本文關(guān)鍵詞：基于CEEMDAN-ELM的短期血糖預(yù)測模型研究　出處：《鄭州大學(xué)》2017年碩士論文　論文類型：學(xué)位論文

  更多相關(guān)文章： 血糖預(yù)測 極限學(xué)習(xí)機(jī) CEEMDAN 低血糖預(yù)警 CGM

【摘要】：由于生活方式的改變,糖尿病患病群體呈年輕化趨勢,已成為嚴(yán)重影響人類健康的疾病。血糖預(yù)測是人工胰臟血糖閉環(huán)控制的關(guān)鍵,可通過調(diào)控胰島素注射劑量和時(shí)間強(qiáng)化糖尿病患者體內(nèi)的血糖控制并降低并發(fā)癥的發(fā)生,為醫(yī)生和患者進(jìn)行血糖控制提供數(shù)據(jù)支持。因此提高血糖預(yù)測精度、增加預(yù)測時(shí)間具有十分重要意義。血糖預(yù)測是根據(jù)人體內(nèi)的歷史血糖值來預(yù)測未來一段時(shí)間血糖濃度的變化趨勢。本文在研究已有的血糖預(yù)測技術(shù)基礎(chǔ)上,提出了一種基于自適應(yīng)白噪聲完整聚合經(jīng)驗(yàn)?zāi)B(tài)分解-極限學(xué)習(xí)機(jī)(Complete Ensemble Empirical Mode Decomposition with Adaptive Noise-Extreme Learning Machine,CEEMDAN-ELM)的短期血糖預(yù)測模型。為提高血糖預(yù)測的精確度,模型首先運(yùn)用信號分析技術(shù),利用CEEMDAN方法對糖尿病患者血糖值時(shí)間序列進(jìn)行平穩(wěn)化處理,逐級分解患者血糖數(shù)據(jù)中存在的不同尺度下的波動(dòng)或變化趨勢以降低血糖值時(shí)間序列的非線性和非平穩(wěn)性,獲得一組含有不同頻段特征的血糖分量;然后對各血糖分量分別利用ELM進(jìn)行預(yù)測;最后融合各血糖分量的預(yù)測結(jié)果,獲得糖尿病患者最終的血糖預(yù)測值。論文在CEEMDAN-ELM短期血糖預(yù)測模型基礎(chǔ)上進(jìn)行了低血糖預(yù)警研究,設(shè)計(jì)了一種新的低血糖預(yù)警方法。本文利用60例Ⅱ型糖尿病患者的血糖數(shù)據(jù)進(jìn)行血糖預(yù)測實(shí)驗(yàn),并采用克拉克網(wǎng)格分析法、配對t檢驗(yàn)等對預(yù)測模型的性能進(jìn)行了檢驗(yàn),采用虛警率和漏警率來評估低血糖預(yù)警效果。結(jié)果表明:與ELM模型和EMD-ELM模型相比,CEEMDAN-ELM短期血糖預(yù)測模型提前45min的血糖預(yù)測達(dá)到了較高的精確度(60例患者的平均RMSE=0.2046,MAPE=2.0855%);提前45min的患者血糖預(yù)測值基本落在了Clarke網(wǎng)格誤差圖的A區(qū)域。在CEEMDAN-ELM短期血糖預(yù)測模型的基礎(chǔ)上提出的低血糖預(yù)警方法使得26例具有低血糖事件的糖尿病患者的虛警率為0.77%,漏警率為8.71%。CEEMDAN-ELM血糖預(yù)測模型提高了預(yù)測精度,延長了預(yù)測時(shí)間,對提高糖尿病的治療效果具有重要意義。
[Abstract]:Because of the change of life style, the diabetic patients tend to be younger, which has become a serious disease affecting human health. Blood glucose prediction is the key to the closed loop control of blood glucose in artificial pancreas. It can enhance the blood glucose control and reduce the incidence of complications in diabetic patients by regulating the dose and time of insulin injection, which can provide data support for doctors and patients to carry out blood glucose control. Therefore, improve the accuracy of blood glucose prediction. It is very important to increase the predicted time. The prediction of blood sugar is based on the historical blood sugar value in human body to predict the trend of blood glucose concentration in the future. An adaptive white noise complete aggregation empirical mode decomposition-extreme learning machine (LLMs) based on adaptive white noise is proposed in this paper. Complete Ensemble Empirical Mode Decomposition with Adaptive. Noise-Extreme Learning Machine. CEEMDAN-ELM) short-term blood glucose prediction model. In order to improve the accuracy of blood glucose prediction, the model first used signal analysis technology. The CEEMDAN method was used to stabilize the time series of blood glucose in diabetic patients. In order to reduce the nonlinearity and nonstationarity of the time series of blood glucose values, a group of blood glucose components with different frequency characteristics was obtained by decomposing the fluctuation or changing trend of different scales in the blood glucose data step by step. Then the blood glucose components were predicted by ELM. Finally, the final blood glucose prediction value of diabetic patients was obtained by combining the predicted results of each component of blood sugar. Based on the CEEMDAN-ELM short-term blood glucose prediction model, hypoglycemia prediction was studied in this paper. A new early warning method for hypoglycemia was designed in this paper. The blood glucose prediction experiment was carried out by using the blood glucose data of 60 patients with type 鈪，

本文編號：1422072