Prof Takashi Washio
Osaka University, JapanMultiagent Simulation for Designing Social Services
Abstract:
Machine learning and data mining techniques are often used to analyze big data acquired from large-scale IoT systems. On the other hand, they now have a promising outlook to be applied to generating the big data. In this talk, I will demonstrate such promising applications of the techniques to the future advanced sensing devices for IoT. Recent development of advanced devices is now enhancing the feasibility of nano-scale and ultratrace sensing of various objective materials, and is becoming good candidates of novel and compact IoT sensors for our society. However, the output of the individual sensing device is noisy and contains limited information on the sensing object in many cases, because effects of thermal disturbances and quantum fluctuations of the objects and the devices are significant in the nanoscopic sensing process. Key techniques to alleviate these limitations are the information extraction from the sensing output signals and the information integration of the multiple sensing outputs by applying machine learning methods. I will introduce the current development of the sensing systems for detecting hazardous viruses/bacteria and toxic compounds by combining the machine learning techniques and the advanced device techniques in a Japanese national project: InSECT (ultra high-speed and multiplexed sensing system using Incredibly Smart, Efficient and Compact devices by insect Technology) under an umbrella of ImPACT (Impulsing Paradigm Change through Disruptive Technologies) program.
Biography:
Takashi Washio is a full professor in Department of Reasoning for Intelligence, The Institute of Scientific and Industrial Research, Osaka University which is located at Ibaraki City, Osaka, Japan. He concurrently serves a director of NEC (NEC Corporation) - AIST (National Institute of Advanced Industrial Science and Technology) AI Cooperative Research Laboratory located at Koto-ku, Tokyo, Japan. His department in Osaka University focuses on basic studies of machine learning and data mining and is a leading research group in Japan. His NEC - AIST cooperative laboratory orients applications of machine learning, data mining and simulation techniques to various scientific, industrial and social fields. His current main research interests are machine learning principles for high dimensional big data in the basic study and machine learning techniques for scientific advanced sensing in the application study. Takashi Washio obtained his M.E. and Ph.D in the field of nuclear measurement and instrumentation control at Tohoku University, Miyagi, Japan, in 1985 and 1988, respectively. He was previously a visiting researcher of a Nuclear Reactor Laboratory of MIT (Massachusetts Institute of Technology), USA from 1988 to 1990, a senior researcher of Mitsubishi Research Institute from 1990 to 1996, and an associate professor in Osaka University from 1996 to 2006.
Back to Keynote Speakers