S
Saptarsi Goswami
Researcher at Bangabasi College
Publications - 67
Citations - 712
Saptarsi Goswami is an academic researcher from Bangabasi College. The author has contributed to research in topics: Feature selection & Cluster analysis. The author has an hindex of 11, co-authored 62 publications receiving 475 citations. Previous affiliations of Saptarsi Goswami include Information Technology University & University of Calcutta.
Papers
More filters
Book ChapterDOI
Filter-Based Feature Selection Methods Using Hill Climbing Approach
TL;DR: A comparison has been done with genetic algorithm, which shows the effectiveness of hill climbing methods in the context of feature selection.
Proceedings ArticleDOI
Feature selection using differential evolution with binary mutation scheme
TL;DR: This paper deals with the approach that involves changing the mutation scheme to allow for conversion to binary before selecting the features, and provides comparable results with existing algorithms like GA.
Posted Content
Quartile Clustering: A quartile based technique for Generating Meaningful Clusters
TL;DR: It is argued that clusters having understandable and distinct semantics defined in terms of quartiles/halves are more appealing to business analysts than the clusters defined by data boundaries or prototypes.
Book ChapterDOI
Topic Modeling for Text Classification
TL;DR: A method, using the concept of entropy, which further increases the accuracy of text classification by using a much sparser representation than usual TF-IDF and also, LSA can get from the topic if there are any synonym words.
Proceedings ArticleDOI
Jeffries-Matusita distance as a tool for feature selection
TL;DR: Jeffries-Matusita (JM) distance improves Bhattacharya distance by normalizing it between 0 and 2, which can provide a good intuition on how good a dataset is for classification and point out the need of or lack of further feature collection.