pp. 2757-2777
S&M4085 Research Paper of Special Issue https://doi.org/10.18494/SAM5173 Published: July 4, 2025 Metaheuristic-based Deep Learning Application for Higher Education Teaching Quality Assessment [PDF] Xin Guo, Ying Chen, Zilong Yin, Ruoying Wang, Dazhi Li, and Shih-Pang Tseng (Received June 3, 2024; Accepted May 26, 2025) Keywords: teaching quality assessment, analytic hierarchy process, estimation distribution of algorithm
To ensure teaching quality, higher education institutions worldwide use a teaching quality assessment (TQA) system to collect students’ feedback regarding courses. How to use a more intelligent method to effectively analyze the feedback to determine practical teaching effectiveness is still the main research challenge at this stage. One of the important issues is applying sensor technology to TQA. In this study, we developed and implemented a TQA system based on analytic hierarchy process–estimation of the distribution algorithm–backpropagation (AHP–EDA–BP) to illustrate the deeper meaning of students’ feedback. AHP–EDA–BP ensured the accuracy of the quantitative analysis. The AHP aggregated the opinions of experts to adjust the weights of the assessment index. The EDA–BP neural network was used to evaluate the grade of teaching quality. The experimental results showed the essential effectiveness of the proposed method. In addition, the TQA system has been applied to the TQA process at Sanda University, Shanghai, China.
Corresponding author: Dazhi Li and Shih-Pang Tseng![]() ![]() This work is licensed under a Creative Commons Attribution 4.0 International License. Cite this article Xin Guo, Ying Chen, Zilong Yin, Ruoying Wang, Dazhi Li, and Shih-Pang Tseng, Metaheuristic-based Deep Learning Application for Higher Education Teaching Quality Assessment, Sens. Mater., Vol. 37, No. 7, 2025, p. 2757-2777. |