Preprocessing and Framework for Unsupervised Anomaly Detection in IoT: Work on Progress

Abstract

A robust increasing on smart sensors in Internet of Thing (IoT) results huge and heterogenous data and becomes a challenge in data prepocessing and analysis for anomaly detection. The lack of IoT publicly available dataset is one issue in anomaly detection research. To resolve that problem, a testbed topology is proposed in this research. In addition, a high-dimensionality data analysis faces a computational complexity. The purpose of this study is to presents a global framework for anomaly detection in IoT and proposes a distributed preprocessing framework. Unsupervised learning approach has been chosen to reduce dimensionality of IoT data traffic.