【摘要】：可穿戴計(jì)算以一種“人機(jī)交互”的新型計(jì)算模式,實(shí)現(xiàn)了人類社會(huì)與信息環(huán)境、物理環(huán)境的連通,在軍事、公共衛(wèi)生、電子消費(fèi)、體育、教育等眾多領(lǐng)域都有著廣泛的應(yīng)用,現(xiàn)已成為學(xué)術(shù)界和工業(yè)界的研究熱點(diǎn)。人體行為識(shí)別技術(shù)是可穿戴計(jì)算中重要的研究分支。本文針對(duì)基于運(yùn)動(dòng)傳感器的人體行為識(shí)別算法開展創(chuàng)新性工作,對(duì)加速度傳感器的數(shù)據(jù)采集、數(shù)據(jù)預(yù)處理,機(jī)器學(xué)習(xí)分類模型以及行為識(shí)別算法展開研究,主要研究?jī)?nèi)容包括:(1)探索了利用智能手機(jī)內(nèi)置的運(yùn)動(dòng)傳感器采集人體行為活動(dòng)數(shù)據(jù),對(duì)獲得的三軸加速度傳感器數(shù)據(jù)進(jìn)行預(yù)處理,去除噪聲并對(duì)數(shù)據(jù)進(jìn)行片段分割;(2)針對(duì)人體行為活動(dòng)中典型的行走、上樓、下樓、坐、站立和跌倒這六種行為,分別進(jìn)行了時(shí)域和頻域特征提取,并對(duì)這六個(gè)行為的時(shí)域和頻域特征兩兩對(duì)比分析,得到了更深層次的特征區(qū)分細(xì)節(jié),建立了各人體行為活動(dòng)的特征數(shù)據(jù)集;(3)在傳統(tǒng)人體行為識(shí)別支持向量機(jī)模型的基礎(chǔ)上,將支持向量分類機(jī)與二次核函數(shù)理論相結(jié)合,通過理論分析構(gòu)造出了二次核支持向量分類機(jī)模型,進(jìn)而提出了基于二次核支持向量分類機(jī)模型的人體行為識(shí)別算法,與現(xiàn)有的基于隨機(jī)森林分類模型的人體行為識(shí)別算法相比,本文算法的識(shí)別精度更高。
[Abstract]:Wearable computing has been widely used in many fields, such as military affairs, public health, electronic consumption, sports, education and so on, because of its new computing mode of "human-computer interaction", which realizes the connection between human society and information environment, physical environment and physical environment. It has become a research hotspot in academia and industry. Human behavior recognition is an important branch of wearable computing. This paper focuses on the innovative work of human behavior recognition algorithm based on motion sensor, and researches on acceleration sensor data acquisition, data preprocessing, machine learning classification model and behavior recognition algorithm. The main research contents are as follows: (1) using the motion sensor built in the smart phone to collect human behavior data, preprocessing the obtained three-axis acceleration sensor data, removing noise and segmenting the data; (2) aiming at the typical walking, going upstairs, going downstairs, sitting, standing and falling, the feature extraction in time domain and frequency domain is carried out respectively, and the characteristics of time domain and frequency domain of these six behaviors are compared and analyzed. The deeper feature distinguishing details are obtained, and the feature data sets of human behavior are established. (3) based on the traditional support vector machine model of human behavior recognition, a quadratic kernel support vector classifier model is constructed by combining the support vector classification machine with the quadratic kernel function theory. Furthermore, a human behavior recognition algorithm based on quadratic kernel support vector classifier model is proposed. Compared with the existing human behavior recognition algorithm based on stochastic forest classification model, the recognition accuracy of this algorithm is higher.
【學(xué)位授予單位】：寧夏大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP391.41;TP212

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 吳婷;周宇;;基于BP神經(jīng)網(wǎng)絡(luò)的人體行為識(shí)別方法研究與實(shí)現(xiàn)[J];教育教學(xué)論壇;2016年51期

2 王賽迪;;基于人工神經(jīng)網(wǎng)絡(luò)的人體識(shí)別算法研究[J];電子世界;2016年17期

3 茍濤;;基于可穿戴式三軸加速度傳感器的人體行為識(shí)別[J];自動(dòng)化應(yīng)用;2015年12期

4 劉欣然;;老人跌倒監(jiān)測(cè)定位裝置的研究[J];無線電通信技術(shù);2016年01期

5 盧先領(lǐng);徐仙;;基于加速度與HGA-BP神經(jīng)網(wǎng)絡(luò)的人體行為識(shí)別[J];計(jì)算機(jī)工程;2015年09期

6 蘇z延，

本文編號(hào)：2367536