基于離散特征的跌倒檢測(cè)智能方法及應(yīng)用
發(fā)布時(shí)間：2018-11-20 07:24
【摘要】：隨著人口老齡化現(xiàn)象加劇,對(duì)老年人跌倒的檢測(cè)與報(bào)警越來(lái)越重要。為提高跌倒檢測(cè)的準(zhǔn)確率,提出一種基于離散特征的跌倒檢測(cè)智能方法。通過(guò)對(duì)人體運(yùn)動(dòng)數(shù)據(jù)的分析,提出7類人體運(yùn)動(dòng)特征;并建立了以BP神經(jīng)網(wǎng)絡(luò)為基礎(chǔ)的跌倒檢測(cè)模型,將提取的離散特征作為模型的輸入,模型的輸出作為跌倒檢測(cè)結(jié)果;通過(guò)對(duì)模型的學(xué)習(xí)與訓(xùn)練后,實(shí)現(xiàn)跌倒檢測(cè)。方法驗(yàn)證和產(chǎn)品應(yīng)用結(jié)果表明:采用基于離散特征的跌倒檢測(cè)智能方法能夠有效地區(qū)分跌倒與非跌倒,提高了跌倒檢測(cè)正確率,降低了誤報(bào)率和漏報(bào)率。
[Abstract]:With the aging of the population, it is more and more important to detect and alarm the fall of the elderly. In order to improve the accuracy of fall detection, an intelligent fall detection method based on discrete features is proposed. Through the analysis of human motion data, seven kinds of human motion characteristics are proposed, and a fall detection model based on BP neural network is established. The extracted discrete features are taken as the input of the model, and the output of the model is regarded as the result of fall detection. After learning and training the model, the fall detection is realized. The results of method verification and product application show that the intelligent method based on discrete feature can effectively distinguish fall from non-fall, improve the correct rate of fall detection, and reduce the false alarm rate and false alarm rate.
【作者單位】： 后勤工程學(xué)院后勤信息與軍事物流工程系;重慶市軟匯科技有限公司;
【基金】：國(guó)家自然科學(xué)基金(61271449,61302175) 重慶市自然科學(xué)重點(diǎn)基金(CSTC2015jcyj BX0017)項(xiàng)目資助
【分類號(hào)】：TP183;TP274
本文編號(hào)：2344238
[Abstract]:With the aging of the population, it is more and more important to detect and alarm the fall of the elderly. In order to improve the accuracy of fall detection, an intelligent fall detection method based on discrete features is proposed. Through the analysis of human motion data, seven kinds of human motion characteristics are proposed, and a fall detection model based on BP neural network is established. The extracted discrete features are taken as the input of the model, and the output of the model is regarded as the result of fall detection. After learning and training the model, the fall detection is realized. The results of method verification and product application show that the intelligent method based on discrete feature can effectively distinguish fall from non-fall, improve the correct rate of fall detection, and reduce the false alarm rate and false alarm rate.
【作者單位】： 后勤工程學(xué)院后勤信息與軍事物流工程系;重慶市軟匯科技有限公司;
【基金】：國(guó)家自然科學(xué)基金(61271449,61302175) 重慶市自然科學(xué)重點(diǎn)基金(CSTC2015jcyj BX0017)項(xiàng)目資助
【分類號(hào)】：TP183;TP274
【相似文獻(xiàn)】
相關(guān)期刊論文 前5條
1 張龍斌;賀國(guó)光;盧宇;;一種在線實(shí)時(shí)快速判定混沌的智能方法[J];天津理工大學(xué)學(xué)報(bào);2007年01期
2 楊則正;用基于信息技術(shù)的智能方法解決復(fù)雜問(wèn)題[J];管理科學(xué)文摘;1995年10期
3 王光波;曹夢(mèng)龍;;基于智能方法的絲狀異纖分離關(guān)鍵技術(shù)研究[J];工業(yè)控制計(jì)算機(jī);2010年04期
4 池越;夏克文;陳國(guó)鷹;蘇昶;;一種基于QPSO和WLS-SVM的智能方法[J];河北工業(yè)大學(xué)學(xué)報(bào);2009年02期
5 ;[J];;年期
相關(guān)會(huì)議論文 前2條
1 張銳;趙陽(yáng);邵柏;趙一彪;馬丁;;統(tǒng)一集智能方法在人-機(jī)-環(huán)境系統(tǒng)工程研究中應(yīng)用[A];人-機(jī)-環(huán)境系統(tǒng)工程研究進(jìn)展（第七卷）[C];2005年
2 付林;賀安之;;一種實(shí)時(shí)檢測(cè)路面面形變的智能方法[A];江蘇、山東、河南、江西、黑龍江五省光學(xué)（激光）聯(lián)合學(xué)術(shù)'05年會(huì)論文集[C];2005年
，本文編號(hào)：2344238
本文鏈接：http://sikaile.net/kejilunwen/zidonghuakongzhilunwen/2344238.html
最近更新
教材專著
