Digital Twin-Assisted Learning Performance Prediction for Shopfloor Employees Using Deep Learning Model

This paper proposes a new model called the Adaptive Educational Competition Optimizer based Dense Resolution High-order Attention Forward Harmonic Network (AECO_DRHAFHNet) for the Learning shopfloor employee's performance. Initially, input data is gathered from physical space, and it is stored in a cloud server. After that, the twin manager retrieves the information for simulating virtual space. Subsequently, the virtual data is stored in the cloud. Using this data, the course sequence prediction is done with DRHAFHNet. The DRHAFHNet is trained using Adaptive Educational Competition Optimizer (AECO). Furthermore, the designed system has attained Normalized Mean Squared Error (MSE), Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) as 0.303,0.550, and 0.326.