黄金正弦算法优化神经网络的体育教学质量评价  

Evaluation of Physical Education Teaching Quality Based on Back Propagation Neural Network Optimized By Golden Sine Algorithm

作　　者：唐礼科 徐莹 Tang Like;Xu Ying(Sichuan Institute of Technology,Deyang,Sichuan 618500,China)

机构地区：[1]四川工业科技学院,四川德阳618500

出　　处：《现代科学仪器》2021年第5期260-264,共5页Modern Scientific Instruments

基　　金：四川青年科技支持项目(19SC094)。

摘　　要：为提高高校体育教学质量评价的精度,针对反向传播神经网络(Back Propagation Neural Network,BPNN)模型性能受其参数选择影响,提出一种基于黄金正弦算法(golden sine algorithm,GoldenSA)优化BPNN(GoldSA-BPNN)的高等院校体育学科教学质量评价模型。首先,从教学内容、教学方法、教学态度和教学效果等4个维度构建出一套基于层次分析法的高校体育教学质量多指标评价体系;其次,将12个高校体育教学质量评价二级指标的得分数据作为BPNN的输入向量,高校体育教学质量水平(优、良、一般和较差)作为BPNN的输出向量,建立一种基于GoldenSA-BPN模型的高校体育课程教学质量评价模型。与PSO-BPNN和BPNN对比可知,GoldenSA-BPNN进行高校体育课程教学质量评价具有更高的分类准确率、特异性以及灵敏度。In order to improve the accuracy of physical education quality evaluation in colleges and universities,the performance of(BPNN)model is affected by its parameter selection.A golden sine algorithm based on BPNN model is proposed.GoldenSA optimized BPNN(GoldSA-BPNN)model for quality evaluation of college physical education teaching.Firstly,a set of multi-index evaluation system of college physical education teaching quality based on AHP is constructed from four dimensions,including teaching content,teaching method,teaching attitude and teaching effect.Secondly,the scores of 12 secondary indicators of college physical education teaching quality evaluation were taken as the input vector of BPNN,and the teaching quality level of college physical education(excellent,good,average and poor)was taken as the output vector of BPNN,and the GoldenSA-BPNN model of college physical education teaching quality evaluation was established.Compared with PSO-BPNN and BPNN,GoldenSA-BPNN has higher classification accuracy,specificity and sensitivity in the evaluation of college physical education teaching quality.

关 键 词：黄金正弦算法 反向传播神经网络 体育教学 质量评价 评价指标 

分 类 号：TM41[电气工程—电器] TP391.1[自动化与计算机技术—计算机应用技术]