Wearable technology allows users to monitor their activity and pursue a healthy lifestyle through the use of embedded sensors. Such wearables usually connect to a mobile application that allows them to set their profile and keep track of their goals. However, due to the relatively “high maintenance” of such applications, where a significant amount of user feedback is expected, users who are very busy, or not as self-motivated, stop using them after a while. It has been shown that accountability improves commitment to an exercise routine. In this work, we present the PRO-Fit framework, a personalized fitness assistant aiming at engaging users in fitness activities, incorporating a social element. The PRO-Fit architecture collects information from activity tracking devices and automatically classifies their activity type. Moreover, the framework incorporates a social recommender system. Using collaborative filtering on user profile and activity data, PRO-Fit generates personalized fitness schedules based on their availability and wellbeing goals. We also incorporate the social network community of the application’s users and identify different tie strengths based on the user’s connections and location. The output of the recommendation process is twofold, as both new activities, as well as fitness buddies, are being recommended to each user.
Saumil Dharia, Magdalini Eirinaki, Vijesh Jain, Jvalant Patel, Iraklis Varlamis, Jainikkumar Vora, and Rizen Yamauchi. "Social Recommendations for Personalized Fitness Assistance" Personal and Ubiquitous Computing (2018): 245-257. doi:10.1007/s00779-017-1039-8