A hierarchical learning framework for Chinese kids physical exercise prescription

摘要

In recent years, although large volumes of data of health-related physical fitness (HRPF) have been collected, the exercise prescription for Chinese kids is still formulated manually by experts. It is necessary to develop an effective and efficient mechanism to recommend an automatic physical exercise prescription. Toward this purpose, this paper presents an experimental study of the framework for physical exercise prescription with HRPF tests data. In this framework, the dictionary is dynamically learned with new features, physical fitness representation is further fed into a BPNN for classification, and the prescription is recommended using collaborative filtering. Extensive experimental results on HRPF tests data of Chinese kids have shown that the proposed framework provides a satisfying approach with respect to the physical exercise prescription.