A Novel Approach for Bluetooth Mesh Network Detection using Machine Learning and Correlation Analysis

Abstract

Bluetooth (BT) mesh networks are used in several ad hoc network communication scenarios, including natural disasters, calamities, war zones, etc. However, there are situations where Bluetooth mesh networks are misused by anti-social elements during riots etc. As of now there no such research article that showcases detection of BT mesh networks using machine learning tools. Therefore, there is a need to build novel methods for detecting the very presence of Bluetooth mesh networks to aid the law enforcement agencies. This paper contributes to building a new dataset for the aid of machine learning tools to detect the presence of Bluetooth mesh networks. The dataset is extracted from a simulated Bluetooth mesh network with 52 BT network traffic attributes, using the Bridgefy application. Further, the dataset is optimized by identifying prime features, using label encoding, one-hot encoding, correlation analysis and evaluated by various Machine Learning (ML) tools. An accuracy of 99.6% is achieved after optimizing the feature set.