Assessment and Prediction of University English Teaching Effect Using Progressive Recurrent Generative Adversarial Network

• Published in: Journal of Electrical Systems Vol. 20; no. 3s; pp. 2335 - 2346
• Main Author: Sun, Zhiyong
• Format: Journal Article
• Language: English
• Published: Paris Engineering and Scientific Research Groups 04.04.2024
• Subjects: Algorithms; Big Data; Correlation coefficients; Data mining; Error analysis; Generative adversarial networks; Machine learning; Optimization; Parameters; Preprocessing
• ISSN: 1112-5209
• DOI: 10.52783/jes.3057

An intelligent evaluation technique of English teaching ability based on enhanced machine learning algorithm is proposed to fully explore the quality of English teaching, fully exploit the effect of intelligent evaluation of English teaching ability. It can guarantee rational allocation of English teaching resources, evaluate big data of constraint parameters of English teaching ability evaluation, attain frequent item sets of English teaching quality depend on big data mining technology. In this paper, Assessment and Prediction of University English Teaching Effect Using Progressive Recurrent Generative Adversarial Network (APETE-PRGAN-GOA) is proposed. Initially the input data is collected from fig share, it is given to preprocessing. The preprocessing, remove useless words using Learnable Edge Collaborative Filtering (LECE). Then the pre-processed output is fed to Prediction of English Teaching Effect. Here, Progressive Recurrent Generative Adversarial Network (PRGAN), is used to Predict English teaching ability. In general, PRGAN classifier does not express any optimization adaption approaches for determining optimum parameters to assure the assessment. Here Gazelle Optimization Algorithm utilized to optimize PRGAN classifier, for English Teaching Effect. The proposed technique executed in Python, performance of proposed technique is analysed with evaluation metrics likes,evaluation accuracy, correlation coefficient, mean squared error, evaluation time, occurrence (time), recall, Fl-score, R°C are analyzed. The proposed APETE-PRGAN-GOA method attains 30.58%, 28.73% and 35.62%, higher evaluation accuracy, 20.48%, 24.73%, 29.32% higher R°C and 30.98%, 26.66% and 21.32% lower mean squared error analysed with existing models such as intelligent assessment method of English teaching ability depend on enhanced machine learning algorithm (ISMETE-CNN), application of machine learning with loT methods in evaluation of English teaching effect in colleges (CNN-ETE - IOT),English teaching evaluation technique depend on association rule algorithm with machine learning (ETE-ARA-SCN) respectively.