2021/01/30 by Luca Varotto, Angelo Cenedese, Varotto, Luca +1
Computer Science · Physics and Astronomy · #Advanced Optical Sensing Technologies #Distributed Sensor Networks and Detection Algorithms #FOS: Electrical engineering #Gaussian Processes and Bayesian Inference #Signal Processing (eess.SP) #Systems and Control (eess.SY) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.2102.03350
openalex publication_date 2021/01/30 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Research on wireless sensors represents a continuously evolving technological\ndomain thanks to their high flexibility and scalability, fast and economical\ndeployment, pervasiveness in industrial, civil and domestic contexts. However,\nthe maintenance costs and the sensors reliability are strongly affected by the\nbattery lifetime, which may limit their use. In this paper we consider a\nwireless smart camera, equipped with a low-energy radio receiver, and used to\nvisually detect a moving radio-emitting target. To preserve the camera lifetime\nwithout sacrificing the detection capabilities, we design a probabilistic\nenergy-aware controller to switch on/off the camera. The radio signal strength\nis used to predict the target detectability, via self-supervised Gaussian\nProcess Regression combined with Recursive Bayesian Estimation. The automatic\ntraining process minimizes the human intervention, while the controller\nguarantees high detection accuracy and low energy consumption, as numerical and\nexperimental results show.\n