多项式SVM算法在可穿戴设备监测学习过程的应用  

Application of Polynomial SVM Algorithm in Wearable Device Monitoring Learning Process

作　　者：刘峥[1] 申红[1] 徐小勇[1] Liu Zheng;Shen Hong;Xu Xiaoyong(Xi'an Railway Vvoeational and Technieal Istitute,xi'an,Shaanxi 710014,China)

机构地区：[1]西安铁路职业技术学院,陕西西安

出　　处：《西安轨道交通职业教育研究》2021年第3期31-35,共5页Xi'an Rail Transit Vocational Education Research

基　　金：陕西省职业技术教育学会课题项目(No.SZJYB19-312)。

摘　　要：课堂活动中学生对教师课程设计元素的学习有效性评价多依赖于标准化的问卷来完成,然而问卷会对学生造成额外的压力造成评估结果失真。为了解决这个问题,使用腕戴式可穿戴设备,该设备可在学生的学习过程中对生理参数进行连续且无干扰的监测。通过对比随机森林算法、线性支持向量机(线型SVM)、径向SVM和多项式SVM算法,计算了与三个问卷调查因子(满意度、有用性和成绩)有关的均方根误差。结果表明,多项式SVM优于其他算法,其中有用性、成绩,满意度的最小错误率分别是13.8%、11.0%、11.8%。从可穿戴式设备获得的生理数据可以代表学生的学习过程。为机器学习算法与人体生理数据研究领域提供了新思路。In classroom activities,students'ev aluation of the learning effectiveness of teachers'curriculum design el-ements mostly depends on standardized questionnaires,which will cause extra pressure on students and distort the evaluation results.In order to solve this problem,this study uses wrist wearable device,which can monitor physio-logical parameters continuously and without interference during the learning process of students.By comparing the random forest algorithm,linear support vector machine(linear SVM),mdial SVM and polynomial SVM,the root mean squae errors related to the three questionnaire factors(satisfaction,usefulness and performance)are calcu-lated.The results show that polynomial SVM is superior to other algrithms,in which the minimum error rates of usefulness,achievement and satisfaction are 13.8%,11.0%and 11.8%,respectively.The physiological data obtained from wearable devices can represent the learning process of students.It povides a new idea for the m-search of machine learning algorithm and human phy siological data.

关 键 词：可穿戴设备 学习过程 机器学习 随机森林 支持向量机 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程] TP212.9[自动化与计算机技术—控制科学与工程]