基于PCA-SVM的在线病理学专业教育质量评价分析  

Quality evaluation of online pathology education based on PCA-SVM

作　　者：李毓 李玉梅 Li Yu;Li Yumei(Inner Mongolia Hulunbuir Vocational and Technical College,Inner Mongolia Hulunbuir 021000;Inner Mongolia Yakeshi City Tulihe Town Central Hospital,Inner Mongolia Yakeshi 022167)

机构地区：[1]内蒙古呼伦贝尔职业技术学院,内蒙古呼伦贝尔021000 [2]内蒙古牙克石市图里河镇中心卫生院,内蒙古牙克石022167

出　　处：《现代科学仪器》2021年第6期269-273,共5页Modern Scientific Instruments

摘　　要：新冠病毒疫情使得在线教育受到了广泛的关注,提升在线教育质量是确保在线教育健康发展的关键。本文提出了基于PCA-SVM的在线病理学课程教育质量评价模型。首先建立了学习中心、交流互动、教学服务、学习准备、学习监督五个指标的评价体系,并采用主成分分析方法最终确定前四个主成分作为SVM的输入。然后采用PSO算法对SVM的参数组合进行优化,得到优化后的SVM分类器。最后采用优化后的SVM分类器对在线病理学课程教育质量进行评价,同时和多元回归分析、BP神经网络、支持向量机模型的评价结果进行对比。结果表明,PCA-SVM在线病理学课程教育质量评价模型精度高,学习效率高。本论文的研究对在线教育质量评价具有一定的参考。The COVID-19 epidemic has caused widespread concern in online education.Improving the quality of online education is the key to ensuring the healthy development of online education.This paper proposes a PCA-SVM based online pathology education quality evaluation model.Firstly,the evaluation system of learning center,communication and interaction,teaching service,learning preparation and learning supervision is established,and the first four principal components are determined as the input of SVM by principal component analysis.Then,PSO algorithm is used to optimize the combination of SVM parameters,and the optimized SVM classifier is obtained.Finally,the optimized SVM classifier is used to evaluate the quality of online pathology education,and the evaluation results are compared with those of multiple regression analysis,BP neural network and support vector machine model.The results show that PCA-SVM online pathology education quality evaluation model has high accuracy and learning efficiency.The research of this paper has a certain reference value for online education quality evaluation.

关 键 词：主成分分析 支持向量机 在线教育质量评价 

分 类 号：G642[文化科学—高等教育学]