Hosted by School of Engineering and ICT University of Tasmania

The 29th Australasian Joint Conference on Artificial Intelligence

2016

Contents

Welcome Message 01Keynote/Invited Speakers 03Overall Schedule 07Detailed Session Program 09Conference Venues 13AI2016 Conference Committee 16

Sponsors

School of Engineering and ICT

School of Engineering and ICTFaculty of Science, Engineering & Technology

School of Engineering and ICTUniversity of Tasmania

School of Engineering and ICT, University of Tasmania

01

On behalf of the organisers of the 29th Australasian Joint Conference on Artificial Intelligence (AI), we would like to extend a warm welcome to all attendees. We hope that the four days will prove both relaxing and intellectually stimulating, and that you can make the most of the networking opportunities with your fellow researchers, educators, practitioners, and professionals. The conference also aims to strengthen artificial intelligence research community by providing a stage exchange ideas and research results, as well as to provide opportunities to collaborate among several parties in artificial intelligence research.

We were privileged this year to have a large number of high-quality submissions, and we trust that you will be able to find many presentations to stimulate your interest.

This conference is the result of the hard work of a number of people. I am indebted to all those who volunteered their time to make it a success; in particular the local conference organisation team.

We are also fortunate to receive support from several gracious donors. It is our pleasure to acknowledge the generosity of the following organisations:

• Australian Computer Society• Korean Institute of Smart Media• Korea Advanced Institute of Science & Technology• School of Engineering and ICT, University of Tasmania

In addition, we are grateful to the Australian Computer Society, whose operating the financial support for the student scholarship offered this year.

Together with AI 2016, we have the 2016 International Conference on Smart Media and Applications (SMA 2016) as a collocated conference. SMA 2016 concentrates on the various aspects of smart media and their applications. The conference provides a change for academic and industry professionals to discuss recent progress in the areas of advanced smart.

Welcome Message

02

While we appreciate that many of you will have to rush back to work straight away, if possible please take a few extra days to enjoy Tasmania. This is much to see and do in and around Hobart, and we will be happy to assist if you need any suggestions or help during your stay. You will also find a wide range of restaurants, as well as other visitor information, listed in the Welcome to Hobart 2017 brochure contained in your backpack.

We thank EasyChair for the use of their conference management system. Special thanks to Springer for publishing the conference proceedings. Finally, we wish to thank the keynote speakers for demonstrating and sharing their research ideas.

Last but not least, we also want to thank all authors and all conference participants for their contribution and support. We hope all participants took this opportunity to share and exchange ideas and thoughts with one another.

Once again let us welcome you to the conference, and we hope you enjoy your stay in Tasmania.

December 2016

AI 2016 Program Chairs

Byeong Ho Kang, University of Tasmania, AustraliaQuan Bai, Auckland University of Technology, New Zealand

03

Data Science for Social Impact: Case Studies, Challenges, and Opportunities

Can Data Science help reduce police violence and misconduct? Can it help prevent children from getting lead poisoning? Can it help cities better target limited resources to improve lives of citizens? We’re all aware of the data science hype right now but turning this hype into any social impact takes effort. In this talk, I’ll discuss lessons learned while working on dozens of projects over the past few years with non-profits and governments on high-impact social challenges. These lessons span from challenges these organizations face when trying to use data science, to understanding how to effectively train and build cross-disciplinary teams to do practical data science, as well as what machine learning and social science research challenges need to be tackled, and what tools and techniques need to be developed in order to have a social and policy impact with data science and machine learning.

Biography

Rayid Ghani is the Director of the Center for Data Science and Public Policy, Chief Data Scientist at the Urban Center on Computation and Data, Research Director at the Computation Institute (a joint institute of Argonne National Laboratory and The University of Chicago), and a Senior Fellow at the Harris School of Public Policy at the University of Chicago. He is also the co-founder of Edgeflip, an analytics startup that grew out of the Obama 2012 Campaign, focused on social media products for non-profits, advocacy groups, and charities.

Ghani is currently in charge of the Eric & Wendy Schmidt Data Science for Social Good Summer Fellowship, at the University of Chicago.

Keynote/Invited Speakers

Prof. Rayid Ghani University of Chicago

Keynote Speech: Tuesday, 6 Dec. 10am - 11am / Wellington Room

04

Towards Safe Semi-Supervised Learning

In many real tasks there are big data but only a small amount of them are with labels, and it is crucial to exploit unlabeled data to help improve the learning performance. Semi-supervised learning is a mainstream technique for this purpose. Although there are many successful stories of semi-supervised learning, it has been found that utilizing unlabeled data may hurt the learning performance in many cases. Thus, it is desirable to have safe semi-supervised learning approaches that are able to improve the performance, and never significantly worse than pure supervised learning. In this talk we will give an introduction to some results along this line of research.

Biography

Zhi-Hua Zhou received his B.Sc., M.Sc. and Ph.D. degrees in computer science from Nanjing University, China, in 1996, 1998 and 2000, respectively, all with the highest honor. He joined the Department of Computer Science & Technology of Nanjing University as an Assistant Professor in 2001, and at present he is a Professor, Deputy Dean of the Department of Computer Science and Technology, Standing Deputy Director of the National Key Lab for Novel Software Technology, and Founding Director of LAMDA (the Institute of Machine Learning and Data Mining) at Nanjing University. He is an ACM Distinguished Scientist and Fellow of the AAAI, CCF, IAPR, IEEE, IET/IEE.

Prof. Zhi-Hua ZhouNanjing University

Keynote Speech: Tuesday, 6 Dec. 11am - 12pm / Wellington Room

05

Innovating Intelligent Crowd Discussion and Consensus Support Systems

Much attention has been focused on the collective intelligence of people worldwide. Interest continues to increase in online democratic discussions, which might become one of the next generation methods for open and public forums. To harness collective intelligence, incentives for participants are one critical factor. If we can incentivize participants to engage in stimulating and active discussions, the entire discussion will head in fruitful ways and avoid negative behaviors that encourage “flaming.” “Flaming” means a hostile and insulting interaction by Wikipedia. In our work, we developed an open web-based forum system called COLLAGREE that has facilitator support functions and deployed it for an internet-based town meeting in Nagoya as a city project for an actual town meeting of the Nagoya Next Generation Total City Planning for 2014-2018. Our experiment ran on the COLLAGREE system during a two- week period with nine expert facilitators from the Facilitators Association of Japan. The participants discussed four categories about their views of an ideal city. COLLAGREE registered 266 participants from whom it gathered 1,151 opinions, 3,072 visits, and

18,466 views. The total of 1,151 opinions greatly exceeded the 463 opinions obtained by previous real-world town meetings. We clarified the importance of a COLLAGREE-type internet based town meeting and a facilitator role, which is one mechanism that can manage inflammatory language and encourage positive discussions. While facilitators, who are one element of a hierarchical management, can be seen as a top-down approach to produce collective discussions, incentive can be seen as a bottom-up approach. In this talk, we also focus on incentives for participants and employ both incentives and facilitators to harness collective intelligence. I propose an incentive mechanism for large-scale collective discussions, where the discussion activities of each participant are rewarded based on their effectiveness. With these incentives, we encourage both the active and passive actions of participants. In this talk, I will present current results about this project.

Biography

Dr. Takayuki ITO is Professor of Nagoya Institute of Technology. He received the B.E., M.E, and Doctor of Engineering from the Nagoya Institute of Technology in 1995, 1997, and 2000, respectively. From 1999 to 2001, he was a research fellow of the Japan Society for the Promotion of Science (JSPS). From 2000 to 2001, he was a visiting researcher at USC/ISI (University of Southern California/Information Sciences Institute). From April 2001 to March 2003, he was an associate professor of Japan Advanced Institute of Science and Technology (JAIST). From 2005 to 2006, he is a visiting researcher at Division of Engineering and Applied Science, Harvard University and a visiting researcher at the Center for Coordination Science, MIT Sloan School of Management. From 2008 to 2010, he was a visiting researcher at the Center for Collective Intelligence, MIT Sloan School of Management. He was a board member of IFAAMAS, the PC-chair of AAMAS2013, PRIMA2009, General-Chair of PRIMA2014, IEEE ICA2016, is the Local Arrangements Chair of IJCAI2020, and was a SPC/PC member in many top-level conferences (IJCAI, AAMAS, ECAI, AAAI, etc). He received the JSAI(Japanese Society for Artificial Intelligence) Achievement Award, 2016, the JSPS Prize, 2014, the Fundamental Research Award of Japan Society for Software Science and Technology,2014, the Prize for Science and Technology (Research Category), The Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science, and Technology, 2013, the Young Scientists’ Prize, The Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science, and Technology, 2007, the Nagao Special Research Award of the Information Processing Society of Japan, 2007, the Best Paper Award of AAMAS2006, the 2005 Best Paper Award of Japan Society for Software Science and Technology, the Best Paper Award in the 66th annual conference of 66th Information Processing Society of Japan, and the Super Creator Award of 2004 IPA Exploratory Software Creation Projects. He was the JST PREST (Sakigake, Super Challenge Type) Research, and a principal investigator of the Japan Cabinet Funding Program for Next Generation World-Leading Researchers (NEXT Program). He is currently principal investigator of JST CREST project. Further, he has several companies, which are handling web-based systems and enterprise distributed systems. His main research interests include multi-agent systems, intelligent agents, collective intelligence, social computing, crowd science and engineering, group decision support systems, agent-mediated electronic commerce, and software engineering on offshoring.

Prof. Takayuki ItoNagoya Institute of Technology

Keynote Speech: Wednesday, 7 Dec. 9am - 10am / Derwent Room 1

06

The Rise of Cognitive Robots

The fields of artificial intelligence and robotics have seen rapid developments over the past decade. Improvements in the sophistication, size and price of sensors and actuators have led to the development of robots that are being deployed in increasingly complex environments. Along with this progress, significant work has led to the development of algorithms that provide for, among other things, localisation, navigation and manipulation as well as the development of software systems—robot middleware—for controlling robots in certain applications. While there has been some work on high-level controllers for robots there is a lot of scope for improvement.

In this talk we will look at the field of cognitive robotics. Cognitive robots reason about their environment and what their sensors tell them, in order to determine their actions. In particular, we look at the experimental cognitive robotics programming languages that have grown out of the research in symbolic artificial intelligence in the areas of reasoning about action and that of planning and scheduling. These languages aim to facilitate the writing of high-level control programs that use symbolic reasoning in their execution to determine an appropriate course of action in carrying out tasks. We also look at experimental applications of this work in robotics and in interactive cinema with the control of virtual characters.

Biography

Maurice Pagnucco is a Professor of Computer Science and Engieering, Deputy Dean (Education) of the Faculty of Engineering and Head of the School of Computer Science and Engineering at UNSW. He joined UNSW in 2001 as a Senior Lecturer and has held the position of Head of School since 2010 and Deputy Dean (Education) since 2015. He has also held appointments at the University of Toronto, Macquarie University and the University of Sydney. Maurice obtained his Bachelor of Science (Hons I) and PhD degrees in Computer Science from the University of Sydney. During his undergraduate studies he also spent a year at the Department of Computer Science of the University of Milan, Italy. His research is focussed on Artificial Intelligence with particular emphasis on Knowledge Representation and Reasoning, Cognitive Robotics, Belief Change and Reasoning About Actions. Maurice was the programme director of the Decision Making theme in the ARC Centre of Excellence for Autonomous Systems and a co-director of the UNSW iCinema Centre for Interactive Cinema Research. His collaboration with the UNSW iCinema Centre for Interactive Cinema Research resulted in a world-first interactive cinema piece controlled using artificial intelligence techniques that premiered at the Sydney Film Festival in 2011.

Prof. Maurice Pagnucco University of New South Wales

Keynote Speech: Thursday, 8 Dec. 9am - 10am / Wellington Room

Overall Schedule

07

Day 1 (5 Dec.) Day 2 (6 Dec.)

9:00am – 10:00am

9:30am Doctoral Consortium(Venue: Engineering Room 304, UTAS)

10:30am - 11:00am Coffee Break(Venue: Foyer-Level 3 Centenary Building, UTAS)

11:00am - 12:00pm Doctoral Consortium (Continue)

Registration/Coffee Break(Venue: Boardwalk Gallery)9:30am: Opening (AI, SMA)Prof. Brian Yates(Venue: Wellington Room)

10:00am– 12:00pm

10:00am: Keynote Speech 1Prof. Rayid Ghani(Venue: Wellington Room)11:00am: Keynote Speech 2Prof. Zhi-Hua Zhou(Venue: Wellington Room)

12:00pm – 1:00pm Lunch (Venue: Foyer-Level 3 Centenary Building, UTAS)

Lunch/AI Committee Meeting Lunch(Venue: Boardwalk Gallery)

1:00pm – 2:00pm

1:00pm - 2:30pm Tutorial Part 1(Venue: Engineering Room 304, UTAS)

1:00pm - 2:30pm Workshop Part 1(Venue: Centenary Lecture Theatre, UTAS)

2:30pm - 3:00pm Coffee Break(Venue: Foyer-Level 3 Centenary Building, UTAS)

3:00pm - 4:30 Tutorial Part 2(Venue: Engineering Room 304, UTAS)

3:00pm - 4:30pm Workshop Part 2(Venue: Centenary Lecture Theatre, UTAS)

4:30pm - 5:30pm Workshop Part 3(Venue: Centenary Lecture Theatre, UTAS)

Panel 1Big Data & Deep LearningProf. Geoff WebbProf. Rayid GhaniProf. Zhi-Hua Zhou(Venue: Wellington Room)SMA 1 (Venue: Derwent Room)

2:00pm – 3:30pm

Session A1: Big Data(Venue: Wellington Room)Session B1: Constraint Satisfaction, Search and Optimisation(Venue: Boardwalk Gallery)SMA 2 (Venue: Derwent Room)

3:30pm - 4:00pm Coffee Break(Venue: Boardwalk Gallery)

4:00pm – 5:30pm

Session A2: Agent & MAS(Venue: Wellington Room)Session B2: Social Intelligence(Venue: Boardwalk Gallery)4:00pm - 5:00pm SMA 3 (Venue: Derwent Room)4:00pm - 6:00pm SMA Poster Session (Venue: Boardwalk Gallery)

6:00pm – Reception (Venue: TSBE Balcony Room, Centenary Building, UTAS)

08

Day 3 (7 Dec.) Day 4 (8 Dec.) Day 5 (9 Dec.)EKP only

8:30am – 9:00am Registration(Venue: Derwent Room 3)

Registration(Venue: Boardwalk Gallery)

9:00am – 10:00amKeynote Speech 3Prof. Takayuki Ito(Venue: Derwent Room 1)

Keynote Speech 4Prof. Maurice Pagnucco(Venue: Wellington Room)

EKP Workshop Session 2

10:00am – 10:30am Coffee Break (Venue: Derwent Room 3)

Coffee Break(Venue: Boardwalk Gallery) Coffee Break

10:30am – 12:00pm

Session A3: AI Applications (1)(Venue: Derwent Room 1)

Session B3: ML & DM (1)(Venue: Derwent Room 2)

Session A6: Knowledge Representation (Venue: Wellington Room)

Session B6: ML & DM (4)(Venue: Boardwalk Gallery)

EKP Workshop Session 3

12:00pm – 1:00pm Lunch(Venue: Derwent Room 3)

Lunch(Venue: Boardwalk Gallery) Lunch

1:00pm – 2:00pm

Panel 2Crowd Intelligence & IoTProf. Takayuki ItoProf. Michael ShengProf. Mary-Anne Williams(Venue: Derwent Room 1)

1:00pm - 2:15pmSession A7: AI Applications (3)(Venue: Wellington Room)

1:00pm - 2:15pmSession B7: ML & DM (5)(Venue: Boardwalk Gallery)

2:15pm - 3:30pmSession A8: Experiential Knowledge Platform (EKP)(Venue: Wellington Room)

2:00pm – 3:30pm

Session A4: Text Mining & NLP(Venue: Derwent Room 1)

Session B4: ML & DM (2)(Venue: Derwent Room 2)

3:30pm - 4:00pm Coffee Break(Venue: Derwent Room 3)

Closing & Coffee break(Venue: Boardwalk Gallery)

4:00pm – 5:30pm

Session A5: AI Applications (2)(Venue: Derwent Room 1)

Session B5: ML & DM (3)(Venue: Derwent Room 2)

EKP Workshop Keynote Speech (Venue: Wellington Room)

6:00pm – Conference Dinner(Venue: Boardwalk Gallery)

09

2:00pm –

3:30pm

Session A1(Venue: Wellington Room)

Session B1(Venue: Boardwalk Gallery)

Big DataCPF: Concept Profiling Framework for recurring drifts in data streamsRobert Anderson, Yun Sing Koh and Gill Dobbile

Bayesian Grouped Horseshoe Regression with Application to Additive ModelsZemei Xu, Daniel F. Schmidt, Enes Makalic, Guoqi Qian and John L. Hopper

Meta-Mining Evaluation Framework : A large scale proof of concept on Meta-LearningWilliam Raynaut, Chantal Soulé-Dupuy and Nathalie Vallès

Constraint Satisfaction, Search and OptimisationLocal Search for Maximum Vertex Weight Clique on Large Sparse Graphs with Efficient Data Structures Yi Fan, Chengqian Li, Zongjie Ma, Lian Wen and Kaile Su

Improving and Extending the HV4D Algorithm for Calculating Hypervolume ExactlyWesley Cox and Lyndon While

An Online Competence-based Concept Drift Detection Algorithm Anjin Liu, Guangquan Zhang, Jie Lu, Ning Lu and Chin-Teng Lin

Assignment Precipitation in Fail First Search (Short)Majid Namazi, Nina Ghooshchi, M.A.Hakim Newton and Abdul Sattar

SMA2 (Venue: Derwent Room)

Please see the detailed list of SMA Conference Presentations at the back of this brochure.

4:00pm –

5:30pm

Session A2(Venue: Wellington Room)

Session B2(Venue: Boardwalk Gallery)

Agent & MASCorrupt Strategic Argumentation: The Ideal and the NaiveMichael Maher

Composability in Cognitive HierarchiesDavid Rajaratnam, Bernhard Hengst, Maurice Pagnucco, Claude Sammut and Michael Thielscher

Lifted Backward Search for General Game PlayingDave De Jonge and Dongmo Zhang

Adaptive Multi-agent Reinforcement Learning with Non-positive RegretDuong Nguyen, Langford White and Hung Nguyen

Social IntelligenceComprehensive Influence Propagation Modelling for Hybrid Social NetworkWeihua Li, Quan Bai and Minjie Zhang

Proactive Skill Posting in Referral NetworksAshiqur Khudabukhsh, Jaime Carbonell and Peter Jansen

Multi-agent planning with collaborative actionsSatyendra Singh Chouhan and Rajdeep Niyogi

Mining Context Specific Inter-Personalised Trust for Recommendation Generation in Preference NetworksQuan Bai, Weihua Li and Jing Jiang

Detailed Session Program

DAY 2 Tuesday, 6 December

10

10:30am –

12:00pm

Session A3(Venue: Derwent Room 1)

Session B3(Venue: Derwent Room 2)

AI Applications (1)Forecasting monthly rainfall up to 18-months in advance using artificial neural networks: Narrogin, Merredin and Southern Cross in the Western Australian wheat-belt as a case studyJohn Abbot and Jennifer Marohasy

Forecasting Monthly Rainfall in the Bowen Basin of Queensland, Australia, using Neural Networks with Niño Indices for El Niño-Southern OscillationJohn Abbot and Jennifer Marohasy

A Generative Deep Learning for Generating Korean AbbreviationsSu Jeong Choi, Seong-Bae Park, A-Yeong Kim and Se-Young Park

Visual Odometry in Dynamic Environments with Geometric Multi-layer Optimisation (Short)Haokun Geng, Hsiang-Jen Chien, Radu Nicolescu and Reinhard Klette

ML & DM (1)Optimization of Traffic Signals using Deep Learning Neural NetworksSaman Lawe and Ruili Wang

Smart Sampling: A Novel Unsupervised Boosting Approach for Outlier DetectionMahsa Salehi, Xuyun Zhang, James Bezdek and Christopher Leckie

Visual Analytical Tool for Higher Order $k$-Means Clustering for Trajectory Data MiningYe Wang, Kyungmi Lee and Ickjai Lee

An Empirically-Sourced Heuristic for Predetermining the Size of the Hidden Layer of a Multi-Layer Perceptron for Large Datasets (Short)Amanda Lunt and Shuxiang Xu

2:00pm –

3:30pm

Session A4(Venue: Derwent Room 1)

Session B4(Venue: Derwent Room 2)

Text Mining & NLPPredicting the Rank of Trending TopicsDohyeong Kim, Soyeon Han, Sungyoung Lee and Byeong Kang

Open-domain Question Answering Framework using WikipediaSaleem Ameen, Hyunsuk Chung, Soyeon Han and Byeong Kang

A Topic Transition Map for Query Expansion: a Semantic Analysis of Click-through Data and Test CollectionsKyung-Min Kim, Yuchul Jung and Sung-Hyon Myaeng

Unsupervised Keyphrase Extraction: Introducing New Kinds of Words to Keyprhases (Short)Tho Thi Ngoc Le

ML & DM (2)Transfer Learning in Probabilistic Logic ModelsPouya Ghiasnzhad Omran, Kewen Wang and Zhe Wang

Artificial Prediction Markets for ClusteringSina Famouri, Sattar Hashemi and Mohammad Taheri

Co-clustering for Dual Topic ModelsSantosh Kumar, Xiaoying Gao and Ian Welch

Articial Neural Network: Deep or Broad? An Empirical Study (Short)Nian Liu and Nayyar A. Zaidi

DAY 3 Wednesday, 7 December

11

DAY 3 Wednesday, 7 December

DAY 4 Thursday, 8 December

4:00pm –

5:30pm

Session A5(Venue: Derwent Room 1)

Session B5(Venue: Derwent Room 2)

AI Applications (2)Enable Efficient Resource Deployment in Multiple Concurrent Emergency Events through a Decentralised MASJihang Zhang, Minjie Zhang, Fenghui Ren and Jiakun Liu

Similarity Matching of Computer Science Unit Outlines in Higher Education Gaurav Langan, James Montgomery and Saurabh Kumar Garg

A Cluster Analysis of Stock Market Data using Hierarchical SOMs Cesar Astudillo, Jorge Poblete, Marina Marina Resta and John Oommen

Cascade Bayesian OptimizationThanh Dai Nguyen, Sunil Gupta, Santu Rana, Vu Nguyen, Svetha Venkatesh, Kyle Deane and Paul Sanders

ML & DM (3)Bayesian Robust Regression with the Horseshoe+ EstimatorEnes Makalic, Daniel F. Schmidt and John L. Hopper

Exceptional Contrast Set Mining: Moving beyond the deluge of the obviousDang Nguyen, Wei Luo, Dinh Phung and Svetha Venkatesh

Concept Drift Detection using Online Histogram-based Bayesian Classifiers (Short) Cesar Astudillo, Javier Gonzlez, John Oommen and Anis Yazidi

An empirical study of a simple naive Bayes classifier based on ranking functions (Short)Kinzang Chhogyal and Abhaya Nayak

10:30am –

12:00pm

Session A6(Venue: Wellington Room)

Session B6(Venue: Boardwalk Gallery)

Knowledge RepresentationUpdate PoliciesAbhijeet Mohapatra, Sudhir Agarwal and Michael Genesereth

Domain Ontology Construction using Web Usage Data (Short)Thi Thanh Sang Nguyen and Haiyan Lu

Learning Functional Argument Mappings for Hierarchical Tasks from Situation Specific Explanations (Short)Gavin Suddrey, Markus Eich, Frederic Maire and Jonathan Roberts

Ontology Based Data Access with Referring Expressions for Logics with the Tree Model Property (Short)David Toman and Grant Weddell

A Multi-Linguistic-Valued TruthsModal Logic (Short)Jinsheng Chen and Xudong Luo

ML & DM (4)Approximating Message Lengths of Hierarchical Bayesian Models Using Posterior SamplesDaniel Schmidt, Enes Makalic and John Hopper

High resolution Self-organizing MapsVan Tuc Nguyen, Markus Hagenbuchner and Tsoi Ah Chung

Kernel Embeddings of Longitudinal DataDarren Shen and Fabio Ramos

A Framework for Mining Semantic-Level Tourist Movement Behaviours from Geo-tagged Photos (Short)Guochen Cai, Kyungmi Lee and Ickjai Lee

12

DAY 4 Thursday, 8 December

1:00pm –

2:15pm

Session A7(Venue: Wellington Room)

Session B7(Venue: Boardwalk Gallery)

AI Applications (3)Parallel Late Acceptance Hill-Climbing Algorithm for the Google Machine Reassignment ProblemAyad Turky, Nasser R. Sabar, Abdul Sattar and Andy Song

Deep Learning for Classification of Malware System Call SequencesBojan Kolosnjaji, Apostolis Zarras, George Webster and Claudia Eckert

High Resolution SOM Approach to Improving Anomaly Detection in Intrusion Detection Systems (Short)Ayu Saraswati, Markus Hagenbuchner and Zhi Quan Zhou

ML & DM (5)Learning High-Level Navigation Strategies via Inverse Reinforcement Learning: A Comparative Analysis (Short)Michael Herman, Tobias Gindele, Jörg Wagner, Felix Schmitt, Christophe Quignon and Wolfram Burgard

Restricted Echo State Networks (Short)Aaron Stockdill and Kourosh Neshatian

Feature-Aware Factorized Collaborative Filtering (Short)Farhad Zafari and Irene Moser

Distributed Genetic Algorithm in GraphX (Short)Seemran Mishra, Young Choon Lee and Abhaya Nayak

2:15pm –

3:30pm

Session A8(Venue: Wellington Room)

Experiential Knowlege Platform (EKP)Utilization of DBpedia Mapping in Cross Lingual Wikipedia Infobox CompletionMegawati Megawati, Sammy Jang and Mun Yi

Medical Prognosis Generation from General Blood Test Results Using Knowledge-Based and Machine-Learning-Based ApproachesYoujin Kim, Jonghwan Hyeon, Kyo-Joong Oh and Ho-Jin Choi

Cognitive-Task-based Information Aid Design for Clinical Diagnosis (Short)Dong-Gyun Ko, Youkyoung Park, Yoochan Kim, Juyoun Kim and Wan Chul Yoon

13

Conference Venues

�

WELLINGTONFOYER

BOARDWALKGALLERY

WELLINGTONROOMS

CONVENTIONS LOADING DOCK

PIER ONE PRIVATEDINING ROOM

PIER ONE RESTAURANT & BARCLUB FORTÈ LOUNGE

BOARDWALK SNACKS

VIP GAMINGLOUNGEACCESS VIA CASINO ONLY

�

LIFT

ACCESS FROM EXHIBITION FOYER

LAWN

AI Conference Spaces

BOARDWALK LEVEL (GROUND FLOOR)

Wrest Point Hotel410 Sandy Bay RoadSandy Bay Tasmania Australia 7005For information about Wrest Point, call the Guest Service Desk on (03) 6221 1888 or e-mail guestservices@wrestpoint.com.au.

14

ONYX BAR

� ��

THE LOFT BISTRO

GREEN ROOM

INTERNET BUREAU

RIVIERA ROOM

MEZZANINEBOARDROOM

LIFT FROM MAIN HOTEL FOYER

DERWENTROOMS

EXECUTUVEBOARDROOM

MOTOR INN ACCOMMODATION

WATER EDGEACCOMMODATIONPORTLIGHT BAR

LIFT

(ACCESS VIA STAIRS ON 1ST FLOOR)

AI Conference Spaces

MEZZANINE LEVEL (2ND FLOOR)

Airport Shuttle to and from HotelShuttle buses operate between Hobart Accommodations (including The Casino & University) and the Airport for every departure and arrival. The shuttle departs outside the terminal after the arrival of every flight, transferring passengers to the city.• Rates: Adult One Way $18 / Return $32 • Phone: 1300 38 55 11 (8:00am - 6:00pm Every day)

TaxisThe taxi rank is located directly out the front of the Hobart Airport building and it costs about $45-$50. Actual fare may vary with traffic, road conditions, weather, surge pricing, variable pricing, airport surcharges, fuel surcharges, etc.

15

Grosvenor

Earl

Stre

et

1

2

3

4

8

5

1015

9

11 12

13

Alexander Street

CrescentDobs

on R

oad

Clar

k Ro

ad

Churchill Avenue

14

Centenary Building (Centenary Lecture Theatre / TSBE Balcony Room)

School of Engineering & ICT (Engineering Room 304)

1. Faculty of Law 2. Surveying & Spatial Sciences Building 3. Engineering Workshop 4. School of Land & Food 5. Chemistry (School of Physical Sciences)

University of Tasmania

Detailed map for UTAS Sandy Bay campus is available at https://sisfm.admin.utas.edu.au/sisfmda-ta/sisfm/Campus_Maps/Sandy_Bay_Building_Map_CAD.pdf

Centenary Building

How to get from Wrest Point to Centenary Building in UTAS

Dianhui Wang La Trobe University, Australia

Wray Lindsay Buntine Monash University, Australia

Reinhard Klette School of Engineering, Auckland University of Technology, New Zealand

Michael Maher University of New South Wales, Canberra, Australia

Jussi Rintanen Aalto University, Finland

Mengjie Zhang Victoria University of Wellington, New Zealand

Thomas Meyer Centre for Artificial Intelligence Research, UKZN and CSIR Meraka, South Africa

Mikhail Prokopenko University of Sydney, Australia

Ian Watson University of Auckland, New Zealand

Stephen Cranefield University of Otago, New Zealand

Jimmy Lee The Chinese University of Hong Kong, Hong Kong

Chengqi Zhang University of Technology, Sydney, Australia

Dongmo Zhang University of Western Sydney, Australia

Fabio Ramos University of Sydney, Australia

Michael Thielscher University of New South Wales, Australia

General ChairsProfessor Geoff WebbMonash University, Australia

Dr. Craig LindleyCSIRO, Australia

Program ChairsAssociate Professor Byeong Ho KangUniversity of Tasmania, Australia

Dr. Quan BaiAuckland University of Technology, New Zealand

Workshop ChairDr. Ashfaqur RahmanCSIRO, Australia

Tutorial ChairDr. Charlotte SennerstenCSIRO, Australia

Doctoral Consortium ChairsDr. Alan BlairUniversity of New South Wales, Australia

Dr. James MontgomeryUniversity of Tasmania, Australia

Publicity ChairDr. Caren HanUniversity of Tasmania, Australia

Senior MembersFatih Porikli Australian National University, Australia

Abhaya Nayak Macquarie University, Australia

AI2016 Conference Committee

16

04

4:00pm-

6:00pm

SMA Poster Session (Venue: Boardwalk Gallery)

Designing the Route Guidance System based on an Obstacle Map for the BlindSeonghee Min, Yoosoo Oh(Daegu University, Korea)

Design of 2-Factor Authentication Technique for NFC-based Security-enriched Payment and Coupon System Applicable to IoT and CloudByungRae Cha(GIST, Korea), MyeongSoo Choi(GenoTech Inc, Korea), Sun Park, JongWon Kim(GIST, Korea)

Implementation of TPMS Sensor Software for Low Power OperationChul Kyun Bae, Sol Lim, Chil Woo Lee, Dae Jin Kim(Chonnam National University, Korea)

Detection of Blurred Text in Digital ImagesVan Khien Pham, Gueesang Lee(Chonnam National University, Korea)

An Accuracy-Improved Indoor Positioning System(AIIPS) based on Mobile Crowd Sensing Yusrina Tifani, YiNa Jeong, ByungKwan Lee(Catholic Kwandong University, Korea)

Analysis on Permission Patterns in Malicious Mobile Applications Using Apriori AlgorithmKwangMin kim, JeongIn kim, EunJi Lee, HanIl Kim, PanKoo Kim(Chosun University, Korea)

Multi-camera Matching for Virtual Reality Object Tracking Kyoung-Hwan Ko, Dong-Ho Yang, Sang-Hun Youn, Keun-Hyung Kim(Jeju National University, Korea)

A Study on Implementation of 360 degree Panoramic Video Service For Mobile EnvironmentJu-Hyun Yoo, Min-Hyeong Lee, Min-Wook Kang , Dong-Ho Yang, Keun-Hyung Kim(Jeju National University, Korea)

Facial Expression Recognition for Affective Computing by using Deep Learning TechniqueNguyen Hai Duong, In Seop Na, Soo Hyung Kim(Chonnam National University, Korea)

Hybrid Index Management using PRAM for Column-StoragesSiwoo Byun(Anyang University, Korea)

Development of Wireless Solar Powered Surveillance Camera system for Power ReductionJi-in Kim, Jae-Young Pyun, Suk-seung Hwang, Goo-Rak Kwon(Chosun University, Korea)

Review on Radio Access Enhancement for LTE-A TechnologyPrasis Poudel(Mokpo National University, Korea), Sang-Hyun Bae(Chosun University, Korea), Chang-Hee Kwon(Hansei University, Korea), Bongseog Jang(Mokpo National University, Korea)

A Study on Information System Advancement Measures for Construction Project Cost-Saving PracticesHyun Ok, Seong-Jin Kim(KICT, Korea)

TB-based User Authentication Method for SmartphonesXin Su(Hohai University, China), Chang Choi, Dongmin Choi(Chosun University, Korea)

A Study on Big Data Pre-Analysis for Big Data Sharing InvigorationSeong Eun Hong, Hwa Jong Kim, Kyung Jin CHA(Kangwon National University, Korea)

Preliminary Formular for Measurement of Information Density in Visual ParagraphJi-Ae Han(Chosun University, Korea)

IoT-based Intelligent Ventilation Heating Control SystemDongOk Cho, JinGwang Koh, MinJi Kim(Sunchon National University, Korea), SeungJae Oh(Cheongam College, Korea), JinYong Jeong, HyunHo Choi, SungKeun Lee(Sunchon National University, Korea)

A Mobile Data Offloading Scheme based on Social Interest Similarity in Pocket Switched NetworksRegin Cabacas(West Visayas State University, Philippines), Hyun Tae Kim, In Ho Ra(Kunsan National University, Korea)

Air Quality Mapping using Correlation of Air Pollutants and Meteorological FactorsRenemae A. Cabacas, Regin A. Cabacas, Rodel P. Dosano(West Visayas State University, Philippines), In Ho Ra(Kunsan National University, Korea)

Requirements of Data Value Chain Framework in a Data-Driven Business EnvironmentHwa Jong Kim(Kangwon National University, Korea)

Tuesday, 6 December

SMA Conference Committee

Honourable chairJoonSeub ChaPresident of KISM, Korea

General ChairGueesang LeeChonnam National University, Korea

Program ChairsKyung Jin ChaKangwon National University, Korea

Yang Sok Kim Keimyoung University, Korea

International Advisory ChairSoon Ja YeomUniversity of Tasmania, Australia

Program CommitteeSe-Jin Kim Chosun University, Korea

Sang-Hyun Bae Chosun University, Korea

Gi Hwan Cho Chonbuk National University, Korea

Hwa Jong Kim Kangwon National University, Korea

Yong Bom Park Dankook University, Korea

Jae Soo Yang Dankook University, Korea

JuHyun Shin Chosun University, Korea

Young-Chul Kim Chonnam National University, Korea

Sicheon You Chosun University, Korea

Yoosoo Oh Daegu University, Korea

ByungRae Cha GIST, Korea

Chil Woo Lee Chonnam National University, Korea

Dae Jin Kim Chonnam National University, Korea

ByungKwan Lee Catholic Kwandong University, Korea

Hanil Kim Jeju National University, Korea

PanKoo Kim Chosun University, Korea

Dong-Ho Yang Jeju National University, Korea

Sang-Hun Youn Jeju National University, Korea

Soo Hyung Kim Chonnam National University, Korea

Siwoo Byun Anyang University, Korea

Jae-Young Pyun Chosun University, Korea

Goo-Rak Kwon Chosun University, Korea

Chang-Hee Kwon Hansei University, Korea

Bongseog Jang Mokpo National University, Korea

JinGwang Koh Sunchon National University, Korea

05

02

SMA Conference Schedule

Tuesday, 6 December

9:00am – 10:00amRegistration/Coffee Break (Venue: Boardwalk Gallery)9:30am: Opening (AI, SMA) Prof. Brian Yates (Venue: Wellington Room)

10:00am – 12:00am

10:00am: Keynote Speech 1Prof. Rayid Ghani (Venue: Wellington Room)

11:00am: Keynote Speech 2Prof. Zhi-Hua Zhou (Venue: Wellington Room)

12:00pm – 1:00pm Lunch/AI Committee Meeting Lunch (Venue: Boardwalk Gallery)

1:00pm – 2:00pm

Panel 1Big data & deep learningProf. Geoff WebbProf. Rayid GhaniProf. Zhi-Hua Zhou(Venue: Wellington Room)

SMA 1 (Venue: Derwent Room)

2:00pm – 3:30pm

Session A1: Big Data (Venue: Wellington Room)

Session B1: Constraint satisfaction, Search and Optimisation(Venue: Boardwalk Gallery)

SMA 2 (Venue: Derwent Room)

3:30pm - 4:00pm Coffee Break (Venue: Boardwalk Gallery)

4:00pm – 5:30pm

Session A2: Agent & MAS (Venue: Wellington Room)

Session B2: Social Intelligence (Venue: Boardwalk Gallery)

4:00pm - 5:00pm SMA 3 (Venue: Derwent Room)

4:00pm - 6:00pm SMA Poster Session (Venue: Boardwalk Gallery)

SMA Conference Presentations

1:00pm –

2:00pm

SMA 1 (Venue: Derwent Room)

Safety-Critical Software analysis method by using UML-Based Requirement Analysis Hi Jung Hwang, Yong Bom Park, Jae Soo Yang(Dankook University, Korea)

Seamless Handoff Scheme for WLAN using an Overlaid Mobility NetworkJae Soo Yang, Chul Woo Kim, Young Bom Park(Dankook University, Korea)

Pattern Mining for Prediction of Injury Severities of Traffic Accident VictimsYeongJi Ju, TaekEun Hong, JuHyun Shin(Chosun University, Korea)

Following Recommendation Method by User Interest Category Classification of SNS PostsTaekeun Hong, Yeongji Ju, Juhyun Shin(Chosun University, Korea)

2:00pm –

3:30pm

SMA 2 (Venue: Derwent Room)

LSS: A Real-Time Detection Algorithm of Shill Bidding in Online AuctionNazia Majadi, Jarrod Trevathan(Griffith University, Australia), Neil Bergmann(University of Queensland, Australia)

Performance Analysis of SIPTO in Smallcell NetworksSe-Jin Kim, Sang-Hyun Bae(Chosun University, Korea)

A Sensor Deployment Scheme with Random and Uniform Node Distribution in 3D Wireless Sensor NetworksA. S. M. Sanwar Hosen, Gi Hwan Cho(Chonbuk National University, Korea)

Towards Superior Information Security Performance in the ICT Outsourcing: The Influence of the IS Control Mechanisms Compatibility and Inter-Organizational Relationship CapitalElizaveta Srednik, Kyung Jin Cha, and Hwa Jong KIM(Kangwon National University, Korea)

An Empirical Evaluation of Job Classification Using Online Job AdvertisementsYang Sok Kim, Choong Kwon Lee(Keimyung University, Korea)

4:00pm –

5:00pm

SMA 3 (Venue: Derwent Room)

Data-Con: A Comprehensive Data Browsing Service for Real-time Data Sharing and Utilization of Big Data EnvironmentHwa Jong Kim, Soon Ja Yeom, Kyung Jin CHA(Kangwon National University, Korea)

Gesture Recognition Based on GMM and SVM Hybrid Model Using EPIC Sensor CUI CHEN, Seok-Hyeon Lee, Young-Chul Kim(Chonnam National University, Korea)

The Relationship between Human Emotions and the Characteristics of Chinese Characters appeared in Plaques for the Korean Heritage GazebosHyeong-Shin Im, Ji-Ae Han, Sicheon You(Chosun University, Korea)

The Relationship between Trigger-Factors and Elements for Fun in Edutainment Applications for ChildrenEugene Kim, Ji-Ae Han, Sicheon You(Chosun University, Korea)

Exploring the use of Big Data Analytics for Improving Support to Students in Higher EducationSi Fan, Saurabh Garg, Soonja Yeom(University of Tasmania, Australia)

Tuesday, 6 December

03

Contents

Welcome Message 01SMA Conference Schedule 02SMA Conference Presentations 03SMA Committee 05

Smart Media & Applications

2016

Welcome Message

Welcome to the International Conference, SMA2016!

It is my great pleasure to welcome you to the international conference on SMA 2016, co-hosted by Korean Institute of Smart Media and University of Tasmania, and specially co-located with the 29th Australasian Joint Conference on Artificial Intelligence.

First of all, I would like to express endless gratitude to University of Tasmania and also thank to SMA/AI 2016 committee members for all your efforts and contribution to this conference.

This conference will be the most comprehensive conference focused on the various aspects of advances in smart media applications and Artificial Intelligence.

The conference aims to bring researchers from academia and industry, as well as practitioners together to share ideas, problems and solutions related to the multifaceted aspects of smart media and applications.

We believe that the conference will provide an opportunity for all participants to update and exchange knowledge of future smart media technology through well-formed presentations and discussions.

We have two cordially invited keynote speakers: Professor Rayid Ghani and Professor Zhi-hua Zhou for special talks with the latest issues in future research for the participants. I believe two speakers will deliver excellent ideas on the latest topics and trends in smart media technology.

SMA 2016 has received lots of high-quality submissions from lots of different countries. I am very much sure of that this conference will give you many opportunities for human networking, collaborating each other, and enhancing the academic relationship each other for the future research.

I am very glad to see lots of distinguished participants joining this conference at the charming city, Hobart, Tasmania, Australia.

I do hope you enjoy the conference and have wonderful days in Hobart.

Thank you very much,

JoonSeub Cha SMA Honourable chair

President, Korean Institute of Smart Media

01

Smart Media & Applications

5 - 8 December 2016Wrest Point Hotel, Hobart, Australia