Design and application of university laboratory safety evaluation system based on fuzzy analytic hierarchy process and back propagation neural network Online publication date: Thu, 22-Dec-2022
by Chengli Guan; Yue Yang; Changhui Chen; Jianhao Feng
International Journal of Applied Decision Sciences (IJADS), Vol. 16, No. 1, 2023
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.
Online publication date: Thu, 22-Dec-2022
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Applied Decision Sciences (IJADS):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email email@example.com