A model for data enrichment over IOT streams at edges of internet

Abstract

In this paper some issues related to the efficiency of processing IoT data are addressed through semantic data enrichment and edge computing. The aim is to cope with big data streams at various levels, from the lowest level of data capturing to the highest level of Cloud platforms and applications. The objective is thus to extract full knowledge contained in the data in real time but also to solve bottlenecks of processing observed in IoT Cloud systems, in which IoT devices are directly connected to Cloud servers. An architecture comprising various levels is introduced, where each level is in charge of specific functionalities in the overall processing chain. In particular, there is a focus on the layer of semantic data enrichment in order to enable further processing and reasoning in upper layers of the architecture. Some preliminary evaluation results are presented to highlight the issues and findings of this study using a case study of pothole detection in roads based on a data stream collected by cars.