Scholarlink

The ability to detect, define, and classify Change of Direction (COD) movements during running plays a crucial role in sports science, as it has been widely used to assess athlete performance. Automating the process of COD classification during live games or training can provide real-time feedback. In this study, we evaluated Machine Learning (ML) and Deep Learning (DL) models for the classification of COD using accelerometers and gyroscope sensor data, and speed data were calculated from the Global Positioning System (GPS) sensor data. We hypothesized that DL algorithms classify COD better than ML classification algorithms. Comparative analysis showed that the best-performing DL and ML models showed similar behavior. Similarly, the statistical analysis observed no significant difference. This emphasized the importance of accurate model selection.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Preliminary Investigation on Machine Learning and Deep Learning Models for Change of Direction Classification in Running

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Pranay Jaiswal,
  • Abhishek Kaushik,
  • Fiona Lawless,
  • Tiago Malaquias,
  • Fergal McCaffery

摘要

The ability to detect, define, and classify Change of Direction (COD) movements during running plays a crucial role in sports science, as it has been widely used to assess athlete performance. Automating the process of COD classification during live games or training can provide real-time feedback. In this study, we evaluated Machine Learning (ML) and Deep Learning (DL) models for the classification of COD using accelerometers and gyroscope sensor data, and speed data were calculated from the Global Positioning System (GPS) sensor data. We hypothesized that DL algorithms classify COD better than ML classification algorithms. Comparative analysis showed that the best-performing DL and ML models showed similar behavior. Similarly, the statistical analysis observed no significant difference. This emphasized the importance of accurate model selection.