Ma Xinyi, Shao Mingrui, Feng Xiaowei, Du Weiping, Yi Qing, Chi Puyan, Li Hai
School of Physical Education, Shanghai Normal University, Shanghai 201418, China.
School of Physical Education, Hainan Normal University, Haikou 571158, China.
Sensors (Basel). 2025 Sep 2;25(17):5423. doi: 10.3390/s25175423.
Traditional assessment methods in physical education often emphasize final grades, lacking real-time monitoring and feedback during the learning process. To address this limitation and enhance the formative evaluation of student performance, this study proposes a real-time assessment system for Baduanjin instruction in physical education, utilizing a commercially available inertial measurement unit-based motion capture device. The system was developed in four stages. First, a dataset was created by recruiting 20 university students and one expert physical education instructor. Participants were asked to perform standardized Baduanjin routines while wearing wireless inertial measurement unit sensors on key body joints. The collected kinematic data, sampled at 100 Hz, included joint angles and movement trajectories. Second, preprocessing and feature extraction techniques were applied to the raw data to construct a labeled dataset for training. Third, supervised machine learning algorithms were used to build models for motion type recognition and motion accuracy evaluation. Model performance was assessed using cross-validation and compared with expert evaluations. Finally, a user-facing formative assessment system was developed and tested in a controlled classroom environment. The system demonstrated a high motion recognition accuracy of 99.77%, and the correlation coefficient between system-assessed motion accuracy and expert ratings exceeded 0.80, indicating strong validity. The results demonstrate that the formative assessment system built on inertial measurement unit is appropriate for the Baduanjin physical education.
体育教育中的传统评估方法通常强调最终成绩，在学习过程中缺乏实时监测和反馈。为了解决这一局限性并加强对学生表现的形成性评价，本研究提出了一种体育八段锦教学实时评估系统，该系统利用市售的基于惯性测量单元的动作捕捉设备。该系统分四个阶段开发。首先，通过招募20名大学生和一名专业体育教师创建了一个数据集。参与者在关键身体关节上佩戴无线惯性测量单元传感器时，被要求进行标准化的八段锦套路动作。以100赫兹采样收集的运动学数据包括关节角度和运动轨迹。其次，对原始数据应用预处理和特征提取技术，以构建用于训练的带标签数据集。第三，使用监督机器学习算法建立动作类型识别和动作准确性评估模型。使用交叉验证评估模型性能，并与专家评估进行比较。最后，开发了一个面向用户的形成性评估系统，并在可控的课堂环境中进行了测试。该系统展示了99.77%的高动作识别准确率，系统评估的动作准确性与专家评分之间的相关系数超过0.80，表明有效性很强。结果表明，基于惯性测量单元构建的形成性评估系统适用于八段锦体育教学。
