Feature Selection by Multiobjective Optimization: Application to Spam Detection System by Neural Networks and Grasshopper Optimization Algorithm

Networks are strained by spam, which also overloads email servers and blocks mailboxes with unwanted messages files. Setting the protective level for spam filtering might become even more crucial users when malicious steps taken since they must deal an increase in number of valid communications being marked as spam. By finding patterns communications, detection systems (SDS) have been developed to keep track spammers filter activity. SDS has enhanced tool detecting reducing rate false positives increasing accuracy detection. The difficulty classifiers is abundance features. importance feature selection (FS) comes from its role directing algorithm’s search ways improve SDS’s classification performance accuracy. As a means enhancing SDS, we use wrapper technique this study that based on multi-objective grasshopper optimization algorithm (MOGOA) extraction recently revised EGOA multilayer perceptron (MLP) training. suggested system’s was verified using SpamBase, SpamAssassin, UK-2011 datasets. Our research showed our novel approach outperformed variety established practices literature much 97.5%, 98.3%, 96.4% respectively.