------------------------------------------------------- 2

Program Committee --------------------------------------------------------------------------------- 3

Organizing Committee ------------------------------------------------------------------------------ 8

Keynote Speakers ------------------------------------------------------------------------------------- 9

Program Overview ------------------------------------------------------------------------------------ 11

Technical Program ------------------------------------------------------------------------------------ 13

The Maps --------------------------------------------------------------------------------------------- 22

- 1 -

WELCOME MESSAGE

This volume contains the proceedings of the Fifth International Conference on Advanced Data Mining and Applications (ADMA 2009), held in Beijing, China on August 17-19, 2009. We are pleased to have a very strong program. Acceptance into the conference proceedings was extremely competitive. From the 322 submissions from 27 countries and regions, the program committee selected 34 full papers and 47 short papers for presentation at the conference and inclusion in the proceedings. The contributed papers cover a wide range of data mining topics and a diverse spectrum of interesting applications. The program committee worked very hard to select these papers through a rigorous review process and extensive discussion, and finally composed a diverse and exciting program for ADMA 2009.

An important feature of the main program was the truly outstanding keynote speakers program. Edward Y. Chang, Director of Research, Google China, gave a talk titled "Confucius and 'Its' Intelligent Disciples". Being right in the forefront of data mining applications to the world's largest knowledge and data base, the Web, Dr. Zhang described how Google's Knowledge Search product helped improve the scalability of machine learning for Web-scale applications. Charles X. Ling, a seasoned researcher in data mining from the University of Western Ontario, Canada, talked about his innovative applications of data mining and artificial intelligence to gifted child education. His talk "From Machine Learning to Child Learning" generated much interest among data miners alike. Daniel S. Yeung, who is a Chair Professor in the School of Computer Science and Engineering, South China University of Technology, in Guangzhou, China, talked about his research insights on sensitivity-based generalization error for supervised learning problems and feature selection. As the President of the IEEE Systems, Man and Cybernetics (SMC) Society and a Fellow of the IEEE, Professor Yeung shared much insight on the integration of data mining theory with practice. To highlight the importance of data mining practice, Longbing Cao from the University of Technology, Sydney Australia, talked about “Data Mining in Financial Markets”, a timely and important topic that can only be understood well with his vast experience in financial data mining applications.

ADMA 2009 was the continued of the success of the ADMA conference series, which is one of the leading international forums for data mining researchers, practitioners, developers and users to exchange edge-cutting ideas, techniques, and experience.

The organization committee and the program committee thank all those who submitted their papers to the conference. We also thank the external reviewers, listed separately, who helped in the review process.

As conference co-chairs and program committee co-chairs, we would like to thank the members of the program committee for their hard work and bearing with the primitive conference management tool. Particularly, we would like to extend our special thanks to Yushun Li, Na Zhai, and Bin Jiang who made significant contributions to the review process and the conference organization. Their efforts are essential to the quality of the conference.

We hope that all participants of ADMA 2009 take the opportunity to exchange exciting research ideas and explore the beautiful city of Beijing.

Qiang Yang and Ronghuai Huang, general co-chairs

Jian Pei, João Gama, and Xiaofeng Meng, program committee co-chairs

- 2 -

PROGRAM COMMITTEE

Steering Committee Chairs Xue Li University of Queensland (UQ), Australia

General Co-Chairs Ronghuai Huang Beijing Normal University, China

Qiang Yang Hong Kong University of Science and Technology, China

Program Co-Chairs Jian Pei Simon Fraser University, Canada

João Gama University of Porto, Portugal

Xiaofeng Meng Renmin University of China, China

Regional Organization Co-Chairs Xiaochun Cheng Middlesex University in London, UK

Soon-Joo Hyun Information and Communications University, Korea

Ah-Hwee Tan Nanyang Technological University, Singapore

Program Committee Hassan Abolhassani Sharif University of Technology, Iran

Reda Alhajj University of Calgary Calgary, Alberta, Canada

José del Campo Ávila University of Malaga, Spain

James Bailey University of Melbourne, Australia

Petr Berka University of Economics, Czech Republic

Michael R. Berthold University of Konstanz, Germany

Fernando Berzal University of Granada , Spain

Rongfang Bie Beijing Normal University, China

Rui Camacho University of Porto, Portugal

André de Carvalho University of Sao Paulo at Sao CarlosSao Carlos, SP,

Brazil

Nick Cercone Department of Science & Engineering, York University,

Canada

Jian Chen Southern China University of Technology, China

Yu Chen Sichuan University, China

Xiaochun Cheng Middlesex University, UK

Frans Coenen University of Liverpool, UK

Bruno Cremilleux Universite de Caen, France

Guangzuo Cui Beijing Normal University, China

Kevin Curran Ulster University, UK

Alfredo Cuzzocrea Institute of High Performance Computing and Networking

- Italian National Research Council and University of

- 3 -

Calabria, Italy

Xiangjun Dong Shandong Institute of Light Industry, China

ZhaoYang Dong The University of Queensland, Australia

Xiaoyong Du Renmin University, China

Mohamad El-hajj University of Alberta, Canada

Floriana Esposito University of Bari, Italy

Yi Feng Zhejiang Gongshang University, China

Raymond Yun Fu University of Illinois at Urbana Champaign (UIUC), USA

João Gama University of Porto, Portugal

Dragan Gamberger Rudjer Boskovic Institute, Croatia

Jean-Gabriel Ganascia University Pierre et Marie Curie(Paris VI), France

Hong Gao Harbin Institute of Technology, China

Junbin Gao Charles Sturt University, Australia

Peter Geczy National Institute of Advanced Industrial Science and

Technology(AIST), Japan

Raúl Giráldez Pablo de Olavide University, Seville , Spain

Christophe Giraud-Carrier Brigham Young University, USA

Bing Guo School of Computer Science & Engineering, SiChuan

University, China

Ming Hua Simon Fraser University, Canada

Jimmy Huang York University, Canada

Alfred Hofmann Springer Verlag, Germany

Tan Ah Hwee Nanyang Technological University, Singapore

Iñaki Inza University Basque Country, Spain

Ping Jiang The University of Bradford, Bradford, UK

Shengyi Jiang Guang Dong University of Foreign Studies, China

Alípio Jorge University Porto, Portugal

Rajkumar Kannan Bishop Heber College, India

Dimitrios Katsaros University of Thessaly, Greece

Mehmet Kaya Firat University, Elazig, Turkey

Adam Krzyzak Concordia University, Canada

Andrew Kusiak University of Iowa, USA

Charles Li Sichuan University, China

Gang Li Deakin University, Melbourne Campus, Australia

Guohe Li China University of Petroleum, China

Jing Li Sheffield University, UK

Xiaoli Li Institute for Infocomm Research, Singapore

Xuelong Li University of London, UK

Yingshu Li Georgia State University, USA

Zhanhuai Li Northwestern Polytechnical University, China

Jing Liu Xidian University, China

Wanquan Liu Curtin University of Technology, WA, Australia

Jiaheng Lu Renmin University of China, China

Ding Ma Chinese People's Public Security University, China

- 4 -

Nasrullah Memon Aalborg University, Denmark

Xiaofeng Meng Renmin University of China, China

Rosa Meo University di Turin, Italy

Rachard Mitchell University of Reading, UK

Juggapong Natwichai Chiang Mai University, Thailand

Daniel Neagu University of Bradford ,UK

Claire Nedellec Laboratoire Mathmatique, Informatique et Genome, France

Michael O’Grady University College Dublin (UCD), Ireland

Arlindo Oliveira Technical University Lisboa, Portugal

Mourad Oussalah University of Birmingham, UK

Tansel ozyer TOBB Economics and Technology University, Turkey

Deepak S Padmanabhan IBM India Research Lab, India

Yanwei Pang Tianjin University, China

Jian Peng Sichuan University, China

Yonghong Peng University of Bradford , UK

Mithun Prasad Rensselaer Polytechnic Institute, USA

Naren Ramakrishnan Virginia Tech, USA

Jan Rauch University of Economics, Prague, Czech Republic

Christophe Rigotti INSA de Lyon, France

Josep Roure-Alcobé University of Mataro, Spain

Ashkan Sami Shiraz University, Iran

Nazha Selmaoui University of New Caledonia (Noumea)

Giovanni Semeraro Universita' degli Studi di Bari, Italy

Xiaowei Shao Tokyo University, Japan

Jialie Shen Singapore Management University, Singapore

Andrzej Skowron Warsaw University, Poland

Mingli Song Hong Kong Polytechnical University, China

Eduardo J. Spinosa University of São Paulo, Brasil

Xingzhi Sun IBM Research, China

Kay Chen Tan National University of Singapore, Singapore

Arthur Tay National University of Singapore, Singapore

Grigorios Tsoumakas Aristotle University, Greece

Ricardo Vilalta University of Houston, USA

Paul Vitanyi CWI, The Netherlands

Guoren Wang Northeastern University, China

Huiqiong Wang City University of Hong Kong, China

Shuliang Wang Wuhan University, China

Wei Wang Fudan University, China

Hau San Wong City University of Hong Kong, China

Dash Wu University of Toronto, Canada

Qingxiang Wu Ulster University, N. Ireland

Zhipeng Xie Fudan University, China

Bingru Yang Beijing Science and Technology University, China

Jingtao Yao University of Regina, Canada

- 5 -

Fusheng Yu Beijing Normal University, China

Jeffrey Xu Yu The Chinese University of Hong Kong, China

Ras Zbyszek University of North Carolina – Charlotte, USA

Sarah Zelikovitz College of Staten Island of CUNY, USA

Jianzhou Zhang Sichuan University, China

Shichao Zhang University of Technology, Sydney, Australia

Tianhao Zhang UPenn, USA

Yang Zhang Northwest A&F University, China

Aoying Zhou East China Normal University, China

Huiyu Zhou Brunel University, UK

Mingquan Zhou Beijing Normal University, China

Shuigeng Zhou Fudan University, China

Xiaofang Zhou University of Queensland (UQ), Australia

Zhi-Hua Zhou Nanjing University, China

Zhanli Zhu Xian Shiyou University, China

External Reviewers Alexandra Carvalho Kelvin Ran Cheng

Alexandre Francisco Kevin Kai Zheng

Ana Cachopo Laurent Gillard

Andre Rossi Linhao Xu

Anna Lisa Gentile Liwei Wang

Asadullah Shaikh Longjiang Guo

Bingru Yang Marc Plantevit

Bruno Feres de Souza Marcio Basgalupp

Cataldo Musto Marcos A. Domingues

Claudia Antunes Max Pereira

Dino Ienco Micky Eunjun Chin

Dominique Gay Mona Alkhattabi

Elena Roglia Murilo Naldi

Felix Qing Xie Nattapon Harnsamut

Frédéric Flouvat Nicola Stokes

Francois Rioult Nuno Escudeiro

Geoffrey Macintyre Nuno Fonseca

George Tzanis Rajkumar Gaire

Ghim-Eng Yap Ruggero Pensa

Henning Koehler Sara Madeira

Huangliang Sun Shuo Shang

Huining Qiu Sophia Alim

Ioannis Katakis Sophie Aubin

Ioannis Partalas Thierry Charnois

- 6 -

Jia Rong Xiaoshi Yin

Jia Zhu Xiaoyan Liu

Jinlong Wang Xiaoyuan Wang

João M. Moreira Xing Jiang

Jonathan Ortigosa Xuan-Hong Dang

Jose Luis Flores Yiping Ke

Jun He Yongli Ren

Keien Liu Zaiben Chen

Kein Xie Zhipeng Cai

- 7 -

ORGANIZING COMMITTEE

Local Organization Co-Chair Guangzuo Cui Beijing Normal University, China

Yushun Li Beijing Normal University, China

Fusheng Yu Beijing Normal University, China

Publicity Co-Chair Ying Zhou Beijing Normal University, China

Finance Chair Ping Li Beijing Normal University, China

Registration Chair Lanqin Zheng Beijing Normal University, China

Web Master Jiangjian Ma Beijing Normal University , China

Ying Yuan Beijing Normal University , China

Sponsoring Institutions National Science Foundation of China, China

School of Educational Technology, Beijing Normal University, China

- 8 -

KEYNOTE SPEAKERS

Edward Y. Chang Director of Research, Google China Edward Chang joined the department of Electrical & Computer Engineering at

University of California, Santa Barbara, in September 1999. Ed received his

tenure in March 2003, and was promoted to full professor of Electrical

Engineering in 2006. His recent research activities are in the areas of

distributed data mining and their applications to rich-media data management

and social-network collaborative filtering. His research group (which consists

of members from UC, MIT, Tsinghua, PKU, and Google) recently parallelized

SVMs (NIPS 07), PLSA (KDD 08), Association Mining (ACM RS 08),

Spectral Clustering (ECML 08),

and LDA (WWW 09) (see MMDS/CIVR keynote slides for details) to run on thousands of machines for mining

large-scale datasets. Ed has served on ACM (SIGMOD, KDD, MM, CIKM), VLDB, IEEE, WWW, and SIAM

conference program committees, and co-chaired several conferences including MMM, ACM MM, ICDE, and

WWW. Ed is a recipient of the IBM Faculty Partnership Award and the NSF Career Award. He heads Google

Research in China since March 2006. He received his M.S. in IEOR and M.S. in Computer Science from UC

Berkeley and Stanford, respectively; and received his PhD in Electrical Engineering from Stanford University in

1999.

Title: Confucius and "its" Intelligent Disciples

Abstract: Confucius is a great teacher in ancient China. His theories and principles were effectively spread

throughout China by his disciples. Confucius is the product code name of Google Knowledge Search product,

which is built at Google Beijing lab by my team. In this talk, I present Knowledge Search key disciples, which are

machine learning subroutines that generates labels for questions, that matches existing answers to a question, that

evaluates quality of answers, that ranks users based on their contributions, that distills high-quality answers for

search engines to index, etc. I will also present the scalable machine learning services that we built to make these

disciples effective and efficient.

Prof. Charles Ling，Department of Computer Science University of Western Ontario, Canada

Title: From Machine Learning to Child Learning

Abstract: Machine Learning endeavors to make computers learn and

improve themselves over time. It is originated from analyzing human

learning, and is now maturing as computers can learn more effectively

than human for many specific tasks, such as adaptive expert systems and

data mining. The effective and fruitful research in machine learning can

now be used to improve our thinking and and learning, especially for our

children. In this talk, I will discuss my efforts in using machine learning

(and AI) for child education in Canada and China. In early 2009,I hosted a TV series (天才孩子家家有) in a major talk show in China (湖湘讲堂). The impact of

such work in China and around the world can be huge.

- 9 -

- 10 -

e election

as the UCI, the 99 KDD

ted.

ing，Associate Professor ,the University of Technology , Sydney (UTS), Australia

itle: Data Mining in Financial Markets

Daniel S. Yeung，Professor, the School of Computer Science and Engineering, South China university of Technology, Guangzhou, China

Title: Sensitivity Based Generalization Error for Supervised Learning Problems with Application in FeaturS Abstract: Generalization error model provides a theoretical support for a

classifier's performance in terms of prediction accuracy. However, existing models

give very loose error bounds. This explains why classification systems generally

rely on experimental validation for their claims on prediction accuracy. In this talk we will revisit this problem

and explore the idea of developing a new generalization error model based on the assumption that only prediction

accuracy on unseen points in a neighbourhood of a training point will be considered, since it will be unreasonable

to require a classifier to accurately predict unseen points "far away" from training samples. The new error model

makes use of the concept of sensitivity measure for multiplayer feedforward neural networks (Multilayer

Perceptrons or Radial Basis Function Neural Networks). The new model will be applied to the feature reduction

problem for RBFNN classifiers. A number of experimental results using datasets such

Cup, and text categorization, will be presen

Cao Longb

T Abstract: The ongoing global financial recession has dramatically

affected public confidence and market development. An example is the

market manipulation schemes hidden in capital markets, which have

caused losses in billions of dollars, dramatically damaging public

confidence and contributing to the global financial and credit crisis. While

most investors lost during market falls, for instance, sophisticated

speculators can manipulate markets to make money by illegally using a

variety of maneuvering techniques such as wash sales. With financial

globalization, manipulators are becoming increasingly imaginative

and professional, employing creative tactics such as using many nominee accounts at different broker-dealers.

However, regulators currently are short on effective technology to promptly identify abnormal trading behavior

related to complex manipulation schemes. As a result, shareholders are complaining that too few market

manipulators were being caught. In this talk, I will discuss issues related to this topic, present case studies and

lessons learned in identifying abnormal trading behavior in capital markets. I will discuss the use of data mining

techniques in this area such as activity mining, combined mining, adaptive mining and domain-driven data mining.

Program Overview

Sunday 16th August

08:30 - 16:00 Registration [Jingshi Building]

Monday 17th August

09:00 - 09:20 Opening Ceremony [Lecture Hall, Yingdong Conference Hall]

09:20 - 10:20 Keynote speech [Lecture Hall] Title: Confucius and "its" Intelligent Disciples Speaker: Edward Y. Chang Chair: Jian Pei

10:20 - 10:40 Photograph Session [In front of Yingdong Conference Hall]

10:40 - 11:00 Tea break [Second floor, Yingdong Conference Hall]

11:00 - 12:00 Session 1 Social networks [Lecture Hall, Yingdong Conference Hall]

Session 2 Text mining [Lecture Room2, Yingdong Conference Hall]

Session 3 Clustering [LectureRoom3, Yingdong Conference Hall]

12:00 - 13:30 Lunch [Buyanfang Restaurant, Eighth Floor, Jingshi Building]

13:30 - 14:30 Keynote speech [Lecture Hall, Yingdong Conference Hall] Title: From Machine Learning to Child Learning Speaker: Charles Ling Chair: Qiang Yang

14:40 - 15:40 Session4 Document clustering

[Lecture Hall] Session5 Tag and social community

mining [LectureRoom2] Session6 Bioinformatics applications

[LectureRoom3]

15:40 - 16:00 Tea break [Second floor, Yingdong Conference Hall]

16:00 - 18:00 Session 7 Spatial mining and OLAP

[Lecture Hall] Session 8 Web search and text

[LectureRoom2] Session 9 Machine learning

[LectureRoom3]

- 11 -

- 12 -

Tuesday 18th August

08:30 - 09:30 Keynote speech [Lecture Hall] Title: Sensitivity Based Generalization Error for Supervised Learning Problems with Application in Feature Selection Speaker: Daniel S. Yeung Chair: Guangzuo Cui

09:30 - 10:00 Tea break [Second floor, Yingdong Conference Hall]

10:00 - 12:00 Session 10 Classification

[Lecture Hall] Session 11 Novel applications

[LectureRoom2] Session 12 Classification and text

mining Ⅰ [LectureRoom3] 12:00 - 13:30 Lunch [Buyanfang Restaurant, Eighth Floor, Jingshi Building]

13:30 - 14:30 Keynote speech [Lecture Hall] Title: Data Mining in Financial Markets Speaker: Longbing Cao Chair: João Gama

14:40 - 15:40 Session 13 Similarity

[Lecture Hall] Session 14 Networks and applications

[LectureRoom2] Session 15 Sequence

[LectureRoom3] 15:40 - 16:00 Tea break [Second floor, Yingdong Conference Hall]

16:00 - 18:00 Visting National Lab in BNU

18:00 - 20:30 Banquet [LAN HUI RESTAURANT]

Wednesday 19th August

08:20 - 10:20 Session 16 Privacy, spam and

anomaly detection [Lecture Hall ] Session 17 Classification and text

mining Ⅱ [LectureRoom2] Session 18 Pattern mining and XML

[LectureRoom3]

10:20 - 10:40 Tea break [Second floor, Yingdong Conference Hall]

10:40 - 11:50 Panel [Lecture Hall] Title: What's HOT in Data Mining? Chair: Charles X. Ling

11:50 - 12:10 Closing Ceremony [Lecture Hall]

Technical Program

Session 1 Social networks (3 papers) Session Chair: Jian Pei, Simon Fraser University, Vancouver [Aug. 17th 11:00~12:00 Lecture Hall ] 401 Virus Propagation and Immunization Strategies

in Email Networks Jiming Liu; ChaoGao; Ning Zhong

Full

402 A Potential-based Node Selection Strategy for Influence Maximization in a Social Network

Yitong Wang; Xiaojun Feng

Full

386 Social Influence and Role Analysis based on Community Structure in Social Network

Tian Zhu; Bin Wu; Bai Wang

Short

Session 2 Text mining (3 papers) Session Chair: Guangzuo Cui, Beijing Normal University, Beijing [Aug. 17th 11:00~12:00 Lecture Room2]

375 A Semi-supervised Topic-driven Approach for Clustering Textual Answers to Survey Questions

Hui Yang; Ajay Mysore; Sharonda Wallace

Full

376 A Hybrid Statistical Data Pre-processing Approach for Language-independent Text Classification

Yanbo J. Wang; Frans Coenen; Robert Sanderson

Full

369 Combining Statistical Machine Learning Models to Extract Keywords from Chinese Documents

Chengzhi Zhang Short

Session 3 Clustering (3 papers) Session Chair: Christoph F. Eick, University of Houston, Houston [Aug. 17th 11:00~12:00 Lecture Room3]

272 Cluster analysis based on the central tendency deviation principle

Julien Ah-Pine Full

215 GOD-CS: A New Grid-Oriented Dissection Clustering Scheme for Large Databases

Cheng-Fa Tsai; Chien-Sheng Chiu

Full

77 Initialization of the Neighborhood EM Algorithm for Spatial Clustering

Tianming Hu; Ji Ouyang; Chao Qu; Chuanren Liu;

Short

Session 4 Document clustering (3 papers) Session Chair: Qiang Yang, Hong Kong University of Science and Technology, Hong Kong [Aug. 17th 14:40~15:40 Lecture Hall ]

290 A Parallel Hierarchical Agglomerative Rayner Alfred Full

- 13 -

Clustering Technique for Billingual Corpora Based on Reduced Terms with Automatic Weight Optimization

326 Chinese Blog Clustering by Hidden Sentiment Factors

Shi Feng; Daling Wang; Ge Yu; Chao Yang; Nan Yang

Full

225 Incremental Document Clustering Based on Graph Model

Tu-Anh Nguyen- Hoang; Kiem Hoang; Danh Bui-Thi; Anh- Thy Nguyen

Short

Session 5 Tag and social community mining (3 papers) Session Chair: Jian Pei, Simon Fraser University, Vancouver [Aug. 17th 14:40~15:40 Lecture Room2]

87 Automatically Identifying Tag Types Kerstin Bischoff; Claudiu S. Firan; Cristina Kadar; Wolfgang Nejdl; Raluca Paiu

Full

356 A Neighborhood Search Method for Link-Based Tag Clustering

Jianwei Cui; Pei Li; Hongyan Liu; Jun He; Xiaoyong Du

Full

158 JCCM: Joint cluster communities on attribute and relationship data in social networks

Li Wan; Jianxin Liao; Chun Wang; Xiaomin Zhu

Short

Session 6 Bioinformatics applications (3 papers) Session Chair: MingJie Tang, Chinese Academy of Sciences, Beijing [Aug. 17th 14:40~15:40 Lecture Room3]

196 Bayesian Multi-topic Microarray Analysis with Hyperparameter Reestimation

Tomonari Masada; Tsuyoshi Hamada; Yuichiro Shibata; Kiyoshi Oguri

Full

279 A Hybrid Method of Multidimensional Scaling and Clustering for Determining Genetic Influence on Phenotypes

Qiao Li; Wenjia Wang; Alexander MacGregor; George Smith

Short

296 Automating Gene Expression Annotation for Liangxiu Han; Short

- 14 -

Mouse Embryo Jano Van Hemert; Richard Baldock; Malcolm Atkinson

Session 7 Spatial mining and OLAP (6 papers) Session Chair: Stefan Jan Skudlarek, University of Tokyo, Tokyo [Aug. 17th 16:00~18:00 Lecture Hall ]

403 Indexing the Function: An Efficient Algorithm for Multi-dimensional Search with Expensive Distance Functions

Hanxiong Chen; Jianquan Liu; Kazutaka Furuse; Jeffrey Xu Yu; Nobuo Ohbo

Full

274 A Framework for Multi-objective Clustering and its Application to Co-location Mining

Rachsuda Jiamthapthaksin; Christoph F. Eick; Ricardo Vilalta

Full

100 Mining User Position Log for Construction of Personalized Activity Map

Hui Fang; Wen-Jing Hsu; Larry Rudolph

Short

191 CCBitmaps:a Space- Time Efficient Index Structure for OLAP

Weiji Xiao; Jianqing Xi

Short

297 Closed Non Derivable Data Cubes Based on Non Derivable Minimal Generators

Hanen Brahmi; Tarek Hamrouni; Riadh Ben Messaoud; Sadok Ben Yahia

Full

32 Analysis and Experimentation of Grid-based Data Mining with Dynamic Load Balancing

Yong Beom Ma; Tae Young Kim; Seung Hyeon Song; Jong Sik Lee

Short

Session 8 Web search and text (6 papers) Session Chair: Guangzuo Cui, Beijing Normal University, Beijing [Aug. 17th 16:00~18:00 Lecture Room2 ]

263 Crawling Deep Web Using a New Set Covering Algorithm

Yan Wang; Jianguo Lu; Jessica Chen

Full

298 Crawling and Extracting Process Data from the Web

Yaling Liu; Arvin Agah

Short

294 Discovering Knowledge from Multi-relational Data Based on Information Retrieval Theory

Rayner Alfred Short

235 Alleviating Cold-Start Problem by using Implicit Feedback

Lei Zhang; Xiang- Wu Meng; Jun-Liang Chen; Si- Cheng Xiong; Kun Duan

Short

- 15 -

57 Semantic Based Text Classification of Patent Documents to a User-Defined Taxonomy

Ashish Sureka; Pranav Prabhakar Mirajkar; Prasanna Nagesh Teli; Girish Agarwal; Sumit Kumar Bose

Short

206 Predicting Click Rates by Consistent Bipartite Spectral Graph Model

Wensheng Guo; Guohe Li

Short

Session 9 Machine learning (6 papers) Session Chair: João Gama, University of Porto, Porto [Aug. 17th 16:00~18:00 Lecture Room3 ]

325 McSOM: Minimal Coloring of Self-Organizing Map

Haytham Elghazel; Khalid Benabdeslem; Hamamache Kheddouci

Full

404 Semi-supervised Discriminant Analysis Based on Dependence Estimation

Xiaoming Liu; J.Tang; Jun Liu; Zhilin Feng; Zhaohui Wang

Full

93 Nearest Neighbor Tour Circuit Encryption Algorithm Based Random Isomap Reduction

Wei Lu; Zheng-an Yao

Full

405 A Novel Component-based Model and Ranking strategy in Constrained Evolutionary Optimization

Yu WU; Yuanxiang LI; Xing XU

Full

313 An Information-Theoretic Approach for Multi-task Learning

Pei Yang; Qi Tan; Hao Xu; Yehua Ding

Full

64 Transfer Learning with Data Edit Yong Cheng; Qingyong Li

Short

Session 10 Classification (6 papers) Session Chair: Hongmei Wang, Changwon National University, Changwon [Aug. 18th 10:00~12:00 Lecture Hall ]

328 Mining Class Contrast Functions by Gene Expression Programming

Lei Duan; Changjie Tang; Liang Tang; Tianqing Zhang; Jie Zuo

Full

389 Instance Selection by Border Sampling in Multi-Class Domains

Guichong Li; Nathalie Japkowicz; Trevor J. Stocki; R. Kurt Ungar

Full

184 Image Classification Approach Based on Rong Zhu; Short - 16 -

Manifold Learning in Web Image Mining Min Yao; Yiming Liu

152 Orthogonal Centroid Locally Linear Embedding for Classification

Yong Wang; Yonggang Hu; Yi Wu

Short

63 Handling Class Imbalance Problems via Weighted BP Algorithm

Xiaoqin Wang; Huaxiang Zhang

Short

134 Several SVM Ensemble Methods Integrated With Under-sampling for Imbalanced Data Learning

Zhiyong Lin; ZhiFeng Hao; XiaoWei Yang; XiaoLan Liu

Short

Session 11 Novel applications (6 papers) Session Chair: Chuan Shi, Beijing University of Posts and Telecommunications, Beijing [Aug. 18th 10:00~12:00 Lecture Room2 ]

90 Social Knowledge-Driven Music Hit Prediction Kerstin Bischoff ; Claudiu S. Firan; Mihai Georgescu; Raluca Paiu; Wolfgang Nejdl

Full

106 Discovery of Migration Habitats and Routes of Wild Bird Species by Clustering and Association Analysis

Mingjie Tang; YuanChun Zhou; Peng Cui; Weihang Wang; Jinyan Li; Haiting Zhang; YuanSheng Hou; BaoPing Yan

Full

354 Investigation of Damage Identification of 16Mn Steel Based on Artificial Neural Networks and Data Fusion Techniques in Tensile Test

Hongwei Wang; Hongyun Luo; Zhiyuan Han; Qunpeng Zhong

Short

44 Learning from video game: A study of video game play on problem-solving

Xue-Min Zhang; Zijiao Shen; Xin Luo; Chunhui Su; Jiaqi Wang

Short

308 A Predictive Analysis on Medical Data based on Outlier Detection Method using Non-Reduct Computation

Faizah Shaari; Azuraliza Abu Bakar; Abdul Razak Hamdan

Short

222 Evaluating the Impact of Missing Data Imputation

Adam Pantanowitz; Tshilidzi Marwala

Short

- 17 -

Session 12 Classification and text mining Ⅰ Session Chair: Yang Zhang, Northwest A&F University, Yangling [Aug. 18th 10:00~12:00 Lecture Room3 ]

171 Feature selection in marketing applications Stefan Lessmann; Stefan Voß

Full

175 A Local Density Approach for Unsupervised Feature Discretization

ShengYi Jiang; Wen Yu

Short

174 Asymmetric Feature Selection for BGP Abnormal Events Detection

Yuhai Liu; Lintao Ma; Ning Yang; Ying He

Short

43 A Theory of Kernel Extreme Energy Difference for Feature Extraction of EEG Signals

Shiliang Sun; Jinbo Li

Short

244 Feature Selection Method Combined optimized Document Frequency with Improved RBF Network

Hao- Dong Zhu; Xiang- Hui Zhao; Yong Zhong

Short

311 A Multi-Strategy Approach to KNN and LARM on Small and Incrementally Induced Prediction Knowledge

JuiHsi Fu; SingLing Lee

Short

Session 13 Similarity (3 papers) Session Chair: João Gama, University of Porto, Porto [Aug. 18th 14:40~15:40 Lecture Hall ]

305 Collaborative Filtering Recommendation Algorithm Using Dynamic Similar Neighbor Probability

Chuangguang Huang; Jian Yin; Jing Wang; Lirong Zheng

Full

299 Calculating Similarity Efficiently in a Small World

Xu Jia; Yuanzhe Cai; Hongyan Liu; Jun He;Xiaoyong Du

Full

315 Quantitative comparison of Similarity Measure and Entropy for fuzzy sets

Hongmei Wang; Sanghyuk Lee; Jaehyung Kim

Short

Session 14 Networks and applications (3 papers) Session Chair: Liangxiu Han, University of Edinburgh, Edinburgh [Aug. 18th 14:40~15:40 Lecture Room2 ]

160 Mining the Structure and Evolution of the Airport Network of China over the Past Twenty Years

Zhengbin Dong; Wenjie Wu; Xiujun Ma; Kunqing Xie; Fengjun Jin

Full

170 Anti-germ Performance Prediction for Anqi Cui; Full - 18 -

Detergents Based on Elman Network on Small Data Sets

Hua Xu; Peifa Jia

408 VisNetMiner: An Integration Tool for Visualization and Analysis of Networks

Chuan Shi; Dan Zhou; Bin Wu; Jian Liu

Short

Session 15 Sequence (3 papers) Session Chair: Stefan Jan Skudlarek, University of Tokyo, Tokyo [Aug. 18th 14:40~15:40 Lecture Room3 ]

320 Discovery of Correlated Sequential Subgraphs from a Sequence of Graphs

Tomonobu Ozaki; Takenao Ohkawa

Full

398 Mining Compressed Repetitive Gapped Sequential Patterns Efficiently

Yongxin Tong; Li Zhao; Dan Yu; Shilong Ma; Zhiyuan Cheng; Ke Xu

Short

135 Online New Event Detection based on IPLSA Xiaoming Zhang; Zhoujun Li

Full

Session 16 Privacy, spam and anomaly detection (6 papers) Session Chair: Liangxiu Han, University of Edinburgh, Edinburgh [Aug. 19th 8:30~10:30 Lecture Hall ]

349 Study on Ensemble Classification Methods towards Spam Filtering

Jinlong Wang; Ke Gao; Yang Jiao; Gang Li

Full

203 Semi Supervised Image Spam Hunter: a Regularized Discriminant EM Approach

Yan Gao; Ming Yang; Alok Choudhary

Full

99 An Outlier Detection Algorithm Based on Arbitrary Shape Clustering

Xiaoke Su; Yang Lan; Renxia Wan; Yuming Qin

Short

173 A Secure Protocol to Maintain Data Privacy in Data Mining

Fodé Camara; Samba Ndiaye; Yahya Slimani

Short

351 Privacy-preserving Distributed k- Nearest Neighbor Mining on Horizontally Partitioned Multi-party Data

Feng Zhang; Gansen Zhao; Tingyan Xing

Short

282 Anomaly Detection Using Time Index Differences of Identical Symbols with and without Training Data

Stefan Jan Skudlarek; Hirosuke Yamamoto

Short

- 19 -

Session 17 Classification and text mining Ⅱ (6 papers) Session Chair: Bingru Yang, University of Science and Technology, Beijing [Aug. 19th 8:30~10:30 Lecture Room2 ]

217 Building a Text Classifier by a Keyword and Wikipedia Knowledge

Qiang Qiu; Yang Zhang; Junping Zhu; Wei Qu

Full

302 OFFD: Optimal Flexible Frequency Discretization for Naive Bayes Classification

Song Wang; Fan Min; Zhihai Wang; Tianyu Cao

Short

192 Classification Techniques for Talent Forecasting in Human Resource Management

Hamidah Jantan; Abdul Razak Hamdan; Zulaiha Ali Othman

Short

147 A Combination Classification Algorithm Based on Outlier Detection and C4.5

ShengYi Jiang; Wen Yu

Short

327 Discovery of Significant Classification Rules from Incrementally Inducted Decision Tree Ensemble for Diagnosis of Disease

Minghao Piao; Jong Bum Lee; Khalid E.K.Saeed; Keun Ho Ryu

Short

88 Application of the Cross-Entropy Method to Dual Lagrange Support Vector Machine

Budi Santosa Short

Session 18 Pattern mining and XML (6 papers) Session Chair: Jiaheng Lu, Renmin University, Beijing [Aug. 19th 8:30~10:30 Lecture Room3 ]

257 Mining Frequent Patterns from Network data flow

Xin Li; Zhi- Hong Deng; Hao Ma; Shi-Wei Tang; Bei Zhang

Short

312 Structure Correlation in Mobile Call Networks Deyong Hu; Bin Wu; Qi Ye; Bai Wang

Short

59 Exploiting Temporal Authors Interests via Temporal-Author-Topic Modeling

Ali Daud; Juanzi Li; Lizhu Zhou; Faqir Muhammad

Short

384 Mining Candlesticks Patterns on Stock Series: A Fuzzy Logic Approach

Mario Linares Vásquez; Fabio Augusto Gonz á lez Osorio Diego Fernando Hernández Losada

Short

- 20 -

330 Similarity Evaluation of XML Documents Based on Weighted Element Tree Model

Chenying Wang; Xiaojie Yuan; Hua Ning; Xin Lian

Short

300 Rewriting XPath Expressions Depending on Path Summary

Xiaoshuang Xu; Yucai Feng; Feng Wang; Yingbiao Zhou

Short

The Panel Chair: Charles X. Ling, University of Western Ontario, London [Aug. 19th 10:40~11:50 Lecture Hall ]

The title of the panel What's HOT in Data Mining?

Panelists Charles X. Ling; Qiang Yang; Longbing Cao; João Gama

- 21 -

The Map Of Beijing Normal University

How to go to the conference site

The following paragraphs are the routes from the Beijing International Airport to the conference venue (Beijing Normal University). You can choose any one to arrive at the destination: First: You can take the Airport Bus to “Beitaipingzhuang” bus-station first (about RMB16), and then take a taxi to Beijing Normal University (about RMB10). The airport bus starts from the airport each 30 minutes. Second: You can take a taxi directly. You would spend about RMB100 from the Airport to the University.

- 22 -

- 23 -

The Map of Beijing Normal University

- 24 -