Sequential Pattern Mining for Intrusion Detection System with Feature Selection for MANETS

For a huge network, large amount of network information generated and we have to process a large volume of multi-dimensional data to find both normal and abnormal activity. Intrusion Detection System (IDS) is required to monitor the network and to detect the malicious nodes and activities in the network. Massive amount of data makes it difficult to detect threats and attacks. Sequential Pattern mining used to identify the patterns of malicious activities which have been an emerging popular trend due to the consideration of quantities, profits and time orders of item. Many existing sequential pattern mining algorithms perform well for dense and large sequences, having costly scans using ‘generate candidate and test ’approach. This approach generates rules slowly or generates few rules omitting some interesting and valuable information with large amount of infrequent candidates. Here we propose a semi supervised sequential pattern mining algorithm with fuzzy logic feature selection and fuzzy weighted support for huge volumes of network logs, which solves the problem of performance speed and time constraints. In our simulation we use the attack log from NS-2 MANET environment and compare the proposed algorithm with the state-of-the-art sequential Pattern Mining algorithm SPADE and Support Vector Machine.