Topic : Human-Centered Integration: Enhancing Visitor Experience through Sensor Agents, Compute Agents, and Human Interaction at Museums

The need to develop human-centered systems that facilitate interactions that strike a good balance of automation introduced by AI and robots with human control is increasing. These interactions are crucial for addressing social challenges by enhancing human abilities while respecting human behavior and preferences. This talk will overview the concepts for developing a platform to measure and improve the quality of visitor experience at a museum. The platform integrates sensor agents that measure human activity, compute agents that produce multi-faceted data from the sensor data, and applications that support humans in understanding and using the data. Sensors can efficiently measure visitor activity, the environment, and features that are difficult or unrecognizable to humans. On the other hand, the quality of the visitor experience cannot be expressed and evaluated only by numerical values but requires human intervention to understand it. This platform integrates devices, programs, and humans, making it possible to assess and verify the quality of the visitor experience, with humans playing a central role. Examples of utilizing multiple sensors, visualizations provided by the compute agents, and applications to support interactions with the curators will be presented.

RENTARO YOSHIOKA received BA in Physics from the College of Liberal Arts, International Christian University, Tokyo, Japan, in 1996. He received his MS (1999) and Ph.D. (2002) in Computer Science and Engineering from the University of Aizu, Fukushima, Japan. He is a Professor at the Graduate School of Computer Science and Engineering, University of Aizu. He has worked on human-computer collaboration, user-centered programming languages/environments, programming learning tools, software engineering, and 3DKanji. His research focuses on Active Knowledge Engineering, especially new knowledge creation/communication data formats, collaborative design of intelligent systems, and practical software engineering approaches to support knowledge creation. He is a member of ACM and IEEE.

Topic : Emotion Sensing for Human-Machine Interaction

With the increasing demand of machine intelligence across a wide range of application scenarios (e.g. digital twin and metaverse), human-machine interaction (HMI) emerges as another essential communication, whereby facial-expression-aware is one of the principal features for natural interaction. The principal branch of my research has been driven by the understanding of mechanism of emotion and facial expression combining knowledge of creative technologies with multiple disciplines, such as psychology, visual computing, and machine learning. Particularly, biometric data precisely record the facial muscle activity or brain activity closely related to facial movements and the internal emotional states. These multiple sensing channels would help provide an insight into the emotion and perception of facial expression, to develop widely accessible HMI solutions able to track facial motions and recognise affective states in a highly efficient and precise manner. This talk will discuss the development of facial expression capture, tracking and reconstruction for emotion detection and representation.

Hui Yu is a Professor with the University of Portsmouth, UK. He is the Head of the Visual Computing Group at the university. He is an Industrial Fellowship of the Royal Academy of Engineering, UK. His main research interest lies in visual computing, particularly in understanding and sensing emotion and the visual information of human related area, which involves and develops knowledge and technologies in vision, machine learning, virtual reality, brain-computer interaction, and robotics. Professor Yu’s research work has led to several awards and successful collaboration with worldwide institutions and industries. Prof. Yu is the PI on grants from a diverse range of funding sources including the EPSRC, EU FP7, RAEng, Royal Society, Innovate UK and Industry. He is the president of the Chinese Automation and Computing Society in the UK. He serves as Associated Editor of IEEE Transactions on Human-Machine Systems, IEEE Transactions on Intelligent Vehicles and IEEE Transactions on Computational Social Systems journal. He is the Deputy Editor-in-Chief of the international journal of network dynamics and intelligence.

Topic : Key Modules, Design and Case Studies of Autonomous Mobile Robots

Autonomous mobile robot (AMR) is a recent hot topic of research and application, which can be applied to many smart industrial and service fields such as semiconductor, aerospace, smart manufacturing, smart service and health care. This speech is especially dedicated to analyzing the key system modules of AMRs and proposing some new and useful intelligent adaptive learning motion control systems, and then demonstrates how the system modules and system integration can be designed for multiple case studies of autonomous mobile robots (AMRs), and finally shows the efficacy and applicability of the proposed methodologies and techniques.

He is currently a life distinguished Professor in the Department of Electrical Engineering, National Chung Hsing University (NCHU), Taichung, Taiwan, where he served the 2012-2014 department chairman. He received his Ph.D degree in Electrical Engineering from Northwestern University, Evanston, IL, USA, 1991. He has been elevated to Fellow of IEEE, IET, CACS, RST and TFSA.

Dr. Tsai has published more than 600 refereed journal and conference papers, and seven patents in the fields of intelligent control and robotics, where he received many prestigious awards and honors from IEEE and numerous professional societies, and many best conference paper awards technically supported by IEEE. He served as the two-term President of Chinese Automatic Control Society (CACS) from 2012-2015 and two-term President of Robotics Society of Taiwan (RST) from 2016 to 2019, and the Vice Dean and Dean of R&D Office, NCHU, from 2019 to 2021. In recent years, he has served associate editors of IEEE Transactions on Systems, Man Cybernetics: Systems, IEEE Transactions on Industrial Informatics, IEEE Transactions on Industrial Cyber-Physical Systems and International Journal of Fuzzy Systems and International Journal of Electrical Engineering. Moreover, he has served as the President of International Fuzzy Systems Association (IFSA) since September 2021, a BoG member and the associate VP for conferences and meetings of IEEE Systems, Man Cybernetics Society (SMCS), the chair of Distinguished Lecture Program of IEEE SMCS since 2022. He served as the Editor in Chief of a new international robotics journal called “iRobotics” from 2018 to 2019. His current interests include advanced nonlinear control methods, deep model predictive control, fuzzy control, neural-network control, deep learning, broad learning and reinforcement learning, and intelligent learning control methods with their applications to advanced mobile robotics, intelligent service robotics, intelligent mechatronics, intelligent automation, smart machinery, smart agriculture and smart semiconductor packaging.

Topic : From YOLOv4 to YOLOv7

YOLOv4 and YOLOv7 are leading object detection systems developed in Taiwan. Since April 2020, Taiwan has maintained the world’s number one position in the field of real-time object detection. In this talk, I will give a detailed story about how YOLOv4 and YOLOv7 were developed in the past four years. Three phases of the development history will be covered. From 2018/4 to 2018/10, a layer-level design called Partial Residual Network was developed. This model is speedy, but the detection accuracy could not do as good as YOLOv3 and M2Det. Later during 2019/1 to 2019/10, we started to consider a stage-level design called Partial Residual Network (CSPN). This time the design is quite successful and later this training strategy became the backbone training strategy of YOLOv4. From 2021/3 to 2022/7, my team put our emphasis on a network-level design, and we call it YOLOv7.

Mark Liao received his Ph.D degree in electrical engineering from Northwestern University in 1990. In July 1991, he joined the Institute of Information Science, Academia Sinica, Taiwan and currently, is a Distinguished Research Fellow. He has worked in the fields of multimedia signal processing, image processing, computer vision, pattern recognition, video forensics, and multimedia protection for more than 30 years. During 2009-2011, he was the Division Chair of the computer science and information engineering division II, National Science Council of Taiwan. He is jointly appointed as a Professor of the Department of Electrical Engineering and Computer Science of National Cheng Kung University. During 2009-2012, he was jointly appointed as the Multimedia Information Chair Professor of National Chung Hsing University. Since August 2010, he has been appointed as an Adjunct Chair Professor of Chung Yuan Christian University. From August 2014 to July 2016, he was appointed as an Honorary Chair Professor of National Sun Yat-sen University. From November 2016 to November 2019, he was appointed as a Chair Professor of National Chiao-Tung University. He received the Young Investigators'' Award from Academia Sinica in 1998; the Distinguished Research Award from the National Science Council of Taiwan in 2003, 2010 and 2013; the National Invention Award of Taiwan in 2004; the Distinguished Scholar Research Project Award from National Science Council of Taiwan in 2008; and the Academia Sinica Investigator Award in 2010. He received the TECO award from the TECO foundation in 2016, and the 64th Academic Award from the Ministry of Education in 2020.
His professional activities include: Co-Chair, 2004 International Conference on Multimedia and Exposition (ICME); Technical Co-chair, 2007 ICME; General Co-Chair, 17th International Conference on Multimedia Modeling; President, Image Processing and Pattern Recognition Society of Taiwan (2006-08); Editorial Board Member, IEEE Signal Processing Magazine (2010-13); Associate Editor, IEEE Transactions on Image Processing (2009-13), IEEE Transactions on Information Forensics and Security (2009-12), IEEE Transactions on Multimedia (1998-2001), and ACM Computing Surveys (2018-2021). Since 2021, he has been a Senior Associate Editor of ACM Computing Surveys. He has been a Fellow of the IEEE since 2013 for contributions to image and video forensics and security.

Discussion Topic

In this panel discussion, we will delve deep into the risks, responsibilities, and regulatory frameworks surrounding generative AI models. Initially, we will explore the potential threats to information security and the spread of disinformation through deepfakes that these modelscan engender. Following this, we will scrutinize the responsibilities that both developers and users hold in ensuring the safe and ethical deployment and use of AI technologies. Lastly, we will survey the existing regulatory landscape influencing generative AI models, discussing potential new regulations that could better safeguard individual privacy and intellectual property rights. The goal is to forge a pathway towards leveraging the benefits of AI technology while mitigating its potential harms.

Prof. Goutam Chakraborty was a full professor in the department of Software & Information Science, Iwate Prefectural University (Iwate State University), Japan, and head of the intelligent informatics laboratory for 22 years. He is now professor emeritus of the same university. Before joining Iwate Prefectural university, he taught in Tohoku university and Aizu University in Japan. Presently he is working as Dean of Global Research and Innovation at MITS, India. Time to time he worked for short periods as a visiting faculty at different universities, including one year at the University of Waterloo, ON, Canada.
He did his Ph.D. in March 1993 from Tohoku University, Japan. Before that, he worked in telecommunication industry for 8 years.
He supervised 14 Ph.D. students and 30 master students. In addition, he co-supervised several graduate students, from Japan and other countries.
His main research interests are Machine learning, Data Analysis, and optimization algorithms, and their applications in medical image analysis, bio-signal analysis, data mining, Wireless communication, and Sensor networks. He also works in matrix completion problems, social networking and recommendation systems. He has published around 300 papers in acclaimed journals and international conferences. His google scholar h-index is 31. He was awarded several projects supported by Japan government and the State Government of Fukushima and Iwate. He is a senior life member of ACM, and a senior member of IEEE.