【摘要】：隨著老齡化的加劇,以及空巢家庭的增多,老人的意外跌倒也隨之增多。而及時(shí)對(duì)跌倒的老人進(jìn)行救助,可有效地降低因跌倒引起的傷殘率與死亡率。因此,老人跌倒檢測(cè)系統(tǒng)以及跌倒檢測(cè)算法成為研究熱點(diǎn),通過(guò)現(xiàn)代科學(xué)技術(shù)來(lái)檢測(cè)跌倒行為,盡可能地降低老年人因跌倒帶來(lái)的傷害。穿戴式的跌倒檢測(cè)系統(tǒng)具有不限制于室內(nèi)、不受周邊環(huán)境干擾、方便攜帶等特點(diǎn),能較好地滿足老人跌倒檢測(cè)系統(tǒng)的需求。本文針對(duì)基于穿戴式系統(tǒng)中的跌倒檢測(cè)算法進(jìn)行相關(guān)研究,主要工作如下:1.在基于加速度與姿態(tài)角閾值的跌倒檢測(cè)算法的基礎(chǔ)上,針對(duì)誤判率較高的問(wèn)題,本文在生物醫(yī)學(xué)領(lǐng)域步態(tài)分析的啟發(fā)下,將足底壓力與加速度、姿態(tài)角信息相結(jié)合,提出了基于多行為特征融合的跌倒檢測(cè)算法。該算法首先對(duì)人體加速度與姿態(tài)角進(jìn)行判定,若均超過(guò)閾值,再對(duì)足底壓力進(jìn)行閾值判定,構(gòu)建足底壓力矩陣并進(jìn)行計(jì)算。若兩個(gè)矩陣都為零,則判定為跌倒,其余情況均判定為不跌倒。算法中加速度、姿態(tài)角、足底壓力的閾值通過(guò)粒子群算法進(jìn)行確定。通過(guò)仿真實(shí)驗(yàn)證明,該算法對(duì)彎腰、下蹲行為的漏報(bào)率較低,對(duì)跌倒的識(shí)別正確率較高。2.針對(duì)基于閾值的跌倒檢測(cè)算法對(duì)閾值的依賴性較大且個(gè)體行為差異對(duì)閾值選取影響較大的問(wèn)題,提出了基于支持向量機(jī)的跌倒檢測(cè)算法。該算法首先對(duì)原始獲取的行為數(shù)據(jù)進(jìn)行特征處理,轉(zhuǎn)化為18維的行為特征向量。利用k折交叉驗(yàn)證選取算法中的最優(yōu)參數(shù),并用此最優(yōu)參數(shù)對(duì)行為特征進(jìn)行訓(xùn)練。用訓(xùn)練得到的模型對(duì)行為測(cè)試集進(jìn)行類別檢測(cè),以獲得該行為特征標(biāo)簽來(lái)識(shí)別跌倒行為。通過(guò)仿真實(shí)驗(yàn),有效檢測(cè)出跌倒行為,驗(yàn)證了該算法的可靠性。3.針對(duì)上述的檢測(cè)效果更優(yōu)的SFDA跌倒檢測(cè)算法,設(shè)計(jì)了基于云的跌倒檢測(cè)系統(tǒng)。該系統(tǒng)主要由穿戴設(shè)備與云服務(wù)器部分組成,穿戴設(shè)備的足部模塊、胸部模塊以及GPRS傳輸模塊將采集的人體行為數(shù)據(jù)上傳至云端,云端以LNMP(Linux+Nginx+MySQL+PHP)為基礎(chǔ)運(yùn)行環(huán)境,對(duì)上傳的行為數(shù)據(jù)進(jìn)行JSON解析、SFDA算法的檢測(cè)與訓(xùn)練、數(shù)據(jù)存儲(chǔ)等一系列后臺(tái)處理以及在前端進(jìn)行顯示。測(cè)試實(shí)驗(yàn)結(jié)果表明,算法在基于云的跌倒檢測(cè)系統(tǒng)中的可行性較好,且該系統(tǒng)對(duì)跌倒行為的檢測(cè)有很高的準(zhǔn)確率。
[Abstract]:With the aggravation of aging and the increasing number of empty nest families, the accidental fall of the elderly also increases. Timely rescue can effectively reduce the disability rate and mortality caused by falls. Therefore, the fall detection system and the fall detection algorithm have become the focus of research, through modern science and technology to detect fall behavior, as far as possible to reduce the elderly fall caused by harm. The wearable fall detection system can meet the needs of the elderly fall detection system because it is not limited to the indoor, free from the interference of the surrounding environment and easy to carry. In this paper, the fall detection algorithm based on wearable system is studied. The main work is as follows: 1. On the basis of the fall detection algorithm based on acceleration and attitude angle threshold, aiming at the problem of high error rate, this paper combines plantar pressure with acceleration and attitude angle information under the inspiration of gait analysis in biomedical field. A fall detection algorithm based on multi-behavior feature fusion is proposed. The algorithm firstly determines the acceleration and attitude angle of human body. If all of them exceed the threshold value, then the foot pressure threshold is determined, and the plantar pressure matrix is constructed and calculated. If both matrices are zero, it is judged to be a fall, and the rest of the cases are determined not to fall. The threshold of acceleration, attitude angle and plantar pressure is determined by particle swarm optimization (PSO). The simulation results show that the algorithm has a lower false report rate for bending and squat behavior, and a higher accuracy rate for recognition of falls. In order to solve the problem that threshold-based fall detection algorithm is dependent on threshold and individual behavior difference has great influence on threshold selection, a fall detection algorithm based on support vector machine (SVM) is proposed. The algorithm firstly processes the original behavior data and transforms them into 18 dimensional behavior feature vectors. The optimal parameters in the algorithm are verified by k-fold crossover, and the optimal parameters are used to train the behavior characteristics. The training model is used to detect the behavior test set to obtain the behavior feature tag to identify the fall behavior. Through the simulation experiment, the fall behavior is effectively detected, and the reliability of the algorithm is verified. 3. 3. A cloud based fall detection system is designed for the above SFDA fall detection algorithm. The system is mainly composed of wearable device and cloud server. The foot module, chest module and GPRS transmission module upload the collected human behavior data to the cloud. The cloud is based on LNMP (Linux Nginx MySQL PHP). The uploaded behavior data is detected and trained by JSON parsing algorithm, and a series of background processing, such as data storage, and display on the front end, are carried out. The experimental results show that the algorithm is feasible in the cloud-based fall detection system, and the system has a high accuracy in the detection of fall behavior.
【學(xué)位授予單位】：浙江理工大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：TP274;TP18

【參考文獻(xiàn)】

相關(guān)期刊論文 前7條

1 耳玉亮;段蕾蕾;葉鵬鵬;高欣;汪媛;鄧曉;紀(jì)翠蓉;金葉;;2014年全國(guó)傷害監(jiān)測(cè)系統(tǒng)老年人非故意傷害病例特征分析[J];中國(guó)健康教育;2016年04期

2 蔣沛良;張碩;李杰;徐青山;;基于腳底壓力信息采集的壓力傳感器探討[J];中國(guó)高新技術(shù)企業(yè);2015年15期

3 王之瓊;曲璐渲;隋雨彤;鮑楠;康雁;;基于極限學(xué)習(xí)機(jī)的跌倒檢測(cè)分類識(shí)別研究[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2014年04期

4 朱勇;張研;宋佳;邱天爽;;基于傾角的跌倒檢測(cè)方法與系統(tǒng)研究[J];生物醫(yī)學(xué)工程學(xué)雜志;2013年01期

5 李立;陳玉娟;翟鳳鳴;崔巴特爾;;老年人不同運(yùn)動(dòng)形式下足底壓力分布特征研究進(jìn)展[J];中國(guó)老年學(xué)雜志;2011年16期

6 秦曉華;段儕杰;袁克虹;申博;;一種老年人移動(dòng)健康監(jiān)護(hù)系統(tǒng)的研究[J];中國(guó)醫(yī)學(xué)物理學(xué)雜志;2011年01期

7 王明鑫;俞光榮;陳雁西;楊云峰;黃四平;胡孫君;;正常中國(guó)成年人足底壓力分析[J];中國(guó)矯形外科雜志;2008年09期

相關(guān)博士學(xué)位論文 前1條

1 石欣;基于壓力感知步態(tài)的運(yùn)動(dòng)人體行為識(shí)別研究[D];重慶大學(xué);2010年

相關(guān)碩士學(xué)位論文 前4條

1 何俊;城鄉(xiāng)老年人跌倒發(fā)生現(xiàn)狀及危險(xiǎn)因素分析[D];寧夏醫(yī)科大學(xué);2015年

2 趙海丹;基于LNMP的智慧農(nóng)業(yè)服務(wù)器平臺(tái)的研究[D];浙江大學(xué);2015年

3 李路;基于多傳感器的人體運(yùn)動(dòng)模式識(shí)別研究[D];山東大學(xué);2013年

4 梁丁;基于MEMS慣性傳感器的跌倒檢測(cè)與預(yù)警研究[D];大連理工大學(xué);2012年

，

本文編號(hào)：2242714