Teaching Management System for Higher Vocational and Technical Education Using Wasserstein Generative Adversarial Network Optimized by Fire Hawk Optimization

The vocational education system is currently undergoing purposeful reform and innovation, recognizing the importance of vocational training in the entire educational framework. Assessing and improving teaching quality in vocational education is critical, and addressing this challenge necessitates. The utilize of AI technology, primarily deep learning, is particularly effective in addressing the diverse and sophisticated aspects of evaluating and improving teaching quality. In this research work, Teaching Management System for Higher Vocational and Technical Education Using Wasserstein Generative Adversarial Network Optimized by Fire Hawk Optimization (TMS-WGAN-FHO) is proposed. The input data are gathered from School database (Educational data),then, input data are pre-processed using Square Root Cubature Kalman Filter for cleaning data. Then, pre-processed data are given to Wasserstein Generative Adversarial Network (WGAN) for evaluating and improving the teaching quality for Higher Vocational and Technical Education. In general, WGAN does not express some adoption of optimization strategies for determining optimal parameters to evaluating, improving quality of teaching management system. Hence Fire Hawk Optimization Algorithm (FHOA) is proposed to optimize WGAN classifier which precisely evaluates the teaching quality Higher Vocational and Technical Education. The proposed TMS-WGAN-FHO method is implemented in MATLAB, and it assessed with several performance metrics likes accuracy, cross validation scores, recall, F1-score, ROC. The results show TMS-WGAN-FHO attains 25.8%, 28.5%, and 21.6% higher Accuracy, 15.1%, 17.2%, and 32.8%higher Precision, 27.5%, 24.6% and 22.3% higher Recall are analysed with existing methods such as, evaluation of the vocational education teaching reform's quality using deep learning (EVE-TRQ-DL), art higher vocational education curriculum design incorporating AI-aided virtual reality technology (AHVE-DIAI-VRT), integrating big data analysis with higher vocational education approaches to educate entrepreneurship and innovation (IBDA-HVE-EEV) methods respectively.