A framework for machine learning based anomaly detection in Internet of Things data analysis

Internet of Things (IoT) systems produce large amounts of raw data in the form of log files. This raw data must then be processed to extract useful information. Machine Learning (ML) has proved to be an efficient technique for such tasks, but there are many different ML algorithms available, each suited to different types of scenarios. In this work, I compare the classification performance of 22 state-of-the-art supervised ML classification algorithms on different IoT smart-buildings datasets, when applied to the problem of anomaly detection. The results show that there is a set of ML algorithms that fits almost perfectly a type of datasets. Based on these results and a characterization of our datasets, this thesis propose a recommendation framework which guides practitioners towards the subset of the 22 ML algorithms which is likely to perform best on their data.