發(fā)布時間：2018-09-05 12:57

【摘要】：當(dāng)今社會,由于工作壓力大、生活作息不規(guī)律等因素導(dǎo)致心血管疾病患者數(shù)量居高不下。如果能夠?qū)π难芟嚓P(guān)參數(shù)加以研究,并分析得到它們之間的關(guān)系,就可以實(shí)現(xiàn)對心血管疾病的監(jiān)控,起到預(yù)防且降低發(fā)病率的作用。血壓是人體的一項(xiàng)重要生理參數(shù),可以反應(yīng)人體的心血管功能狀況。而脈搏波信號包含很多人體生理病理信息,通過脈搏波特征參數(shù)測血壓簡單、成本低、精確度高、能夠連續(xù)測量等優(yōu)勢,有廣闊的發(fā)展前景。本文基于血壓測量的理論基礎(chǔ),建立了兩種血壓連續(xù)測量模型。一種是按照傳統(tǒng)做法通過回歸分析構(gòu)建血壓模型;另一種以深度學(xué)習(xí)TensorFlow為框架,借助BP神經(jīng)網(wǎng)絡(luò)訓(xùn)練血壓和特征參數(shù)的關(guān)系,構(gòu)建神經(jīng)網(wǎng)絡(luò)的血壓模型。實(shí)驗(yàn)結(jié)果證明,通過兩種模型計算的血壓誤差都在3mmHg標(biāo)準(zhǔn)值之內(nèi),而第二種模型誤差在2mmHg之內(nèi)。符合國際標(biāo)準(zhǔn)值。本文的主要工作如下:首先,采用光電心率脈搏計(指尖式)完成了脈搏波信號的采集,用小波變換法和五點(diǎn)三次法完成信號的濾波;在特征點(diǎn)的提取上,提出一種混合算法用于識別特征點(diǎn),即閾值差分法、小波變換法和微分法相結(jié)合的方法,結(jié)果表明,此算法能夠準(zhǔn)確得提取出特征點(diǎn)。其次,建立了基于線性回歸的血壓測量模型,即通過提取脈搏波的時域特征參數(shù),分析血壓與特征參數(shù)的相關(guān)性,利用逐步回歸分析的方法得到血壓模型,通過估算血壓值,與標(biāo)準(zhǔn)血壓相比,誤差在3mm Hg以內(nèi)。最后,提出一種以深度學(xué)習(xí)TensorFlow為框架,建立血壓的BP神經(jīng)網(wǎng)絡(luò)模型,即以脈搏波特征參數(shù)作為BP神經(jīng)網(wǎng)絡(luò)的輸入量,通過訓(xùn)練數(shù)據(jù)得到血壓模型。通過TensorFlow中dropout對所構(gòu)建的神經(jīng)網(wǎng)絡(luò)瘦身,去除一定量的特征參數(shù),能夠消除過擬合現(xiàn)象,減小誤差,從而建立最優(yōu)模型。為了清楚表達(dá)本文所構(gòu)建的血壓模型,運(yùn)用可視化工具TensorBoard來呈現(xiàn)最終所構(gòu)建的血壓神經(jīng)網(wǎng)絡(luò)模型。通過估算血壓,與標(biāo)準(zhǔn)血壓相比,誤差在2mm Hg以內(nèi),比傳統(tǒng)做法更加精確。
[Abstract]:In today's society, the number of patients with cardiovascular disease is high due to the heavy work pressure and irregular living and rest. If the cardiovascular parameters can be studied and the relationship between them can be analyzed, the monitoring of cardiovascular disease can be realized, and the incidence of cardiovascular disease can be prevented and reduced. Blood pressure is an important physiological parameter, which can reflect the cardiovascular function of human body. Pulse wave signal contains a lot of physiological and pathological information of human body. It is simple to measure blood pressure by pulse wave characteristic parameters, low cost, high accuracy, and can be continuously measured, so it has a broad development prospect. Based on the theory of blood pressure measurement, two continuous blood pressure measurement models are established in this paper. One is to construct blood pressure model by regression analysis according to the traditional method; the other is to build BP model of neural network with the help of BP neural network to train the relationship between blood pressure and characteristic parameters in the framework of in-depth learning TensorFlow. The experimental results show that the blood pressure error calculated by the two models is within the 3mmHg standard value, while the second model error is within the 2mmHg. Conforms to the international standard value. The main work of this paper is as follows: firstly, the pulse wave signal is collected by using the photoelectric heart rate meter (fingertip type), the signal filtering is completed by wavelet transform and 5.3 times, and the feature points are extracted. A hybrid algorithm is proposed to identify feature points, that is, threshold difference method, wavelet transform method and differential method. The results show that the algorithm can extract feature points accurately. Secondly, a blood pressure measurement model based on linear regression is established, that is, by extracting the time domain characteristic parameters of pulse wave and analyzing the correlation between blood pressure and characteristic parameters, the blood pressure model is obtained by stepwise regression analysis, and the blood pressure value is estimated. Compared with the standard blood pressure, the error is within 3mm Hg. At last, a BP neural network model of blood pressure is established based on the framework of deep learning TensorFlow, that is, the characteristic parameters of pulse wave are used as input of BP neural network, and the blood pressure model is obtained by training data. Through dropout in TensorFlow, the neural network is reduced and a certain number of characteristic parameters are removed, which can eliminate the over-fitting phenomenon and reduce the error, thus the optimal model can be established. In order to express the blood pressure model clearly, the final BP neural network model is presented by using the visualization tool TensorBoard. By estimating blood pressure, compared with standard blood pressure, the error is within 2mm Hg, which is more accurate than traditional method.
【學(xué)位授予單位】：曲阜師范大學(xué)
【學(xué)位級別】：碩士
【學(xué)位授予年份】：2017
【分類號】：R443.5;TP181

【參考文獻(xiàn)】

相關(guān)期刊論文 前10條

1 魏安海;尹軍;萇飛霸;李姝穎;周德強(qiáng);顏樂先;;無創(chuàng)連續(xù)血壓測量技術(shù)的研究進(jìn)展[J];中國醫(yī)療設(shè)備;2015年11期

2 劉彥偉;朱健銘;梁永波;陳真誠;;經(jīng)驗(yàn)?zāi)B(tài)分解和小波變換的連續(xù)血壓測量[J];計算機(jī)仿真;2015年11期

3 鄭英;陸清茹;左梅;王迷迷;黃卉;;基于ZigBee技術(shù)的病房病人心率監(jiān)測系統(tǒng)設(shè)計[J];電子制作;2015年17期

4 張宇博;舒紅平;岳希;;指端脈搏曲線特征參數(shù)提取方法研究[J];軟件導(dǎo)刊;2015年04期

5 劉沛;龐宇;吳寶明;王普領(lǐng);馬勛;;脈搏波形態(tài)特征與血壓相關(guān)性的研究[J];生命科學(xué)儀器;2015年01期

6 孫薇;唐寧;江貴平;;脈搏波信號特征點(diǎn)識別與預(yù)處理方法研究[J];生物醫(yī)學(xué)工程學(xué)雜志;2015年01期

7 王賽;陸小左;;淺談中醫(yī)脈診認(rèn)識方式的歷史沿革[J];河南中醫(yī);2015年01期

8 楊建;;脈搏波信號采集與分析方法的研究[J];電腦與信息技術(shù);2014年03期

9 李章俊;王成;朱浩;金凡;馬俊領(lǐng);;基于光電容積脈搏波描記法的無創(chuàng)連續(xù)血壓測量[J];中國生物醫(yī)學(xué)工程學(xué)報;2012年04期

10 于瀟;林君;李肅義;;無創(chuàng)血壓測量技術(shù)的發(fā)展概況[J];廣東醫(yī)學(xué);2012年15期

相關(guān)碩士學(xué)位論文 前10條

1 付南;無袖帶連續(xù)血壓關(guān)聯(lián)因素分析及其非線性建模[D];南昌大學(xué);2016年

2 張笑東;無創(chuàng)血壓連續(xù)檢測技術(shù)研究[D];中國科學(xué)院研究生院(沈陽計算技術(shù)研究所);2016年

3 董鋒;基于脈搏波特征的連續(xù)血壓測量方法研究[D];云南大學(xué);2015年

4 周興忠;多信息同步采集系統(tǒng)構(gòu)建與血壓測量方法研究[D];蘭州理工大學(xué);2014年

5 沈蓉;血壓模擬平臺的構(gòu)建與連續(xù)血壓測量方法的研究[D];蘭州理工大學(xué);2014年

6 顏國棟;基于脈搏波的無創(chuàng)血壓測量方法研究[D];天津理工大學(xué);2013年

7 唐弘玲;基于信號處理的Android手機(jī)心率監(jiān)測軟件設(shè)計與實(shí)現(xiàn)[D];東華大學(xué);2013年

8 劉效林;基于脈搏波的無創(chuàng)連續(xù)血壓檢測的研究[D];北京交通大學(xué);2012年

9 鄒冬;點(diǎn)云模型的尖銳特征提取與分片分析[D];南京師范大學(xué);2012年

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

，

本文編號：2224343