Anomaly Detection in IoT : State-of-the-Art Techniques and Implementation Insights

Current work in the area of anomaly detection for the Internet of Things (IoT) is rapidly expanding. Therefore, this paper attempts to contribute to the field by shedding light on the intricacies of anomaly detection. We have explored and compared a variety of anomaly detection types and techniques, from traditional machine learning approaches to more sophis- ticated deep learning methods such as convolutional neural networks, graphical neural networks reinforcement learning and the combination of complex techniques. This research provides valuable insights into the diversity of approaches available to address the challenges of anomaly detection in the IoT domain. The comparative analysis of the results provides valuable findings on the strengths and weaknesses of different anomaly detection techniques. These insights can help researchers and practitioners select the most appropriate methods based on the specific requirements of their IoT applications.