Performance Evaluation of Machine Learning for Prediction of Network Traffic in a Smart Home

Abstract

The network system of smart homes using a Internet of Things (IoT) device is increasing in parallel with cybersecurity challenges as these loT devices have some vulnerabilities such as hardware and software limitations that leads to difficulties with time to fit security features to any IoT systems. Therefore, the Intrusion Detection Systems (IDS) is the suggested method to mitigate these cyberattacks and monitor the requests in smart homes. IDS has the capacity to protect the smart home network and detect real-time vulnerabilities and threats. In this paper, we applied and compared four types of machine learning algorithms which are random forest, xgboost, decision tree, and k-nearest neighbors on two sorts of datasets. We randomly selected three samples from each dataset. The results show that our models for each algorithm can effectively achieve a satisfying seemingly classification accuracy with the lowest false positive rate.