Keynote Speech【2】

Goutam Chakraborty


Iwate Prefectural University, Japan


Prof. Goutam Chakraborty is Professor and head of the Intelligent Informatics laboratory, Department of the Software and Information Science, Iwate Prefectural University (IPU), Japan, since 2002. Before joining IPU, he worked at the university of Aizu, Japan, and at Tohoku University, Japan. He spent short periods as visiting professor at different universities, including one year (2006-2007) at the University of Waterloo, Canada. His research interests are Soft Computing algorithms and their applications to solve pattern recognition, prediction, scheduling and optimization problems including applications in wired and wireless Networks. Recently, he is interested in the analysis of various time-series signals, collected by sensors from Human body as well as machines.
He published around 200 peer reviewed research papers in well recognized journals and international conferences. He also delivered key-note speeches and invited talks at various international conferences. He contributed as editor of various journals, and edited books. He organized IEEE conferences in various capacities. Presently, Prof. Chakraborty is steering co-chair of technical committee on Awareness Computing, IEEE SMC, and vice-chair of IEEE CIS task force on Awareness Computing. He is a senior member of IEEE, and a life member of ACM.

Topic: Analysis of Time-Series Data – A Case Study with Electroencephalogram Signal for BCI Speller

One way of modeling a dynamic system is by analyzing the set of time-series data collected by sensors attached to the system. Modeling of the set of time-series is an important data-mining task for prediction in future, or detection of deviation from normal behavior (anomaly). Depending on the target application, and based on the domain knowledge, we need to design an efficient algorithm for analysis. In this talk, I will explain how analysis of time-series-data collected from sensors attached to human body as system can reveal the state of the system. Analysis of the electrical signals like EEG and ECG could reveal the metal and physical state. As for the tools used for analysis, I will explain: distance measurement for time-series signals, clustering techniques, multi-objective optimization using genetic algorithm, artificial neural network for classification. We will consider two bio-signals, ECG and EEG. The types of signals are different, one periodic and the other not. The applications are different too, EEG for BCI application, ECG to monitor heart-health.