Anomaly detection in Internet of Things using feature selection and classification based on Logistic Regression and Artificial Neural Network on N-BaIoT dataset

Abstract

According to the paradigm of the Internet of Things (IoT), physical devices are connected to each other and to the Internet such that they operate automatically. One of the major challenges in the IoT is to detect and prevent intruders into the network and devices, a challenge that traditional solutions of Intrusion Detection Systems (IDS) are not responsive for it or at least not very efficient to use in IoT. In this article, we address the problem of using machine learning methods for anomaly detection and two methods for feature extraction and classification are proposed. The first method is feature extraction and classification using Logistic Regression (LR) and the second method is to use an Artificial Neural Network (ANN) for classification. To evaluate the performance of the proposed method, the N_BaIoT dataset, which consists of data samples related to nine devices IoT and several attacks is used according to a number of criteria for evaluating the performance of the proposed methods. Simulation results in comparison with other four deep learning methods in terms of F1-score and precision show that using logistic regression, is more efficient and the highest classification accuracy (equivalent to 99.98%) can be achieved.