Physical Exercise Recommendation and Success Prediction Using Interconnected Recurrent Neural Networks
This work addresses physical inactivity, a major healthcare cost driver, by providing personalized exercise support through mobile technology, representing an incremental improvement in predictive modeling for health behavior.
The paper tackles the problem of promoting healthier lifestyles by developing an exercise recommendation system that predicts individual success rates, using interconnected recurrent neural networks to recommend workouts and forecast completion probabilities, achieving improved prediction accuracy over a prior computational cognitive model on a four-week mobile health dataset.
Unhealthy behaviors, e.g., physical inactivity and unhealthful food choice, are the primary healthcare cost drivers in developed countries. Pervasive computational, sensing, and communication technology provided by smartphones and smartwatches have made it possible to support individuals in their everyday lives to develop healthier lifestyles. In this paper, we propose an exercise recommendation system that also predicts individual success rates. The system, consisting of two inter-connected recurrent neural networks (RNNs), uses the history of workouts to recommend the next workout activity for each individual. The system then predicts the probability of successful completion of the predicted activity by the individual. The prediction accuracy of this interconnected-RNN model is assessed on previously published data from a four-week mobile health experiment and is shown to improve upon previous predictions from a computational cognitive model.