Work place: Department of Mathematics, Tiruchirappalli
E-mail: nalla@nitt.edu
Website:
Research Interests: Computer systems and computational processes, Autonomic Computing, Data Structures and Algorithms, Combinatorial Optimization, Mathematics of Computing
Biography
Dr. R. Nallaswamy: Professor of Department of Mathematics in National Institute of Technology, Tiruchirapalli, interested in bio-mathematics, optimization techniques and soft computing.
DOI: https://doi.org/10.5815/ijitcs.2012.05.03, Pub. Date: 8 May 2012
Feature selection has been keen area of research in classification problem. Most of the researchers mainly concentrate on statistical measures to select the feature subset. These methods do not provide a suitable solution because the search space increases with the feature size. The FS is a very popular area for applications of population-based random techniques. This paper suggests swarm optimization technique, binary particle swarm optimization technique and its variants, to select the optimal feature subset. The main task of the BPSO is the selection of the features used by the SVM in the classification of spambase data set. The results of our experiments show a very strong relation between number of features and accuracy. Comparison of the optimized results and the un-optimized results showed that the BPSO-MS method could significantly reduce the computation cost while improving the classification accuracy.
[...] Read more.DOI: https://doi.org/10.5815/ijieeb.2012.01.06, Pub. Date: 8 Feb. 2012
Recent years, feature selection is chief concern in text classification. A major characteristic in text classification is the high dimensionality of the feature space. Therefore, feature selection is strongly considered as one of the crucial part in text document categorization. Selecting the best features to represent documents can reduce the dimensionality of feature space hence increase the performance. Feature selection is performed here using Document Frequency Threshold. This paper focus on SVM based text message classification using document frequency threshold. The experiment is performed with NUS SMS text messages data set. An experimental result shows that the results of proposed method are more efficient.
[...] Read more.Subscribe to receive issue release notifications and newsletters from MECS Press journals