FDFA: a fog computing assisted distributed analytics and detecting system for family activities

Researches have shown that taking parting in family activities could establish good relationships with family members. Fine-grained family activities detection is proven effective for increasing self-awareness and motivating people to modify their life styles for improved well being. Mobile health provides the possibility to solve this problem. However, with the increase of such applications, the requirements for computation, communication, and storage capability are becoming higher and higher. Fog computing, a new computing paradigm, utilizes a collaborative multitude of end-user clients or near-user edge devices to conduct a substantial amount of computing, communication, storage, and so on. In this paper, we propose FDFA, the first fog computing assisted distributed analytics and detecting system for family activities using smartphones and smart watches. Specifically, FDFA firstly uses the built-in sensors to obtain sensing data, such as the striding frequency and heart rate of the users, the sound of environment, and so forth. Then, a fog computing assisted resolution framework is proposed to efficiently detect family activities in an unobtrusive manner based on sensed data. Finally, considering the characteristics of different people, FDFA sets a personal plan for family members in doing some exercise and making continuous progress in the process of communicating. We have fully implemented FDFA on the Android platform and the extensive experimental results demonstrate that FDFA is easy to use, accurate, and appropriate for family activities with the accuracy of 79.1% and the user satisfaction degree of 82.4%. Moreover, the system can achieve more than 90% bandwidth efficiency and offer low-latency real time response with fog computing.