CONTENTS · search topics in AI with brain and communications; topics in-clude BMI, signal...

C O N TE N TS

1. Welcome to IEEE/IEIE

ICCE-Asia 2018 _ 02

2. Technical Program Overview _ 05

3. Committee- Organizing Committee _ 06

- Technical Program Committee _ 07

4. Time Table _ 09

5. Floor Map _ 11

6. Conference Information- Presentation _ 14

- Lunch _ 14

- Social Program _ 15

7. Plenary Talks _ 16

8. Tutorials _ 22

9. Technical Program- Special Session _ 36

- Regular Session _ 45

- Poster Session _ 52

11. Conference Venue _ 65

2

Welcome to IEEE/IEIEICCE-Asia 2018

Hwan-yong-ham-ni-da (welcome in Korean). On behalf of the organizing committee of the Third International Conference on Consumer Electronics-Asia (ICCE-Asia) sponsored by both the IEEE Consumer Electronics (CE) Society and the Institute of Electronic and Information Engineers (IEIE), it is our great pleasure to welcome you to the most beautiful is-land in East Asia which is located just 64km off the southern coast of Korea- the Jeju Island.

The latest technology wave in consumer electronics has ushered in the era of Artificial Intelligence or AI. It is without a question that this exciting new era presents a huge number of technical challenges and, at the same time, offers tremen-dous opportunities, for developers and researchers in the con-sumer electronic industry. This year’s conference theme is “AI and drone”. We hope that the latest R&D results at the conference can lay the foundation to the development of next generation technologies for a better bright future.

As you will witness in the next few days, we have put to-gether a very exciting technical program that includes oral and poster presentation, 3 plenary speakers, 9 tutorials and 11 special sessions. Under the guidance of our very able Technical Program Chair Professor Sangheon Pack, over 260 papers were reviewed in a timely manner. The three plenary speak-ers are Prof. Junho Oh at KAIST on Robot Technology and Future, Chairman Minhwa Lee at Korea Creative Economy Research Network (KCERN) on Technology Model of the Fourth Industrial Revolution and Professor Angela Schoellig (University of Toronto) on the topic of drone.

The 9 tutorials related to AI organized by tutorial Chair Prof. Junmo Kim are as follows: (1) Explainable Artificial Intelligence: Models and Applications, (2) Deep Neural Net-works for Recognition in Videos, (3) Energizing and Power-ing Microsensors, (4) Multi-task and Continual Learning for Deep Reinforcement Learning, (5) Deep Reinforcement Learn-ing and AlphaGo, (6) Bayesian Analysis and Its Applications in AI, (7) Interface Between Data Collection and Statistical Modeling - An Industrial Statistician's Perspective, (8) Tensor-Flow Recipes for Deep Learning Method, and (9) Visually-Grounded Question and Answering: from VisualQA to MovieQA.

3

The 11 special sessions organized by Special Session Chair Prof. Sang Wan Lee are as follows: (1) AI World Cup ses-sion: presentation of winners in AI World Cup Contest, (2) Women in the Electronics Industry: provides the opportunity to network and share the experience for women engineers and researchers, and mentors female participants. (3) WEIE Workshop - AI with brain and communication: discuss re-search topics in AI with brain and communications; topics in-clude BMI, signal processing, micro wave and mobile system, machine learning and deep learning, and service computing. (4) Quantum AI: presents recent advances in quantum com-puting technologies and discusses possibilities to build AI with increased computation capacity, speed, while reducing power consumption. (5) Advanced image processing and un-derstanding: to understand recent trend in image processing and understanding. (6) Control and Its Applications: discuss various emerging topics on control and optimization with ap-plications of unmanned aerial vehicles and autonomous driv-ing systems. (7) Intelligent Cyber-Physical System (iCPS): in-troduces cutting-edge technologies on software platform and software engineering for intelligent Cyber-Physical Systems (CPS). (8) Digital Acquisition and Reconstruction: discuss high-quality digital acquisition and reconstruction of real ob-jects (multimedia data). (9) Emotion recognition for social ro-bots: discuss recent progress in emotion recognition technol-ogy for human-like social robots. (10) Journal Paper Presentation Session, and (11) AI young investigator session.

Apart from the conference, we would like to draw atten-tion to Jeju Island, also known as the “Island of the Gods”, is a favorite vacation spot for Koreans as wells as for many foreigners. Island offers a wide range of activities: hiking on Halla-san (South Korea's highest peak) or Olle-gil(routes), catching sunrises and sunsets over the ocean, riding horses, touring all the locales from a favorite television K-drama, or just lying around on the sandy beaches.

The Organizing Committee of ICCE-Asia 2018 is thankful for the generous support from industry and Korean Tourism Organization. We wish express our heart-felt appreciation.

We would like to thank every member of the Organizing Committee especially Organizing Chair Jong-Moon Chung, and TPC members, without whom this conference would not be possible. We would like especially to acknowledge the many student volunteers who are going to be instrumental throughout the conference. The staff members, the student volunteers, and the Organizing Committee shall continue to serve the delegates throughout the conference.

4

The organizing committee is confident that you will find the ICCE-Asia 2018 a memorable and pleasant event that shall have a lasting impact on your professional career.

General ChairChang D. Yoo

Korea Advanced Institute of Science and Technology

General Co-chairJoonki Paik

Chung-Ang University

Seung-Kwon AhnVice President IEIE & President of LG Science Park and LG

Technology Council

Sharon PengPresident IEEE CE Society

Dong Eui ChangKAIST

5

Technical Program Overview

It is great pleasure to welcome all of you to ICCE-Asia 2018 on behalf of all technical program committee members. First of all, I would like to express my sincere thanks to all program committee members and organizing members who dedicated to the wonderful technical program in ICCE-Asia 2018.

In this year, more than 260 papers from 18 countries have been submitted to regular and special sessions. After rigorous review process, around 160 regular papers were selected and they are organized into 4 oral presentation sessions and 3 poster presentation sessions. In addition, around 50 special session papers were arranged in 11 sessions that cover artifi-cial intelligence (AI), cyber-physics systems (CPS), quantum computing, robots, and so on.

In ICCE-Asia 2018, we have invited three valuable ple-nary speakers: Prof. Jun Ho Oh (Korea Advanced Institute of Science and Technology (KAIST)), Dr. Min-Hwa Lee (Korea Creative Economy Research Network (KCERN)), and Prof. Angela Schoellig (University of Toronto Institute for Aeros-pace Studies (UTIAS)). In addition, 9 tutorials were planned to provide both fundamental theory and practical techniques, and their topics include explainable AI, deep neural net-works/deep reinforcement learning, microsensors, bayesian analysis/statistical modeling, TensorFlow, and visually-grounded question and answering. All of them contributed to our ex-cellent technical program.

I believe and promise that ICCE-Asia 2018 will be the best opportunity to broaden your perspectives and build real rela-tionships for better collaboration in this field.

Thank you very much.

Technical Program ChairSangheon Pack

Korea University, Korea

6

Committee

Organizing Committee

General ChairChang Dong Yoo (KAIST)

General Co-ChairJoonki Paik (Chung-Ang University)

Seung-Kwon Ahn (Vice President IEIE &President LG Science Park and LG Technology Council)

Sharon Peng (President IEEE CE Society)

Dong Eui Chang (KAIST)

Technical Program Committee ChairSangheon Pack (Korea University)

Organizing ChairJong-Moon Chung (Yonsei University)

Industrial Relations ChairJaesik Choi (UNIST)

Jun-jin Kong (Samsung Electronics Co., Ltd.)

Industry Liaison ChairStefan Mozar (CEO Dynexsys)

Publicity ChairJang-Myung Lee (Pusan National University)

Alex James (Nazarbayev University)

Plenary and Tutorial ChairJunmo Kim (KAIST)

Publication ChairDonggyu Sim (Kwangwoon University)

Special Session ChairSang Wan Lee (KAIST)

Registration ChairGil-Jin Jang (Kyungpook National University)

7

Local ChairJinwook Burm (Sogang University)

Finance ChairGwangsu Kim (KAIST)

International Advisory Committee ChairSung-Jea Ko (Korea University)

Stephen Dukes (IEEE Consumer Electronics Society)

Technical Program Committee

TPC ChairSangheon Pack (Korea University)

TPC MemberByung Tae Oh (Korea Aerospace University)

Chang-Su Kim (Korea University)

Chang-Woo Lee (The Catholic University)

Changwoo Yoon (ETRI)

Chee Sun Won (Dongguk University)

Cheulhee Hahm (Samsung Electronics)

Dong Seog Han (Kyungpook National University)

Dongyoung Koo (Korea University)

Goo-Rak Kwon (Chosun University)

Heejun Roh (Korea University)

Hong Min-Cheol (Soongsil University)

Hui Yong Kim (ETRI)

Humaira Nisar (Universiti Tunku Abdul Rahman)

Hyeon-Jeong Suk (KAIST)

HyungWon Kim (Chungbuk National University)

Hyunhee Park (Korean Bible University)

Jaeseok Kim (Yonsei University)

Jae-Young Pyun (Chosun University)

Jang Woon Baek (ETRI)

JeongYon Shim (Kangnam University)

Jong Ki Han (Sejong University)

Junbeom Hur (Korea University)

Kwang-Soon Choi (Korea Electronics Technology Institute)

Michael O'Grady (University College Dublin)

Milan Bjelica (University of Novi Sad)

Moongu Jeon (Gwangju Institute of Science and Technology (GIST))

8

Muhammad Mahmood (Korea University)

Seon Wook Kim (Korea University)

Shouyi Yin (Tsinghua University)

Soochan Kim (Hankyong National University)

Sooyong Choi (Yonsei University)

Sooyoung Kim (Chonbuk National University)

Sudarshan Tsb (PES University, Bangalore, INDIA)

Sunwoo Kim (Hanyang University)

Thinagaran Perumal (University Putra Malaysia)

Tran Trung Duy (Posts and Telecommunications Institute of Technology)

Vivek M (SRM University)

Wei Wei (Xi'an University of Technology)

Won Woo Ro (Yonsei University)

Wonjong Kim (ETRI)

Yonghwan Kim (Korea Electronics Technology Institute)

Young-cheol Park (Yonsei University)

Arun Kudana (Continental Automotive)

Bob Frankston (Frankston)

Haneul Ko (Korea University)

Hyung-Min Lee (Korea University)

In Tae Ryoo (Kyung Hee University)

Koustabh Dolui (Fondazione Bruno Kessler)

Kyeongok Kang (ETRI)

Nippun Kumaar Aa (Amrita Vishwa Vidyapeetham, Amrita School of Engineering)

Soo Jin Kim (Korea University)

Stefan Mozar (Dynexsys Pty Ltd, Sydney)

9

Time Table

June 24th (Sun), 2018

RoomTime

Grand Ballroom 1

Grand Ballroom 2

Grand Ballroom 3

Grand Ballroom 4

Udo Mara Biyang ChujaPoster(Lobby)

11:00- Registration

12:00-13:30

Tutorial 1

Prof. Taesup Moon

Tutorial 2

Prof. Sae-Young

Chung

Tutorial 3

Prof. Gil-Jin Jang

13:30-13:45 Break

13:45-15:15

Tutorial 1

Prof. Taesup Moon

Tutorial 2

Prof. Sae-Young

Chung

Tutorial 3

Prof. Gil-Jin Jang

15:15-15:30 Break

15:30-17:00

Tutorial 4

Prof. Jaesik Choi

Tutorial 5

Prof. Bohyung

Han

Tutorial 6

Prof. Gabriel A. Rincón-

Mora

17:00-17:15 Break

17:15-18:45

Tutorial 4

Prof. Jaesik Choi

Tutorial 5

Prof. Bohyung

Han

Tutorial 6

Prof. Gabriel A. Rincón-

Mora

19:00- Reception

June 25th (Mon), 2018

RoomTime

Grand Ballroom 1

Grand Ballroom 2

Grand Ballroom 3

Grand Ballroom 4


08:30-16:00 Registration

09:00-11:00 RS1 RS2 RS3 SS1 SS2 SS3 SS4Poster

Session 109:30-11:00

11:10-11:30 Opening Ceremony (Grand Ballroom 1)

11:30-12:30 Plenary I (Grand Ballroom 1)

12:30-13:30 Lunch (TAMMORA 1F)

13:30-14:30 Plenary II (Grand Ballroom 1)

14:30-15:30 Plenary III (Grand Ballroom 1)

15:30-15:40 Coffee Break

15:40-17:40 SS5 RS4 SS6 SS7 SS8Poster

Session 216:10-17:40

18:30 BANQUET (Grand Ballroom 1)

10

June 26th (Tue), 2018

RoomTime

Grand Ballroom 1

Grand Ballroom 2

Grand Ballroom 3

Grand Ballroom 4


08:30-13:00 Registration

08:45-10:15

Tutorial 7

Prof. Youngdeok

Hwang

Tutorial 8

Jung-Woo Ha

10:15-10:30 Break

10:30-12:00

Tutorial 7

Prof. Youngdeok

Hwang

Tutorial 8

Jung-Woo Ha

12:00-13:00 Lunch (TAMMORA 1F)

13:00-15:00

Tutorial 9

Prof. Gwangsu

Kim(13:00-16:00)

RS5 RS6 RS7 RS8 SS9 SS10 SS11Poster

Session 313:00-14:30

11

Floor Map

2F

- Registration : Lobby (2F)- Opening Ceremony : GrandBallroom 1- Banquet : GrandBallroom 1- Lunch : TAMMORA (1F)

12

Conference Information

Author RegistrationAt least one author of every accepted paper should have a Regular Registration no later than May 31, 2018 to be pre-sented at the conference and included in the proceedings.One regular registration will cover the publication of only one accepted paper. Each additional accepted paper by the same “corresponding” author will follow the policy described below.

Accepted Papers(by the Same

Author)First Paper

Second Paper

Third PaperRest of the

Paper

One PaperRegular

registration

Two PapersRegular

registrationStudent

Registration

Three PapersRegular

registrationStudent

RegistrationStudent

Registration

Four Papers or More

Regular registration

Student Registration

Student Registration

Free

Pre-Registration Fee

Category

Overseas Domestic

Non-IEEE, IEIE, CES

member

IEEE member

IEEE CES or IEIE member

Non-IEEE,IEIE,CES member

Regular USD 750 USD 700 USD 650 KRW 825,000

StudentRegistration

USD 475 USD 425 KRW 522,500 KRW 467,500

AdditionalProceeding

USD 50 KRW 55,000

AdditionalBanquet

USD 70 KRW 77,000

13

Registration Fee includes

Regular RegistrationAdmission to All Sessions, Conference Proceedings, Banquet, Coffee Breaks

Student RegistrationAdmission to All Sessions, Conference Proceedings, Coffee Breaks* A banquet ticket is not included.

Payment MethodCredit CardAll transactions by credit card will appear on your statement as payment to Conference by ‘Allat’

Bank Transfer⋅Name of Bank: CITI Bank Korea, Science Technology

Branch, Seoul, Korea⋅SWIFT Code: CITIKRSX⋅Account Number: 186-04460-247-01⋅Name of Account Holder: The Institute of Electronics and

Information Engineers* You should transfer registration fee within 7 days from registration.* You should send a copy of transaction with your name on it to the

secretariat by fax (+82 2 552 6093) or e-mail ([email protected]) for confirmation.

* All bank remittance charges are to be paid by the registrants.

Cancellation and Refund PolicyTo cancel your registration, please notify the secretariat by an email to [email protected]. Refunds will be made if cancella-tion occurs before May 31, 2018, with the processing fee of USD 100 (KRW110,000). No refund will be made after May 31, 2018 or for no show. If you have any questions regarding the registration, please contact the secretariat.

All dates and time are indicated in KST (The local time in Korea)

14

Presentation

Oral PresentationPlease meet the session chair at your session at least 15 mi-nutes before the session starts. You should identify yourself to the session chair and check in with the AV staff to go over your equipment needs. You need to bring your ppt file on USB memory, and load it on the computer in your session room. You also need to confirm whether it is working properly. This is very important to pay attention to this time frame. The visual equipment provided is a beam projector.

Time assignment including discussion is as follow

Tutorial : 180 minutesPlenary : 60 minutesRegular : 15 minutes

Poster PresentationThe size of the poster board is 100cm × 180cm. You need to prepare your poster within this size and attach it on the poster board in your session room at least 10 minutes before the ses-sion starts, and then remove your poster immediately after the session finishes.

Lunch

Lunch will be provided to all participants during the conference. Please bring your lunch coupon with your name tag.

Location TAMMORA (1F)

Operating TimeJune 25 (Mon) 12:30-13:30June 26 (Tue) 12:00-13:00

15

Social Program

Welcome ReceptionDate : Sunday, June 24, 2018Time : 19:00Place : Lobby (2F)

An invitation to the welcome reception is extended to all par-ticipants including registered students.

Opening CeremonyDate : Monday, June 25, 2018Time : 11:10-11:30Place : GrandBallroom I

All registered participants are cordially invited to join us and celebrate the official opening.

BanquetDate : Monday, June 25, 2018Time : 18:30Place : GrandBallroom I

We hope this banquet will offer you a good opportunity to promote friendship with participants. Delicious food and spe-cial performance will be offered at the banquet. A banquet ticket is included in the Regular Registration. Student Regist-ration does not include the banquet.

16

Plenary Talks

Plenary Talk 1

11:30~12:30 Monday, June 25, 2018

Room: Grand Ballroom 1

Prof. Jun Ho Oh⋅Professor of Mechanical Engineering

⋅Director of Humanoid Robot Research Center(Hubo Lab)⋅Korea Advanced Institute of Science and Technology

Robot Technology and the Future

Abstract

World widely, various types of intelligent service robots are being on the research, and already became well ac-quainted with human beings. Also, many people expect these robots will be living together with mankind at work or home in the foreseeable future. Nevertheless, many people yet have a pessimistic point of view about the ultimate form of robot would be impossible to be realized in the real at the technol-ogy view. And the technology level required to accomplish a task given by the user is very different according to the appli-cation requirement. Some simple task may be achieved by simple robotic technology but some others are not. That means that commercial realization of service robot strongly depends on the gap between market requirement and technol-ogy level available. The lecture will also mention the history of robot development and application of robot in the various fields.

Biography

Prof. Jun Ho Oh received his B.S. and M.S. degree from Yonsei University, Seoul, Korea in 1977 and 1979, respectively. After short working at Korea Atomic Energy Research Institute as a researcher from 1979 to 1981, he re-ceived Ph.D. degree in mechanical engineering in the field of automatic control at U.C., Berkeley in 1985. He is now a chair professor of mechanical engineering and the director of Humanoid robot research center(Hubo Lab) at Korea Advanced Institute of Science and Technology (KAIST).

17

He performed many industry and government research projects in motion control, sensors, microprocessor applica-tions, and robotics, etc. He is especially interested in mecha-tronics and system integration. In the recently ten years, he completed unique humanoid robot series KHR-1, KHR-2, Hubo and Hubo 2. And he also developed Albert Hubo and Hubo FX-1. He leaded team KAIST and won Darpa Robot Challenge final as first place at Pomona, Ca, USA in 2015. He is currently studying to improve the performance of hu-manoid robot for faster and more stable walking, robust robot system integration and light weight design, etc. He is a mem-ber of ASME and IEEE. And he also is the member of the National Academy of Engineering of Korea and the member of Korea Academy of Science and Technology.

18

Plenary Talk 2

13:30~14:30 Monday, June 25, 2018


Min-Hwa Lee, Ph.D.⋅Chairman of KCERN

⋅Visiting Professor of KAIST

Technology model of the Fourth Industrial Revolution, AI+12 Tech

Abstract

Various concepts are being developed based on hyper-connectivity and superintelligence of the Fourth Industrial Revolution. However, existing concepts shaped by the techno-logical perspective have not been able to explain the significance of the Fourth Industrial Revolution. In this paper, the compre-hensive offline-online (O2O) convergence of the Fourth Industrial Revolution is used to define the revolution as a “convergence of online and offline worlds for human” By analyz-ing unicorn companies, which are the icons of the Fourth Industrial Revolution, the O2O parallel model that overcomes the limitations of the offline world and a 4-step convergence proc-ess for self-organization are provided. Further, the limitations of the existing technological models of the Fourth Industrial Revolution are observed, and the “AI+12 Tech” (Artificial Intelligence+12 Technologies) model, a O2O convergence tech-nological model is suggested, with six digital transformation tech-nologies that transform atom to bit and six analog transformation technologies that transform optimized data by artificial in-telligence to real atom world again.

Biography

Based on the study results and numerous published research papers in KAIST, Dr. Min-Hwa Lee established S. Korea’s first venture company, Medison Co., Ltd. in 1985, which has grown into a global medical equipment company. Through this experi-ence, he promoted and contributed on the establishment of more than 30 medical companies accounting for 70% of S. Korea’s medical equipment exports.

He played a leading role in founding Korea Venture Business Association in 1995 and announced the Vision 2005. He also paved the way for venture companies to flourish in S. Korea by

19

enacting special law on venture companies, establishing KOSDAQ, and initiating various venture policies including stock option, venture building and laboratory business start-up. In ad-dition, he wrote a number of books such as Han-Business Management, The history of S. Korea Venture Industry, How to Become a Country with Venture Superpower in 21st Century, Beyond Bio-Enterprise, and he contributed to keep the pride of S. Korean software while leading the campaign to save ‘Hangul’.

The awards he has received include Gold Tower Order of Industrial Service Merit, Silver and Iron Tower Order of Industrial Service Merit from S. Korea Government, Small and Medium Business CEO Award, Korea Management Award and Korea Engineering Technology Award.

Since 1998, he has been a chairman of Small and Medium Business Committee, Regulatory Reform Committee, Presidential Commission on Judicial Reform, KAIST Alumni Association and has contributed to the vitalization of venture sharing activities. He was also selected as one of 2007 Top 60 Engineers in S. Korea.

In 2008 he has advocated Eurasian Network movement as S. Korea’s strategy to become a developed country, and with the re-spect to the movement he established Eurasian Network Association. and is supporting the Eurasian humanities research and study of the Humanities Institute.

In 2008, he proposed ‘Venture 2.0’ movement for a new leap forward of venture business with the belief that it would be a dy-namic force for S. Korea’s growth, and he has been leading the projects related to venture biotope, fair trade, M&A market.

On July 23rd, 2009, Dr. Min-Hwa Lee was appointed the first ombudsman at Office of the Small and Medium Business Ombudsman whose foundation was part of the government’s de-regulation policy. While fulfilling his duty as the ombudsman, he worked on finding out unnecessary regulations that needed to be changed and eliminating unreasonable regulations.

On February 17th 2011, the Ministry of Knowledge Economy launched the ‘Korea Digital Hospital Export Agency (KOHEA)’, a private-run organization dedicated to exporting digital hospital package. Dr. Min-Hwa Lee became the first chairman of KOHEA and is currently still serving.

On June, 2009, Dr. Min-Hwa Lee has established the Creative Economy Research Society to plan the civilian future of S. Korea.

Dr. Min-Hwa Lee is teaching entrepreneurship and venture as a visiting professor at KAIST University and is also supervising the nurturing of young gifted entrepreneurs.

20

Plenary Talk 3

14:30~15:30 Monday, June 25, 2018


Prof. Dr. Angela Schoellig⋅University of Toronto Institute for Aerospace Studies

(UTIAS)

Topic Area: Robotics, Control Theory, Machine Learning, Dynamic Systems, Quadrotors,

Self-Driving Vehicles

Biography

Angela Schoellig is an Assistant Professor at the University of Toronto Institute for Aerospace Studies (UTIAS), where she heads the Dynamic Systems Lab. She is also an Associate Director of the Center for Aerial Robotics Research and Education (CARRE) at the University of Toronto. With her team, she conducts research at the interface of robotics, con-trols and machine learning. Her goal is to enhance the per-formance, safety and autonomy of robots by enabling them to learn from past experiments and from each other. Angela has been working with aerial vehicles for the past nine years and, more recently, has applied her motion planning, control and learning algorithms to self-driving vehicles. You can watch her robots perform slalom races and flight dances at www.youtube.com/user/angelaschoe.

She is a recipient of a Sloan Research Fellowship (as one of two in the area of robotics; US/Canada-wide award), a Ministry of Research, Innovation & Science Early Researcher Award, a Connaught New Researcher Award, and the Best Robotics Paper Award at CRV 2014. She is one of Robohub’s “25 women in robotics you need to know about (2013)”, win-ner of MIT’s Enabling Society Tech Competition, finalist of Dubai’s 2015 $1M “Drones for Good” competition, and youngest member of the 2014 Science Leadership Program, which promotes outstanding scientists in Canada. She has been a keynote speaker at various outreach events including TEDxUofT, Lift China, and the Girls Leadership in Engi-neering Experience weekend.

21

Angela received her Ph.D. from ETH Zurich (with Prof. Raffaello D’Andrea), and holds both an M.Sc. in Engineering Science and Mechanics from the Georgia Institute of Technology (with Prof. Magnus Egerstedt) and a Masters de-gree in Engineering Cybernetics from the University of Stuttgart, Germany (with Prof. Frank Allgöwer). Her Ph.D. was awarded the ETH Medal and the 2013 Dimitris N. Chorafas Foundation Award (as one of 35 worldwide).

22

Tutorials

Tutorial 1

12:00~15:15 Sunday, June 24, 2018


Prof. Taesup Moon⋅Sungkyunkwan University (SKKU)

Multi-task and continual learning for deep reinforce-ment learning

Abstract

Recently, deep reinforcement learning, which combines deep neural networks with reinforcement learning has made significant impacts in several areas that involve interactive environments for learning, e.g., game playing and robotics. Although those impacts were impressive, namely, often ach-ieving superhuman performance as in AlphaGo and Atari game playing, one of the important remaining challenges is to make those algorithms quickly generalize to correlated tasks (multi-task) and not forget already learned tasks (continual). In this tutorial, I will first review some basic methods that were shown to be effective for deep RL, such as policy gra-dient, deep Q-network, and actor-critic methods. Then, I will cover more recent approaches that attempt to address chal-lenges for multi-task and continual deep RL and summarize the high-level ideas of those approaches, e.g., model ex-pansion / distillation, Bayesian regularization, modular ap-proaches, and using external memory structures. Finally, I will conclude with some potential future research directions.

Biography

Taesup Moon received the B.S. degree in electrical en-gineering from Seoul National University in 2002 and the M.S. and Ph.D. degrees in electrical engineering from Stanford University in 2004 and 2008, respectively. From 2008 to 2012, he was a Research Scientist with Yahoo! Labs, Sunnyvale, CA, and he held a Post-Doctoral Researcher ap-

23

pointment with the Department of Statistics, UC Berkeley, from 2012 to 2013. From 2013 to 2015, he was a Research Staff Member with Samsung Advanced Institute of Technology, Samsung Electronics, Inc. From 2015 to 2017, he was an Assistant Professor at the Department of Informa-tion and Communication Engineering, Daegu- Gyeongbuk Institute of Science and Technology (DGIST). Since March 2017, he has been an Assistant Professor at the School of Electronic and Electrical Engineering, College of Information and Communication Engineering, Sungkyunkwan University (SKKU).

His research interests include diverse areas such as ma-chine learning (deep learning), information theory, signal processing, speech recognition, and remote sensing. He is a recipient of GE Scholarship and Samsung Scholarship.

24

Tutorial 2

12:00~15:15 Sunday, June 24, 2018


Prof. Sae-Young Chung⋅KAIST

Deep Reinforcement Learning and AlphaGo

Abstract

Deep reinforcement learning can solve seemly intractable reinforcement learning problems such as learning to play ar-cade games directly from video and learning to play the game of Go. In this tutorial, I will first talk about some basics of deep reinforcement learning including value-based methods, deep Q-network (DQN), policy-based methods, actor-critic methods, A3C, hierarchical reinforcement learning, issues with exploration and learning speed, and model-based re-inforcement learning. I will then talk about AlphaGo and AlphaGo Zero, principles behind their operations, and how training is done for them.

Biography

Sae-Young Chung received the B.S. and M.S. degrees in electrical engineering from Seoul National University, Seoul, South Korea, in 1990 and 1992, respectively and the Ph.D. degree in electrical engineering and computer science from the Massachusetts Institute of Technology, Cambridge, MA, USA, in 2000. From September 2000 to December 2004, he was with Airvana, Inc., Chelmsford, MA, USA. Since January 2005, he has been with the School of Electrical Engineering, KAIST, Daejeon, South Korea, where he is currently Professor. He served as Associate Editor for the IEEE Transactions on Communications from 2009 to 2013 and for the IEEE Transactions on Information Theory from 2014 to 2016. He served as the Technical Program Co-Chair of the 2014 IEEE International Symposium on Information Theory and as the Technical Program Co-Chair of the 2015 IEEE Information Theory Workshop. His research interests include information theory, deep learning, and reinforcement learning.

25

Tutorial 3

12:00~15:15 Sunday, June 24, 2018


Prof. Gil-Jin Jang⋅Kyungpook National University

TensorFlow Recipes for Deep Learning Methods

Abstract

This tutorial is for the beginners in deep learning and TensorFlow. The main objective of the tutorial is to help the be-ginners write their own TensorFlow programs by introducing ref-erence program examples from the basic concept to the advanced network architectures. Topics include primitive TensorFlow data structures such as variables, placeholders, tensors, and matrices; implementation skills for graph building, network layers, loss function design, and training algorithms; basic neural network ar-chitectures; convolutional neural networks (CNNs) with MNIST and CIFAR10 examples; advanced architectures including AlexNet and VGGNet; recurrent neural networks (RNNs) with text processing examples; extra implementation tips.

Biography

Dr. Gil-Jin Jang is an associate professor at Kyungpook National University, South Korea. He received his B.S. and M.S. degree in computer science from the Korea Advanced Institute of Science and Technology (KAIST), Daejon, South Korea in 1997 and 1999 respectively. He also received his Ph.D. degree in the same department in February 2004. From 2004 to 2006 he was a research staff at Samsung Advanced Institute of Technology and from 2006 to 2007 he worked as a research engineer at Softmax, Inc. in San Diego. From 2008 to 2009 he joined Shiley Eye Center at University of California, San Diego as a postdoctoral scholar. From November 2009 to February 2014 he was an assis-tant professor at School of Electrical and Computer Engineering, Ulsan National Institute of Science and Technology (UNIST). Dr. Jang's research interests include deep learning and machine learning theories, acoustic signal processing, speech recognition and enhancement, computer vision, multimedia data analysis, and biomedical signal engineering.

26

Tutorial 4

15:30~18:45 Sunday, June 24, 2018


Prof. Jaesik Choi⋅UNIST

Explainable Artificial Intelligence: Models and Applications

Abstract

Recent advances in artificial intelligence have strong po-tential to change our lives in a disruptive manner. Big data and enhanced computing power have led the way to build successful applications in many domains such as Go game and autonomous navigation. However, there is still a notice-able gaps to apply recently advanced AI technology to vari-ous practical applications in our daily lives. One of the main challenges is to make the decisions of AI systems under-standable/explainable to human. As an examples, many ap-plications in medical diagnosis are not yet successful used, since the reasons of decision are not often explainable to medical doctors. In this talk, recent research in explainable artificial intelligence will be introduced. Moreover, the goals of explainable AI project supported by the ministry of science and technology and IITP will be presented.

Biography

Prof. Jaesik Choi is an associate professor in the School of Electrical and Computer Engineering at UNIST and an affili-ate researcher of the Lawrence Berkeley National Laboratory.

His research is concerned with statistical inference and machine learning for large-scale artificial intelligence prob-lems including scaling up inference algorithms for large-scale dynamic systems, predictive analysis for time series data and its application to large-scale manufacturing systems. Some of his recent research results include the Lifted Relational Kalman Filtering (a scalable, linear time Kalman filtering al-gorithm), the Spatio-Temporal Pyramid Matching Kernel (the first pyramid matching kernel for spatio-temporal data), and

27

the Relational Automatic Statistician (an automated, explain-able interface for multivariate time series data).

He has been an associate professor at UNIST since September 2017. Previously, he was an assistant professor at UNIST since July 2013. He was a Computer Scientist Postdoctoral Fellow of Computational Research Division at the Berkeley Lab. He received his Ph.D in Computer Science from University of Illinois at Urbana-Champaign in 2012 and received B.S. degree in Computer Engineering from Seoul National University in 2004.

Currently, he is a POSCO fellow professor. He is a direc-tor of UNIST Explainable Artificial Intelligence Center.

28

Tutorial 5

15:30~18:45 Sunday, June 24, 2018


Prof. Bohyung Han⋅Electrical and Computer Engineering at

Seoul National University, Korea

Deep Neural Networks for Recognition in Videos

Abstract

Deep neural networks are successful in various recognition problems with video data such as action classification and lo-calization, object detection in videos, video generation, video captioning, visual tracking, visual surveillance, etc. However, there are still a lot of challenges, especially compared to rec-ognition in images, that should be overcome for development of practical systems. The main topics of this tutorial include representation learning of videos, neural network archi-tectures of video recognition algorithms, and practical issues in algorithm implementation. In particular, I present recent trends and progresses of visual recognition in videos, and de-scribe critical limitations of the research in the problem. At the end of the tutorial, I briefly discuss a couple of potentially desirable directions for research in video recognition to make bigger achievements.

Biography

Bohyung Han is currently an Associate Professor in the School of Electrical and Computer Engineering at Seoul National University, Korea. Prior to the current position, he was an Associate Professor in the Department of Computer Science and Engineering at POSTECH, Korea and a visiting research scientist in Machine Intelligence Group at Google, Venice, CA, USA. He received the B.S. and M.S. degrees from the Department of Computer Engineering at Seoul National University, Korea, in 1997 and 2000, respectively, and the Ph.D. degree from the Department of Computer Science at the University of Maryland, College Park, MD, USA, in 2005. He served or will be serving as an Area Chair or Senior Program Committee member of major conferences

29

in computer vision and machine learning including CVPR, ICCV, NIPS, IJCAI and ACCV, a Tutorial Chair in ICCV 2019, and a Demo Chair in ACCV 2014. He is also serving as Area Editor in Computer Vision and Image Understanding and Associate Editor in Machine Vision Applications. He is interested in various problems in computer vision and ma-chine learning with emphasis on deep learning. His research group won Visual Object Tracking (VOT) Challenge in 2015 and 2016.

30

Tutorial 6

15:30~18:45 Sunday, June 24, 2018


Prof. Gabriel A. Rincón-Mora, Ph.D.⋅NAI Fellow, IEEE Fellow,

and IET Fellow Georgia Institute of Technology

Energizing and Powering Microsensors

Abstract

Networked wireless microsensors can not only monitor and manage power consumption in small- and large-scale ap-plications for space, military, medical, agricultural, and con-sumer markets but also add cost-, energy-, and life-saving in-telligence to large infrastructures and tiny devices in remote and difficult-to-reach places. Ultra-small systems, however, cannot store sufficient energy to sustain monitoring, inter-face, processing, and telemetry functions for long. And re-placing or recharging the batteries of hundreds of networked nodes can be labor intensive, expensive, and oftentimes impossible. This is why alternate sources are the subject of ar-dent research today. Except power densities are low, and in many cases, intermittent, so supplying functional blocks is challenging. Plus, tiny lithium-ion batteries and super capaci-tors, while power dense, cannot sustain life for extended periods. This talk illustrates how emerging microelectronic systems can draw energy from elusive ambient sources to power tiny wireless sensors.

Biography

Gabriel A. Rincón-Mora was Design Team Leader at Texas Instruments in 1994-2003, Adjunct Professor at the Georgia Institute of Technology (Georgia Tech) in 1999-2001, and Director of the Georgia Tech Analog Consortium in 2001-2004 and has been Professor at Georgia Tech since 2001 and Visiting Professor at National Cheng Kung University in Taiwan since 2011. He is Fellow of the American National Academy of Inventors (NAI), Fellow of the Institute of Electrical and Electronics Engineers (IEEE), and Fellow of the Institution of Engineering and Technology (IET). His

31

scholarly products include 9 books, 4 book chapters, 42 pat-ents, over 170 articles, over 26 commercial power-chip de-signs, and over 130 international speaking engagements. He was inducted into Georgia Tech’s Council of Outstanding Young Engineering Alumni and named one of “The 100 Most Influential Hispanics” by Hispanic Business magazine. He received the National Hispanic in Technology Award, Charles E. Perry Visionary Award, Orgullo Hispano Award, Hispanic Heritage Award, IEEE Service Award, IEEE Certificate of Appreciation, and Commendation Certificate from the Lieutenant Governor of California.

32

Tutorial 7

08:45~12:00 Tuesday, June 26, 2018


Prof. Youngdeok Hwang⋅Sungkyunkwan University

Interface between data collection and statisticalmodeling - an industrial statistician's perspective

Abstract

Statistics has advanced while trying to give an answer to the urgent challenges from the advances in industry--from Fisher’s pioneering work on agricultural experiment and Box’s contribution on manufacturing revolution to recent ris-es of “data science.” This talk briefly reviews the historical as-pect of statistics from an industrial statistician’s perspective. It introduces the interactive nature of the data collection and modeling in industrial statistical research with some examples. Also introduced are experiences of interdiscipli-nary collaboration to solve challenging problems that entail the effort from diverse background.

Biography

Youngdeok Hwang is an assistant professor at the Department of Statistics, Sungkyunkwan University (SKKU). Before joining SKKU, he worked as a statistician at IBM TJ Watson Research Center from 2012 to 2017. He re-ceived his master's and doctoral degrees from University of Wisconsin at 2010 and 2012, respectively. His research areas include developing new statistical methodologies for solving problems in industry and engineering - in the area of design and analysis of computer experiments, remote-sensing tech-nology, wireless sensor networks and IoT.

33

Tutorial 8

08:45~12:00 Tuesday, June 26, 2018

Room: Grand Ballroom 3Jung-Woo Ha

⋅NAVER Corp.Jung-Woo Ha works as the leader of Clova machine learn-

ing team and the Clova AI Research Director of NAVER &LINE. He received his BS and PhD from the department of

computer science in Seoul National University in 2004 and 2015. He got the best PhD thesis award of the department

of computer science of SNU. He has interests in deep learning-based computer vision, natural language process-

ing, audio signal modeling and recommendation.

Jin-Hwa Kim⋅Seoul National University

He is a Ph.D. candidate in Biointelligence Lab. at Seoul National University. He has been studying machine learning

and artificial intelligence under the supervision of Professor Byoung-Tak Zhang. In September 2017, He re-

ceived a 2017 Google Ph.D. Fellowship in Machine Learning. He was a research intern at Facebook AI Research (Menlo Park, CA) mentored by Yuandong Tian, Research Scientist,

from January to May in 2017. In 2015, he received Master of Science in Engineering degree from Seoul National

University, and, in 2011, Bachelor of Engineering degree from Kwangwoon University (summa cum laude). He was a software engineer in Search Infra Development Team at SK

Communications (Seoul, Republic of Korea) from 2011 to 2012.

Kyung Min Kim⋅Seoul National University

Kyung Min Kim received his B.S. from Hongik University, Seoul, Korea in 2013. He is currently pursuing Ph.D degree

in Computer Science in the field of machine learning at Seoul National University while working for Surromind

Robotics. He won MovieQA Challenge in 2017 and has hold 1st position to date. He awarded Naver Ph.D. Fellowship in

2017.

Visually-Grounded Question and Answering: from VisualQA to MovieQA

Abstract

The advancement of computer vision and natural lan-guage processing based on deep learning has resulted in the remarkable progress of visually-grounded language learning. In particular, visual question and answering (VQA) has become one of the most interesting and preferred research topics in computer vision since the VQA challenge started in 2016. Beyond VQA, MovieQA also emerged a challenging topic as a new multimodal semantic learning tasks. In this talk, we in-

34

troduce two visually-grounded question and answering such as VQA and MovieQA. This talk includes the task definition, data preparation, various state-of-the art approaches for two multimodal QAs. In addition, we explain the challenging is-sues of these tasks and discuss of their future direction.

35

Tutorial 9

13:00~16:00 Tuesday, June 26, 2018


Prof. Gwangsu Kim⋅KAIST

Bayesian analysis and its applications in AI

Abstract

This tutorial will introduce the fundamental concepts of probability, maximum likelihood estimator and Bayesian, and processes to perform data analysis using Bayesian approach. It will cover the properties and problems to be aware of in Bayesian analysis, and show the examples used in clustering, deep neural networks, and online learning.

Biography

Gwangsu Kim is a research associate professor in the School of Electrical Engineering at KAIST, and a member of Bayesian Research of the Korean Statistical Society.

His research is concerned with statistical inference and machine learning to use Bayesian. Bayesian nonparametrics such as Dirichlet process, beta process and Gaussian process (basis expansion) are the main interests of his research. He used Bayesian and machine learning methodologies in vari-ous areas and models such as signal analysis via Gabor frame, structured regression in medical research, detecting abrupt changes in hydrology, nonparametric Bayesian surviv-al analysis, random effects analysis in medical research and sociology. His recent works are the submodular sampling, and the statistical properties of deep neural networks.

He was a research assistant professor in Seoul National University at March 2016 ~ August 2017 (March 2012 ~ August 2013) and a research professor in Korea University at September 2014 ~ February 2016. He received his Ph.D. (Statistics) in Seoul National University at 2012, and received his Bachelor's degree in Seoul National University at 2006. He has served as an advisory for the projects ordered by Ministry of Unification, Korea Maritime Institute, etc.

36

Technical Program

Special Session

‣ January 25 (Mon) 09:00~11:00

SS01 ‣ AI Young Investigator Session

Room: UdoChair: Junmo Kim (KAIST, Korea)01 Transfer Learning Across Domain and Task for End-to-End

Control of Self-Driving CarsDooseop Choi, Taeg-Hyun An, KyoungHwan An, and Jeong-Dan ChoiETRI, Korea

02 Optical coherence tomography for imaging of brain stroke in vivoWoo June ChoiChung-Ang University, Korea

03 Demonstration of nano-scaled optical devices based on metasurfacesSoo Jin KimKorea University, Korea

04 Interpretable Deep Learning on Electronic Medical Records in the Republic of KoreaYoung Bin KimChung-Ang University, Korea

05 GPU Virtualization for High Performance ComputingCheol-Ho HongChung-Ang University, Korea

06 Energy-Efficient Wireless Neural Stimulating Systems for Implantable Medical DevicesHyung-Min LeeKorea University, Korea

07 A review on Name Lookup Algorithm Using Path Compression and Bloom FiterJungwon LeeEwha Womans University, Korea

08 Riemannian Submanifold Framework for Log-Euclidean Metric LearningSung Woo Park1 and Junseok Kwon2

1CAU, Korea, 2University of Chung-Ang, Korea

37

09 A Review on Motion Planning and Intelligent Manipulation of Articulated Robots in Unstructured EnvironmentsDonghyung KimETRI, Korea

10 Modeling Challenges of Neural Network Acceleration HardwareWilliam J. SongYonsei University, Korea

11 UDLR Convolutional Network for Adaptive Image DenoiserSungmin Cha and Taesup MoonSungkyunkwan University, Korea

12 A Study on Information Sharing Using Bloom Filters in Named Data NetworkingJu Hyoung Mun Ewha Womans University, Korea

‣ January 25 (Mon) 09:00~11:00

SS02 ‣ Journal Paper Presentation Session

Room: MaraChair: Dong-Gyu Shim (Kwangwoon University, Korea)01 Comparative study of experimental and theoretical model of

highly-efficient GaInP/Si tandem solar cellsRached Ganouni1,2, Mourad Talbi1, Hatem Ezzaouia1

1Nanostructures And Advanced Technology at CRTEn, Tunisia, 2University of Sciences of Manar, Tunisia

02 Ultra-Low Power Pulse Oximeter with 32.768 kHz Real ClockWonjun Lee1, Youngsun Han2, Chulwoo Kim1, Jae-sung Rieh1,Jongsun Park1, Jae Young Park3, and Seon Wook Kim1

1Korea University, Korea, 2Kyungil University, Korea, 3Korea University College of Medicine, Korea

03 Fast Lamp Pairing-based Vehicle Detection Robust to Atypical and Turn Signal Lamps at Night MangiKyeong Min Jeong and Byung Cheol SongInha University, Korea

04 Automatic detection of sleep stages based on accelerometer signals from a wristbandMinsoo Yeo1, Yong Seo Koo2, and Cheolsoo Park1

1Kwangwoon University, Korea, 2Seoul Asan Hospital, Korea

38

05 Analysis of 5 nm Circular and Trapezoidal Nanowires by Using Three-Dimensional SimulationsMangi Han and Youngmin KimKwangwoon University, Korea

06 Simple Contending-type MAC Scheme for Wireless Passive Sensor Networks: Throughput Analysis and OptimizationJin Kyung Park, Heewon Seo, and Cheon Won ChoiDankook University, Korea

07 Review of the Applications of Wavelet Theory to Image ProcessingAparnaVyas1 and Joonki Paik2

1Manav Rachna University, India, 2Chung Ang University, Korea

‣ January 25 (Mon) 09:00~11:00

SS03 ‣ Control and Its Applications

Room: BiyangChair: Jun Moon (UNIST, Korea)01 Nonlinear Backstepping Control Design for Coupled Nonlinear

SystemsWonhee KimChung-Ang University, Korea

02 Decentralized Optimal Control for Leader-Follower Tilted-HexarotorsMyoung Hoon Lee and Jun MoonUlsan National Institute of Science and Technology, Korea

03 L1 Adaptive Control Architecture for the Application of Missile Attitude Control Using Jet VaneHanmin LeeAgency for Defense Development, Korea

04 Integrated Guidance and Control Under State ConstraintsJongho Park1, Tae-Hun Kim1, Bong-Gyun Park1, and Jong-Han Kim2

1Agency for Defense Development, Korea, 2Kyung Hee University, Korea

05 Linear Parameter Varying Observer Design for Vehicle LocalizationChang Mook KangAgency for Defense Development, Korea

39

‣ January 25 (Mon) 09:00~11:00

SS04 ‣ Advanced Image Processing and Understanding

Room: ChujaChair: Changick Kim (KAIST, Korea)01 Psycho-physical Vision Models and Their Applications to

Image ProcessingSung-Ho BaeKyung-Hee University, Korea

02 Is CNN Always the Optimal Algorithm for Pedestrian Detection in Surveillance Videos?Sangjun Kim1, Sooyeong Kwak2, and Byoung Chul Ko1

1Keimyung University, Korea, 2Hanbat National University, Korea

03 Attention Level Evaluation Using Gaze and Head Pose TrackingMin-Hyun Kim, JinChul Kim, and Chan-Su LeeYeungnam University, Korea

04 Wildfire Detection in Video Based Using Random Forests and Part-Based ModelWoon Cho1, Changeui Son2, Seokmok Park2, Young hoon Lim2, and Joonki Paik2

1The University of Tennessee, USA, 2Chung-Ang University, Korea

05 Low-light Image Enhancement Using Block-based Dark Channel Prior and Gaussian PyramidArk Sinha1, Joongchol Shin2, Jinho Park2, Jinsol Ha2, and Joonki Paik2

1SRM Institute of Science and Technology, India, 2Chung-Ang University, Korea

06 Improved Kernelized Correlation Filter in the Scale Space for Online Object TrackingVivek Maik1, Yeongbin Kim2, Hasil Park2, Sein Park2, and Joonki Paik2

1The Oxford College of Engineering, India, 2Chung-Ang University, Korea

07 Slope-Based Histogram Equalization for Real-Time Display of High-Quality Infrared ImagerySeungyoun Lee1,2, Daeyeong Kim2, and Changick Kim2

1Agency for Defense Development, Korea, 2KAIST, Korea

40

‣ January 25 (Mon) 15:40~17:40

SS05 ‣ Quantum-AI

Room: Grand Ballroom 4Chair: June-Koo Kevin Rhee (KAIST, Korea)01 Quantum computing and IBM Q

Hanhee PaikIBM T.J. Watson, USA

02 Quantum Computing Based on Ion-trap systemTaehyun KimSK Telecom, Korea

03 Small Scale Quantum Machine LearningFrancesco PetruccioneUniv. of Kwazulu-Natal, S. Africa

04 Enablers for Practical Quantum Artificial IntelligenceJune-Koo Kevin RheeKAIST, Korea

‣ January 25 (Mon) 15:40~17:40

SS06 ‣ Emotion Recognition for Social Robots

Room: MaraChair: Byung Cheol Song (Inha University, Korea)01 Emotion Recognition Considering Cultural Differences in

Emotion ExpressionSe-Song Kim and Seung-Won JungDongguk University, Korea

02 Investigation of Embedding Methods for Korean Gag Chat-botTaewon Park, Junhyun Bae, Changmin Woo, Jeongwoo Seo,Jaeseok Park, Donghyun Kang, and Minho LeeKyungpook National University, Korea

03 A Multi-Feature Approach for Audio-Based Emotion RecognitionKyungtae Kim and Bowon LeeInha University, Korea

04 Deep Transfer Learning for Emotion Recognition NetworksMin Kyu Lee, Dae Ha Kim, Dong Yoon Choi, and Byung Cheol SongInha University, Korea

41

05 Inner Emotion Recognition using Multi Bio-SignalsJinho Shin, Junho Maeng, and Deok-Hwan KimInha University, Korea

‣ January 25 (Mon) 15:40~17:40

SS07 ‣ AI with Brain and Communication

Room: BiyangChair: Incheon Paik (University of Aizu, Japan)01 Readability Categorization of Eiken Document using Machine

LearningYui Takeda and Incheon PaikUniversity of Aizu, Japan

02 Evaluation of Superior Generation Selection Method in Genetic Algorithm for Service Selection in Big Data SpaceSheng Zhang and Incheon PaikUniversity of Aizu, Japan

03 Constraint-aware Dynamic Partial Order Plan Generation for Big Data Analytics based on Automatic Service CompositionT. H. Akila, S. Siriweera, and Incheon PaikUniversity of Aizu, Japan

04 Intruder Detection Using Radio Wave Propagation CharacteristicsSatoru Yasukawa and Minseok KimNiigata University, Korea

05 A Hybrid Brain Computer Interface Based on Audiovisual Stimuli P300Xuyang Zhao1,3, Gaochao Cui1, Longhao Yuan1,3, Toshihisa Tanaka2,3,4, Qibin Zhao3,5, and Jianting Cao1,3,6

1Saitama Institute of Technology, Japan, 2Tokyo University of Agriculture and Technology, Japan, 3RIKEN AIP, Japan, 4RIKEN CBS, Japan, 5Guangdong University of Technology, China, 6Hangzhou Dianzi University, China

06 TENSORIZING GENERATIVE ADVERSARIAL NETSXingwei Cao1, Xuyang Zhao1,2, and Qibin Zhao1,3

1RIKEN AIP, Japan, 2Saitama Institute of Technology, Japan, 3Guangdong University of Technology, China

42

‣ January 25 (Mon) 15:40~17:40

SS08 ‣ Intelligent Cyber-Physical Systems

Room: ChujaChair: Jaehoon Jeong (Sungkyunkwan University, Korea)01 Extensible Intelligent Simulator Architecture for the

Development of Cyber-Physical SystemsDaegeun Choe, Yiwen (Chris) Shen, Bien Aime Mugabarigira, and Jaehoon (Paul) JeongSungkyunkwan University, Korea

02 Context-Aware Navigator for Road Safety in Vehicular Cyber-Physical SystemsBien Aime Mugabarigira, Yiwen (Chris) Shen, Daegeun Choe, and Jaehoon (Paul) JeongSungkyunkwan University, Korea

03 A New CPS Middleware Architecture for Interconnecting Heterogeneous Devices in Smart CarsHoa-Hung Nguyen, Howon Jung, Jae-Hyun Park, Kwang-Wook Yun, Yoon-Ho Choi, and Han-You JeongPusan National University, Korea

04 Goal-based Code Generation for Intelligent CPSHohyeon Jeong, Misoo Kim, and Eunseok LeeSungkyunkwan University, Korea

05 A Scalable Big Data Architecture in various Cyber-Physical SystemsDae-ho Kim, Sung-min Yang, Ji-hyeon Yoon, and Ok-ran JeongGachon University, Korea

06 Patch Image and System Structure for Automatic Hot-patching PlatformHaegeon Jeong and Kyungtae KangHanyang University, Korea

07 QoS-Aware Service Migration in Edge Cloud NetworksJaewook Lee, Joonwoo Kim, Yujin Tae, and Sangheon PackKorea University, Korea

43

‣ January 26 (Tue) 13:00~15:00

SS09 ‣ Women in the Electronics Industry

Room: MaraChair: Ji-Hyeong Han (SeoulTech, Korea)01 Light Field based Time-space Transcendence 360 Video

ConstructionChae Eun RheeInha University, Korea

02 Actively Tunable Metasurfaces for Applications of Nanophotonic DevicesJinyoung HwangKorea Aerospace University, Korea

03 Behavior Selection of Social Robots Using Developmental Episodic Memory-based Mechanism of ThoughtWoo-Ri Ko1 and Jong-Hwan Kim2

1ETRI, Korea, 2KAIST, Korea

04 Developing new applications for society based on new technologies and open hardware platformYoung Ah SeongThe University of Tokyo & JST ERATO, Japan

‣ January 26 (Tue) 13:00~15:00

SS10 ‣ AI World Cup Session

Room: BiyangChair: Chang Dong Yoo (KAIST, Korea) / Junmo Kim, KAIST /Sangwan Lee, KAISTdiscuss research topics in AI with brain and communications; topics include BMI, signal processing, micro wave and mobile system, machine learning and deep learning, service computing, etc.01 Learning Soccer Agent by PPO with Experience Replay

Giseung ParkKAIST, Korea

02 Knowledge-based robot soccer strategy using PID controlLucas Avanci GaudioKAIST, Korea

03 A Competitive Path to Build Artificial Football Agents for AI WorldcupDr. JeeHang LeeKAIST, Korea

44

04 Relative position-based cooperative soccer by vector between ball and goalJooSeung YoonKAIST, Korea

05 Rule-based robot soccer for AI WorldcupVu ThangKAIST, Korea

‣ January 26 (Tue) 13:00~15:00

SS11 ‣ Digital Acquisition and Reconstruction

Room: ChujaChair: Jong-Il Park (Hanyang University, Korea)01 High Density Point Cloud Registration with ICP Algorithm

Hyun-Min Kang, Yong-Mun Park, Byung-Jun Kim,and Yong-Duek SeoSogang University, Korea

02 Multispectral imaging using color-filtered stereo RGB cameraKyudong Sim and Jong-Il ParkHanyang University, Korea

03 High Resolution Stitching System of Artwork ImagesYounkyoung Lee1, Sang Hwa Lee2, Kyudong Sim1, and Jong-Il Park1

1Hanyang University, Korea, 2Seoul National University, Korea

04 BRDF sampling method by arc-shaped lighting deviceHoe-Min Kim1 and Jong-Il Park2

1Korea Photonics Technology Institute, 2Hanyang University, Korea

45

Regular Session

‣ January 25 (Mon) 09:00~11:00

RS01 ‣ Internet of Things (IoT)

Room: Grand Ballroom 2Chair: Soumya Kanti Datta (EURECOM, France)01 Development of a gateway for Open ADR-ECHONET Lite

protocols with Raspberry Pi boardNuttasit Petchsom and Wanchalerm PoraChulalongkorn University, Thailand

02 Low Complexity HEVC Solution for Visual Sensor Network using Raspberry Pi PlatformThao Nguyen Thi Huong1, Tien Vu Huu1, and Xiem HoangVan2

1PTIT - Posts and Telecommunications Institute of Technology, Vietnam, 2VNU - University of Engineering and Technology, Vietnam

03 Next-Generation, Data Centric and End-to-End IoT Architecture Based on MicroservicesSoumya Kanti Datta and Christian BonnetEURECOM, Sophia Antipolis, France

04 Development of Smart Water Heater Complied with MQTT and ECHONET Lite ProtocolsNatapon Tansangworn and Wanchalerm PoraFaculty of Engineering, Chulalongkorn University, Thailand

05 Internet of Things application in Smart Tram - Automatic fare collection system developmentPedro B. V. Bermudez, Kiwoong Jung, HyeonCheol Hwang, YongGuk Oh, and Jaeho KwakUniversity of Science and Technology, Korea Railroad Research Institute, Korea

06 Viewport extraction method for wide FOV in 360 VR video systemGeon-Won Lee and Jong-Ki HanSejong University, Korea

46

‣ January 25 (Mon) 09:00~11:00

RS02 ‣ Communications and Networking

Room: Grand Ballroom 3Chair: Seokhyun Yoon (Dankook University, Korea)01 Variable Channel Threshold-Based Hybrid AF-DF Cooperative

Communications with Packet SplittingKen Tezuka, Kazuki Maruta, and Chang-Jun AhnChiba University, Japan

02 Architecture and Routing Protocols for Airborne Internet AccessAbdullah Numani, Syed Junaid Nawaz, and Muhammad Awais JavedCOMSATS Institute of Information Technology, Pakistan

03 Internet Access over Visible LightTrio Adiono, Syifaul Fuada, Rosmianto Aji Saputro, and Muhamad LuthfiUniversity Center of Excellence on Microelectronics, Institut Teknologi Bandung, Indonesia

04 Adaptive Long-term Reference Selection based Efficient Scalable Video Coding for Visual Surveillance SystemsXiem HoangVan, Le Dao Thi Hue, and Giap PhamVanVNU - University of Engineering and Technology, Vietnam

05 Quorum-based Device Discovery Scheme for LTE-based D2D Communication SystemsChih-Shun Hsu1, Yuh-Shyan Chen2, and Hsin-Mao Huang2

1Shih Hsin University, Taiwan, 2National Taipei University, Taiwan

06 Maximum Likelihood Cell-Type Classification using Gene-Expression DataDongmug Kang, Seokhyun Yoon, and Kyoungpil RaDankook University, Korea

‣ January 25 (Mon) 09:00~11:00

RS03 ‣ Artificial Intelligence (AI)

Room: Grand Ballroom 4Chair: Dong Eui Chang (KAIST, Korea)01 Contrast Enhancement Using Haze Thickness Model for

Consumer Imaging SystemsVivek Maik1, Heunseung Lim2, Kwanwoo Park2, Minseo Kim2, Soohwan Yu2, and Joonki Paik2

1The Oxford College of Engineering, India, 2Chung-Ang University, Korea

47

02 Image Based HTM Word Recognizer for Language processingAidana Irmanova, Olga Krestinskaya, and Alex Pappachen JamesNazarbayev University, Kazakhstan

03 Performance Evaluation of Convolutional Neural Networks to Detect and Classify Malaysian FoodMohammed A. Subhi and Sawal MD. AliUniversiti Kebangsaan Malaysia, Malaysia

04 Detection of Collusive App-pairs Using Machine LearningMd Faiz Iqbal Faiz, Md Anwar Hussain, and Ningrinla MarchangNorth Eastern Regional Institute of Science and Technology, India

05 CortexNet: Convolutional Neural Network with Visual Cortex in human brainMobeen Ahmad, Jooyeon Joe, and Dongil HanSejong University, Korea

06 Prioritized Stochastic Memory Management for Enhanced Reinforcement LearningTaehwan Kwon and Dong Eui ChangKorea Advance Institute of Science and Technology, Korea

‣ January 25 (Mon) 15:40~17:40

RS04 ‣ Circuit and Systems

Room: UdoChair: Hyung-Min Lee (Korea University, Korea)01 A Simple Design and Realization Technique of a Broadband

Low-Noise Amplifier for Wireless Frequency RangeKassen Dautov and Mohammad HashmiNazarbayev University, Kazakhstan

02 An extended Lamport-like one-time password scheme and its applicationsYuji Suga sugaInternet Initiative Japan Inc., Japan

03 Physically Unclonable Function Using Ring Oscillator Collapse in 0.5 V Near-Threshold Voltage for Low-Power Internet of ThingsJeongsik Yoo1,2, Doyoun Kim1, Hyunsu Park1, Minseob Shim1, Choonghwan Lee1, and Chulwoo Kim1

1Korea University, Korea, 2Samsung Electronics, Korea

48

04 A 1Gbps Referenceless Clock and Data Recovery Using Injection PLLSoowan Jin, Changzhi Yu, Hyunmook Kim, and Jinwook BurmSogang University, Korea

05 Implementation of an SDR-based LTE Base-station System with a Novel Interface between USRP and Multicore DSPJaeho Lee1, Heungseop Ahn1, Daejin Kim1, Seungwon Choi1, Ildo Jung2, and Jehoon Oh2

1Hanyang University, Korea, 2LG Uplus, Korea

06 A Robust 400-MHzCrystal-less Super-regenerative Transceiverusing Injection-pulling frequency synthesizerSeong Joong Kim1, Kang-Yoon Lee2, and Sang Joon Kim1

1Samsung Electronics, Korea, 2Sungkyunkwan University, Korea

‣ January 26 (Tue) 13:00~15:00

RS05 ‣ CE Applications

Room: Grand Ballroom 2Chair: JeongYon Shim (Kangnam University, Korea)01 Fast Stereo Matching Using Label-Based Aggregation with

Selective Cost Volume FilteringArijit Mukherjee1, Nakeun Choi2, Sijung Kim2, Jinbeum Jang2, Minwoo Shin2, and Joonki Paik2

1SRM Institute of Science and Technology, India, 2Chung-Ang University, Korea

02 Optimal Selection Mechanism for Decision Making based on Future Simulation in the Knowledge NetworkJeongYon ShimKangnam University, Korea

03 A Packet Visualization Tool For IndividualsHyunsu Mun1, Kihyun Choi1, Jinhyeok Kim1, Isung Cho1, Jeasung Na1, Hanul Park1, Seungtae Kim1, Youngseok Lee1, Zachary Siebers2, Sarah Rausch2, and John Springer2

1Chungnam National University, Korea, 2Purdue University, USA

04 A Useful Multi-Window Monitor DesignGuangchao Zhai, Yongming Tang, and Tianpeng WangSoutheast University, China

49

05 Baseline Calculation of Industrial Factories for Demand Response ApplicationAnut Arunaun and Wanchalerm PoraChulalongkorn University, Thailand

06 A Predictive Initialization of Hidden State Parameters in a Hidden Markov Model for Hand Gesture RecognitionHyokeun Lee, Donghyeon Lee, and Hyuk-Jae LeeSeoul National University, Korea

‣ January 26 (Tue) 13:00~15:00

RS06 ‣ Object Identification

Room: Grand Ballroom 3Chair: Jung-Woo Choi (KAIST, Korea)01 Ring-Shaped ROI Selection in Fisheye Lens Images for Parking

Monitoring SystemsWoon Cho1, JaeMin Lee2, Seokmok Park2, and Joonki Paik2


02 Personal Sound Zone for Automotive Applications: a review of personal audio technologies and applicationsJung-Woo ChoiKAIST, Korea

03 Enhancing Global Contexts Modeling for Video Object DetectionSunghun Kang, Cao Van Nguyen, and Chang D. YooKAIST, Korea

04 Vanishing Point Estimation Using Parallel Coordinates and Point-Line DualityNimish Pastaria1, Hyungtae Kim2, Dasol Jeong2, Minjung Lee2, and Joonki Paik2

1SRM, Institute of Science and Technology, India, 2Chung-Ang University, Korea

05 Robust Object Tracking Using Weighted Gray Transformation with Kernelized Correlation FilterNimish Pastaria1, Jungsup Shin2, Heegwang Kim2, Jinbeum Jang2, Hyun wook Lee2, and Joonki Paik2


06 Robust HDR Video Synthesis Using Superpixel-Based Illumination Invariant Motion EstimationTu Van Vo and Chul LeePukyong National University, Korea

50

‣ January 26 (Tue) 13:00~15:00

RS07 ‣ Image/Signal Processing

Room: Grand Ballroom 4Chair: Gil-Jin Jang (Kyungpook National University, Korea)01 Multi-Hop Global Average Pooling for Convolutional Neural

Networks for Image ClassificationSangwon Lee and Gil-Jin JangKyungpook National University, Korea

02 Tensor-Train Decomposition for Multimodal Video CategorizationJunyeong Kim, Cao Van Nguyen, and Chang D. YooKAIST, Korea

03 L0 Smoothing-Based Saliency Map Estimation Using Simplified Color FeaturesArk Sinha1, Donggeun Kim2, Sangwoo Park2, Jaeseung Lim2, Shuxiang Song2, and Joonki Paik2


04 HOG-AdaBoost Implementation for Human Detection Employing FPGA ALTERA DE2-115Trio Adiono, Kevin Shidqi Prakoso, Christoporus Deo Putratama, Bramantio Yuwono, and Syifaul FuadaInstitut Teknologi Bandung, Indonesia

05 Histogram-Based Image Retrieval Keyed by Normalized HSY Histograms and Its Experiments on a Pilot DatasetMasaki Takeishi1, Daisuke Oguro1, Hisakazu Kikuchi1, and Jaeho Shin2

1Niigata University, Japan, 2Dongguk University, Korea

06 Efficient Structure of Deep Neural Network for Smart Phone Image Super-ResolutionWoo Jin Jeong, Bok Gyu Han, Hyeon Seok Yang, Jae Jun Sim, Yong Chae Cho, and Young Shik MoonHanyang University, Korea

51

‣ January 26 (Tue) 13:00~15:00

RS08 ‣ CE Algorithm

Room: UdoChair: Jang-Myung Lee (Pusan National University, Korea)01 Enhanced Digital Audio Watermarking using Genetic Algorithm

Rizki Rivai Ginanjar, Dong Seong Kim, and Chang Bae MoonKumoh National Institute of Technology, Korea

02 An Efficient Distance Estimation Method based on Bluetooth Low Energy and UltrasoundSuk-Un Yoon, Jongha Woo, JungYon Cho, and Cheul-Hee HahmSamsung Electronics Co., Ltd., Korea

03 Impedance Feedback Control using Dynamic Modeling of User’s Arm and Haptic Interface SystemTaeEon Kim, Dong-Eon Kim, Seon-woo Kim, and Jangmyung LeePusan National University, Korea

04 A Direct Load Control Algorithm for Air Conditioners Concerning Customers’ ComfortKusapon Phetsuwan and Wanchalerm PoraFaculty of Engineering Chulalongkorn University, Thailand

05 Bluetooth Based Indoor Positioning Using Machine Learning AlgorithmsPranesh Sthapit, Hui-Seon Gang, and Jae-Young PyunChosun University, Korea

06 Asymptotic analysis of direction of arrival estimation performance of uniform circular arrayJin Hak Kim and Sae-Young ChungKAIST, Korea

52

Poster Session

‣ January 25 (Mon) 09:30~11:00

PS01

Room: LobbyChair: Jinyoung Hwang (Korea Aerospace University)01 Architecture Exploration Method for CNN HW Acceleration

using SoC Virtual PlatformSungjae Yoon, Hanjin Cho, and Wonjong KimElectronics and Telecommunication Research Institute (ETRI), Korea

02 Analysis of Overfitting Problem Solutions in Convolutional Neural NetworksWonsik Yang, Sunho Seo, Younghwan Shin, Jusik Yoon, Wonsuk Yoo, and Jong-Moon ChungYonsei University, Korea

03 Job Dispatching and Scheduling Algorithm with Cooperative Operation in Edge-CloudsWoo-Joong Kim, Jae-Ho Jeong, and Chan-Hyun YounKAIST, Korea

04 Adversarial Label Manifold Learning with Application to Semantic Scene SegmentationDonghoon Lee, Sunghun Kang, Luu Minh Tung, and Chang D. YooKAIST, Korea

05 A two-step approach for DNN-based emotional speech synthesis using multi speaker-emotional speech data setSangjun Park, Jinuk Park, Heejin Choi, and Minsoo HahnKAIST, Korea

06 Associative domain adaptation of depth estimation using synthetic indoor data to real indoor dataKang Min Bae, Luu Minh Tung, and Chang D. YooKAIST, Korea

07 Survey for Deep Unsupervised Domain AdaptationHyoungwoo Park, Luu Minh Tung, and Chang D. YooKAIST, Korea

08 Review of Surface Normal EstimationHaeyong Kang, Trung Pham, and Chang D. YooKAIST, Korea

53

09 Review of Acoustic Scene Classification Methods Based on Deep LearningHyunsin Park, Cao Van Nguyen, and Chang D YooKAIST, Korea

10 Deep Bayesian Active Learning using Submodular functionJaewon Lee, Cao Nguyen Van, and Chang D. YooKAIST, Korea

11 Playing Bi-Wheeled Robotic Soccer with Deep Q Learning Based on High-Level Action ModelingMinuk Ma, Hyunjun Jang, Minjeong Ju, and Chang D. YooKAIST, Korea

12 Learning and Ensemble of Layer-by-Layer Object Detection using Single-Shot Object Detector for Traffic CameraJongmin Yu, Donghwuy Ko, and Moongu JeonGIST, Korea

13 Real-time Traffic Sign RecognitionVinh Quang Dinh, Younkwan Lee, Hyunguk Choi, and Moongu JeonGIST, Korea

14 Runtime-optimized Linear ClassificationJongmin Kim, Pham Xuan Trung, and Chang D.YooKAIST, Korea

15 Deep Structured Output Learning for Multi-label Image AnnotationJongmin Kim, Pham Xuan Trung, and Chang D.YooKAIST, Korea

16 Cross-dataset Person Re-identification with Deep Identification-verification NetworkJongmin Kim, Pham Xuan Trung, and Chang D.YooKAIST, Korea

17 A Co-classification Framework for Transfer Learning Using a Semi-supervised Topic ModelJongmin Kim, Sungrack Yun, Pham Xuan Trung, and Chang D.YooKAIST, Korea

18 An Efficient Convolutional Neural Network for Classification of Screen rendered Text ImagesXiaopeng Yin, Donghyeon Lee, and Hyukjae LeeSeoul National University, Korea

54

19 Accurate License Plate Recognition and Super-Resolution using a Generative Adversarial Networks on Traffic Surveillance VideoYounkwan Lee, JaeWoong Yun, Yoojin Hong, Juhyun Lee, and Moongu JeonGIST, Korea

20 Voice Activity Detection Using an Ensemble ModelJuntae Kim, Jaeseok Kim, and Minsoo HahnKAIST, Korea

21 Deep Least Squares Regression-Based Speaker-Dependent Layer Initialization for DNN Acoustic Model AdaptationYounggwan Kim, Youngmoon Jung, Yeunju Choi, and Hoirin KimKAIST, Korea

22 Score Fusion based Vocabulary Independent Spoken Term DetectionHyungjun Lim, Jahyun Goo, Sungmin Lim, and Hoirin KimKAIST, Korea

23 Image Pattern Classification Using MFCC and HMMZahra Shah, Minsu Kim, and Gil-Jin JangKyungpook National University, Korea

24 Learning from Imbalanced and Hierarchically Dual-labeled DataJuseung Yun1, Youngdong Kim1, Junho Yim1, Hansang Cho2, and Junmo Kim1

1KAIST, Korea, 2SAMSUNG ELECTRO-MECHANICS, Korea

25 Training Flownet on Monkaa DatasetMuhammad Sarmad, Juan Luis Gonzalez, and Hyunjoo Jenny LeeKAIST, Korea

26 Find Optimal Model among Various Neural Networks Models Using Monte-Carlo Tree SearchJaeyoung Moon, Misun Kim, and Dongil HanSejong University, Korea

27 Improving Video Captioning with Non-Local Neural NetworksJaeyoung Lee and Junmo KimKAIST, Korea

28 Improved Multi-task ConvNet for Facial Image InpaintingHongyu Wang and Byeungwoo JeonSungkyunkwan University, Korea

29 Predicting Winning Rate in Game ContentsYu-cheol Kim, Jaemin Kim, Myoung-young Kim, and Won-hyung LeeChung-Ang University, Korea

55

30 Performance Analysis of Regularization Methods of Deep Learning with a Small-sized Dataset in MNISTSoyoon Bae, Taewoo Kim, and Chan-Hyun YounKAIST, Korea

31 Collaborative Method for Incremental Learning on Image ClassificationByungju Kim and Junmo KimKAIST, Korea

32 Dog Noseprint Identification using Gabor Filter based Feature MatchingSungmin Cho, Jinwook Paeng, Taehong Kim, Chanil Kim,and Junseok KwonChung-Ang University, Korea

33 Adaptive Filter Network with Differentiable Mask ControlYegang Lee, Heechul Jung, Dongyoon Han, and Junmo KimKAIST, Korea

34 FSF-C Net: Face Spatial Frequency-Critic Network for Face Super ResolutionKihyun Kim, Hak Gu Kim, and Yong Man RoKAIST, Korea

35 INCREMENTAL LEARNING IN DEEP CONVOLUTIONAL NEURAL NETWORK VIA ADAPTIVE REGULARIZATIONSihyeon Seong, Pyunghwan Ahn, Jiwhan Kim, and Junmo KimKAIST, Korea

36 Analysis of Performance Enhancements in Contention Resolution Diversity Slotted ALOHA (CRDSA) SystemsHyoungdae Kim, Junsung Kim, Sooeun Song, Changsung Lee,Jinbae Lee, and Jong-Moon ChungYonsei University, Korea

37 Lighting Variability Correction for Pill IdentificationSeungtae Kang, Gil-Jin Jang, and Minho LeeKyungpook National University, Korea

38 Deep Learning-Based Kronecker Compressive ImagingThuong Nguyen Canh and Byeungwoo JeonSungkyunkwan University, Korea

39 Adaptive Terminal Sliding Mode Control for A 3-DOF ManipulatorYudong Zhao, Shikai Zhang, Yueyuan Zhang, and Jangmyung LeePusan National University, Korea

56

40 Multiple Mobile Robots Formation Control Based on Sliding Mode ControlYudong Zhao, Yueyuan Zhang, Shikai Zhang, and Jangmyung LeePusan National University, Korea

41 Simulation of UWB Radar-based Positioning Performance for a UAV in an Urban AreaHalim Lee, Woohyun Kim, and Jiwon SeoYonsei University, Korea

42 Smoothing Multi-scan Multi-Target TrackingSufyan Memon and Hungsun SonUlsan National Institute of Science & Technology, Korea

43 3D Map Generation and Localization for Autonomous DrivingFarzeen Munir, Shoaib Azam, Ahmad Muqeem Sheri, YeongMin ko, and Moongu JeonGIST, Korea

44 A Centralized Location Monitoring System for Mobile ObjectsHuicheol Ahn, Taehyun Seo, Dongil Jeong, Jiseong Jeong,Yongwoon Hwang, and Chung Ghiu LeeChosun University, Korea

45 State-of-Charge(SOC) Monitoring of the Drone’s Battery Pack by Flight Altitude/Mode ConditionsPyeongyeon Lee, Jinhyung Park, Dongho Han, Dongyoon Lee,and Jonghoon KimChungnam National University, Korea

‣ January 25 (Mon) 16:10~17:40

PS02

Room: LobbyChair: Soo Jin Kim (Korea University)01 DDoS attack at the MAC layer in the wireless network

Seong Oun Hwang, Ji-Hoon Park, and Byung-Seo KimHongik University, Korea

02 Dependent Attack Effects on HEAVENS for Automotive Cybersecurity ModelRyang Ki, Sung Ha Lee, and Dong Kyue KimHanyang University, Korea

57

03 Using Deep Neural Networks and TF-IDF for Document CategorizationWalter R. Oliveira Jr., Flavio Bortolozzi, and Edson J. R. JustinoPUC-PR

04 Energy-aware resource prediction in virtualized data centers: A Machine learning approachAlanazi Rayan and Yunmook NahDankook University, Korea

05 Adaptive Operating Mode Conversion Technique for Optimal Scheduling of Solar Energy SystemTai-Yeon Ku1, Wan-Ki Park1, and Hoon Choi2

1ETRI, Korea, 2Chungnam National University, Korea

06 Accelerating FPGA for SIFT-Based Real Time Object Recognition in Mobile Edge ComputingJae-Ho Jeong, Eun-Young Oh, Woo-Joong Kim, and Chan-Hyun YounKAIST, Korea

07 Experimentally Optimized Asymmetric Doherty Power Amplifier Using Gysel Input DividerYoontae Lee, Woojin Choi, Hansik Oh, Cheon-Seok Park, and Youngoo YangSungkyunkwan University, Korea

08 Feasibility analysis of digital terrestrial TV broadcasting with scalable bandwidthJaeHwui Bae1, JaeHyun Seo1, YoungSu Kim1, Jae-Young Lee1,Namho Hur1, Heung Mook Kim1, Ho Jae Kim2, and Hyoung-Nam Kim2

1ETRI, Korea, 2Pusan National University, Korea

09 High Gain Antenna with Air-gap to Reduce the Design Complexity and Array SizeJinHyoung Kim1,2, Kwonhong Lee1, Cheolung Cha1,and Yongtaek Hong2

1Korea Electronics Technology Institute, Korea, 2Seoul National University, Korea

10 Design of High Gain Antenna Array Structure for Wireless Power TransmissionKwonHong Lee1,2, JinHyoung Kim1, HyunYong Yu2,and CheolUng Cha1

1Korea Electronics Technology Institute, Korea, 2Korea University Electrical and Electronic Engineering, Korea

58

11 Transparent Dipole Loop Antenna using a μ-Metal Mesh on the Transparent Mobile Applications for UHF band Service ReceivingVan Thai Trinh and Chang Won JungSeoul National University of Science and Technology, Korea

12 Enhanced VFDM Spectrum-Sharing Technique for Smart PlatformGashema Gaspard, Dong-Seong Kim, and Jae-Min LeeKumoh National Institute of Technology, Korea

13 Evaluating the Impact of Mobility over Kappa-mu Generalized Fading Channels in Digital CommunicationEkkaphot Meesa-ard1, Suwat Pattaramalai1, and M.D.C Madapatha2

1King Mongkut's University of Technology, Thailand, 2Asian Institute of Technology, Thailand

14 The Achievable Rate Maximization of Wireless-powered Cooperative NetworkEunhye Park, Jimin Bae, and Youngnam HanKAIST, Korea

15 Wideband Aperture-Coupled Stack-Patch Antenna Design with Characteristic Mode AnalysisLaxmikant Minz, Rao Shahid Aziz, Muhammad Tayyab Azim, and Seong Ook ParkKAIST, Korea

16 Design and Evaluation of External Cable Assemblies for System Bus ExpansionYoung Woo Kim1,2, Wonok Kwon1,2, Hyukje Kwon1, Chanho Park1, and Myeong-Hoon Oh1,2

1ETRI, Korea, 2University of Science & Technology, Korea

17 A Normalized Proportional Fair Scheduler for QoS Provision in Hybrid Full Duplex SystemJin-Taek Lim and Youngnam HanyKAIST, Korea

18 Design and Experiments of Dual Polarization Concentric UCA for OAM GenerationJinu Gong, Jinyeop Na, Seungjae Jung, Gye-Tae Gil,and Joonhyuk KangKAIST, Korea

19 The Design of Hybrid V2X Communication PlatformSeong Keun Jin, Han Gyun Jung, Soo Hyun Jang, Dae Kyo Shin,and Sang Hun YoonKorea Electronics Technology Institute, Korea

59

20 Design of small area and Low power Decimation filter for SD ADC with Configurable Decimation RatioNabeel Ahmad, Muhammad Riaz Ur Rehman, SangYun Kim,Imran Ali, Behnam Samadpoor Rikan, Khuram Shehzad,Syed Adil Ali Shah, and Kang-Yoon LeeSungkyunkwan University, Korea

21 Performance study of Spark on YARN cluster using HiBenchHooYoung Ahn, Hyunjae Kim, and Woongshik YouETRI, Korea

22 Analog Memory Controller for Memristive Crossbar ArrayMoldir Assangali, Olga Krestinskaya, and Alex Pappachen JamesNazarbayev University, Kazakhstan

23 Real Time Monitoring of Image-Based Visual Range Using a Visual Range MeterKyungwon KimGyeongju University, Korea

24 Saliency-guided Feature Matching for Self-driving SystemsAugustine H. Cha and Wonjun KimKonkuk University, Korea

25 Fast Inter Mode Decision by Estimating the Lower Bound on the Rate-Distortion Cost for HEVCJinwoo Jeong, Sungjei Kim, and Yong-Hwan KimKorea Electronics Technology Institute (KETI), Korea

26 Fast Pedestrian Detection Using Local Binary Pattern Feature ChannelLeeyeon Ahn, Jinbeum Jang, Youngran Jo, Sijung Kim,and Joonki PaikChung-Ang University, Korea

27 Depth from Focus Enhancement through Joint FilteringUsman Ali and Muhammad Tariq MahmoodKorea University of Technology and Education, Korea

28 Design of VLSI Architecture for Parallelizing and Accelerating Simple Linear Iterative ClusteringSung-Joon Jang and Sang-Seol LeeKorea Electronics Technology Institute, Korea

29 Video Stabilization Using Feature-Based ClassificationThien-Pham Minh and Min-Cheol HongSoongsil University, Korea

60

30 Motion-Constrained HEVC Encoder for Tile-based 360 VR Video Streaming SystemSungjei Kim, Jinwoo Jeong, and Yong-Hwan KimKorea Electronics Technology Institute (KETI), Korea

31 Dark object-free shadow detection from a single imageJihee Han and Wonjun KimKonkuk University, Korea

32 Image matting using feature combination and guided filterKyoungman Kim, Dongchil Kim, and Sungjoo ParkKorea Electronics Technology Institute (KETI), Korea

33 Single-Channel Object Detection Using Multi-Channel Local Binary Pattern and Neural NetworkWoon Cho1, Yeonseung Choo2, Jinbeum Jang2, and Joonki Paik2


34 Motion History Image-based Depth GenerationManbae KimKangwon National University, Korea

35 Development of an efficient pipeline retrofitting application for a water treatment facilityChethana B, Ashok Kumar Patil, and Young Ho ChaiChung-Ang University, Korea

‣ January 26 (Tue) 13:00~14:30

PS03

Room: LobbyChair: Seong Oun Hwang (Hongik University)01 Online Multi-Object Tracking using Selective Deep Appearance

MatchingYoung-chul Yoon, Young-min Song, Kwangjin Yoon,and Moongu JeonGwangju Institute of Science and Technology, Korea

02 Water boiling transition detection method using frequency dependent acoustic energy analysisEunsuk Choi, Onejae Sul, Seungoh Yoem, Gunwoo Ryu,and Seung-Beck LeeHanyang University, Korea

61

03 Technical Review: Neural Recording Circuits for Bidirectional Neural InterfaceYoontae Jung, Hyuntak Jeon, Taeju Lee, Ho Yong Seong,CheolJun Park, and Minkyu JeKAIST, Korea

04 Technical Review: Interface Integrated Circuits for Metal-Oxide Gas SensorsHo Yong Seong, Soon-Jae Kweon, Ji-Hoon Suh, Jeongeun Lee, CheolJun Park, Yoontae Jung, and Minkyu JeKAIST, Korea

05 Technical Review: Electromagnetic Sensor System for Localization of Medical DevicesCheolJun Park, Hyunwoo Park, Jaesuk Choi, Hongseok Shin,Yoontae Jung, Ho Yong Seong, and Minkyu JeKAIST, Korea

06 Release process for high-stress SU-8 structureMi Kyung Kim, Geon Kook, Gayoung Eom, Sungwoo Lee, Kiup Kim, and Hyunjoo J. LeeKAIST, Korea

07 The effect of different catalyst on gas sensing performances of MWCNTs-rGO networkUsman Yaqoob, Rahman Md Habibur, and Hyeon Cheol KimUniversity of Ulsan, Korea

08 Catalytic activity of quantum size Pd/Mg based bimetallic thin film deposited on alumina substrate for fast hydrogen gas sensingRahman Md Habibur, Usman Yaqoob, and Hyeon Cheol KimUniversity of Ulsan, Korea

09 The Automated Heart Disease Detection System with Dry-Electrode Based Outdoor ShirtsEun-Bin Park and Jong-Ha LeeKeimyung University, Korea

10 Security Analysis of Mobile Health-care ApplicationsOleg Surnin, JooYoung Lee, Rasheed Hussain, Nikita Ulianov,Iuliia Sharafitdinova, and Adil MehmoodInnopolis University, Russia

11 Measurement of Respiration using UWB Impulse Radar on the LPC4088Young-Jin Park and Hui-Sup ChoDGIST, Korea

62

12 FPGA based Sync Block for real-time Analog Mean Delay (AMD) Fluorescence Lifetime Imaging SystemByungjun Park, Seungrag Lee, and Youngjae WonOsong medical innovation foundation, Korea

13 DNN-GRU multiple layers for VAD in PC Game CafeGyeowoon Jung, Namhyun Cho, Heeman Kim, and Hoonyoung ChoNCSOFT, Korea

14 A Novel C-RAN Architecture Based on the ETSI-Standard Radio Virtual MachineHeungseop Ahn1, Daejin Kim1, Seungwon Choi1, Ildo Jung2, and Jehoon Oh2

1Hanyang University, Korea, 2LG Uplus, Korea

15 A Design of low Cross Regulation DPWM Single Inductor Multiple Outputs DC-DC ConverterZaffar Hayat Nawaz Khan, Nabeel Ahmad, Danial Khan,Syed Adil Ali Shah, Young-Jun Park, and Kang-Yoon LeeSungkyunkwan University, Korea

16 Performance Comparison of Multi-Level Coding Schemes for Flash MemoryJieun Oh and Seokju HanKAIST, Korea

17 Three Level Buck Converter with Schmitt Trigger Ramp GeneratorJin-Woo So, Dong-Hyun Lee, Ho-Yong Lee, and Kwang-Sub YoonInha University, Korea

18 A Low Power 12bit CMOS SAR A/D Converter with 6 MSB bit Sharing TechniqueHo-Yong Lee, Dong-Hyun Lee, Jin-Woo So, and Kwang-Sub YoonInha University, Korea

19 Design of a low power CMOS RMS RF power detector with wide rangeKun Huang, Danial Khan, Shen Huang, Dong-Soo Lee,and Kang-Yoon LeeSungkyunkwan University, Korea

20 3D Thermal Analysis for a 7-die Memory Stacked Motion Estimation ProcessorShuping Zhang1, Jinjia Zhou2,3, and Shinji Kimura1

1Waseda University, Japan, 2Hosei University, Japan, 3JST, PRESTO, Japan

63

21 A Delay-Encoding Scheme of Ultrasonic Beamformer ASIC for Reduction of on-Chip Memory SizeNam-Kyu Kim, Sung-Phyo Choi, and Ji-Yong UmHannam University, Korea

22 TDOA-based ASF Map Generation to Increase Loran Positioning Accuracy in KoreaJaehui Hwang, Pyo-Woong Son, and Jiwon SeoYonsei University, Korea

23 A Novel Enhanced Inverted PWM Driving Scheme for Three-Phase BLDC Motor DriveYongKeun Lee and JongKwang KimSeoul National University of Science and Technology, Korea

24 A Simple Method of Measuring Cogging Torque in BLDC Motors Using DynamometerKangSoo Lee, JongKwang Kim, and YongKeun LeeSeoul National University of Science and Technology, Korea

25 Iterative Normalized Matched Filtering for Detection of Chemical Agents in Hyperspectral ImagingHyeong-Geun Yu1, Jay-Hoon Lee1, Dong-Jo Park1, Hyun-Woo Nam2, and Byeong-Hwang Park2

1KAIST, Korea, 2Agency for Defense Development, Korea

26 Dynamic Diversity Adjustment for Stable Convergence of Generic Algorithm-based Convergence of Generic Algorithm-based Sensor CalibrationSung-Joon Jang and Sang-Seol LeeKorea Electronics Technology Institute, Korea

27 In-memory Disk-based Virtual Desktop Service using OpenstackDae Won Kim, Soo Cheol Oh, Jae Geun Cha, Sun Wook Kim,Ji Hyeok Choi, and Seong Woon KimElectronics and Telecommunications Research Institute, Korea

28 Constructing Resilient Region in Dynamic Optimization Systems via Dynamic Adjustment of Bias ThresholdsIpoom Jeong and Won Woo RoYonsei University, Korea

29 A Field Study on Improving the API Usability of Software Platforms for Consumer Electronics DevicesHobum Kwon and Wonyoung ChoiSamsung Electronics, Korea

64

30 Near-Data Processing Optimization for Efficient Neural Network ComputationSungwoo Ahn, Won Jeon, and Won Woo RoYonsei University, Korea

31 Infrared and Visible Image Fusion using Multi-Scale Decomposition and Visual Saliency MapYunfan Chen, Han Xie, Donghoon Yeo, and Hyunchul ShinHanyang University, Korea

32 Epileptic Seizure detection for Multi-channel EEG With Recurrent 3D-Convolutional Neural NetworksGwangho Choi1, Chulkyun Park1, Junkyung Kim1, Kyoungin Cho1, Tae-Joon Kim2, HwangSik Bae1, Kyeongyuk Min1, Ki-Young Jung2, and Jongwha Chong1

1Hanyang University, Korea, 2Seoul National University Hospital, Korea

65

Conference Venue :Ramada Plaza Hotel, Jeju, Korea

Ramada Plaza Jeju is Korea’s first coastal hotel

Located only five minutes away from Jeju International Airport and Jeju Port, Ramada Plaza Jeju gives you a unique experience as if you are in a cruise ship on the ocean.

Ramada Plaza Jeju has been founded and financed by the Korean Teachers Credit Union under a franchise agreement with Ramada International as the highest grade hotel “Ramada Plaza”. Designed after the Northern European cruise ship SILJA LINE, this resort-type business hotel opened on July 1 2003 with 400 rooms and suites in a building with 9 floors above ground and 1 underground floor.

The hotel with unique, prestige interior designs has various types of rooms and suites, and banquet halls in different sizes including Grand Ballroom capable of accommodating up to 1,500 guests for seminars, meetings, and wedding ceremonies. With other convenient and versatile facilities, Ramada Plaza Jeju provides guests with some of the best hotel services and experience.

CONTENTS · search topics in AI with brain and communications; topics in-clude BMI, signal...

Documents

Transcript of CONTENTS · search topics in AI with brain and communications; topics in-clude BMI, signal...