Edge-Based Anomalous Sensor Placement Detection for Participatory Sensing of Urban Heat Islands

Abstract

Crowdsensing temperature data have enabled a paradigm shift in the ways we collect data and analyze the heat exposure effects on individuals and communities. The use of low-cost sensors has helped in gathering granular spatiotemporal temperature data and capturing ever-changing ambient environmental conditions. However, this practice poses challenges such as sensor failures and data integrity. One of the main concerns of the participatory sensing approach is the misplacement of temperature sensors in a way that they are not exposed to the natural outdoor environment. We propose a novel approach to detect anomalous sensor placement in a semi-real-time manner at the edge of the Internet. We introduce a sliding window technique in conjunction with supervised learning classifiers to detect anomalously-placed sensors effectively. This approach is based on the empirical observation that temperature readings show more frequent fluctuations while exposed to the outdoor environment. We also conduct a series of comparative performance analysis of different classifiers including SVM, Logistic Regression, and Random Forest.