Title: Feature Selection of Network Flow Based on Machine Learning
Abstract: This paper studies stages of feature selection in machine learning. CSF algorithm selects feature based on the correlation between features as well as features and categories, but information gain algorithm only considers the contribution values of individual feature to classification. It combines the subsequent learning algorithm to set appropriate threshold and complete feature selection, thus the consideration of redundancy between features are neglected. In view of this, we introduce symmetrical imbalance to improve information gain algorithm. We hope the improved information gain algorithm can increase classification accuracy through further removing its redundant features. Finally, under three kinds of learning algorithms, we compare the classification effect of three feature selection methods on WEKA platform respectively.
Publication Year: 2018
Publication Date: 2018-01-01
Language: en
Type: book-chapter
Indexed In: ['crossref']
Access and Citation
AI Researcher Chatbot
Get quick answers to your questions about the article from our AI researcher chatbot