Title: Hybrid teaching quality evaluation based on PSO-BP neural network

Authors: Ying Zhou; Lei Zhang

Addresses: School of Literature and Education, Bengbu University, Bengbu, 233030, China ' School of Mathematics and Physics, Bengbu University, Bengbu, 233000, China

Abstract: The existing methods for evaluating the quality of blended learning lack unified standards and evaluation systems, resulting in low comparability of evaluation results. Therefore, a hybrid teaching quality evaluation method based on PSO-BP neural network was studied. Firstly, the selection of quality evaluation indicators for blended learning should follow the principles of scientificity, comprehensiveness, and testability. Then, the analytic hierarchy process (AHP) was used to construct a mixed teaching quality evaluation index system. Finally, the obtained evaluation indicators will be used as inputs for the PSO-BP neural network, and through the learning and optimisation capabilities of the neural network, hybrid teaching quality evaluation will be achieved. The experimental results indicate that, the R² of the PSO-BP neural network model for evaluating the quality of blended learning is 0.985, indicating high fitting ability. The actual level is consistent with the evaluation level, with an evaluation error of less than 2%, indicating practicality.

Keywords: PSO-BP neural network; analytic hierarchy process; AHP; evaluation of blended teaching quality.

DOI: 10.1504/IJCEELL.2025.146018

International Journal of Continuing Engineering Education and Life-Long Learning, 2025 Vol.35 No.3/4, pp.312 - 330

Received: 03 Apr 2024
Accepted: 06 Nov 2024
Published online: 01 May 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article