Title: Genetic and Firefly algorithm in Instance and Feature Selection: An Approach for Malware Detection

Issue Number: Vol. 8, No. 4
Year of Publication: Dec - 2018
Page Numbers: 232-238
Authors: Ankur Singh Bist
Journal Name: International Journal of Digital Information and Wireless Communications (IJDIWC)
- Hong Kong
DOI:  http://dx.doi.org/10.17781/P002467

Abstract:


Instance selection is used to extract useful data from actual data samples in order to enhance the predictive performance. Feature selection is used to select important features from dataset. In an experiment we used firefly algorithm for feature selection and genetic algorithm for instance selection. Further we used SVM, Random forest and Convolutional Neural Network for classifying malwares. Proposed method produced satisfactory results and can be used in real time antivirus engines for better performance.