Usage of IoT edge approach for road quality analysis

In the paper, the authors present the analysis of implementation of IoT system for road quality analysis. The proposed system was prepared for edge processing, on device. It allows to reduce the amount of data sent to cloud computing aggregation subsystem, sending only 2.5% of the original data. Several algorithms for road quality analysis were implemented on a real device and tested under real conditions. The system was compared with the state-of-the-art offline processing approach and showed the same accuracy on a set of known road artefacts, while detecting 92% of the artefacts recognized by the original cloud computing processing system.