【摘要】：近年來,隨著我國老齡化的加速發(fā)展,高血壓的發(fā)病率日益升高。高血壓是多種疾病的誘發(fā)因素,做好對高血壓患者體征數(shù)據(jù)的采集和分析,對于預防高血壓及其并發(fā)癥有著重要的作用。如何采集患者實時的體征數(shù)據(jù),存儲這些數(shù)據(jù),并根據(jù)數(shù)據(jù)分析與預測患者的血壓趨勢等問題亟需應對和解決。云計算、物聯(lián)網和“互聯(lián)網+”的飛速發(fā)展,4G和無線網絡的快速覆蓋,Android和可穿戴智能設備的快速普及,都為解決上述問題提供了便利條件�；贏ndroid的血壓數(shù)據(jù)采集系統(tǒng)圍繞數(shù)據(jù)采集、分析與預警,從數(shù)據(jù)采集、數(shù)據(jù)存儲、數(shù)據(jù)分析三個層次來解決上述問題。該系統(tǒng)實現(xiàn)了數(shù)據(jù)采集內容及時準確,傳輸渠道通暢,分析預警快速有效,模塊擴展方便易用。論文的研究工作圍繞著數(shù)據(jù)采集、數(shù)據(jù)存儲和數(shù)據(jù)算法三方面展開。數(shù)據(jù)采集方面,對藍牙血壓計的協(xié)議進行了分析,基于Android平臺設計異構藍牙數(shù)據(jù)采集系統(tǒng),支持多種藍牙協(xié)議的解析,通過抽象上層的工作流程,使用策略模式設計了易于添加藍牙設備的協(xié)議解析方案。數(shù)據(jù)存儲方面,Android端通過網絡將數(shù)據(jù)上傳到云平臺,設計了使用MongoDB建立血壓存儲數(shù)據(jù)庫集群的方案,實現(xiàn)了服務器資源的橫向擴展。數(shù)據(jù)算法方面,根據(jù)高血壓數(shù)據(jù)的特點,將時間序列預測法應用到血壓數(shù)據(jù)的預測上,使用向量自回歸算法設計了預測方案和模型,預測結果較為準確。最后,完成了系統(tǒng)功能性界面的設計實現(xiàn),實現(xiàn)了歷史記錄和預警信息的可視化,并進行了整個系統(tǒng)的聯(lián)調測試。本論文將Android、藍牙和云平臺相結合,實現(xiàn)了血壓數(shù)據(jù)采集、存儲、分析的流程化操作。采集系統(tǒng)支持多種異構藍牙設備,存儲系統(tǒng)具有較高的擴展性,預警系統(tǒng)可以較好的分析患者的疾病風險。本系統(tǒng)的實現(xiàn),對于醫(yī)療大數(shù)據(jù)的采集和分析有一定借鑒意義。
[Abstract]:In recent years, with the accelerated development of aging in China, the incidence of hypertension is increasing. Hypertension is the inducing factor of many diseases. It is very important to collect and analyze the data of physical signs of hypertension patients for the prevention of hypertension and its complications. How to collect and store the data of patients' physical signs, and how to analyze and predict the trend of patients' blood pressure according to the data, and so on, should be dealt with and solved urgently. The rapid development of cloud computing, the Internet of things and the Internet of things, the rapid coverage of 4G and wireless networks, and the rapid spread of Android and wearable smart devices all provide a convenient solution to these problems. The blood pressure data acquisition system based on Android solves the above problems from three levels: data acquisition, analysis and early warning, data acquisition, data storage and data analysis. The system realizes timely and accurate data collection, smooth transmission channel, fast and effective analysis and early warning, and easy to use. This paper focuses on data acquisition, data storage and data algorithm. In the aspect of data acquisition, the protocol of bluetooth sphygmomanometer is analyzed. The heterogeneous Bluetooth data acquisition system is designed based on Android platform, which supports the analysis of various Bluetooth protocols. A protocol resolution scheme which is easy to add Bluetooth device is designed by using policy mode. In the aspect of data storage, the Android terminal uploads the data to the cloud platform through the network, designs the scheme of establishing the blood pressure storage database cluster with MongoDB, and realizes the lateral expansion of the server resources. In terms of data algorithm, according to the characteristics of hypertension data, the time series prediction method is applied to the prediction of blood pressure data. The prediction scheme and model are designed by using vector autoregressive algorithm, and the prediction results are more accurate. Finally, the design and implementation of the functional interface of the system is completed, and the visualization of historical records and warning information is realized. In this paper, Android, Bluetooth and cloud platform are combined to realize blood pressure data acquisition, storage and analysis. The acquisition system supports a variety of heterogeneous Bluetooth devices, and the storage system is highly scalable, and the early warning system can better analyze the disease risk of patients. The realization of this system has certain reference significance for the collection and analysis of medical big data.
【學位授予單位】：北京郵電大學
【學位級別】：碩士
【學位授予年份】：2016
【分類號】：TP277;TP393.09;TP316

【參考文獻】

相關期刊論文 前10條

1 陳偉偉;高潤霖;劉力生;朱曼璐;王文;王擁軍;吳兆蘇;李惠君;鄭哲;蔣立新;胡盛壽;;《中國心血管病報告2014》概要[J];中國循環(huán)雜志;2015年07期

2 顏延;秦興彬;樊建平;王磊;;醫(yī)療健康大數(shù)據(jù)研究綜述[J];科研信息化技術與應用;2014年06期

3 張松;田林亞;;時間序列分析在地鐵沉降監(jiān)測中的應用[J];測繪工程;2014年10期

4 周煒;;云環(huán)境下提升MongoDB自動分片性能研究[J];科技創(chuàng)新導報;2013年29期

5 鄧志飛;應良佳;王軍威;;基于IODA算法MongoDB負載均衡的改進[J];現(xiàn)代電信科技;2013年07期

6 馬亮亮;;基于PCA-ARIMA模型的高血壓發(fā)病率預測[J];河北北方學院學報(自然科學版);2013年02期

7 徐金茍;;低能耗藍牙4.0協(xié)議原理與實現(xiàn)方法[J];微型電腦應用;2012年10期

8 劉璐;薛秀芹;羅先露;金凡;孫俊;;無線體域網的體系結構及面臨的挑戰(zhàn)[J];電腦知識與技術;2012年29期

9 袁鋒;陳守強;;高效挖掘高血壓醫(yī)案關聯(lián)規(guī)則的模型構建[J];計算機工程與應用;2011年36期

10 呂明育;李小勇;;NoSQL數(shù)據(jù)庫與關系數(shù)據(jù)庫的比較分析[J];微型電腦應用;2011年10期

相關碩士學位論文 前5條

1 楊澤軍;基于Android平臺的健康感知信息采傳系統(tǒng)研究與實現(xiàn)[D];山東師范大學;2013年

2 沈姝;NoSQL數(shù)據(jù)庫技術及其應用研究[D];南京信息工程大學;2012年

3 劉順;基于WeHealth的物聯(lián)網通信協(xié)議研究與優(yōu)化[D];北京郵電大學;2012年

4 王海波;云計算中數(shù)據(jù)庫的關鍵問題研究與實現(xiàn)[D];吉林大學;2011年

5 田立明;基于Web的健康預測服務系統(tǒng)[D];大連理工大學;2006年

，

本文編號：2370480