Online Change Detection for Energy-Efficient Mobile Crowdsensing

Mobile crowdsensing is power hungry since it requires continuously and simultaneously sensing, processing and uploading fused data from various sensor types including motion sensors and environment sensors. Realizing that being able to pinpoint change points of contexts enables energy-efficient mobile crowdsensing, we modify histogram-based techniques to efficiently detect changes, which has less computational complexity and performs better than the conventional techniques. To evaluate our proposed technique, we conducted experiments on real audio databases comprising 200 sound tracks. We also compare our change detection with multivariate normal distribution and one-class support vector machine. The results show that our proposed technique is more practical for mobile crowdsensing. For example, we show that it is possible to save 80% resource compared to standard continuous sensing while remaining detection sensitivity above 95%. This work enables energy-efficient mobile crowdsensing applications by adapting to contexts.