Mobile crowdsourcing based context-aware smart alarm sound for smart living

Alarm sounds are acknowledged to play an important role in daily life; however, sometimes improper alarm sounds may mess things up. In this paper, we construct a smart alarm sound recommendation system working with smartphones to deliver smart alarm sounds by considering not only specified information, such as sleep patterns, but also context information such as weather, and social information. Our system aims to provide a smart life through orchestrating sensing data collected by multiple sensors on smartphones and collaborating with cloud computing to recommend preferable alarm sounds. To demonstrate the effectiveness and efficiency of our system, we conduct experiments of using our system to recommend smart alarm sounds to wake people up in the morning. Experimental results show that our system can improve people emotional states by about 10.73%, compared to traditional alarm sound delivery methods.