You can view the full text of this article for free using the link below.

Title: Design and application of university laboratory safety evaluation system based on fuzzy analytic hierarchy process and back propagation neural network

Authors: Chengli Guan; Yue Yang; Changhui Chen; Jianhao Feng

Addresses: Yangjiang Polytechnic, Yangjiang, 529566, China ' Yangjiang Polytechnic, Yangjiang, 529566, China ' Guangzhou Panyu Polytechnic, Guanzhou, 511483, China ' Yangjiang Polytechnic, Yangjiang, 529566, China

Abstract: In view of the present questions of university laboratory management and security, the scientific and reasonable index system of laboratory safety evaluation was constructed from five aspects, such as safety rules and regulations, environmental safety, emergency management, publicity and education, equipment and reagents, and personnel factors. Fuzzy analytic hierarchy process (FAHP) was used to determine the weight of criteria layer, index layer and laboratory safety level, respectively. Then, the laboratory safety evaluation model using back propagation (BP) neural network based on MATLAB was constructed. The quantitative index layer data is used as the network input. The existing evaluation results were trained first, and then the unknown data were tested. The correlation coefficient between the target value and network prediction value could reach 0.9725. Moreover, the evaluation results were consistent with the conclusion of FAHP, which shows that the model has good applicability. It provides a more scientific, intelligent and simple quantitative evaluation method for evaluation of university laboratory safety.

Keywords: university laboratory safety; BP neural network; fuzzy analytic hierarchy process; evaluation model; evaluation index.

DOI: 10.1504/IJADS.2023.127968

International Journal of Applied Decision Sciences, 2023 Vol.16 No.1, pp.114 - 128

Received: 16 Nov 2021
Accepted: 06 Dec 2021

Published online: 22 Dec 2022 *

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