Detecting anomalies in IoT sensor data using machine learning algorithms
Vidur Mehta, Shubhangi Sharma, G. Abirami · 2024
In today&s;s interconnected world, the integration of Internet of Things (IoT) devices into networks has become increasingly prevalent. This extensive connectivity has raised concerns about threats and the evolving landscape of attacks. Recent studies have proposed machine learning (ML) and deep learning (DL) techniques to detect and classify such anomalies within the IoT framework. The primary objective of this project is to determine the most effective algorithm for detecting various types of attacks on such devices. The initiative aims to fortify IoT sensor networks by adopting a proactive stance to identify and mitigate potential threats, thereby safeguarding the integrity of these interconnected systems. According to our findings, deep learning algorithms like ANN exhibit greater accuracy compared to machine learning methods such as logistic regression and SVM, making them well-suited for future IoT measures.