IoT Network Anomaly Detection Using Machine Learning and Deep Learning Techniques - Research Study

The Internet of Things (IoT) is a network of connected devices that captures all the data from the set of devices. Due to the growth of IoT networks, sources of anomalies exist, such as intrusion detection systems, data leakage, and fraud detection. The issue of anomalies in an IoT network is the effect of system mitigation and causing abnormalities that lead to destructive consequences. Machine learning can be used within IoT to detect anomalies because it can find hidden patterns in IoT data by analyzing vast data amounts using sophisticated algorithms. Deep learning algorithms can analyze sensor data from IoT devices to produce predictions or detect patterns, and that can improve the IoT system's efficiency. The objective of the paper is to explore recent existing techniques in the context of anomaly detection in IoT Networks. The study is conducted to observe the sets of machine learning, and deep learning methods that focus on different datasets and aim to detect a specific anomaly to see what the most appropriate solution is to implement.