Article: Integrating deep learning and wearable technology for real-time, scalable and objective physical education assessment Journal: International Journal of Information and Communication Technology (IJICT) 2025 Vol.26 No.10 pp.42 - 60 Abstract: In traditional PE, we often assess students with very subjective assessments and miss all the nuances and intricacies of motor skills that are complex. This study introduces a deep learning-based framework using CNNs and LSTMs with wearable tech that increases evaluation accuracy and feedback - a multimodal dataset comprising the data from several devices like accelerometers and heart rate monitors. Teacher-based assessments (72% agreement) were surpassed by 89% accuracy of the proposed SkillNet model. It reduced inter-rater variability by 35% and the evaluation time by 40%. Student engagement rose from 60% to 85%, with improved motivation. This system provides accurate, scalable objective assessment, real-time feedback, and enriched learning in PE. Inderscience Publishers - linking academia, business and industry through research

Title: Integrating deep learning and wearable technology for real-time, scalable and objective physical education assessment

Authors: Wang Chen

Addresses: Physical Education, Chongqing Vocational and Technical University of Mechatronics, Chongqing, 402760, China

Abstract: In traditional PE, we often assess students with very subjective assessments and miss all the nuances and intricacies of motor skills that are complex. This study introduces a deep learning-based framework using CNNs and LSTMs with wearable tech that increases evaluation accuracy and feedback - a multimodal dataset comprising the data from several devices like accelerometers and heart rate monitors. Teacher-based assessments (72% agreement) were surpassed by 89% accuracy of the proposed SkillNet model. It reduced inter-rater variability by 35% and the evaluation time by 40%. Student engagement rose from 60% to 85%, with improved motivation. This system provides accurate, scalable objective assessment, real-time feedback, and enriched learning in PE.

Keywords: deep learning in physical education; automated PE assessment; wearable technology in education; real-time feedback mechanisms; objective motor skill evaluation.

DOI: 10.1504/IJICT.2025.146096

International Journal of Information and Communication Technology, 2025 Vol.26 No.10, pp.42 - 60

Received: 19 Feb 2025
Accepted: 09 Mar 2025
Published online: 06 May 2025 *

Title: Integrating deep learning and wearable technology for real-time, scalable and objective physical education assessment

Keep up-to-date