基于粒子群和人工神經(jīng)網(wǎng)絡(luò)的近紅外光譜血糖建模方法研究
發(fā)布時間：2018-10-09 13:58
【摘要】：現(xiàn)有的近紅外光譜無創(chuàng)血糖建模方法大多是基于多波長近紅外光譜信號,不利于無創(chuàng)血糖儀在家庭中普及,并且這些建模方法沒有考慮單個個體每天血糖變化規(guī)律的差異性。針對這些問題,本文以血糖吸收最強(qiáng)的1 550 nm近紅外光吸光度為自變量、血糖濃度為因變量,結(jié)合粒子群(PSO)算法和人工神經(jīng)網(wǎng)絡(luò)(ANN)建立了一種無創(chuàng)血糖檢測模型——PSO-2ANN模型。該模型以兩個結(jié)構(gòu)和參數(shù)確定的人工神經(jīng)網(wǎng)絡(luò)為基本的子模塊,通過粒子群算法優(yōu)化兩個子模塊的權(quán)重系數(shù)得到最終的模型。使用PSO-2ANN模型對10名志愿者的實(shí)驗(yàn)數(shù)據(jù)進(jìn)行預(yù)測。結(jié)果表明,其中9名志愿者的預(yù)測相對誤差率均小于20%;通過PSO-2ANN模型得到的血糖濃度預(yù)測值分布在克拉克誤差網(wǎng)格A、B區(qū)域的比重為98.28%,證實(shí)了PSO-2ANN模型具有比傳統(tǒng)人工神經(jīng)網(wǎng)絡(luò)模型更為理想的預(yù)測精度和穩(wěn)健性。另外,單個個體由于外界環(huán)境、心情、精神狀態(tài)等因素的影響,每天血糖的變化規(guī)律可能會出現(xiàn)一定程度的差異性,PSO-2ANN模型只需要調(diào)節(jié)一個參數(shù)便能修正這種差異性。本文提出的PSO-2ANN模型為克服血糖濃度預(yù)測的個體差異性提供了新的思路。
[Abstract]:Most of the existing NIR modeling methods are based on multi-wavelength NIR signals, which is not conducive to the popularity of non-invasive blood glucose meters in the family, and these modeling methods do not take into account the differences of individual daily blood glucose changes. Aiming at these problems, a noninvasive blood glucose detection model, PSO-2ANN model, is established by combining particle swarm (PSO) algorithm and artificial neural network (ANN). The model is based on two artificial neural networks whose structure and parameters are determined, and the final model is obtained by optimizing the weight coefficients of the two sub-modules by particle swarm optimization (PSO). PSO-2ANN model was used to predict the experimental data of 10 volunteers. The results show that The predicted relative error rate of 9 volunteers was less than 20, and the predicted blood glucose concentration by PSO-2ANN model was 98.28% in the Clark error grid, which proved that the PSO-2ANN model had a better performance than the traditional artificial neural network model. A more ideal prediction accuracy and robustness. In addition, due to the influence of external environment, mood, mental state and other factors, the variation of daily blood glucose may be different to a certain extent. PSO-2ANN model only need to adjust one parameter to correct this difference. The PSO-2ANN model proposed in this paper provides a new idea for overcoming the individual differences in blood glucose concentration prediction.
【作者單位】： 重慶大學(xué)生物工程學(xué)院;重慶市醫(yī)療電子工程技術(shù)中心;
【基金】：國家自然科學(xué)基金項(xiàng)目(81371713) 中央高�；究蒲袠I(yè)務(wù)費(fèi)專項(xiàng)(106112015CDJZR235522)
【分類號】：R587.1;TN219
本文編號：2259595
[Abstract]:Most of the existing NIR modeling methods are based on multi-wavelength NIR signals, which is not conducive to the popularity of non-invasive blood glucose meters in the family, and these modeling methods do not take into account the differences of individual daily blood glucose changes. Aiming at these problems, a noninvasive blood glucose detection model, PSO-2ANN model, is established by combining particle swarm (PSO) algorithm and artificial neural network (ANN). The model is based on two artificial neural networks whose structure and parameters are determined, and the final model is obtained by optimizing the weight coefficients of the two sub-modules by particle swarm optimization (PSO). PSO-2ANN model was used to predict the experimental data of 10 volunteers. The results show that The predicted relative error rate of 9 volunteers was less than 20, and the predicted blood glucose concentration by PSO-2ANN model was 98.28% in the Clark error grid, which proved that the PSO-2ANN model had a better performance than the traditional artificial neural network model. A more ideal prediction accuracy and robustness. In addition, due to the influence of external environment, mood, mental state and other factors, the variation of daily blood glucose may be different to a certain extent. PSO-2ANN model only need to adjust one parameter to correct this difference. The PSO-2ANN model proposed in this paper provides a new idea for overcoming the individual differences in blood glucose concentration prediction.
【作者單位】： 重慶大學(xué)生物工程學(xué)院;重慶市醫(yī)療電子工程技術(shù)中心;
【基金】：國家自然科學(xué)基金項(xiàng)目(81371713) 中央高�；究蒲袠I(yè)務(wù)費(fèi)專項(xiàng)(106112015CDJZR235522)
【分類號】：R587.1;TN219
【相似文獻(xiàn)】
相關(guān)期刊論文 前1條
1 郭奕瑞;李玉倩;王高帥;劉曉田;張路寧;張紅艷;王炳源;王重建;;人工神經(jīng)網(wǎng)絡(luò)模型在2型糖尿病患病風(fēng)險預(yù)測中的應(yīng)用[J];鄭州大學(xué)學(xué)報(醫(yī)學(xué)版);2014年02期
相關(guān)重要報紙文章 前1條
1 記者 周前進(jìn);人工神經(jīng)網(wǎng)絡(luò)可篩查糖尿病[N];健康報;2000年
相關(guān)碩士學(xué)位論文 前1條
1 洪燁;基于機(jī)器學(xué)習(xí)算法的糖尿病預(yù)測模型研究[D];哈爾濱工業(yè)大學(xué);2016年
，本文編號：2259595
本文鏈接：http://www.lk138.cn/kejilunwen/dianzigongchenglunwen/2259595.html
最近更新
教材專著
