Feature selection is an important preprocessing step for any pattern classification or data mining problem. The main objective of feature selection is to retain the most discriminatory information for classification or the most characteristic information for knowledge extraction. Basically it comprises of two steps. The first one deals with the evaluation measure for evaluating a feature or a feature set and the second one deals with the search algorithm for finding out the best feature subset from all possible subsets of features according to the selected evaluation measure.

In this talk, I would like to present some of our proposed evaluation measures and their merits and demerits. I would also like to show the effectiveness of their use with proposed search algorithms using soft computing techniques for feature subset selection by simulation results with bench mark data sets.

Biography

Basabi Chakraborty received B.Tech, M.Tech and Ph. D degrees in RadioPhysics and Electronics from Calcutta University, India and worked in Indian Statistical Institute, Calcutta, India until 1990. From 1991 to 1993 she worked as a part time researcher in Advanced Intelligent Communication Systems Laboratory in Sendai, Japan. She received another Ph. D in Information Science from Tohoku University, Sendai in 1996. From 1996 to 1998, she worked as a postdoctoral research fellow in Research Institute of Electrical Communication, Tohoku University, Japan. In 1998 she joined as a faculty in Software and Information Science department of Iwate Prefectural University, Iwate, Japan. Her main research interests are in the area of Pattern Recognition, Image Processing, Soft Computing Techniques, Biometrics, Data Mining and Online Social Media Mining. She is a senior member of IEEE, member of ACM, Japanese Neural Network Society (JNNS), Japanese Society of Artificial Intelligence (JSAI), Executive committee member of ISAJ (Indian Scientists Association in Japan), IEEE JC WIE (Women in Engineering).