School of Physical Education, Changzhou University, Changzhou Jiangsu 213164, China.
J Environ Public Health. 2022 Sep 24;2022:7684320. doi: 10.1155/2022/7684320. eCollection 2022.
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.
随着经济的快速发展，人们对公共健康的追求不断提高。身体活动是实现公共健康的重要方式。过度的身体活动强度和不舒服的身体活动形式会影响人们的身心健康。合理的身体活动强度和合理的身体活动形式将有益于公共健康。人们需要根据身体功能参数和心理健康参数选择相应的运动模式。然而，人们很难理解身体活动模式与公共健康相关参数之间的关系，这限制了人们建立合理的运动模式。本研究使用大数据技术设计了一种智能运动导向的公共卫生数据分析方案。它主要使用 MLCNN 方法和 LSTM 方法来提取身体功能参数特征、心理健康参数特征和运动参数特征。研究结果表明，MLCNN 方法和 LSTM 可以准确地提取和预测与运动和公共健康相关的参数特征。最大的相对平均误差仅为 2.52%，这是身体性能参数特征的预测值。最小的预测误差也是 2.27%，这部分相对误差来自于对运动参数的预测。
