Efficient Bayesian Communication Approach for Smart Agriculture Applications

Abstract

To meet the food demand of the future, farmers are turning to the Internet of Things (IoT) for advanced analytics. In this case, data generated by sensor nodes and collected by farmers on the field provide a wealth of information about soil, seeds, crops, plant diseases, etc. Therefore, the use of high tech farming techniques and IoT technology offer insights on how to optimize and increase yield. However, one major challenge that should be addressed is the huge amount of data generated by the sensing devices, which make the control of sending useless data very important. To face this challenge, we present a Bayesian Inference Approach (BIA), which allows avoiding the transmission of high spatio-temporal correlated data. In this paper, BIA is based on the PEACH project, which aims to predict frost events in peach orchards by means of dense monitoring using low-power wireless mesh networking technology. Belief Propagation algorithm has been chosen for performing an approximate inference on our model in order to reconstruct the missing sensing data. According to different scenarios, BIA is evaluated based on the data collected from real sensors deployed on the peach orchard. The results show that our proposed approach reduces drastically the number of transmitted data and the energy consumption, while maintaining an acceptable level of data prediction accuracy.