智慧家居中基于计算机数据感知的老人行为识别技术  

Elderly Behavior Recognition Technology Based on Computer Data Perception in Smart Home

作　　者：陈观鸿 梁炼[2] CHEN Guanhong;LIANG Lian(Zhongshan Overseas Chinese Secondary School,Zhongshan 528400,China;Sun Yat-sen Memorial Hospital,Sun Yat-sen University,Guangzhou 510120,China)

机构地区：[1]中山市华侨中学,广东中山528400 [2]中山大学孙逸仙纪念医院,广东广州510120

出　　处：《微型电脑应用》2023年第5期15-17,共3页Microcomputer Applications

基　　金：全国教育信息技术研究重点课题(184420038)。

摘　　要：为了对居家老人的日常行为进行研究和分析,及时发现老人日常行为中的异常情况,提出利用智能家居中的传感器传输的数据,通过支持向量机对老人日常行为进行建模和识别,同时利用高斯混合模型搭建日常行为异常的模型,并通过这2种模型对老人的日常行为进行检测数据的解读。研究结果表明:通过支持向量机模型能够很好地分析老人的日常行为,并且准确率高达90%;通过高斯模型进行实验分析,能够得到当马氏距离和标准差的比值在3倍以内的时候,日常行为中的异常行为表现得不明显,也就是说这时候老人的日常行为不存在危险性,是正常的。这项研究成果能够更好地掌握老人的日常行为活动,能在发生异常的第一时间得到反馈,这对当今社会的养老建设具有一定程度上的贡献。In order to discuss and analyze the daily behavior of the elderly at home and find out the abnormal situation in the daily behavior of the elderly in time,through the sensor data transmission in smart home,support vector machine(SVM)is used for daily behavior model construction and recognition.Meantime,the Gaussian mixture model is applied for constructing the abnormal daily behavior model.Experimental data of the elderly’s daily behavior are discussed through these two models.The results show that:the SVM model can well analyze the elderly’s daily behavior,and the accuracy can be as high as 90%;the experimental analysis of Gaussian model reveals when the ratio of Mahalanobis distance and standard deviation is less than three times,the abnormal behavior is not obvious,and in other words,there is no danger in the elderly’s daily behavior at this time.The research can help better grasping the elderly’s daily behavior,thereby getting feedback at the first time when there is abnormal,which has a certain contribution to the pension construction.

关 键 词：智慧家居 行为识别 高斯模型 支持向量机 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]