Filter-Based Ensemble Feature Selection and Deep Learning Model for Intrusion Detection in Cloud Computing

In recent years, the high improvement in communication, Internet of Things (IoT) and cloud computing have begun complex questioning security. Based on development, cyberattacks can be increased since present security techniques do not give optimal solutions. As a result, authors this paper created filter-based ensemble feature selection (FEFS) employed deep learning model (DLM) for intrusion detection. Initially, data were collected from global datasets KDDCup-99 NSL-KDD. The utilized validation proposed methodology. database was to empower prediction. FEFS is combination three extraction processes: filter, wrapper embedded algorithms. above process, essential features selected enabling training process DLM. Finally, classifier received chosen features. DLM recurrent neural network (RNN) Tasmanian devil optimization (TDO). RNN, weighting parameter with assistance TDO. technique implemented MATLAB, its effectiveness assessed using performance metrics including sensitivity, F measure, precision, recall accuracy. method compared conventional such as an RNN (DNN) RNN–genetic algorithm (RNN-GA), respectively.