【摘要】：血壓是衡量人體健康狀況的重要指標(biāo),特別是連續(xù)血壓,它能夠間接反應(yīng)出心臟和血管的運(yùn)行狀況,是臨床上進(jìn)行疾病診斷、治療效果觀察以及疾病預(yù)防判斷的重要依據(jù)。但現(xiàn)在市面上的連續(xù)血壓測(cè)量設(shè)備,主要為可穿戴式電子血壓計(jì)都有著精確度差的缺點(diǎn),不能準(zhǔn)確的判斷人體是否出現(xiàn)危險(xiǎn)病態(tài),所以對(duì)血壓連續(xù)準(zhǔn)確的測(cè)量以及異常狀況的有效判斷在預(yù)防心血管并發(fā)癥以及對(duì)長(zhǎng)期高血壓患者的降壓用藥起到良好的監(jiān)督作用和重要意義。因此,針對(duì)上述問(wèn)題,本文對(duì)于血壓連續(xù)測(cè)量提出了一種新型方法-基于脈象分類的血壓自適應(yīng)連續(xù)測(cè)量。該方法采用新型傳感器一RF射頻雷達(dá)實(shí)現(xiàn)對(duì)人體橈動(dòng)脈脈搏波的雙路信號(hào)獲取,然后引入分層定勢(shì)聯(lián)想機(jī)制模型實(shí)現(xiàn)脈象的引導(dǎo)式自動(dòng)分類,最后通過(guò)分級(jí)自適應(yīng)血壓預(yù)測(cè)模型實(shí)現(xiàn)血壓的實(shí)時(shí)測(cè)量。論文的主要研究?jī)?nèi)容包括:(1)深入了解RF-射頻雷達(dá)的工作原理以及其優(yōu)勢(shì),設(shè)計(jì)一套人體橈動(dòng)脈脈搏波采集系統(tǒng),并利用Labview搭建出一套數(shù)據(jù)實(shí)時(shí)顯示與數(shù)據(jù)保存系統(tǒng)。通過(guò)與脈搏波采集系統(tǒng)金標(biāo)準(zhǔn)進(jìn)行對(duì)比驗(yàn)證了該系統(tǒng)的有效性。(2)脈象的準(zhǔn)確分類是后期血壓預(yù)測(cè)的基礎(chǔ),只有實(shí)現(xiàn)準(zhǔn)確的分類才能保證血壓預(yù)測(cè)的準(zhǔn)確性�；谌祟惗▌�(shì)思維機(jī)制,我們提出了基于分層定勢(shì)聯(lián)想機(jī)制的脈象分類模型。首先進(jìn)行友邦因子分析實(shí)現(xiàn)脈象粗分類并確定引導(dǎo)方向,然后利用定勢(shì)聯(lián)想神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)對(duì)脈象的有效分類。神經(jīng)元交互聯(lián)想網(wǎng)絡(luò)融合了引導(dǎo)式變異以及脈象演變規(guī)則具有較強(qiáng)的定勢(shì)聯(lián)想能力,可以有效地實(shí)現(xiàn)被測(cè)脈象與典型脈象的自聯(lián)想。(3)在血壓的預(yù)測(cè)階段,我們引入了分級(jí)自適應(yīng)血壓預(yù)測(cè)模型。首先,通過(guò)脈象建立其與血壓線性模型的內(nèi)部聯(lián)系,根據(jù)被測(cè)人的脈象以及相關(guān)信息實(shí)現(xiàn)一級(jí)血壓模型的動(dòng)態(tài)調(diào)整。然后,利用訓(xùn)練好的帶參數(shù)庫(kù)的PSO-BP神經(jīng)網(wǎng)絡(luò)實(shí)現(xiàn)二級(jí)血壓最終結(jié)果的調(diào)整。實(shí)驗(yàn)結(jié)果表明,基于分層定勢(shì)聯(lián)想機(jī)制的脈象分類模型可以對(duì)人體常見脈象實(shí)現(xiàn)較高的分類準(zhǔn)確度,其準(zhǔn)確率達(dá)到92.86%,相比其他方法具有更好的分類效果。同時(shí),血壓自適應(yīng)預(yù)測(cè)模型的預(yù)測(cè)準(zhǔn)確度總體達(dá)到了 94.65%,能夠?qū)Ξ惓Ｑ獕簲?shù)據(jù)做到準(zhǔn)確的判斷,并且對(duì)個(gè)人血壓的連續(xù)追蹤趨勢(shì)實(shí)現(xiàn)較好的跟隨性。
[Abstract]:Blood pressure is an important index to measure human health, especially continuous blood pressure. It can indirectly reflect the operation of heart and blood vessels. It is an important basis for clinical diagnosis, observation of therapeutic effect and judgment of disease prevention. However, the existing continuous blood pressure measurement devices on the market, mainly wearable electronic sphygmomanometers, have the disadvantage of poor accuracy and cannot accurately judge whether the human body is in danger or not. Therefore, continuous and accurate measurement of blood pressure and effective judgment of abnormal condition play a good role in the prevention of cardiovascular complications and antihypertensive medication in long-term hypertensive patients. Therefore, to solve the above problems, this paper proposes a new method for continuous blood pressure measurement, which is adaptive continuous blood pressure measurement based on pulse classification. In this method, a new type of sensor, RF radio frequency radar, is used to obtain the dual signals of human radial pulse wave, and then the hierarchical setting association mechanism model is introduced to realize the guided automatic classification of pulse images. Finally, a hierarchical adaptive blood pressure prediction model is used to realize the real-time blood pressure measurement. The main contents of this paper are as follows: (1) deeply understand the working principle and advantages of RF- RF radar, design a pulse wave acquisition system of human radial artery, and set up a real-time data display and data storage system using Labview. The validity of the system is verified by comparing it with the gold standard of pulse wave acquisition system. (2) the accurate classification of pulse image is the basis of blood pressure prediction in the later stage, and the accuracy of blood pressure prediction can only be guaranteed by accurate classification. Based on the human fixed thinking mechanism, we propose a pulse classification model based on hierarchical stereotype association mechanism. Firstly, the coarse classification of pulse images is realized by friendly factor analysis and the guiding direction is determined. Then, the effective classification of pulse images is realized by using the fixed associative neural network. The neural interactive association network combines the guided mutation and pulse evolution rules, and has a strong ability of setting association, which can effectively realize the autoassociation between the measured pulse and the typical pulse. (3) in the stage of blood pressure prediction, We introduce a hierarchical adaptive blood pressure prediction model. Firstly, the internal relation between pulse and blood pressure linear model is established, and the first order blood pressure model is dynamically adjusted according to the pulse and related information. Then, a trained PSO-BP neural network with parameter library is used to adjust the final results of secondary blood pressure. The experimental results show that the classification model based on hierarchical fixed pattern association mechanism can achieve higher classification accuracy for common human pulse images, and the accuracy is 92.86, which is better than other methods. At the same time, the prediction accuracy of the adaptive blood pressure prediction model is 94.65, which can accurately judge the abnormal blood pressure data, and achieve a better follow-up to the continuous tracking trend of individual blood pressure.
【學(xué)位授予單位】：北京交通大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R443.5

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 郭友達(dá);雷恒波;徐雅潔;邢曉曼;康明才;孫明山;;基于動(dòng)脈張力法和STM32L的24h動(dòng)態(tài)血壓計(jì)設(shè)計(jì)[J];單片機(jī)與嵌入式系統(tǒng)應(yīng)用;2016年09期

2 張洋;李毅彬;陳曉萌;鄧寧;;基于多種傳感器的無(wú)創(chuàng)連續(xù)血壓測(cè)量研究[J];電子技術(shù)應(yīng)用;2016年05期

3 梅艷;倪淑明;李治國(guó);;原發(fā)性高血壓患者心血管危險(xiǎn)因素對(duì)動(dòng)脈彈性的影響[J];中國(guó)現(xiàn)代醫(yī)學(xué)雜志;2016年02期

4 洋洋;陳小惠;王保強(qiáng);姜吉榮;;脈搏信號(hào)中有效信號(hào)識(shí)別與特征提取方法研究[J];電子測(cè)量與儀器學(xué)報(bào);2016年01期

5 虞秋葉;;社區(qū)老年高血壓患者用藥管理的護(hù)理干預(yù)方法[J];中國(guó)醫(yī)藥科學(xué);2013年18期

6 任海靜;李亞芹;任海妹;;社區(qū)老年高血壓患者用藥管理的護(hù)理干預(yù)研究[J];中國(guó)全科醫(yī)學(xué);2012年25期

7 白智峰;;老年高血壓患者脈壓和動(dòng)脈彈性的臨床研究[J];臨床醫(yī)學(xué)工程;2012年02期

8 呂海姣;嚴(yán)壯志;陸維嘉;;一種基于脈搏波的無(wú)創(chuàng)連續(xù)血壓測(cè)量方法[J];中國(guó)醫(yī)療器械雜志;2011年03期

9 王志剛;賴麗娟;熊冬生;吳效明;;基于AR模型和支持向量機(jī)的急性低血壓預(yù)測(cè)[J];中國(guó)生物醫(yī)學(xué)工程學(xué)報(bào);2011年02期

10 高樹枚;宋義林;田中志信;山越憲一;;基于容積補(bǔ)償法的手腕式血壓連續(xù)檢測(cè)系統(tǒng)[J];中國(guó)醫(yī)療器械雜志;2009年05期

相關(guān)博士學(xué)位論文 前3條

1 劉磊;基于多普勒超聲信號(hào)的脈象分析與分類研究[D];哈爾濱工業(yè)大學(xué);2013年

2 宋丹;基于記憶—評(píng)價(jià)—引導(dǎo)機(jī)制的免疫優(yōu)化算法研究[D];中南大學(xué);2013年

3 張冬雨;面向脈診的脈搏信號(hào)與血流信號(hào)分類研究[D];哈爾濱工業(yè)大學(xué);2010年

相關(guān)碩士學(xué)位論文 前8條

1 董驍;可穿戴式多生理參數(shù)監(jiān)護(hù)系統(tǒng)的研究[D];北京工業(yè)大學(xué);2015年

2 劉鑫;基于PTT的無(wú)創(chuàng)連續(xù)血壓測(cè)量方法研究[D];云南大學(xué);2015年

3 何龍;基于獨(dú)立成分分析的脈搏波血壓算法研究[D];華中科技大學(xué);2015年

4 甘亞晨;遠(yuǎn)程生理參數(shù)系統(tǒng)的血壓測(cè)量方法研究[D];重慶理工大學(xué);2015年

5 黃飛;基于貝葉斯網(wǎng)絡(luò)和本體的高血壓患者心血管風(fēng)險(xiǎn)水平分類系統(tǒng)研究[D];太原理工大學(xué);2014年

6 黃軻;基于視覺(jué)感知的弱對(duì)比度車輛目標(biāo)識(shí)別[D];北京交通大學(xué);2014年

7 拜軍;基于生物雷達(dá)的脈搏波傳導(dǎo)時(shí)間提取技術(shù)的初步研究[D];第四軍醫(yī)大學(xué);2013年

8 王繼寸;基于脈搏波的無(wú)創(chuàng)連續(xù)血壓測(cè)量方法研究[D];天津大學(xué);2009年

，

本文編號(hào)：2276713