program - adma 2017 2017-program.pdfkeynote speech i: on application-aware information extraction...

http://www.adma2017.net/

Program

The 13th International Conference on Advanced Data

Mining and Applications (ADMA)

Collocated with

The 26th ACM International Conference on Information

and Knowledge Management (CIKM)

Singapore, 5-6 November 2017

1 |Page


Conference Venue

NTU Alumni House at Marina Square

6 Raffles Boulevard, #02-27/28, Marina Square Shopping Mall, Singapore 039594

2 |Page


TABLE OF CONTENT

ORGANIZATION .................................................................................................................. 3

KEYNOTES ......................................................................................................................... 7

INDUSTRY TALKS ............................................................................................................ 10

CONFERENCE PROGRAM .............................................................................................. 14

CONFERENCE DAY 1 ...................................................................................................... 15

CONFERENCE DAY 2 ...................................................................................................... 19

MAP ................................................................................................................................... 23

SPONSORSHIP ................................................................................................................. 24

ADMA 2017

The 13th International Conference on Advanced Data Mining and Applications aims at

bringing together the experts on data mining from all over the world, and provides an

international forum for the dissemination of original research results in data mining,

spanning applications, algorithms, software and systems, and different applied disciplines

with potentials in data mining, such as social media and social network mining, bio-

medical science, green computing, and smart nation applications. ADMA will promote the

same close interaction and collaboration among practitioners and researchers.

CIKM 2017 CIKM is a premier forum for research on topics at the confluence of information retrieval,

data management, and knowledge management. This year, CIKM highlights

technologies and insights that materialize the “Smart Cities, Smart Nations” vision

shared by many urban areas and their countries, while it brings together international and

Singapore technology providers and seekers to explore technology and business

collaboration opportunities through open innovation.

3 |Page


ADMA 2017 General Chairs Aixin Sun, Nanyang Technological University

Hady Lauw, Singapore Management University

Program Chairs Gao Cong, Nanyang Technological University

Wen-Chih Peng, National Chiao Tung University

Proceedings Chairs Chenliang Li, Wuhan University Wei Emma Zhang, Macquarie University

Publicity Chairs Ju Fan, Renmin University of China Hongzhi Yin, University of Queensland

Special Issue Chairs Michael Sheng, Macquarie University Xiuzhen Zhang, RMIT University

Local Arrangement Chairs David Lo, Singapore Management University Zhen Hai, Institute for Infocomm Research, A*STAR

Registration Chair Victor Chu, Nanyang Technological University

4 |Page


Demo Chairs Zhifeng Bao, RMIT University

Xin Cao, The University of New South Wales

Awards Committee Chair Xiaoli Li, Institute for Infocomm Research, A*STAR

Web Chair Yihong Zhang, Nanyang Technological University

Steering Committee Xue Li, University of Queensland, Australia (Chair) Jie Cao, Nanjing University of Finance and Economics, China Michael Sheng, Macquarie University, Australia Jie Tang, Tsinghua University, China Shuliang Wang, Beijing Institute of Technology, China Kyu-Young Whang, Korea Advanced Institute of Science and Technology, Korea Min Yao, Zhejiang University, China Osmar Zaiane, University of Alberta, Canada Chengqi Zhang, University of Technology Sydney, Australia Shichao Zhang, Guangxi Normal University, China

Program Committee

Swati Agarwal, IIIT-Delhi

Djamal Benslimane, Lyon 1 University

Tossapon Boongoen, Mae Fah Luang University

Yi-Shin Chen, National Tsing Hua University

Lisi Chen, Hong Kong Baptist University

Yuan Fang, Institute for Infocomm Research

Kaiyu Feng, Nanyang Technological University

Philippe Fournier-Viger, Harbin Institute of Technology Shenzhen Graduate School

Tao Guo, Nanyang Technological University

Jialong Han, Nanyang Technological University

Bryan Hooi, Carnegie Mellon University

Wei Hu, Nanjing University

Guangyan Huang, Deakin University

Chih-Chieh Hung, Tamkang University

5 |Page


Shafiq Joty, University of British Columbia

Jianxin Li, University of Western Australia

Xutao Li, Harbin Institute of Technology

Haiquan Li, University of Arizona

Cheng-Te Li, National Cheng Kung University

Jinyan Li, University of Technology Sydney

Gang Li, Deakin University

Guosheng Lin, Nanyang Technological University

Bin Liu, IBM Thomas J. Watson Research Center

Cheng Long, Queen's University Belfast

Xudong Luo, Guangxi Normal University

Marco Maggini, University of Siena

Toshiro Minami, Kyushu Institute of Information Sciences and Kyushu University

Yasuhiko Morimoto, Hiroshima University

Gunarto Sindoro Njoo, National Chiao Tung University

Tuan Anh Pham, Nanyang Technological University

Hai Phan, University of Oregon

Tieyun Qian, Wuhan University

Yongrui Qin, University of Huddersfield

Wenjie Ruan, University of Oxford

Dharmendra Sharma, University of Canberra

Michael Sheng, Macquarie University

Hyun Ah Song, Carnegie Mellon University

Guojie Song, Peking University

Eiji Uchino, Yamaguchi University

Xianzhi Wang, Singapore Management University

Hongzhi Wang, Harbin Institute of Technology

Qinsi Wang, Carnegie Mellon University

Chenguang Wang, IBM Research

Wei Wei, Huazhong University of Science and Technology

Yu-Ting Wen, National Chiao Tung University

Feng Xia, Dalian University of Technology

Zhipeng Xie, Fudan University

Guandong Xu, University of Technology Sydney

Hui-Gwo Yang, National Chiao Tung University

Zijiang Yang, York University

Dezhong Yao, Nanyang Technological University

Lina Yao, The University of New South Wales

6 |Page


Qi Yu, Rochester Institute of Technology

Quan Yuan, University of Illinois at Urbana-Champaign

Guang Lan Zhang, Boston University

Wei Emma Zhang, Macquarie University

Shichao Zhang, Guangxi Normal University

Kaiqi Zhao, Nanyang Technological University

Yong Zheng, Illinois Institute of Technology

Xiaofeng Zhu, Guangxi Normal University

Demo Program Committee

Yingke Chen, Sichuan University

Xin Huang, Hong Kong Baptist University

Yuchen Li, National University of Singapore

Xutao Li, Harbin Institute of Technology, Shen Zhen

Hua Mao, Sichuan University

Ryan McConville, Bristol University, UK

Ruiming Tang, Huawei Noah Ark lab

Qingyao Wu, South China University of Technology

Jianqiu Xu, Nanjing University of Aeronautics and Astronautics

Yi Yu, National Institute of Informatics, Japan

Chao Zhang, University of Illinois at Urbana-Champaign

Zhiwei Zhang, Hong Kong Baptist University

Yuxin Zheng, Tencent

Jingbo Zhou, Baidu Research

7 |Page


Sunday 5 Nov 2017, 8:30am-9:30am

Keynote Speech I: On Application-Aware Information Extraction for Big Data in Social Networks

Due to the paradigm shift to the Cloud computing, data has been accumulated at fast pace in various

applications. Among others, the number of social network activities is increasing drastically. It has

become very desirable to conduct various analyses for applications on social networks. However, as

the scale of a social network has become prohibitively large, it is infeasible to scrutinize the data and

extract the key essence from the entire social network. This issue becomes further complicated due

to the heterogeneous nature of the data. As a result, a significant amount of research effort has been

elaborated upon extracting the essential application-dependent information from a social network. In

this talk, we shall examine some recent studies on data processing and information extraction for

social networks. Explicitly, we shall explore the methods for three levels of information extraction in a

social network, namely, parameter extraction, information extraction, and structure extraction, and

interpret them from their respective objectives. We then comment on how to conduct application-

aware information extraction for big data in social networks.

Ming-Syan Chen received the Ph.D. degrees in Computer,

Information and Control Engineering from The University of Michigan,

Ann Arbor, MI, USA. He is now an NTU Chair Professor and also the

Dean of the College of Electrical Engineering and Computer Science

at National Taiwan University. He was a research staff member at

IBM Thomas J. Watson Research Center, NY, USA, the

President/CEO of Institute for Information Industry (III), and the

Director of Research Center of Information Technology Innovation

(CITI) in the Academia Sinica. His research interests include

databases, data mining, social networks, and IoT applications. He is a recipient of the National Chair

Professorship and also the Academic Award of the Ministry of Education, the NSC (National Science

Council) Distinguished Research Award, Y.Z. Hsu Science Chair Professor Award, Pan Wen Yuan

Distinguished Research Award, Teco Award, Honorary Medal of Information, and K.-T. Li Research

Breakthrough Award for his research work, and also the Outstanding Innovation Award from IBM

Corporate for his contribution to a major database product. Dr. Chen is a Fellow of ACM and a Fellow

of IEEE.

8 |Page


Sunday 5 Nov 2017, 9:30am-10:30am

Keynote Speech II: I’m Telling You - You Ain’t the Only One Who Needs MapReduce Algorithms!

There is a growing trend of applications including Internet-of-Things (IoT) that should handle big data.

For such applications, the MapReduce framework has recently attracted a lot of attention. Google’s

MapReduce or its open-source equivalent Hadoop is a powerful tool for building applications to deal

with big data. MapReduce is a programming model that allows easy development of scalable parallel

applications to process big data on large clusters of commodity machines. I will introduce Hadoop

MapReduce available to everyone and present how to design efficient MapReduce algorithms for big

data analysis based on my experiences. Since Spark is recently developed to overcome the

shortcomings of MapReduce which it is not optimized for iterative algorithms, I will finally discuss

Spark.

Kyuseok Shim is currently a professor at electrical and computer

engineering department in Seoul National University, Korea. Before

that, he was an assistant professor at computer science department in

KAIST and a member of technical staff for the Serendip Data Mining

Project at Bell Laboratories. He was also a member of the Quest Data

Mining Project at the IBM Almaden Research Center. Kyuseok has

been working in the area of databases focusing on data mining,

search engines, recommendation systems, MapReduce algorithms,

privacy preservation, query processing and query optimization. His

writings have appeared in a number of professional conferences and journals including ACM, VLDB

and IEEE publications. He served as a Program Committee Co-Chair for PAKDD 2003, WWW 2014,

ICDE 2015 and APWeb 2016. Kyuseok was previously on the editorial board of VLDB as well as

IEEE TKDE Journals. He was named an ACM Fellow for his contributions to scalable data mining and

query processing research in 2013. He is currently a member of the VLDB Endowment Board of

Trustees and a steering committee member of PAKDD as well as DASFAA conferences.

9 |Page


Monday 6 Nov 2017, 8:30am-9:30am

Keynote Speech III: LAMP and GENIE: Just-in-Time Model Construction for Predictive Traffic Analytics

Traffic situations are often dynamic and predictive models constructed for traffic analytic can often be

outdated by the time sufficient data are collected to construct them. In this talk, we will look at LAMP

and GENIE, a system that we built to support just-in-time model construction over dynamically

changing data. LAMP (semi-LAzy Mining Paradigm) is a new data mining paradigm for predictive

analytics. Instead of pre-computing big, complex models, LAMP build small, local prediction model

during prediction time. This is done by dynamically searching for data that are representative of the

existing situation and then building a model from the selected data. To facilitate the efficient search of

data from a huge database, we build GENIE (GEneric InvErted index), a unified framework to support

storage and retrieve of Big Data with various types of structure. GENIE is developed to leverage on

the ever growing parallel processing power of Graphics Processing Units (GPUs) to support efficient

search. By utilizing the efficient search engine of GENIE, we are able to ensure that LAMP is efficient

enough for dynamic car trajectories prediction. In the talk, we will also look at some of our ongoing

work on traffic analytics including traffic visualization, obstacle detection and intention analysis.

Information on LAMP and GENIE is available at http://www.comp.nus.edu.sg/~atung/gl/ .

Dr Anthony K. H. Tung is currently an Associate Professor in the

Department of Computer Science, National University of Singapore

(NUS). He received both his B.Sc.(2nd Class Honour) and M.Sc. in

computer sciences from the National University of Singapore in 1997 and

1998 respectively. In 2001, he received the Ph.D. in computer sciences

from Simon Fraser University (SFU). Dr Anthony Tung main research

areas are on searching, mining and visualizing complex data. More

recently, he also looks into the creation of innovative big data

applications over the data processing techniques that he had developed

over the past 18 years. Anthony is also the deputy director of NUS SeSaMe research center

(http://sesame.comp.nus.edu.sg/).

10 |Page


Monday 6 Nov 2017, 9:30am-10:00am

Industry Talk I: Data Mining-based Cost Optimisation for Electricity Retailers

Singapore’s electricity market will be fully liberalised in 2018. With more than 25 electricity retailers,

there will be adoption of various new business models and technologies, which will benefit end-

consumers. In this talk, we will highlight AI / machine learning / data mining techniques for cost

optimisation, which can help these electricity retailers gain competitive advantage. We will give real-

world examples of their business problems, data mining objectives, and types of energy and

maintenance use cases.

Dr Phua Chun Wei Clifton is at NCS Group, working on artificial intelligence, machine learning, and

advanced analytics under NCS Digital. He leads a team of more than 30 highly capable data

scientists, and mentor them in their activities. In his free time, Clifton volunteers professional services

to events, conferences, and journals (related to data mining/analytics, security and health informatics).

Was also part of teams which won some analytics competitions. His specialization was Big Data

analytics in public security (attack and disaster preparation/recovery/response; cyber security; internal

security; and predictive policing) and fraud (government, banking, and insurance).

11 |Page


Monday 6 Nov 2017, 10:00am-10:30am

Industry Talk II: Advancing Ensembles for Population Data Mining

Ensembles remain the model builder of choice for data miners in real world applications. Since the

introduction of the concept in the 1980's they have proven to be a reliable modeller of first choice, with

variations to the algorithms advancing over the years, from random forests through to extreme

gradient boosted trees. Indeed, even neural networks can be viewed within an ensemble framework.

However, a focus within data mining has remained on building point (ensemble) models in business

applications. The advent of general access to massive compute over massive data, as now available

through cloud services, has benefited the application of neural network algorithms which are data and

compute hungry. We have an opportunity now to also consider the case for data and compute hungry

massive ensemble modelling. In this presentation I will review the ensemble landscape and share the

ensemble driven concept of data genetics using massive ensembles over customer populations as a

new approach for data mining, utilising the massive compute and data now available.

Dr Graham Williams recently joined Microsoft as Director of Data Science Asia/Pacific after over 30

years as researcher, developer and educator in Artificial Intelligence, Machine Learning, Data Mining,

Analytics and Data Science. He was previously lead Data Scientist for the Australian Government’s

Center of Excellence in Data Analytics, Director of Data Science at the Australian Taxation Office,

and Principal Research Scientist with CSIRO Australia. Over 30 years he has also been an active

contributor to the Open Source ecosystem with open source software projects across Data Mining,

Data Science, and R. Graham has authored many books, papers, Internet resources and software

packages for data mining. His latest book released in July 2017 introduces the Essentials of Data

Science. His research contributions have included developing the concept of ensembles of models

through Ensemble Decision Tree Induction (1989), HotSpots for identifying target areas in very large

data collections (1992), WebDM data mining as a service (1995), and Rattle as a simple to use

Graphical User Interface for data mining using R (2005).

12 |Page


Monday 6 Nov 2017, 11:00am-11:30am

Industry Talk III: Personalised News and Video Recommendation System at LinkSure

In recent years, the Internet industry has shifted more and more towards digital content distribution

through online services. In this talk we overview the overall system design and architecture of

LinkSure News and Video Recommendations, the challenges encountered in practice, and the

lessons learned from the production deployment of these systems at LinkSure. Specifically, we will

highlight how news selection and personalisation of recommendations are formulated and addressed

at LinkSure. By presenting our experiences of applying techniques at the intersection of

recommender systems, information retrieval, machine learning, and statistical modelling in a large-

scale industrial setting and highlighting the open problems, we hope to stimulate further research and

collaborations.

Dr Rubing Duan is the director of big data department at LinkSure (the leading company of internet

access services) and a manager of the Asia Big Data Association. He received B.Sc. in computer

science from National University of Defence Technology, China, M.Sc. in data science from Central

South University, China, Ph.D. in data mining and distributed computing from the University of

Innsbruck, Austria. Previously, he has worked as a postdoctoral research fellow at the University of

Souther California, USA. His main research interests include recommender system, quantitative

analysis and strategies, deep learning, large-scale computing system, etc. In last few years, his team

has won more than 10 prodigious awards and achievements (funded by Rakuten, SingTel, IEEE,

ACM etc.) in the area of big data models and algorithms.

13 |Page


Monday 6 Nov 2017, 11:30am-12:00pm Industry Talk IV: Innovation Opportunities in the Logistics Industry

Learn about DHL’s trend research approach as well as how it applies cutting edge technologies such

as robotics, augmented reality, IOT and analytics to meet the evolving needs of the supply chain

industry.

Timothy Kooi is currently an Innovation Leader at the DHL’s Innovation Center, where he is

responsible for trend research and converting new trends into proof-of-concepts. He is also the Head

of Data Analytics for the Customer Solutions and Innovation BU for the region, responsible for

deepening the use of data analytics to generate new value-add and business growth opportunities.

Prior to DHL, he was the Asia-Pacific Head of development and profitability for the Burger King Brand.

He was also with EDBI, the strategic investment arm of the Singapore Economic Development Board

(EDB) for a number of years, focused on Singapore-based investments. He started out his career

with the EDB with their Logistics industry development group.

Monday 6 Nov 2017, 12:00pm-12:30pm Industry Talk V: AI in Healthcare - Opportunities and Challenges from a Health System’s Perspective

Artificial intelligence and its application in healthcare industry are gaining momentum in the past two

years. We are going to talk about the challenges we face and opportunities we see in developing and

deploying AI-driven solutions to improve clinical outcome, operation efficiency and reduce cost of care.

Sijia Wang is team lead from Health Insights Department, Integrated Health Information

Systems(IHiS). Sijia currently lead hospital data science projects and data science competency

center. IHiS is the technology agency of Ministry of Health Holdings Singapore with mission to

digitize, connect and analyze Singapore’s health ecosystem.

14 |Page


7:00pm - 9:00pm Saturday 4 Nov 2017 Reception at Conference Venue

Time Sunday 5 Nov 2017 Monday 6 Nov 2017

07:30am -

08:10am

Registration

Conference Venue

08:10am -

08:30am

Opening Session

Basil 1&2&3

Registration

Conference Venue

08:30am -

09:30am

Keynote I

On Application-Aware Information Extraction for Big Data in Social Networks

Prof. Ming-Syan Chen

Basil 1&2&3

Keynote III

LAMP and GENIE: Just-in-Time Model Construction for Predictive Traffic Analytics

Prof. Anthony K. H. Tung

Basil 1&2&3

09:30am -

10:30am

Keynote II

I’m Telling You - You Ain’t the Only One Who Needs MapReduce Algorithms!

Prof. Kyuseok Shim

Basil 1&2&3

Industry Talk I by Dr Phua Chun Wei Clifton

Industry Talk II by Dr Graham Williams

Basil 1&2&3

10:30am -

11:00am

Morning Tea

Conference Venue

Morning Tea

Conference Venue

11:00am -

12:30pm

Session 1-1 Machine Learning

Basil 3

Session 1-2 Social Network and Social Media Mining

Basil 2

Industry Talk III by Dr Rubing Duan

Industry Talk IV by Timothy Kooi

Industry Talk V by Sijia Wang

Basil 1&2&3

12:30pm -

01:30pm

Lunch

Conference Venue

Demo Session 1

Basil 1

Lunch

Conference Venue

01:30pm -

03:00pm

Session 2-1 User Behavior

and Profile Analysis

Basil 3

Session 2-2 Medical Informatics

Basil 2

Session 4-1 Text Mining and Natural Language Processing

Basil 3

Session 4-2 Distributed and High

Performance Computing

Basil 2

03:00pm -

03:30pm

Afternoon Tea

Conference Venue

Demo Session 2

Basil 1

Afternoon Tea

Conference Venue

03:30pm -

05:10pm

Session 3-1 Data Mining Algorithms

Basil 3

Session 3-2 Recommendation Systems

Basil 2

Session 5-1 Data Mining Applications

Basil 3

Session 5-2 Smart Nation Applications

Basil 2

07:00pm -

09:00pm

Conference Diner

Mortar Restaurant & Bar

Conference Banquet and Award Function

Marina Mandarin Singapore

15 |Page


Sunday 5 Nov 2017 – ADMA NTU Alumni House at Marina Square 6 Raffles Boulevard, #02-27/28, Marina Square Shopping Mall, Singapore 039594

TIME Function Location

7:30am Registration Conference Venue

8:10am Conference Opening Basil 1&2&3

08:30am

9:30am

Keynote Speech I

On Application-Aware Information Extraction for Big Data in Social Networks

Prof. Ming-Syan Chen College of Electrical Engineering and Computer Science National Taiwan University

Basil 1&2&3

09:30am

10:30am

Keynote Speech II

I’m Telling You - You Ain’t the Only One Who Needs MapReduce Algorithms! Prof. Kyuseok Shim Electrical and Computer Engineering Department Seoul National University, Korea

Basil 1&2&3

10:30am

11:00am

Morning Tea

Conference venue

11:00am – 12:30pm Parallel Paper Presentations

Session 1-1: Machine Learning 11:00am – 12:30pm, Basil 3 Session Chair: Dr Zhen Hai, Institute for Infocomm Research, A*STAR, Singapore Mixed Membership Sparse Gaussian Conditional Random Fields (Spotlight)

Jie Yang, Henry C.M. Leung, S.M. Yiu and Francis Y.L. Chin Supervised Feature Selection Algorithm Based on Low-Rank and Manifold Learning (Spotlight) Shichao Zhang, Yue Fang, Cong Lei, Jilian Zhang and Xiaoyi Hu StruClus: Scalable Structural Graph Set Clustering with Representative Sampling (Spotlight)

Till Schäfer and Petra Mutzel Effects of Dynamic Subspacing in Random Forest

Md Nasim Adnan and Zahid Islam

16 |Page


Employing Hierarchical Clustering and Reinforcement Learning for Attribute-based Zero-Shot Classification

Liu Bin, Li Yao, Junfeng Wu and Xiaosheng Feng

Session 1-2: Social Network and Social Media Mining 11:00am – 12:30pm, Basil 2 Session Chair: Dr Guojie Song, Peking University, China From Mutual Friends to Overlapping Community Detection: A Non-negative Matrix Factorization Approach (Spotlight) Xingyu Niu, Hongyi Zhang, Micheal R. Lyu and Irwin King A Feature-based Approach for the Redefined Link Prediction Problem in Signed Networks (Spotlight)

Xiaoming Li, Hui Fang and Jie Zhang A Solution to Tweet-Based User Identification across Online Social Networks

Yongjun Li, Zhen Zhang and You Peng (Video is available at https://pan.baidu.com/s/1c2cuyvm) Empirical Analysis of Factors Influencing Twitter Hashtag Recommendation on Detected Communities

Areej Alsini, Amitava Datta, Jianxin Li and Du Huynh Language-independent Twitter Classification using Character-based Convolutional Networks Shiwei Zhang, Xiuzhen Zhang, Jeffrey Chan and Stephen Wa FRISK: A Multilingual Approach to Find twitteR InterestS via wiKipedia Coriane Nana Jipmo, Gianluca Quercini and Nacéra Bennacer

12:30pm

01:30pm

Lunch

Demo Session

Conference venue

Basil 1

1:30pm – 3:00pm Parallel Paper Presentations

Session 2-1: User Behavior and Profile Analysis 1:30pm – 3:00pm, Basil 3 Session Chair: Dr Chu Wing Yan Victor, Nanyang Technological University, Singapore

Modeling Check-in Behavior with Geographical Neighborhood Influence of Venues (Spotlight)

Thanh-Nam Doan and Ee-Peng Lim Your Moves, Your Device: Establishing Behavior Profiles using Tensors (Spotlight) Eric Falk, Jérémy Charlier and Radu State An Approach for Identifying Author Profiles of Blogs

Chunxia Zhang, Yu Guo, Jiayu Wu, Shuliang Wang and Zhendong Niu Generating Topics of Interests for Research Communities

Nagendra Kumar, Rahul Utkoor, Bharath Kumar Reddy Appareddy and Manish Singh

17 |Page


Session 2-2: Medical Informatics 1:30pm – 3:00pm, Basil 2 Session Chair: Dr Xiuzhen Zhang, RMIT University, Australia Predicting Clinical Outcomes of Alzheimer's Disease from Complex Brain Networks (Spotlight) Xingjuan Li, Yu Li and Xue Li

Doctoral Advisor or Medical Condition: Towards Entity-specific Rankings of Knowledge Base Properties (Spotlight)

Simon Razniewski, Vevake Balaraman and Werner Nutt Drug-drug Interaction Extraction via Recurrent Neural Network with Multiple Attention Layers

Zibo Yi, Shasha Li, Jie Yu, Yusong Tan and Qingbo Wu

Analyzing Performance of Classification Techniques in Detecting Epileptic Seizure Mohammad Khubeb Siddiqui, Md. Zahidul Islam and Muhammad Ashad Kabir Multiclass Lung Cancer Diagnosis by Gene Expression Programming and microarray datasets

Hasseeb Azzawi, Jingyu Hou, Russul Alanni and Yong Xiang

03:00pm

03:30pm

Afternoon Tea

Demo Session

Conference venue

Basil 1


Session 3-1: Data Mining Algorithms 3:30pm – 5:10pm, Basil 3 Session Chair: Dr Chih-chieh Hung, Tamkang University, Taiwan

Querying and Mining Strings Made Easy (Spotlight)

Majed Sahli, Essam Mansour and Panos Kalnis A Higher-Fidelity Frugal Quantile Estimator

Anis Yazidi, Hugo Lewi Hammer and John Oommen Discovering Group Skylines with Constraints by Early Candidate Pruning

Ming-Yen Lin, Yueh-Lin Lin and Sue-Chen Hsueh Mobile Robot Scheduling with Multiple Trips and Time Windows

Shudong Liu, Shili Xiang, Xiaoli Li and Huayu Wu Long-Term User Location Prediction Using Deep Learning and Periodic Pattern Mining

Mun Hou Wong, Vincent S. Tseng, Sun-Wei Liu and Cheng-Hung Tsai Environmental Sound Recognition using Masked Conditional Neural Networks

Fady Medhat, David Chesmore and John Robinson

18 |Page


Session 3-2: Recommendation Systems 3:30pm – 5:10pm, Basil 2 Session Chair: Dr Kaiqi Zhao, Nanyang Technological University, Singapore

Fair Recommendations Through Diversity Promotion (Spotlight) Pierre-René Lhérisson, Fabrice Muhlenbach and Pierre Maret A Hierarchical Bayesian Factorization Model for Implicit and Explicit Feedback Data (Spotlight)

Binh Nguyen and Atsuhiro Takasu Group Recommender Model Based on Preference Interaction

Wei Zheng, Bohan Li, Wang Yanan, Hongzhi Yin, Xue Li, Donghai Guan and Xiaolin Qin Identification of Grey Sheep Users By Histogram Intersection In Recommender Systems

Yong Zheng, Mayur Agnani and Mili Singh An Evolutionary Approach for Learning Conditional Preference Network from Inconsistent Examples

Mohammad Haqqani and Xiaodong Li Color-sketch simulator: a guide for color-based visual known-item search

Jakub Lokoc, Anh Nguyen Phuong, Marta Vomlelová and Chong-Wah Ngo

Demo Sessions Time: 12:30pm – 1:30pm; 3:00pm – 3:30pm Venue: Basil 1 Demo Chairs: Dr Zhifeng Bao, RMIT University, Australia Dr Xin Cao, The University of New South Wales, Australia

An Interactive Web-based Toolset for Knowledge Discovery from Short Text Log Data

Michael Stewart, Wei Liu, Rachel Cardell-Oliver and Mark Griffin Tools and Infrastructure for Supporting Enterprise Knowledge Graphs

Sumit Bhatia, Nidhi Rajshree and Anshu Jain Carbon: Forecasting Civil Unrest Events by Monitoring News and Social Media Wei Kang, Jie Chen, Jiuyong Li, Jixue Liu, Lin Liu, Grant Osborne, Nick Lothian, Brenton Cooper, Terry Moschou and Grant Neale SWYSWYK: a new Sharing Paradigm for the Personal Cloud

Paul Tran-Van, Nicolas Anciaux and Philippe Pucheral Detect Tracking Behavior among Trajectory Data

Jianqiu Xu A System for Querying and Analyzing Urban Regions

Wee Boon Koh 7:00pm

9:00pm

Conference Dinner Mortar Restaurant & Bar

19 |Page


Monday 6 Nov 2017 – ADMA NTU Alumni House at Marina Square 6 Raffles Boulevard, #02-27/28, Marina Square Shopping Mall, Singapore 039594

TIME Function Location

7:30am Registration Conference Venue

8:30am

9:30am

Keynote Speech III

LAMP and GENIE: Just-in-Time Model Construction for Predictive Traffic Analytics Prof. Anthony K. H. Tung Department of Computer Science National University of Singapore

Basil 1&2&3

9:30am

10:00am

Industry Talk I

Data Mining-based Cost Optimisation for Electricity Retailers Dr Phua Chun Wei Clifton NCS Group

Basil 1&2&3

10:00am

10:30am

Industry Talk II

Advancing Ensembles for Population Data Mining Dr Graham Williams Cloud AI Research, Microsoft

Basil 1&2&3

10:30am

11:00am

Morning Tea Conference Venue

11:00am

11:30am

Industry Talk III

Personalised News and Video Recommendation System at LinkSure Dr Rubing Duan Big Data Department, LinkSure

Basil 1&2&3

11:30am

12:00pm

Industry Talk IV

Innovation opportunities in the Logistics industry Dr Timothy Kooi Asia Pacific Innovation Center, DHL Customer Solutions and Innovation

Basil 1&2&3

12:00pm

12:30pm

Industry Talk V

AI in Healthcare - Opportunities and Challenges from a Health System’s Perspective Sijia Wang Health Insights Department, Integrated Health Information Systems

Basil 1&2&3

20 |Page


12:30pm

1:30pm

Lunch Conference Venue


Session 4-1: Text Mining and Natural Language Processing 1:30pm – 3:00pm, Basil 3 Session Chair: Dr June-jae Kim, Institute for Infocomm Research, A*STAR, Singapore

Calling for Response: Automatically Distinguishing Situation-aware Tweets During Crises (Spotlight)

Xiaodong Ning, Lina Yao, Xianzhi Wang and Boualem Benatallah Feature Analysis for Duplicate Detection in Programming QA Communities (Spotlight) Wei Emma Zhang, Michael Sheng and Yanjun Shu Structured Sentiment Analysis

Abdulqader Almars, Xue Li, Xin Zhao, Ibrahim A.Ibrahim, Weiwei Yuan and Bohan Li Quality Prediction of Newly Proposed Questions in CQA by Leveraging Weakly Supervised Learning

Yuanhao Zheng, Bifan Wei, Jun Liu, Meng Wang, Weitong Chen, Bei Wu and Yihe Chen

Improving Chinese Sentiment Analysis via Segmentation-based Representation Using Parallel CNN Yazhou Hao, Qinghua Zheng, Yangyang Lan, Yufei Li, Meng Wang, Sen Wang and Chen Li Entity Recognition by Distant Supervision with Soft List Constraint

Hongkui Tu, Zongyang Ma, Aixin Sun, Zhiqiang Xu and Xiaodong Wang

Session 4-2: Distributed and High Performance Computing 1:30pm – 3:00pm, Basil 2 Session Chair: Dr Zhifeng Bao, RMIT University, Australia

Distributed Training Large-Scale Deep Architectures (Spotlight)

Shang-Xuan Zou, Chun-Yen Chen, Jui-Lin Wu, Chun-Nan Chou, Chia-Chin Tsao, Kuan-Chieh Tung, Ting-Wei Lin, Cheng-Lung Sung and Edward Chang

Fault Detection and Localization in Distributed Systems using Recurrent Convolutional Neural Networks (Spotlight)

Guangyang Qi, Lina Yao and Anton Uzunov Comparing MapReduce-Based k-NN Similarity Joins On Hadoop For High-dimensional Data

Premysl Cech, Jakub Marousek, Jakub Lokoc, Yasin Silva and Jeremy Starks Hybrid Subspace Mixture Models For Prediction and Anomaly Detection in High Dimensions Jenn-Bing Ong and Wee-Keong Ng Diversity and Locality in Multi-Component, Multi-Layer Predictive Systems: A Mutual Information Based Approach

Bassma Al-Jubouri and Bogdan Gabrys

21 |Page


03:00pm

03:30pm

Afternoon Tea Conference Venue


Session 5-1: Data Mining Applications 3:30pm – 5:10pm, Basil 3 Session Chair: Dr Xin Cao, University of New South Wales, Australia

Improving Real-Time Bidding Using a Constrained Markov Decision Process (Spotlight)

Manxing Du, Redouane Sassioui, Georgios Varisteas, Radu State, Mats Brorsson and Omar Cherkaoui Efficient Revenue Maximization for Viral Marketing in Social Networks (Spotlight) Yuan Su, Xi Zhang, Sihong Xie, Philip S. Yu and Binxing Fang A Joint Human/Machine Process for Coding Events and Conflict Drivers (Spotlight)

Bradford Heap, Alfred Krzywicki, Susanne Schmeidl, Wayne Wobcke and Michael Bain An Intelligent Weighted Fuzzy Time Series Model Based on A Sine-Cosine Adaptive Human Learning Optimization Algorithm and Its Application to Financial Markets Forecasting

Ruixin Yang, Mingyang Xu, Junyi He, Stephen Ranshous and Nagiza Samatova Identifying Unreliable Sensors Without a Knowledge of the Ground Truth in Deceptive Environments

Anis Yazidi, John Oommen and Morten Goodwin Making Use of External Company Data to Improve the Classification of Bank Transactions

Erlend Vollset, Eirik Folkestad, Jon Atle Gulla and Marius Rise Gallala

A Framework for Clustering and Dynamic Maintenance of XML Documents

Ahmed Al-Shammari, Chengfei Liu, Mehdi Naseriparsa, Bao Quoc Vo and Tarique Anwar

Session 5-2: Smart Nation Applications 3:30pm – 5:10pm, Basil 2 Session Chair: Dr Jianqiu Xu, Nanjing University of Aeronautics and Astronautics, China

An empirical study on collective online behaviors of extremist supporters (Spotlight)

Jung-Jae Kim, Yong Liu, Wee Yong Lim and Vrizlynn L. L. Thing

People-Centric Mobile Crowdsensing Platform for Urban Design

Shili Xiang, Lu Li, Si Min Lo and Xiaoli Li PowerLSTM: Power Demand Forecasting Using Long Short-Term Memory Neural Network

Yao Cheng, Chang Xu, Daisuke Mashima, Vrizlynn L. L. Thing and Yongdong Wu Generating Life Course Trajectory Sequences with Recurrent Neural Networks and Application to Early Detection on Social Disadvantage

Lin Wu, Michele Haynes, Andrew Smith, Tong Chen and Xue Li

22 |Page


STA: a Spatio-temporal Thematic Analytics Framework for Urban Ground Sensing

Guizi Chen, Wee Siong Ng and Usha Nanthani Kunasegaran Mining Load Profile Patterns for Australian Electricity Consumers

Vanh Khuyen Nguyen, Wei Emma Zhang, Quan Z. Sheng and Jason Merefield Location-aware Human Activity Recognition

Tam Nguyen, Daniel Fernandez, Quy T.K Nguyen and Ebrahim Bagheri Privacy and Utility Preservation for Location Data Using Stay Region Analysis

Manoranjan Dash and Sin Teo 7:00pm

9:00pm

Conference Banquet and Award Function Marina Mandarin Singapore

23 |Page


NTU Alumni House at Marina Square

6 Raffles Boulevard, #02-27/28, Marina Square Shopping Mall, Singapore 039594

Tel: (+65) 6252 7277

Email: [email protected]

24 |Page


25 |Page


Date Notes

26 |Page


Date Notes

27 |Page


Date Notes

28 |Page
