Using Clustering for Forensics Analysis on Internet of Things

In the world of the internet of things (IoT), many connected objects generate an enormous amount of data. This data is used to analyze and make decisions about specific phenomena. If an object generates wrong data, it will influence the analysis of this collected data and the decision later. A forensics analysis is necessary to detect IoT nodes that are failing. This paper deals with a problem: the detection of these nodes, which generate erroneous data. The study starts to collect in a cloud computing server temperature measurements (the case study); using temperature sensors, the communication of the nodes is based on the HIP (host identity protocol). The detection is made using a data mining classification technique, in order to group the connected objects according to the collected measurements. At the end of the study, very good results were found, which opens the door to further studies.