Documente Academic
Documente Profesional
Documente Cultură
org
BigComp 2017
2017 IEEE International Conference on
Big Data and Smart Computing
February 13-16, 2017
MAISON GLAD JEJU Hotel, Jeju Island, Korea
Conference Program
Organized by
Sponsored by
Technically Co-Sponsored by
Patron by
BigComp 2017
Table of Contents
Keynote Speeches.....................................................................................................9
Invited Talk............................................................................................................. 11
Paper Sessions........................................................................................................12
Tutorial-1................................................................................................................17
Workshop-1............................................................................................................18
Workshop-2............................................................................................................20
Workshop-3............................................................................................................22
Venue.......................................................................................................................24
Travel Information.................................................................................................26
Program Co-Chairs
Registration Co-Chairs
Song Chong KAIST, Korea
Zhifeng Bao RMIT University, Australia
Wookey Lee Inha University, Korea
Min Song Yonsei University, Korea
Jaideep Srivastava University of Minnesota, USA
Jeffrey Yu The Chinese University of Hong Kong, China
Web Co-Chairs
Publication Co-Chairs Chulyun Kim Sookmyung Womens University, Korea
www.bigcomputing.org 3
BigComp 2017
Technical Program Committee
Tianrui Li Southwest Jiaotong University Raymondchi-Wing Wong the Hong Kong University of Science and Technology
Wenjie Li The Hong Kong Polytechnic University Huayu Wu Institute for Infocomm Research
Taesoo Lim Sungkyul University Xiaokui Xiao Nanyang Technological University
Yujin Lim Sookmyung Womens University Meng Xiaofeng Renmin University of China
Tokwang Ling NUS Stephan Yau Arizona State University
Guanfeng Liu Soochow University Jeonghyun Yi Soongsil University
Mengchi Liu Carleton University Hongzhi Yin University of Queensland
Woong-Kee Loh Gacheon Univ. Seongjoon Yoo Sejong University
Robert Luk The Hong Kong Polytechnic University Yong-Ik Yoon Sookmyung Womens University
Paolo Merialdo Universita degli Studi Roma Tre Ge Yu Northeastern University
Jun-Ki Min Korea University of Technology and Education Hwanjo Yu POSTECH
Mukesh Mohania IBM India Research Lab Jeffrey Yu The Chinese University of Hong Kong
Yang-Sae Moon Kangwon National University Liang-Chih Yu Yuan Ze University
Ponrudee Netisopakul KMAKE LAB Min-Ling Zhang Southeast University
Jaechun No Sejong University Xiaofang Zhou University of Queensland
Yasuo Okabe Kyoto University Yu Zhuang Texas Tech University
Naoaki Okazaki Tohoku University
Cheong Hee Park Chungnam National University
Hohyun Park Chung-Ang University
Sanghyun Park Yonsei University
Sehyun Park Daegu University
Mario Pavone University of Catania
Zhiyong Peng Wuhan University
Matthias Renz Ludwig-Maximilians University
Markus Schneider University of Florida
Friedhelm Schwenker Ulm University
Tomohide Shibata Kyoto University
Kyuseok Shim Seoul National University
Myung Keun Shin SK C&C
Akbar Siami Namin Texas Tech University
Mye Sohn Sunkkyunkwan University
Min Song Yonsei University
Jaideep Srivastava University of Minnesota
Kazutoshi Sumiya Kwansei Gakuin University
Vincent Tseng National Chiao Tung University
Yuen-Hsien Tseng National Taiwan Normal University
Shoko Wakamiya Nara Institute of Science and Technology
Chaokun Wang Tsinghua University
Jianmin Wang Tsinghua University
Wei Wang UNSW
Wendy Hui Wang Stevens Institute of Technology
Jef Wijsen University of Mons
Fai Wong University of Macau
www.bigcomputing.org 5
BigComp 2017
Greetings
Welcome to Jeju island and the 4th International Conference on Big Data and Smart Computing 2017
(IEEE BigComp 2017). The conference will take place during February 13th February 16th, 2017 at
the Maison Glad Jeju Hotel in Jeju Island, Korea. It is our great pleasure to meet all of the participants,
authors, invited speakers, and distinguished guests in IEEE BigComp 2017.
IEEE BigComp 2017 is co-sponsored by KIISE and IEEE Computer Society, and technically co-
sponsored by China Computer Federation and Information Processing Society of Japan. This year,
we have received a number of good quality paper submissions and selected outstanding papers for
presentation in IEEE BigComp 2017. We hope you will participate in twelve oral presentation sessions,
three workshops and three poster sessions in various areas of big data and smart computing. In addition
to presentations of recent research discoveries, we have also invited two distinguished keynote speakers,
Prof. Doheon Lee in Bio-Synergy National Research Center, KAIST, Korea and Prof Zhi-Hua Zhou in
Department of Computer Science & Technology, Nanjing University, China to share their insights on big
data research and perspectives of machine learning, respectively. We believe that IEEE BigComp 2017
will be an excellent opportunity to share the recent research trends among the experts from around the
world, and we hope that you will enjoy this world premier conference.
Jeju Island, the warmest region in Korea, is well known for natural wonders, including waterfalls,
white sand beaches and a dormant volcano at the center of the island. We hope that you will experience
the rich heritage of Jeju Island and Korea and find a uniqueness of its customs. We are sure that you will
truly enjoy this conference and wish you a memorable stay!
www.bigcomputing.org 7
BigComp 2017
Conference Program (At a Glance)
Track 1 Track 2 Track 3
TIME (CRYSTAL) (JADE) (AMETHYST)
Day1: February 13 (Monday), 2017
08:00 - 18:00 Registration
08:30 - 09:45 WS-1: Keynote Speech
09:45 - 10:30
WS-1:
10:30 - 11:00(CB) BigData4Healthcare
11:00 - 12:30
12:30 - 14:00 Lunch (AZALEA Restaurant)
14:00 - 15:15 WS-2: Keynote Speech
15:15 - 16:00
Tutorial-1 WS-3: ASC 2017
16:00 - 16:30(CB) WS-2: Exobrain
16:30 - 18:00
18:00 - 18:30 Break
18:30 - 20:00 Welcoming Reception (CRYSTAL)
Day2 : February 14 (Tuesday), 2017
08:00 - 18:00 Registration
08:30 - 10:30 Regular Session-1 Regular Session-2 Regular Session-3
10:30 - 10:40 Coffee Break
10:40 - 11:00 Opening
11:00 - 12:30 Keynote Speech-1
12:30 - 14:00 Lunch (AZALEA Restaurant)
14:00 - 16:00 Regular Session-4 Regular Session-5 Regular Session-6
16:00 - 17:00 Invited Talk
17:00 - 18:00 Poster Session-1 Poster Session-2 Poster Session-3
18:00 - 19:30 Banquet (CRYSTAL)
Day3 : February 15 (Wednesday), 2017
08:00 - 18:00 Registration
09:00 - 10:30 Keynote Speech-2
10:30 - 11:00 Coffee Break
11:00 - 12:40 Regular Session- 7 Regular Session-8 Regular Session-9
12:40 - 14:00 Lunch (AZALEA Restaurant)
14:00 - 16:00 Regular Session-10 Regular Session-11 Regular Session-12
16:00 - 16:20 Coffee Break
16:20 - 17:50 Panel Discussion
17:50 - 18:00 Closing
Day4 : February 16 (Thursday), 2017
08:00 - 18:00 Registration
09:00 - 10:30 Business Meeting
10:30 - 11:00 Coffee Break
Abstract:
Recently, there are growing interests in combinational bio-agents interacting with multiple targets to overcome the
limitations of the current single target approaches. Many drug development efforts based on the Paul Ehrlichs magic
bullet principle, where a single therapeutic agent with ideal selectively could successfully regulate a single target causing
a particular disease, have been suffering critical hindrances including unwanted off-target effects and degraded efficacy.
Synergistic regulation of multiple targets with multiple agents is expected to remedy those hindrances. Furthermore, recent
trends of 4P healthcare require more comprehensive spectrum of bio-agents for disease prevention as well as treatment.
Functional food and ingredients have drawing increasing attention especially for preventive medicine and life-time
healthcare. As they are composed of multiple components inherently, their precise interactions with human physiology are
thought to be synergistic regulation of multiple targets with multiple agents This talk introduces a national initiative where
multiple-agent-multiple-target systems biology technology for natural product-based healthcare is being developed. Core
components of the technology platform are virtual cell and human systems, which are computational models of molecular,
cellular, and organ-level physiological mechanisms. The synergistic effects of multiple agents on multiple targets are
simulated and predicted with those virtual systems, and validated in real systems including model cells and animals.
Short Biography
Doheon Lee received the B.S., M.S., and Ph.D. degrees in computer science from Korea Advanced
Institute of Science and Technology (KAIST), Korea, in 1990, 1992, and 1995, respectively. Currently,
he is a professor in Department of Bio and Brain Engineering, KAIST, and the director of Bio-Synergy
Research Center (BSRC), a Korean national research project where over 30 principal investigators are
collaborating for natural product bioinformatics and systems biology. He was a visiting professor of
Stanford University, Indiana University, Translational Genomics Research Institute (TGEN) and Univ.
of Texas at Austin, USA. He is also a technical advisor for CRS Diogenes SRL, Italy. He was an Associate Editor for ACM
Transactions on Internet Technology for nine years. He is also serving Computers in Biology and Medicine, International
Journal of Data Mining in Bioinformatics, and Healthcare Informatics Research as an Editorial Board Member. He is a co-
founder of ACM International Workshop on Data and Text Mining for Biomedical Informatics. He has published over 100
academic journal papers in bioinformatics, systems biology, and data mining. He also has around 20 technical patents.
www.bigcomputing.org 9
BigComp 2017
Keynote Speeches
Abstract:
Machine learning has achieved great success in both research and application during the past decade. It originated as a
research branch of artificial intelligence (AI), and becomes the mainstream of current AI research. In this talk, we will
briefly introduce the progress and status of machine learning, and discuss on some future perspectives. We will comment
on strengths and weakness of deep learning. Then, we will talk about challenges and opportunities introduced by open
environment machine learning tasks. Moreover, considering that in its current form of data + algorithm, machine
learning suffers from many weakness or even bottlenecks, such as the need of large amount of training data, the difficulty
of adapting to environmental change, the incomprehensibility, etc., we advocate to explore the form of learnware, which is
a well-performed pre-trained learning model with a specification explaining its purpose and/or specialty. Learnwares can
be put into a market, such that when one is going to tackle a machine learning task, rather than building his model from
scratch, he can do it in this way: Figure out his own requirement, and then browse/search the market, identify and adopt a
good learnware whose specification matches his requirement. In some cases he can use the learnware directly, whereas in
more cases he may need to use his own data to adapt/polish the learnware. Nevertheless, the whole process can be much
less expensive and more efficient than building a model from scratch by himself. If learnwares come to reality, strong
machine learning models can be achieved even for tasks with small data, and data privacy will become a less serious issue
for machine learning tasks. More importantly, it will enable common end users to achieve tricky learning performances
that previously can only be achieved by machine learning experts.
Short Biography
Zhi-Hua Zhou is a Professor and Founding Director of the LAMDA Group at Nanjing University. His
main research interests are in artificial intelligence, machine learning and data mining. He authored the
books Ensemble Methods: Foundations and Algorithms and Machine Learning (in Chinese), and
published more than 100 papers in top-tier international jour! nals and conference proceedings. His
work have received more than 23,000 citations, with a h-index of 74. He also holds 18 patents and has
good experiences in industrial collaborations. He has received various awards, including the National
Natural Science Award of China (premium science award in China), the PAKDD Distinguished Contribution Award, the
Microsoft Professorship Award, 12 international paper/competition awards, etc. He serves as the Executive Editor-in-Chief
of Frontiers of Computer Science, Associate Editor-in-Chief of Science China, and Associate Editor of ACM TIST, IEEE
TNNLS, etc. He founded ACML (Asian Conference on Machine Learning) and served as General co-chair of IEEE ICDM
2016, Program co-chair IJCAI 2015 Machine Learning track, etc. He also serves as the Chair of the IEEE CIS Data Mining
and Big Data Analytics Technical Committee, the CCF Artificial Intelligence Technical Committee, etc. He is a Fellow of
the ACM, AAAI, AAAS, IEEE, IAPR, IET/IEE and CCF.
Abstract:
We know little about microbes. Recently, huge amounts of data are generated from many microbiome projects such as the
Human Microbiome Project (HMP), Metagenomics of the Human Intestinal Tract (MetaHIT),etc. These datasets provide
opportunities to study the mystery of the microbial world, and analyzing these data will help us to better understand
the function and structure of the microbial community of the human body, earth and other environmental eco-systems.
However, the huge data volume, the complexity of the microbial community and the intricate data properties have created
a lot of opportunities and challenges for data analysis and mining. In this talk, I will discuss a computational framework to
tackle these challenging issues, focusing on the following three tasks: 1) visualization approaches to visualize microbiome
data and to infer microbial interactions and relations; 2) computational methods for identifying and visualizing higher-
order microbial interactions and relations from three types of microbiome datasets: metagenomes, bacterial genomes and
literatures respectively; 3) the extracted interactions and relations from different knowledge sources will be integrated in a
knowledge graph. Statistical and machine learning approaches is discussed for consistency checking of inferred microbial
interactions and relations.
Short Biography
Xiaohua Tony Hu is a professor and the founding Co-Director of the NSF Center (I/U CRC) on Visual
and Decision Informatics (NSF CVDI), IEEE Computer Society Bioinformatics and Biomedicine
Steering Committee Chair, and IEEE Computer Society Big Data Steering Committee Chair. He
joined Drexel University in 2002. Earlier, he worked as a research scientist in Nortel Research Center,
and Verizon Lab (the former GTE labs). In 2001, he founded the DMW Software in Silicon Valley,
California. Tonys current research interests are in data/text/web mining, big data and bioinformatics.
He has published more than 270 peer-reviewed research papers in various journals, conferences and books. His research
projects are funded by the National Science Foundation (NSF), US Dept. of Education, the PA Dept. of Health, the Natural
Science Foundation of China (NSFC). He has obtained more than US$8.0 million research grants in the past 8 years as PI
or Co-PI (PIs of 7 NSF grants, PI of 1 IMLS grant in the last 8 years), has graduated 18 Ph.D. students from 2006 to 2016,
and is currently supervising 10 Ph.D. students.
www.bigcomputing.org 11
BigComp 2017
Paper Sessions
Day 1 Monday, February 13, 2017 Day 2 Tuesday, February 14, 2017
08:30-12:30, February 13 (Monday) 08:30-10:30, February 14 (Tuesday)
Workshop 1 BigData4Healthcare (08:30-12:30, Regular Session 1: Network Models for Smart
JADE) Computing (I)
Keynote Speech: Patient Safety Events Prediction and Chair: Chong-Kwon Kim (Seoul National University)
Prevention using Clinical Big Data from Electronic [RS1-1] SEM: A Softmax-based Ensemble Model for
Health Records CTR Estimation in Real-Time Bidding Advertising
Hyeoun-Ae Park (Professor, College of Nursing, Seoul National Wen-Yuan Zhu (Industrial Technology Research Institute), Chun-
University, Korea / President, International Medical Informatics Hao Wang, Wen-Yueh Shih, Wen-Chih Peng, and Jiun-Long Huang
Association) (National Chiao Tung University)
Session WS1-1: Deep Learning Techniques for Medical [RS1-2] The Design and Benchmarking of a Cloud-
Applications based Platform for Processing and Visualization of
Session WS1-2: Healthcare Robotics and Rehabilitation Traffic Data
Session WS1-3: Big Data Techniques for Healthcare and Yikai Gong, Luca Morandini, and Richard O. Sinnott (The University
Well-Being of Melbourne)
[RS1-3] Improving Wi-Fi Performance using Smart AP
Kiseog Kim, Junhyun Park, and Chong-kwon Kim (Seoul National
14:00-18:00, February 13 (Monday)
University)
Tutorial 1 (14:00-18:00, CRYSTAL)
Machine Learning with Time Series Data Regular Session 2: Big Data Science for
Jaesik Choi (Ulsan National Institute of Science and Technology, Humanware
Korea) Chair: Fong Ci Lin (National Taiwan University)
[RS2-1] Smart Computing Mechanism for Noise
Workshop 2 Exobrain (14:00-18:00, JADE) Detection and Elimination in ECG Signal
Keynote Speech: Korean Semantic Resources & Korean Te-Wei Ho, Fong-Ci Lin, Ching-Miao Lin, and Feipei Lai (National
Semantic Processing Systems Taiwan University)
Cheol-Young Ock (Professor, School of IT Convergence, University of
[RS2-2] An Augmented Reality Application with Hand
Ulsan, Korea)
Gestures for Learning 3D Geometry
Invited Talk I: Commercial Deployment of Spoken Hong-Quan Le and Jee-In Kim (Konkuk University)
Dialog Systems [RS2-3] Head Pose-free Eye Gaze Prediction for Driver
Kyungduk Kim (NAVER Corp.)
Attention Study
Invited Talk II: The Exobrain Project Past, Present, Yafei Wang (Dalian University of Technology), Tongtong Zhao, Xueyan
and Future Ding (Dalian Maritime University), Jiming Bian (Dalian University of
Ho-Jin Choi (KAIST) Technology), and Xianping Fu (Dalian Maritime University)
Session WS2-1: Language Technologies for Human- [RS2-4] Music Synchronization with Video Using
Machine Knowledge Communication Emotion Similarity (short)
Ki-Ho Shin and In-Kwon Lee (Yonsei University)
Workshop 3 ASC 2017 (14:00-18:00,
AMETHYST) Regular Session 3: Image Retrieval and
Visualization
Session WS3-1: Sentimental and Affective Computing
Chair: Soonju Kang (Kyungpook National University)
Applications
[RS3-1] Efficient Fall Detection Based on Event Pattern
Session WS3-2: Sentimental and Affective Computing
Matching in Image Streams
Models
Hyun-Gook Kang, Minseo Kang, and Jae-Gil Lee (KAIST)
[RS3-2] Principal Elements for Visualizing Event
18:30-20:00, February 13 (Monday) Sequence Data Applied to 3D Cascading Diagrams
Youngju Oh, Seokyeol Kim, and Jinah Park (KAIST)
Welcoming Reception (CRYSTAL)
[RS3-3] Homecare Kit Platform Supporting Multiple Jeongwoo Kim, Jungrim Kim, Won Gi Choi, and Sanghyun Park
Bio-signals Acquisition and Analysis in Daily-life (Yonsei University)
Seol Young Jeong, Moon Sik Choi, Soon Ju Kang, and Ho-Won Lee [RS5-4] Position-Restricted Approximate String
(Kyungpook National University) Matching with Metric Hamming Distance
Sung-Hwan Kim and Hwan-Gue Cho (Pusan National University)
10:40-11:00, February 14 (Tuesday)
Opening of IEEE BigComp2017 Regular Session 6: Artificial Intelligence
Chair: Wookey Lee (Inha University, Korea) Techniques for Big Data
Welcoming Addresses Chair: Seung-Ik Lee (ETRI)
Choong Seon Hong, Kyung Hee University, Korea [RS6-1] CP-decomposition with Tensor Power Method
Xiaofang Zhou, University of Queensland, Australia for Convolutional Neural Networks Compression
Marcella Astrid (University of Science and Technology) and Seung-Ik
11:00-12:30, February 14 (Tuesday) Lee (ETRI)
www.bigcomputing.org 13
BigComp 2017
Paper Sessions
Day 3 Wednesday, February 15, 2017 Regular Session 9: Big Data and Mobile
Applications
09:00-10:30, February 15 (Wednesday) Chair: Victor Parque (Waseda University)
Keynote Speech 2 [RS9-1] A Power- and Storage-Efficient HLS Media
Chair: Chulyun Kim (Sookmyung Womens University) Server for Multi-Bitrate VOD Services
Sungchan Hur, Sukhyeun Cho, Youngho Kim, and Jeong Seop Sim (Inha
Machine Learning: Status and Perspectives University)
Zhi-Hua Zhou, Department of Computer Science & Technology,
Nanjing University, China [RS9-2] On Succinct Representation of Directed Graphs
(short)
Victor Parque and Tomoyuki Miyashita (Waseda University)
11:00-12:40, February 15 (Wednesday)
[RS9-3] Machine Learning based Path Management for
Regular Session 7: Network Models for Smart Mobile Devices over MPTCP (short)
Computing (II) Jonghwan Chung, Dahyeon Han, Jiyoung Kim, and Chong-Kwon Kim
Chair: Kyoungsoo Bok (Chungbuk National University) (Seoul National University)
[RS7-4] Forensic Analysis of the Backup Database File [RS10-3] Predicting Indoor Spatial Movement Using
in KakaoTalk Messenger (short) Data Mining and Movement Patterns
Jusop Choi, Jaewoo Park, and Hyoungshick Kim (Sungkyunkwan Luan Duong Minh Lam, Antony Tang (Swinburne University of
University) Technology), and John Grundy (Deakin University)
Regular Session 8: IoT and Security Architecture Regular Session 11: Challenges in Memory
for big data Management for big data
Chair: The-Hien Dang-Ha (University of Oslo) Chair: Hideyuki Kawashima (University of Tsukuba)
[RS8-1] Graph of Virtual Actors (GOVA): a Big Data [RS11-1] JUMPRUN: A Hybrid Mechanism to
Analytics Architecture for IoT Accelerate Item Scanning for In-Memory Databases
The-Hien Dang-Ha (University of Oslo), Davide Roverso (eSmart Hongyeol Lim and Giho Park (Sejong University)
Systems), and Roland Olsson (Hogskolen i Ostfold) [RS11-2] Accelerating Read Atomic Multi-partition
[RS8-2] Accelerated Search over Encrypted Cloud Data Transaction with Remote Direct Memory Access
Fateh Boucenna, Omar Nouali, Adel Dabah (CERIST), and Samir Naofumi Murata, Hideyuki Kawashima, and Osamu Tatebe (University
Kechid (USTHB) of Tsukuba)
[RS8-3] Efficient Parallel Summation on Encrypted [RS11-3] A Performance Study on Large-Scale Data
Database System Analytics Using Disk-Based and In-Memory Database
Kentaro Horio, Hideyuki Kawashima, and Osamu Tatebe (University Systems
of Tsukuba) Pingfu Chao, Dan He, Shazia Sadiq (The University of Queensland),
Kai Zheng (Soochow University), and Xiaofang Zhou (The University
[RS8-4] A Noise Parameter Configuration Technique of Queensland)
to Mitigate Detour Inference Attack on Differential
Privacy (short) [RS11-4] Challenges in Memory Subsystem Design for
Taebo Jung, Kangsoo Jung, Sehwa Park, and Seog Park (Sogang Future Smartphone Systems
University) Yunjoo Park and Hyokyung Bahn (Ewha Womans University)
www.bigcomputing.org 15
BigComp 2017
Paper Sessions
Regular Session 12: Semantic Web and Social Day 4 Thursday, February 16, 2017
Informatics
Chair: Tak-Lam Wong(The Education University of Hong Kong) 09:00-10:30, February 16 (Thursday)
[RS12-1] Sentiment Trend Analysis in Social Web Business Meeting
Environments
Kyunglag Kwon, Yunwan Jeon, Chanho Cho, Jongwoo Seo, In-Jeong
Chung (Korea University), and Hansaem Park (KAIST)
[RS12-2] Large-Scale Incremental OWL/RDFS
Reasoning over Fuzzy RDF Data
Batselem Jagvaral, Lee Wangon, Hyun-Kyu Park, Myungjoong Jeon,
Nam-Gee Lee, and Young-Tack Park (Soongsil University)
[RS12-3] Revisit Tag-based Profiles In The Folksonomy:
How Many Tags Are Sufficient For Profiling? (short)
Haoran Xie (The Education University of Hong Kong), An Liu
(Soochow University), Fu Lee Wang (Caritas Institute of Higher
Education), Tak-Lam Wong (The Education University of Hong
Kong), Xiao Liu (Soochow University), and Yanghui Rao (Sun Yat-sen
University)
Abstract
Time series models are essential to predict the future events in various applications such as finance, military and weather
forecasting. This tutorial will first introduce traditional linear/non-linear dynamic models to analyze time-series data. This
tutorial explain two recent advances in time series analysis: (1) Gaussian Processes based kernel decomposition method
for time series data and (2) Deep Learning (Convolutional Neural Network) based method and its application on EEG
(electroencephalogram) analysis.
Schedule
14:00-15:00 Unit1. Basics of Dynamic Models
Contents: Kalman Filter, Extended KF, Unscented Kalman Filter ad Particle Filter
15:00-15:15 Break
15:15-16:15 Unit2. Gaussian Processes based methods
Contents: Gaussian Processes, Automatic Statistician
16:15-16:30 Break
16:30-17:30 Unit3. Deep Learning based methods
Contents: Recurrent Convolutional Layers, EEG data analysis
Short Biography
Education
May 2012: PhD, Computer Science, University of Illinois at Urbana-Champaign
August 2004: BS, Computer Engineering, Seoul National University
Positions
July 2013 Present: Assistant Professor, School of Electrical and Computer Engineering, Ulsan
National Institute of Science and Technology
January 2013 July 2013: Postdoc, Lawrence Berkeley National Laboratory
May 2012 January 2013: Postdoc, University of Illinois at Urbana-Champaign
Selected Research Publications
The Relational Automatic Statistician, International Conference on Machine Learning, 2016
Spatio-Temporal Pyramid Matching, Computer Vision and Image Understanding, 2013
Lifted Relational Kalman Filtering, International Joint Conference on Artificial Intelligence, 2011
Research Interests
Statistical Inference, Probabilistic Graphical Model, Dynamic Bayesian Models, Robot Task Planning
www.bigcomputing.org 17
BigComp 2017
Workshop-1
Keynote Speech
08:30-09:45, February 13 (Monday), 2017
Chair: Ho-Jin Choi, KAIST
Patient Safety Events Prediction and Prevention using Clinical Big Data from Electronic Health Records
Speaker : Hyeoun-Ae Park (Seoul National University; President of International Medical Informatics Association)
Abstract:
The study aims to develop and test a patient safety event prediction and prevention system integrated with electronic health
records (EHR) system. Specific objectives are to develop risk prediction models for patient safety events such as fall,
pressure ulcer and adverse drug events of chemotherapy using big data analytics and integrate the models into EHR, and
to develop an evidence-based CDSS providing healthcare providers with tailored recommendations to prevent and manage
these patient safety events. We used a database containing EHRs of the patients discharged from Jan 1, 2015 to May 31,
2016 in a tertiary teaching hospital in Korea. The case group consists of patients with a safety event and the control group
without any safety event during hospital stay. Features were extracted from 10 different data sources and normalized based
on criteria such as completeness, currency, structure and granularity of documentation. Significant features were selected
using data visualization techniques and univariate statistical analyses. For fall and pressure ulcer, Cox-hazard model was
used to predict the time of patient safety event and logistic regression to predict the risk of patient safety event. For side
effect of chemotherapy, neural network architectures were used. The performance of prediction models for measures
of binary and survival outcomes was assessed using a variety of different methods and metrics such as goodness of fit
statistics, area under the ROC curve, sensitivity and specificity, and true positives.
Short Biography
Hyeoun-Ae Park is the President of International Medical Informatics Association (IMIA). She is also
a professor of College of Nursing at Seoul National University (SNU) teaching Nursing and Medical
Informatics at SNU. Prior to joining SNU in 1992, she was a research fellow at Korean Institute of Health
and Social Affairs. Dr. Park received her BS in Nursing from SNU, her MS and PhD in Biostatistics and
Health Informatics from the University of Minnesota. She had been a visiting scholar at health informatics
department at the University of Minnesota, and SNOMED CT International at the College of American
Pathologists. Her areas of research are healthcare vocabulary and terminology, especially around ICNP and SNOMED CT. Her
recent research focuses on ontology as a framework for social big data, and data mining and big data analytics in healthcare. She
served as a vice president of the IMIA in charge of Working Groups and Special Interest Groups for over 6 years from 2007 to
2013. She also served as the chair of NI Special Interest Group of the IMIA from 2012 to 2015. She received 2004 Distinguished
Leadership Award for Internationals and School of Nursing 100 Distinguished Alumni Award in 2008 from University of
Minnesota. She is a Fellow of American Academy of Nursing. She received Lael Cranmer Gatewood Distinguished Lectureship
Award for her leadership in Health Informatics at the 50th anniversary of Health Informatics Program at University of Minnesota.
Program
09:45-10:30, February 13 (Monday), 2017 [WS1-2-1] Rehabilitation Posture Correction Using
Deep Neural Network
Session WS1-1: Deep Learning Techniques for Seung-Ho Han, Han-Gyu Kim, and Ho-Jin Choi (KAIST)
Medical Applications [WS1-2-2] Neural Network-based Autonomous
Chair : Jung-Woo Ha (NAVER Corp.) Navigation for a Homecare Mobile Robot
[WS1-1-1] Clinical Opinions Generation from General ByungSoo Ko, Ho-Jin Choi, Chansol Hong, Jong-Hwan Kim, Oh Chul
Blood Test Results Using Deep Neural Network with Kwon, and Chang D. Yoo (KAIST)
Principle Component Analysis and Regularization [WS1-2-3] Discriminative Restricted Boltzmann
YouJin Kim, Han-Gyu Kim, Jonghwan Hyeon, and Ho-Jin Choi Machine for Emergency Detection on Healthcare Robot
(KAIST) Han-Gyu Kim, Seung-Ho Han, and Ho-Jin Choi (KAIST)
[WS1-1-2] Diagnosing Cervical Cell Images Using Pre-
trained Convolutional Neural Network as Feature 11:45-12:30, February 13 (Monday), 2017
Extractor
Jonghwan Hyeon, Ho-Jin Choi (KAIST), Byung Doo Lee, and Kap No Session WS1-3: Big Data Techniques for
Lee (Seegene Medical Foundation) Healthcare and Well-Being
[WS1-1-3] Predicting High-Risk Prognosis from Chair: Young-Seob Jeong (SoonChunHyang University)
Diagnostic Histories of Adult Disease Patients via Deep [WS1-3-1] Data Collection and Analysis of Smartphone
Recurrent Neural Networks Use and Sleep of Secondary School Children
Jung-Woo Ha, Adrian Kim, Dongwon Kim (NAVER Corp.), Jeonghee Heejune Ahn, Giang T. Nguyen, Heyoung Lee (SeoulTech), Sun-Jin Jo,
Kim (NAVER LABS Corp.), Jeong-Whun Kim, Jin Joo Park, and Eun-Jin Kim, and Hyeon-Woo Yim (Catholic University of Korea)
Borim Ryu (Seoul National University Bundang Hospital)
[WS1-3-2] Multi-source Food Hazard Event Extraction
for Public Health
10:30-11:00 Coffee Break Hwon Ihm, Kyoungrok Jang, Kangwook Lee, Gwan Jang, Min-Gwan
Seo, Kyoungah Han, and Sung-Hyon Myaeng (KAIST)
11:00-11:45, February 13 (Monday), 2017
[WS1-3-3] Context-based Healthy Lifestyle
Session WS1-2: Healthcare Robotics and Recommendation for Enhancing Users Wellness
Rehabilitation Chae-Gyun Lim, Zae Myung Kim, and Ho-Jin Choi (KAIST)
Chair: Han-Gyu Kim (KAIST)
www.bigcomputing.org 19
BigComp 2017
Workshop-2
Keynote Speech
14:00 - 15:15, February 13 (Monday), 2017
Chair: Ho-Jin Choi (KAIST)
Korean Semantic Resources & Korean Semantic Processing Systems
Cheol-Young Ock (Professor, School of IT Convergence, University of Ulsan, Korea)
Abstract:
For semantic processing such as sentence understanding and QA, many sematic resources are needed. One of most
important semantic resources is a semantic network. Prof. Ock has been constructing a Korean WordNet, namely Ulsan
Word Map (UWordMap) since 2002. The Ulsan Word Map has semantic hierarchy(hypernym and hyponym) like WordNet,
but it has another important information, subcategorization of argument of predicate. In this speech Prof. Ock will
introduce a structure of the UWordMap and how to use for word sense disambiguation of Korean and for understanding a
Query in Exo Brain SW.
Word representation, an important area in natural language processing(NLP) used machine learning, is a method that
represents a word not by text but by distinguishable symbol. Existing word embedding employed a large number of corpora
to ensure that words that were position near by in text. However, corpus-base word embedding need a lot of corpora
because the frequency of word occurrence and increase the number of words. Another word embedding(Sense Vector) is
done using dictionary definitions and semantic relationship information(hypernyms and antonyms). Then similar senses
words have similar vector. Furthermore, it was possible to distinguish vectors of antonym words. In this speech Prof. Ock
will introduce the Sense Vector and its applications of sematic operations.
Short Biography
Cheol-Young Ock is a professor of the school of IT convergence, University of Ulsan, Ulsan, Rep. of
Korea. He received his BS (1982), MS (1984), and PhD (1993) degrees in computer engineering from
the National University of Seoul, Seoul, Rep. of Korea. He has been a visiting professor at the Russia
Tomsk Institute (1994) and Glasgow University (1996). He has been the chairman of the sigHCLT
(2007~2008) in the KIISE, Rep. of Korea. He has been a visiting researcher at the National Institute
of Korean Language (2008). He received an honorary doctorate from the department of Information
and Computer Science, National University of Mongolia, Ulaanbaatar, Mongolia (2007). He received a government medal
as a meritorious engineer of Korean language development (2016). He has been constructing a Korean WordNet, namely
Ulsan Word Map (UWordMap) since 2002. His research interests include natural language processing (WSD), machine
learning, and text mining.
Program
Workshop 2 Exobrain 2017 Session WS2-1: Language Technologies for
15:15-16:00, February 13 (Monday), 2017 Human-Machine Knowledge Communication
Chair: Han-Gyu Kim (KAIST)
Invited Talk I
[WS2-1] Money Extraction and Normalization from
Chair: Young-Seob Jeong (SoonChunHyang University)
Texts
Commercial Deployment of Spoken Dialog Systems Young-Seob Jeong (SoonChunHyang University), Joong-Hwi Shin,
Kyungduk Kim (NAVER Corp.) Hyoung-Gyu Lee, Ying-Xiu Quan, and Jun-Seok Kim (NAVER Corp.)
[WS2-2] A Model of Korean Sentence Similairty
16:00-16:30 Coffee Break Measurement Using Sense-based Morpheme Embedding
and RNN Sentence Encoding
16:30-17:00, February 13 (Monday), 2017 Kyo-Joong Oh, Dongkeon Lee, Ho-Jin Choi (KAIST), and Jeong Hur
Invited Talk II (ETRI)
Chair: Kyo-Joong Oh (KAIST) [WS2-3] An Adaptive Vocabulary Learning Application
through Modeling Learners Linguistic Proficiency and
The Exobrain Project Past, Present, and Future
Interests
Ho-Jin Choi (KAIST)
Zae Myung Kim, Suin Kim, Alice Oh, and Ho-Jin Choi (KAIST)
17:00-18:00, February 13 (Monday), 2017 [WS2-4] The ChatBot Feels You - A Counseling Service
Using Emotional Response Generation
Dongkeon Lee, Kyo-Joong Oh, and Ho-Jin Choi (KAIST)
www.bigcomputing.org 21
BigComp 2017
Workshop-3
Workshop Co-Chairs Xiangping Zhai Nanjing University of Aeronautics and Astronautics, China
Wenji Ma Columbia University, USA
Haoran Xie The Education University of Hong Kong, Hong Kong
Yunhui Zhuang City University of Hong Kong, Hong Kong
Tak-Lam Wong The Education University of Hong Kong, Hong Kong
Debby Dan Wang Caritas Institute of Higher Education, Hong Kong
Fu Lee Wang Caritas Institute of Higher Education, Hong Kong
Xiaodong Li Hohai University, China
Raymond Wong University of New South Wales, Australia
Di Zou The Hong Kong Polytechnic University, Hong Kong
Xiaohui Tao University of Southern Queensland, Australia
Zhiwen Yu South China University of Technology, China
Yi Cai South China University of Technology, China
Programme Committee Yanghui Rao Sun Yat-sen University, China
Zhaoqing Pan Nanjing University of Info Sci & Tech, China Wenjuan Cui China Academy of Sciences, China
Raymong Y. K. Lau City University of Hong Kong, Hong Kong Wei Chen Agricultural Information Institute of CAAS, China
Ke Li Birmingham University, UK Tao Wang Southampton University, UK
Xudong Mao City University of Hong Kong, Hong Kong Gualiang Chen TU Delft, Netherland
Program
14:00-16:00, February 13 (Monday), 2017 16:30-18:00, February 13 (Monday), 2017
Session WS3-1: Sentimental and Affective Session WS3-2: Sentimental and Affective
Computing Applications Computing Models
Chair: Tak-Lam Wong (EdUHK, Hong Kong) Chair: Tak-Lam Wong (EdUHK, Hong Kong)
[WS3-1-1] High-Level Online User Attribution Model [WS3-2-1] A New Samples Selecting Method based on K
Based on Human Polychronic Monochronic Tendency Nearest Neighbors
Ikuesan Richard Adeyemi (University of Pretoria), Shukor Abd Kan Yang, Yi Cai, Zhiwei Cai, Xingwei Tan (South China University
Razak (Universiti Teknologi Malaysia), Hein S. Venter (University of of Technology), Haoran Xie, Tak-Lam Wong and Wai Hong Chan (The
Pretoria), and Mazleena Salleh (Universiti Teknologi Malaysia) Education University of Hong Kong)
[WS3-1-2] Market Impact Analysis via Sentimental [WS3-2-2] Sentimental Feature based Collaborative
Transfer Learning Filtering Recommendation
Xiaodong Li (Hohai University), Haoran Xie, Tak-Lam Wong (The Jingjing Cao and Wenfeng Li (Wuhan University of Technology)
Education University of Hong Kong) and Fu Lee Wang (Caritas
Institute of Higher Education) [WS3-2-3] An Effective Hybrid Model for Opinion
[WS3-1-3] LanguageTool based University Rumor Mining and Sentiment Analysis
Kai Yang, Yi Cai, Dongping Huang, Jingnan Li, Zikai Zhou and Xue
Detection on Sina Weibo
Lei (South China University of Technology)
Ying Jiang, Yujie Liu (Beijing Normal University) and Yalin Yang
(Zhuhai Weizhi Technology Co., Ltd.)
[WS3-1-4] Personalized Microblog Recommendation
Using Sentimental Features
Wenjuan Cui, Yi Du, Zhihong Shen, Yuanchun Zhou and Jianhui Li
(Chinese Academy of Sciences)
2F of main building
JADE
HALL
AMETHYST
HALL
CRYSTAL
HALL
www.bigcomputing.org 23
BigComp 2017
Venue
Accommodations
The Organizing Committee of BigComp2017 is pleased to negotiate with MAISON GLAD JEJU Hotel with discounted rates.
Please note that the special discounted rate can only be provided for reservation with the hotel reservation form and before the
deadline. The special rates and blocked rooms are for February 12-15, 2016 and on a first-come first-served basis. Once room blocks
at these hotels have been filled, we may not be able to secure further rooms with the hotels at the special rates quoted. Therefore,
early hotel reservation is highly recommended.
How to reserve?
Please return the completed reservation form (doc-KR, doc-EN) to the hotel by February 1, 2017.
Our reservation agent will sent you confirmation letter after booking.
Every inquiry about hotel reservation should be sent to Mr. Seongmoon Heo (the hotel) below.
To : Mr. Seongmoon Heo
Fax Number : +82 2 2278 2109
Telephone Number : +82 2 2278 2100
E-mail : oraseoul@oraresort.com
www.bigcomputing.org 25
BigComp 2017
Travel Information
Mt. Hallasan
Mt. Hallasan is the central peak of the gently
sloping shield volcano of Jeju Island. It is the
highest mountain in South Korea, reaching 1,950
m above the sea level. Mt. Hallasan boasts peculiar
volcanic landscape, produced by the crater lake
Baeknokdam at the summit, the precipitous rocky
cliffs of the Yeongsilgiam, and about 40 volcanic
cones. Baeknokdam crater is exceptional in that the
western half of that area is formed by trachyte lava,
whereas the eastern half is made of basalt lava. It is assumed that the trachytic lava dome was produced
first followed by the creation of the crater by basaltic volcanic activity. The mountain has been protected
from human activity since 1970 and is renowned for its unique ecology and biodiversity in addition to
volcanic geology and geomorphology.
Seongsan Ilchulbong
Seongsan Ilchulbong is an archetypal tuff
cone formed by hydrovolcanic eruptions upon
a shallow seabed about five thousand years
ago. The 180 m-high tuff cone, dominating
the eastern seaboard of Jeju Island, not only
preserves its bowl-like crater but also provides
excellent sea-cliff exposures of diverse
internal structures. These features have great
geologic value in that they provide a basis
for interpreting the eruptive and depositional
processes of hydromagmatic volcanoes worldwide in addition to the past volcanic activity of this tuff
cone.
The Seongsan Ilchulbong Tuff Cone is underlain by highly permeable, 120 m-thick lava. The lava
contained abundant water when they were submerged in seawater 5,000 years ago. The ascending magma
interacted with the groundwater within the lava, resulting in a tuff cone via powerful hydrovolcanic
eruptions. The groundwater and seawater were continuously supplied to the volcanic conduit through the
permeable lava, maintaining hydroexplosions until the end of the eruption of the tuff cone.
Vertical and spiral-shaped pillars of rocks surround the climbing path of Seongsan Ilchulbong Tuff Cone.
www.bigcomputing.org 27
BigComp 2017
Travel Information
During the hydrovolcanic eruption of this tuff cone, the pyroclastic (ash) deposits of the tuff cone piled
up steeply near the crater rim. Rain on the deposits forced a flow down the slope, and the deposits were
eroded over time by rain flushing thus creating a land that appears deeper than the ground itself.
Unique rocks like these surrounding the climbing path did not just spring out overnight but have been
formed by different erosion processes of unconsolidated tuff deposits by the rill-flow.
Geomunoreum
There are so many Oreums on Jeju Island that you can not climb them all even if you climb one every
day for a year. Geomunoreum is considered the best among them. Its name of Geomunoreum (Black
oreum) was derived from the fact that dense forest in its crater shows weird block color, and also means
a holy mountain. Its summit reaches 456m above sea level and measures 4.5km in circumference. At
the summit lies a deep crater, and the crater is shaped like a horse-shoe with a large opening in the
northeastern rim.
Gotjawal, ancient forests, grows in the interior of Geomunoreum crater. In these forests, nature has
carved deep crevices called Sumgol into the rocks. The crevices act as natural waterways that channel
rainwater into the ground. As it penetrates layers of scoria and basalt, the water is naturally cleansed of
impurities and fortified with minerals.
To see Geomunoreum, visitors must sign up for a guided tour at the Visitor Center.
www.bigcomputing.org 29
BigComp 2017
MEMO
www.bigcomputing.org 31
BigComp 2017
www.bigcomputing.org