WiSleep: Scalable Sleep Monitoring and Analytics Using Passive WiFi Sensing.

摘要: Sleep deprivation is a public health concern that significantly impacts one's well-being and performance. an intimate experience, state-of-the-art sleep monitoring solutions are highly-personalized to individual users. With motivation expand at large-scale contribute data understanding, we present WiSleep, analytics platform using smartphone network connections passively sensed from WiFi infrastructure. We propose unsupervised ensemble model of Bayesian change point detection predict wake-up times. Then, validate our approach ground truth user study in campus dormitories private home. Our results find WiSleep outperforming established methods for users with irregular patterns while yielding comparable accuracy regular sleepers average 79.5\% accuracy. This client-side based methods, albeit utilizing only coarse-grained information. Finally, show can process 20,000 on single commodity server, allowing it scale large populations low server requirements.