Many IoT systems generate a huge and varied amount of data that need to be processed and responded to in a very short time. One of the major challenges is the high energy consumption due to the transmission of data to the cloud. Edge computing allows the workload to be offloaded from the cloud at a location closer to the source of data that need to be processed while saving time, improving privacy, and reducing network traffic. In this paper, we propose an energy efficient approach for IoT data collection and analysis. First of all, we apply a fast error-bounded lossy compressor on the collected data prior to transmission, that is considered to be the greatest consumer of energy in an IoT device. In a second phase, we rebuild the transmitted data on an edge node and process it using supervised deep learning techniques. To validate our approach, we consider the context of driving behavior monitoring in intelligent vehicle systems where vital signs data are collected from the driver using a Wireless Body Sensor Network (WBSN) and wearable devices and sent to an edge node for stress level detection. The experimentation results show that the amount of transmitted data has been reduced by up to 103 times without affecting the quality of medical data and driver stress level prediction accuracy.

In-network data aggregation is considered an effective technique for conserving energy communication in wireless sensor networks. It consists in eliminating the inherent redundancy in raw data collected from the sensor nodes. Prior works on data aggregation protocols have focused on the measurement data redundancy. In this paper, our goal in addition of reducing measures redundancy is to identify near duplicate nodes that generate similar data sets. We consider a tree based bi-level periodic data aggregation approach implemented on the source node and on the aggregator levels. We investigate the problem of finding all pairs of nodes generating similar data sets such that similarity between each pair of sets is above a threshold t. We propose a new frequency filtering approach and several optimizations using sets similarity functions to solve this problem. To evaluate the performance of the proposed filtering method, experiments on real sensor data have been conducted. The obtained results show that our approach offers significant data reduction by eliminating in network redundancy and outperforms existing filtering techniques.