Ning Liu
Multimodal human–machine collaboration, machine learning data monitoring, mechanical and electrical systems, intelligent algorithm,university physical education (PE) courses, course optimisation
With the expansion of university enrollment, the management of physical education (PE) courses has become a challenge due to complex constraints like venue availability, equipment, and scheduling conflicts. This study integrates machine learning with multimodal human–machine collaboration in electromechanical systems to enable intelligent teaching control. We construct an intelligent scheduling model that leverages machine learning for data mining, pattern recognition, and optimisation. This model analyses key constraints – including equipment requirements tied to electromechanical systems – and learns from historical data to correlate these with scheduling objectives. A multimodal human– computer interface allows managers to input dynamic requirements and teachers to provide real-time feedback, enabling the system to draft and intelligently present scheduling plans. The model dynamically refines these strategies based on real-time interaction, ultimately generating an optimal schedule that balances teaching efficiency, resource utilisation, and collaboration experience. Results show that this intelligent control method, combining machine learning and human–machine collaboration, significantly improves the efficiency and flexibility of PE resource allocation.
Important Links:
Go Back
