The information about the Keynote Speakers of ICAMDS2016 is as follows, which will be updated regularly.
In Chinese >>
Dr. Sreeparna Banerjee, Professor
Department of Natural Science, West Bengal University of Technology (Makaut, West Bengal), India
Biography: Sreeparna Banerjee completed her Bachelor's, Master's and PhD in Physics degrees, all in Physics from Presidency College, Calcutta University and the University of Virginia USA, respectively, followed by a postdoctoral fellowship in Computational Physics in the USA. Subsequently, she has been engaged in research in Pattern Recognition, Artificial Intelligence and Computer Vision as well as Theoretical Physics at the Indian Statistical Institute, Kolkata. She was then a faculty in the Indian Institute of Information Technology, Calcutta, where she also served as its acting Director for a year before it became amalgamated with West Bengal University where she is currently a senior faculty. Her research interests include Molecular Dynamics simulations, Charge transfer problems in Atomic and Molecular Physics and AI, Pattern Recognition, Computer Vision, Data Mining and Machine Learning applications in Astrophysics, Meteorology and Biomedicine and is currently working on Case Based Reasoning in the diagnosis of abnormalities of the retina from Retina fundus images, for which she has received a Government sponsored project.
Topic: Case Based Reasoning in Mining of Sparse and Big Data
Abstract: Case Based Reasoning (CBR) is a paradigm in Artificial Intelligence/Data Science in which similar cases have similar solutions. This idea is based on the methods employed by doctors to diagnose an illness whereby similar problems have similar treatments. CBR is particularly useful for poorly understood domains with a small body of knowledge which is already stored and is suitably augmented with new knowledge. Thus one can start with sparse data and gradually deal with big data. The talk will focus on different aspects of this paradigm, namely the notion of knowledge containers like vocabul.