• 1Priyanka Sharma
• 2Rajni Ranjan Singh Makwana

IDS is security software that detects a network for malicious activity or policy violations. An IDS work by monitoring system for known attack patterns and utilized to identify the types of attack. In this work a hybrid feature selection model has been introduced to perform random forest classification of NSL-KDD dataset. Here 20 unique combinations of wrapper and filter feature selection methods have been created to select relevant attributes. To analyze the effectiveness and usefulness of proposed way an observation has been accomplished using WEKA machine learning tool. It is observed that filter method based gain ratio feature selection method gives better result that is 99.46% (in 10 fold cross validation) and 99.99% (in use training set).

IDS is security software that detects a network for malicious activity or policy violations. An IDS work by monitoring system for known attack patterns and utilized to identify the types of attack. In this work a hybrid feature selection model has been introduced to perform random forest classification of NSL-KDD dataset. Here 20 unique combinations of wrapper and filter feature selection methods have been created to select relevant attributes. To analyze the effectiveness and usefulness of proposed way an observation has been accomplished using WEKA machine learning tool. It is observed that filter method based gain ratio feature selection method gives better result that is 99.46% (in 10 fold cross validation) and 99.99% (in use training set).

"RANDOM FOREST CLASSIFICATION OF NSL-KDD DATASET USING HYBRID FEATURE SELECTION MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 12, page no.444-453, December-2018, Available :http://www.jetir.org/papers/JETIR1812462.pdf

"RANDOM FOREST CLASSIFICATION OF NSL-KDD DATASET USING HYBRID FEATURE SELECTION MODEL", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 12, page no. pp444-453, December-2018, Available at : http://www.jetir.org/papers/JETIR1812462.pdf