Wen Jia, Zeng Pinhong
Faculty of International Education, Yibin University, Yibin, China.
Faculty of Economics and Business Administration, Yibin University, Yibin, China.
PLoS One. 2025 Feb 10;20(2):e0313608. doi: 10.1371/journal.pone.0313608. eCollection 2025.
This study aims to enhance educational quality and academic standards by proposing a model based on critical research ability indicators to objectively evaluate the sustainable scientific research capabilities of university teachers.
Using T-S fuzzy neural network technology, we developed an evaluation model to measure the sustainability of university teachers' research capabilities. We collected data from 126 university teachers, using 90 samples for training and 36 for testing, to ascertain the model's applicability and accuracy.
The T-S fuzzy neural network showcased exceptional learning efficiency and achieved a 98.15% accuracy rate in assessing the sustainable scientific research capabilities of university teachers, outperforming both Naive Bayes and BP neural networks in effectiveness.
The research successfully constructs a T-S fuzzy neural network-based evaluation model for assessing the sustainable scientific research capabilities of university teachers. With high accuracy and broad applicability, this model is an effective tool for objectively evaluating university teachers' research capabilities, clearly achieving the study's objective.
本研究旨在通过提出一个基于批判性研究能力指标的模型，客观评估高校教师的可持续科研能力，以提高教育质量和学术水平。
利用T-S模糊神经网络技术，开发了一个评估模型来衡量高校教师科研能力的可持续性。我们收集了126名高校教师的数据，其中90个样本用于训练，36个用于测试，以确定该模型的适用性和准确性。
T-S模糊神经网络展现出卓越的学习效率，在评估高校教师的可持续科研能力方面达到了98.15%的准确率，在有效性上优于朴素贝叶斯和BP神经网络。
本研究成功构建了一个基于T-S模糊神经网络的评估模型，用于评估高校教师的可持续科研能力。该模型具有高准确性和广泛适用性，是客观评估高校教师科研能力的有效工具，明确实现了研究目标。
