支持向量回歸在人體血紅蛋白無創(chuàng)檢測中的應(yīng)用
發(fā)布時(shí)間:2018-06-10 15:11
本文選題:無創(chuàng)檢測 + 人血紅蛋白。 參考:《分析化學(xué)》2017年09期
【摘要】:采用線性漸變?yōu)V光片(Linear variable filter,LVF),優(yōu)化設(shè)計(jì)高性能、便攜式的人體血液成分近紅外檢測設(shè)備,研究了支持向量回歸(Support vector regression,SVR)模型對人體血紅蛋白(Hemoglobin,Hb)的預(yù)測能力及穩(wěn)定性,以實(shí)現(xiàn)貧血疾病的無創(chuàng)診斷。無創(chuàng)采集100位志愿者食指前端光譜信息并劃分定標(biāo)集、驗(yàn)證集1和2。應(yīng)用網(wǎng)格搜索方法優(yōu)選懲罰參數(shù)與核函數(shù)參數(shù)c=5.28,g=0.33,用以建立穩(wěn)健的SVR模型。隨后,分別對驗(yàn)證集1和2中Hb水平進(jìn)行定量分析。實(shí)驗(yàn)結(jié)果表明:預(yù)測標(biāo)準(zhǔn)偏差(RMSEP)分別為10.20 g/L和10.85 g/L,相對預(yù)測標(biāo)準(zhǔn)偏差(R-RMSEP)為6.85%和7.48%,測量精度較高且SVR模型對不同樣品的適應(yīng)性較強(qiáng),基本滿足臨床檢測要求。基于SVR算法自行設(shè)計(jì)的LVF型近紅外光譜檢測設(shè)備在貧血癥的無創(chuàng)診斷中有著良好的應(yīng)用前景。
[Abstract]:Linear variable filter was used to optimize the design of high performance and portable near infrared detection equipment for human blood composition. The predictive ability and stability of support vector regression (SVR) model for human hemoglobin (HB) were studied. In order to achieve non-invasive diagnosis of anemia. Noninvasive spectral information was collected from the front end of index finger of 100 volunteers and the calibration set was divided into two sets: 1 and 2. The penalty parameter and kernel function parameter cn5.28g / 0.33 are selected by grid search method to establish a robust SVR model. Then, the HB levels in validation set 1 and 2 were quantitatively analyzed respectively. The experimental results showed that the prediction standard deviation (RMSEPs) was 10.20 g / L and 10.85 g / L respectively, and the relative standard deviation (R-RMSEPV) was 6.85% and 7.48%, respectively. The accuracy of the prediction was higher and the SVR model was more adaptable to different samples, which basically met the requirements of clinical detection. LVF NIR detector based on SVR algorithm has a good application prospect in noninvasive diagnosis of anemia.
【作者單位】: 中國科學(xué)院長春光學(xué)精密機(jī)械與物理研究所;中國科學(xué)院大學(xué);吉林大學(xué)第一醫(yī)院腫瘤中心;
【基金】:國家高技術(shù)研究發(fā)展計(jì)劃(863計(jì)劃)(No.2012AA022602) 國家自然科學(xué)基金(Nos.61308067,61475155) 吉林省科技發(fā)展計(jì)劃項(xiàng)目(No.20140204078GX) 應(yīng)用光學(xué)國家重點(diǎn)實(shí)驗(yàn)室基金資助項(xiàng)目~~
【分類號】:O657.33;R446.11
,
本文編號:2003651
本文鏈接:http://sikaile.net/kejilunwen/huaxue/2003651.html
最近更新
教材專著