• 1
  • 2
  • 3

Keynote Speakers


Keynote Speaker

Prof. Edwin Wang

University of Calgary, Canada

Dr. Edwin Wang is Professor and AISH Chair in Cancer Genomics at the University of Calgary. He was a Senior Investigator at the National Research Council Canada and Professor at McGill University. He has a undergraduate training in Computer Science and a PhD training in Experimental Molecular Genetics (UBC, 2012). He is the member of the AACR-Cancer Systems Biology Think Tank, which consists of ~30 world leaders in the field for discussing key problems and cutting-edge directions. He is an Editor of PLoS Computational Biology, the top journal in the field of bioinformatics. He has edited the book of Cancer Systems Biology (2010), the first book of the field. His pioneering work of microRNA of singling networks opens the new research area: network biology of non-coding RNAs. His pioneering work of cancer network motifs has been featured in the college textbook, GENETICS (2014/2017) written by a Nobel Laureate, Dr. Hartwell and the father of systems biology, Dr. Hood.

Speech Title: "From Health Genomics to Intelligent Precision Health"

Abstract: Cancer is the leading cause of death and the third largest burden in the healthcare system in the world. Each year, more than 15 million new cancer patients are diagnosed and 7-8 million people die from cancer in the world. Current precision oncology is focusing on cancer treatment, however, with some notable exceptions, improvements in overall survival and morbidity over the past few decades have been modest. Historical data suggest that early detection of cancer is crucial for its ultimate control and prevention. To meet the challenges of the surge in cancer cases in the future, it is envisioned that, besides the promotion of lifestyle changes, improving early diagnosis is the best strategy for reducing the impact of carcinogenesis.
Both genetic and environmental factors (e.g., pollution, lifestyle and so on) interact to induce cancer initiation, progression and metastasis. Therefore, we are aiming to combine the genome sequencing, imaging and electronic medical records of individuals to identify high-risk cancer individuals, ‘healthy lifestyle patterns’ for cancer prevention, and monitor high-risk cancer individuals for cancer early detection. To do so, we have complied a cohort which contains 5 million people whose medical records have been collected. Among them, 0.5 million people’ genomic information has been determined. We are developing new algorithms by applying machine learning and deep learning approaches to the cohort to meet the goals mentioned above.

Prof. Kiyoshi Hoshino

University of Tsukuba, Japan

Prof. Kiyoshi Hoshino received two doctor's degrees; one in Medical Science in 1993, and the other in Engineering in 1996, from the University of Tokyo respectively. From 1993 to 1995, he was an assistant professor at Tokyo Medical and Dental University School of Medicine. From 1995 to 2002, he was an associate professor at University of the Ryukyus. From 2002, he was an associate professor at the Biological Cybernetics Lab of University of Tsukuba. He is now a professor. From 1998 to 2001, he was jointly appointed as a senior researcher of the PRESTO "Information and Human Activity" project of the Japan Science and Technology Agency (JST). From 2002 to 2005, he was a project leader of a SORST project of JST. His research interests include biomedical measurement and modelling, medical engineering, motion capture, computer vision, and humanoid robot design.

Speech Title: "Technology for Acquiring Biosignals Generated during Eye Movements"

Abstract: The objective of our study is to provide a method for measuring user’s eye movements day and night with a high degree of accuracy without imposing a psychological burden on a device-wearer, regardless of brightness of image contents. Specifically, our method, in particular, makes possible; (1) tracing the points where the user is looking at (i.e. line of sight); (2) detection of any of bad physical conditions, such as dizziness and sick-feeling, or the signs of them (i.e. nystagmus or cycloduction); and (3) estimation of the degree of distraction of attention (i.e. the degree of heterophoria between the eyes).
To this end, a faint blue light with less brightness is illuminated in the vicinity of the eyeballs as an auxiliary light to improve the grayscale contrast of the blood vessels in the tunica conjunctiva or sclera of an eyeball. Moreover, the above method is used together with a combination of techniques for equalizing the individual image partitions of the gray-level and for determining a banalization threshold based on the difference in grayscale value between the target and its adjacent pixels, so as to remove eyelashes and faint-colored thin blood vessels, achieving an improvement in grayscale contrast of the characteristic blood vessels. Furthermore, using a method for tracing the images of the characteristic template blood vessels is used to measure the user’s eye movements.

Assoc. Prof. Simon Fong

University of Macau, China

Simon Fong graduated from La Trobe University, Australia, with a 1st Class Honours BEng. Computer Systems degree and a PhD. Computer Science degree in 1993 and 1998 respectively. Simon is now working as an Associate Professor at the Computer and Information Science Department of the University of Macau. He is a co-founder of the Data Analytics and Collaborative Computing Research Group in the Faculty of Science and Technology.  Prior to his academic career, Simon took up various managerial and technical posts, such as systems engineer, IT consultant and e-commerce director in Australia and Asia. Dr. Fong has published over 373 international conference and peer-reviewed journal papers, mostly in the areas of data mining, data stream mining, big data analytics, meta-heuristics optimization algorithms, and their applications. He serves on the editorial boards of the Journal of Network and Computer Applications of Elsevier, IEEE IT Professional Magazine, and various special issues of SCIE-indexed journals.

Plenary Speaker

Assoc. Prof. Hu Han

Chinese Academy of Sciences, China

Hu Han is an Associate Professor of the Institute of Computing Technology (ICT), Chinese Academy of Sciences (CAS). He received the B.S. degree from Shandong University, and the Ph.D. degree from ICT, CAS, in 2005 and 2011, respectively, both in computer science. Before joining faculty of ICT, CAS in 2015, he was a Research Associate in the Department of Computer Science and Engineering at Michigan State University, and a visiting researcher at Google in Mountain View from 2011 to 2015. His research interests include computer vision, pattern recognition, and image processing, with applications to biometrics. He has authored or co-authored more than 30 scientific papers, including IEEE Trans. PAMI, IEEE Trans. IFS, Pattern Recognition, ECCV, etc., with over than 930 citations according to Google Scholar (Aug. 2017). He has served as the program committee member of a number of international conferences on computer vision and biometrics, such as ICB, IJCB, ACCV, and CCBR. He was a recipient of the ICCV2015 apparent age estimation competition runner-up award, the CCBR2016 Best Student Paper award, and ACCV2012 Best Reviewer Award. He is a member of the IEEE.

Speech Title: "Attribute Estimation from Face: Approaches and Applications"

Abstract: Face attribute estimation has many potential applications in video surveillance, face retrieval, and social media. Despite tremendous progress in attribute learning in recent years, joint estimate of a wide variety of face attributes accurately and efficiently from a single face image remains a challenging problem due to the data imbalance, label noise, etc. In this talk, I will briefly review the representative approaches for face attribute learning and highlight some of our latest research work on facial attribute from the exterior to the interior. In particular, I will cover our face attribute learning approaches in terms of the feature representation methods and the classification models. In addition, we also extend face attribute estimation into a more general scope, i.e., from the exterior to the interior such as heart rate estimation from the face.