Get Adobe Flash player


The data collected by different sensors need to be analyzed for various recognition problems, such as human activity recognition from wearable sensors, odor recognition from chemical sensors (E-nose) or detection of explosives from calorimetric sensor array. Feature selection is an important step towards dimensionality reduction of high dimensional data and facilitates further analysis by selecting important information while discarding unwanted or redundant information. Feature subset selection techniques also help in finding good sensor subsets and can be applied to optimize sensor locations in wireless sensor networks. In this talk, I will discuss soft computing based approaches for feature subset selection and present some proposed algorithms useful for pattern recognition or mining of real life sensors’ data with simulation experiments and results.


Basabi Chakraborty received her B. Tech, M.Tech and Ph.D degrees in Radio Physics and Electronics from University of Calcutta, India. She worked in National Center for Knowledge based Computing Systems and Technology affiliated to Indian Statistical Institute, Calcutta, India until 1990. From 1991 to 1993 she worked as a visiting researcher in Advanced Intelligent Communication Systems Laboratory in Sendai, Japan. She received another Ph. D in Information Science from Tohoku University, Sendai in 1996. Currently she is a faculty in Software and Information Science department of Iwate Prefectural University, Japan. Her main research interests are in the area of Pattern Recognition, Image Processing, Soft Computing Techniques, Biometrics, Data Mining, Social Network Analysis and Cognitive Science. She is a senior member of IEEE, member of ACM, Japanese Neural Network Society (JNNS), Japanese Society of Artificial Intelligence (JSAI), executive committee member IEEE JC WIE (Women in Engineering) and ISAJ (Indian Scientists Association in Japan).