首页|Findings from Delhi Technological University Has Provided New Data on Machine Le arning (Performance Analysis of Anomalybased Network Intrusion Detection Using Feature Selection and Machine Learning Techniques)
Findings from Delhi Technological University Has Provided New Data on Machine Le arning (Performance Analysis of Anomalybased Network Intrusion Detection Using Feature Selection and Machine Learning Techniques)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Machine Learning. According to news reporting originating from New Delhi, India, by NewsRx correspondents, research stated, "Data and information, being a criti cal part of the Internet, are vital to network security. Intrusion Detection Sys tem (IDS) is required to preserve confidentiality, data integrity, and system av ailability from attacks." Our news editors obtained a quote from the research from Delhi Technological Uni versity, "IDS collects network data from various places that may contain feature s that are redundant and irrelevant, leading to an increase in processing time a nd low detection rate. This study proposes a three-phase networkbased IDS to co unter this issue. Initially, network data is captured and preprocessed. In the s econd phase, we perform feature extraction, selection, and ranking to obtain the optimal feature set. A novel Dynamic Mutual Information-based Genetic Algorithm for feature selection (DMI-GA), aiming to enhance the performance of machine le arning (ML) techniques by identifying an optimal set of features, is also propos ed in this work. Finally, well-known ML models are employed to detect intrusions within this refined set of network traffic features. Experimental results demon strate a significant improvement in detection accuracy when the ML models are tr ained and tested on an optimal set of features. It is also observed that DMI-GA combined with the Random Forest classifier, achieves the highest detection accur acy of 99.94 %, surpassing the performance of existing state-of-the- art anomaly-based network intrusion detection systems."
New DelhiIndiaAsiaCybersecurityC yborgsEmerging TechnologiesMachine LearningDelhi Technological University
NETL
NSTL
