A hybrid model combining environmental analysis and machine learning for predicting AI education quality

Abstract Due to the evolution of the management system of educational institutions, the need to use artificial intelligence-based tools in the university is felt more and more. Therefore, platforms based on artificial intelligence (AI) are getting more developed day by day. Therefore, in this study,...

Full description

Saved in:
Bibliographic Details
Main Author: Xinyu Ren
Format: Article
Language:English
Published: Nature Portfolio 2025-04-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-92556-x
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849737370814906368
author Xinyu Ren
author_facet Xinyu Ren
author_sort Xinyu Ren
collection DOAJ
description Abstract Due to the evolution of the management system of educational institutions, the need to use artificial intelligence-based tools in the university is felt more and more. Therefore, platforms based on artificial intelligence (AI) are getting more developed day by day. Therefore, in this study, firstly, by dividing the macro environment into three different parts, including external, intermediate, and internal, a set of corrective measures in the university teaching and learning management in the background of AI education is proposed, and also the effects of their application in the management of teaching and learning in universities were discussed. Also, in order to evaluate the quality of AI training programs in higher education, a new approach based on the multilayer perceptron (MLP) algorithm was presented in which the capuchin search algorithm (CapSA) was used to adjust the weight vector of the neural network. According to the results, Proposed and ANN (SCG) models had the best and worst performance respectively in reproducing observations. The results showed that corrective measures in all environments can help the development of AI education in universities. The results of conducting a case study and examining various evaluation indicators showed that the proposed approach in this study has a good accuracy in predicting the target variable (quality of education). The values of CCC, SROCC, PLCC and R2 indices related to the proposed model are equal to 0.9611, 0.9805, 0.9731, and 0.9803, respectively, which are all higher than the corresponding values in other models.
format Article
id doaj-art-7aa10eb6c9cf45d7ae1aebbd17785f63
institution DOAJ
issn 2045-2322
language English
publishDate 2025-04-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-7aa10eb6c9cf45d7ae1aebbd17785f632025-08-20T03:06:57ZengNature PortfolioScientific Reports2045-23222025-04-0115111710.1038/s41598-025-92556-xA hybrid model combining environmental analysis and machine learning for predicting AI education qualityXinyu Ren0Business With Financial Management, Northumbria UniversityAbstract Due to the evolution of the management system of educational institutions, the need to use artificial intelligence-based tools in the university is felt more and more. Therefore, platforms based on artificial intelligence (AI) are getting more developed day by day. Therefore, in this study, firstly, by dividing the macro environment into three different parts, including external, intermediate, and internal, a set of corrective measures in the university teaching and learning management in the background of AI education is proposed, and also the effects of their application in the management of teaching and learning in universities were discussed. Also, in order to evaluate the quality of AI training programs in higher education, a new approach based on the multilayer perceptron (MLP) algorithm was presented in which the capuchin search algorithm (CapSA) was used to adjust the weight vector of the neural network. According to the results, Proposed and ANN (SCG) models had the best and worst performance respectively in reproducing observations. The results showed that corrective measures in all environments can help the development of AI education in universities. The results of conducting a case study and examining various evaluation indicators showed that the proposed approach in this study has a good accuracy in predicting the target variable (quality of education). The values of CCC, SROCC, PLCC and R2 indices related to the proposed model are equal to 0.9611, 0.9805, 0.9731, and 0.9803, respectively, which are all higher than the corresponding values in other models.https://doi.org/10.1038/s41598-025-92556-xTeachingUniversityMacroArtificial intelligenceEducationMultilayer perceptron
spellingShingle Xinyu Ren
A hybrid model combining environmental analysis and machine learning for predicting AI education quality
Scientific Reports
Teaching
University
Macro
Artificial intelligence
Education
Multilayer perceptron
title A hybrid model combining environmental analysis and machine learning for predicting AI education quality
title_full A hybrid model combining environmental analysis and machine learning for predicting AI education quality
title_fullStr A hybrid model combining environmental analysis and machine learning for predicting AI education quality
title_full_unstemmed A hybrid model combining environmental analysis and machine learning for predicting AI education quality
title_short A hybrid model combining environmental analysis and machine learning for predicting AI education quality
title_sort hybrid model combining environmental analysis and machine learning for predicting ai education quality
topic Teaching
University
Macro
Artificial intelligence
Education
Multilayer perceptron
url https://doi.org/10.1038/s41598-025-92556-x
work_keys_str_mv AT xinyuren ahybridmodelcombiningenvironmentalanalysisandmachinelearningforpredictingaieducationquality
AT xinyuren hybridmodelcombiningenvironmentalanalysisandmachinelearningforpredictingaieducationquality