Detection of Fraudulent data in IOT devices using Machine Learning framework

Abstract

The Internet of Things (IoT) refers to a network of physical objects, or "things," that are based in software and other technologies in order to communicate and exchange data with other devices and systems over the internet. These gadgets range from common domestic items to high-tech industrial instruments. Currently more than 7 millions users are connected today. Experts predict that by 2023, there will be more than 10 billion connected IoT devices, and by 2026, there will be 23 billion. IoT devices generate a vast volume of data in a variety of modalities, with differing data quality characterised by their speed in terms of time and location reliance. In such a scenario, machine learning algorithms can play a critical role in providing biotechnology-based security and permission, as well as anomaly detection to improve the usability and security of internet-of-things (IoT) platforms The detection of IoT devices using the Machine Learning framework is offered to achieve this goal. Five machine learning models are evaluated using various metrics with a vast collection of input feature sets in this ML framework. Each model calculates a spam score based on the input attributes that have been adjusted. This score represents the IoT device's dependability under various conditions. The proposed technique is validated using certain common appliances. The acquired findings support the suggested scheme's effectiveness in comparison to other current schemes.