|Date||September 11, 2018 (Tuesday)|
|Profile||Dr. Tsuyoshi Ide (井手剛 博士) is a Senior Technical Staff Member at IBM Thomas J. Watson Research Center, NY, USA. He started his career at IBM Research as a research staff member in 2000 at Tokyo Laboratory after he finished his Ph.D. at the University of Tokyo in physics. In 2013, he transferred to T. J. Watson Research Center as a manager of Services Science. He is currently a member of AI & Blockchain Solutions IBM Research. His primary research interest lies in developing new machine learning approaches to model complex industrial problems. In Japan, he is most known as the author of textbooks in anomaly detection. For more detail, see his personal website http://ide-research.net/.|
|Title||Recent advances in machine learning from industrial sensor data|
Sensor data analytics is one of the major application fields of data mining and machine learning. Typically taking real-valued time-series data from physical sensors as the input, its problem setting includes a variety of tasks depending on application domains, not limited to the traditional regression and classification. This talk will first
introduce technical challenges in industrial sensor data analytics. Then it will cover recent developments in machine learning algorithms in sensor data analytics. Major topics include change detection using directional statistics and multi-task extension of graph-based anomaly detection.