Key result
MLCNN and LSTM methods predict sports and public health features with ~2% relative mean error.
Why the study?
It is difficult to understand the relationship between physical activity patterns and public health-related parameters, limiting the establishment of reasonable exercise patterns.
A big data analysis platform using MLCNN and LSTM methods can accurately predict physical and mental health parameters related to sports activity.
ML models may support sports health parameter research; leaves open clinical adoption without prospective validation.
People's pursuit of public health continues to improve with the rapid economic development. Physical activity is an important way to achieve public health. Excessive physical activity intensity and uncomfortable forms of physical activity can affect people's physical and mental health. Reasonable physical activity intensity and reasonable physical activity form will be beneficial to public health. People need to choose the corresponding sports mode according to physical function parameters and mental health parameters. However, it is difficult to understand the relationship between physical activity patterns and public health-related parameters, which limits people to establish reasonable exercise patterns. This research uses big data technology to design an intelligent sports-oriented public health data analysis scheme. It mainly uses MLCNN method and LSTM method to extract physical function parameter features, mental health parameter features, and sports parameter features. The research results show that the MLCNN method and LSTM can accurately extract and predict the parametric features related to sports and public health. The largest relative mean error is only 2.52%, which is the predicted value of the physical performance parameter characteristics. The smallest prediction error is also 2.27%, and this part of the relative error comes from the prediction of sports parameters.
No takes yet. Share an insight, caveat, or question.
Liu et al. (2022) studied Public health and physical activity. MLCNN and LSTM methods was evaluated on Prediction of parametric features related to sports and public health. The MLCNN and LSTM methods accurately extracted and predicted parametric features related to sports and public health, with relative mean errors ranging from 2.27% to 2.52%.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: