Asgharzadeh, HosseinGhaffari, AliMasdari, MohammadGharehchopogh, Farhad Soleimanian2025-04-182025-04-182024Asgharzadeh, H., Ghaffari, A., Masdari, M., & Gharehchopogh, F. S. (2024). An Intrusion Detection System on The Internet of Things Using Deep Learning and Multi-objective Enhanced Gorilla Troops Optimizer. Journal of Bionic Engineering, 21(5), 2658-2684.1672-65292543-2141http://dx.doi.org/10.1007/s42235-024-00575-7https://hdl.handle.net/20.500.12713/6483In recent years, developed Intrusion Detection Systems (IDSs) perform a vital function in improving security and anomaly detection. The effectiveness of deep learning-based methods has been proven in extracting better features and more accurate classification than other methods. In this paper, a feature extraction with convolutional neural network on Internet of Things (IoT) called FECNNIoT is designed and implemented to better detect anomalies on the IoT. Also, a binary multi-objective enhance of the Gorilla troops optimizer called BMEGTO is developed for effective feature selection. Finally, the combination of FECNNIoT and BMEGTO and KNN algorithm-based classification technique has led to the presentation of a hybrid method called CNN-BMEGTO-KNN. In the next step, the proposed model is implemented on two benchmark data sets, NSL-KDD and TON-IoT and tested regarding the accuracy, precision, recall, and F1-score criteria. The proposed CNN-BMEGTO-KNN model has reached 99.99% and 99.86% accuracy on TON-IoT and NSL-KDD datasets, respectively. In addition, the proposed BMEGTO method can identify about 27% and 25% of the effective features of the NSL-KDD and TON-IoT datasets, respectively.eninfo:eu-repo/semantics/openAccessIntrusion DetectionInternet of ThingsConvolutional Neural NetworkMulti-ObjectiveGorilla Troops OptimizerArticle21526582684WOS:0012646271000012-s2.0-85197801400Q110.1007/s42235-024-00575-7Q1