Evaluation algorithm of student's movement normality based on movement trajectory analysis in higher vocational physical education teaching

Abstract

This study proposes a new technique for assessing student movement normality in higher vocational physical education teaching by creating an evaluation algorithm based on movement trajectory analysis. Using advanced motion capture and machine learning approaches, notably Support Vector Machine (SVM) classification, the project seeks to provide objective and data-driven methodologies for assessing and optimizing movement proficiency. The methodology entails collecting data with high-precision motion capture equipment, preprocessing trajectory data to extract kinematic, temporal, and spatial information, and developing algorithms for classification using SVM. The algorithm's performance is evaluated using a variety of criteria, including accuracy, precision, recall, and the F1 score. The results show that the algorithm is successful at reliably discriminating between normal and pathological movement patterns, with high accuracy (92.5%), balanced precision (94.2%), and recall (91.8%). Furthermore, the study is consistent with broader trends in educational technology and individualized learning, seeking to build a culture of physical literacy and well-being in higher vocational physical education teaching. In general, the findings of this study have important implications for improving instructional techniques and fostering optimal movement skill acquisition in students.