Integration of Fuzzy with Incremental Import Vector Machine for Intrusion Detection

IDM design and implementation remain a difficult undertaking and an unsolved research topic. Multi-dimensional irrelevant characteristics and duplicate information are included in the network dataset. To boost the effectiveness of IDM, a novel hybrid model is developed that combines Fuzzy Genetic Algorithms with Increment Import Vector Machines (FGA-I2VM), which works with huge amounts of both normal and aberrant network data with high detecting accuracy and low false alarm rates. The algorithms chosen for IDM in this stage are machine learning algorithms, which learn, find, and adapt patterns to changing situations over time. Pre-processing is the most essential stage in any IDM, and feature selection is utilized for pre-processing, which is the act of picking a collection or subset of relevant features for the purpose of creating a solution model. Information Gain (IG) is utilized in this FGA-I2VM model to pick features from the dataset for I2VM classification. To train the I2VM classifier, FGA uses three sets of operations to produce a new set of inhabitants with distinct patterns: cross over operation, selection, and finally mutation. The new population is then put into the Import Vector Machine, a strong classifier that has been used to solve a wide range of pattern recognition issues. FGA are quick, especially considering their capacity to discover global optima. Another advantage of FGA is their naturally parallel nature of assessing the individuals within a population. As a classifier, I2VM has self-tuning properties that allow patterns to attain global optimums. The FGA-efficacy I2VM model's is complemented by information gain, which improves speed and detection accuracy while having a low computing cost

Automated summary

The study develops a novel hybrid model that combines fuzzy genetic algorithms with increment import vector machines (FGA-I2VM), which achieves high detecting accuracy and low false alarm rates in handling large amounts of network data. Pre-processing and feature selection are crucial steps in the model. Using FGA for training and optimization, combined with information gain, improves the speed and accuracy of the model.