Abstract:
Digital recommendation systems are crucial. They’re used in Spotify and Netflix. Physical exercise recommendation systems receive less research. Sedentary lifestyles cause many diseases and healthcare costs. This paper introduces a recommendation system that recommends daily exercise to users based on their history, profiles, and similar users. Deep recurrent neural networks with user-profile and temporal attention mechanisms power the recommendation system. Exercise recommendation systems do not allow click feedback from participants, unlike streaming recommendation systems. We propose real-time, expert-in-the-loop active learning. When uncertainty is low, the active learner asks an expert for advice. This paper derives the marginal distance probability distribution function and uses it to determine when to ask experts for feedback. The real-time active learner improved recommendation system accuracy on mHealth and MovieLens datasets.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
