摘要
人工智能的发展,为高校对教学质量进行科学与全面的评价提供了新路径。对深度神经网络(DNN)进行改进,提出一种新的深度循环神经网络(DRNN)算法,同时在DRNN上引入优化的麻雀搜索(ISSA)算法,最终建立基于改进ISSA算法的深度循环神经网络(ISSA-DRNN)的大学英语教学质量评价模型。该模型既可充分提取和保留数据中有价值的特征以提高模型的评价性能,又可对模型中的隐含层神经元数目自动寻优,最终实现大学英语教学质量的精准评价。最后通过与其他方法的比较,验证了以上所提教学质量评价模型的可行性、优越性与普适性。
The development of artificial intelligence has provided a new way for colleges and universities to conduct comprehensive scientific evaluation of the quality of teaching.This study improves the deep neural network(DNN)and proposes a new deep recurrent neural network(DRNN)algorithm.Furthermore,the optimized sparrow search algorithm(ISSA)is introduced into the DRNN.Finally,a model is established to evaluate the quality of college English teaching on the basis of the improved deep recurrent neural network with sparrow search algorithm(ISSA-DRNN).This model can not only fully extract and retain the valuable features in the data but also improve the performance of evaluation.In addition,it can automatically optimize the number of neurons in the hidden layer of the model and eventually achieve accurate evaluation of the quality of college English teaching.Finally,the feasibility,superiority and universality of the model are verified through the comparison with other methods.
作者
巩长芬
彭荣荣
GONG Changfen;PENG Rongrong(School of Education of Nanchang Institute of Science&Technology,Nanchang Jiangxi 330108,P.R.China)
出处
《重庆电力高等专科学校学报》
2023年第5期39-43,共5页
Journal of Chongqing Electric Power College
基金
2022年度江西省高校人文社科项目(JY22253)
2022年度南昌工学院人文社科项目(NGRW-22-08)。
关键词
英语教学
质量评价
深度循环神经网络
改进麻雀搜索算法
实验对比
English teaching
quality evaluation
deep recurrent neural network
improved sparrow search algorithm
experimental comparison
