Answers are grounded in this paper and cite their sources.
An eCoach system may allow people to manage a healthy lifestyle with health state monitoring (e.g., physical activity) and personalized recommendation generation. Daily step count is an important feature to provide a direct and indirect reflection on individual activity levels. Therefore, a personalized, predictive model may be beneficial to forecast future “steps” to motivate participants based on the temporal “step” pattern. Here, we have conceptualized the idea with a Bidirectional Long-ShortTerm-Memory (LSTM) model for weekly activity forecasting and a rule-base for personalized recommendation generation with Ontology reasoning and querying in activity eCoaching. First, we have used the publicly available “PMData” dataset of 16 adults (M: 13; F: 3) to train and test the models and explore the possibility of accurate univariate time-series forecasting of “step counts”. Second, we have created an Ontology and a rule-base to generate personalized activity recommendations to motivate participants to accomplish their activity goals (e.g., complete “X” steps daily and stay active for the entire week).
No takes yet. Share an insight, caveat, or question.
Chatterjee et al. (2022) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: