Hypertriglyceridemia Serum Recognition Using Fluorescence Spectroscopic Analysis Based on Probabilistic Neural Networks

LI Peng; WANG Le-xin; ZHAO Zhi-min

doi:null

您当前的位置：

首页 >

文章列表页 >

Hypertriglyceridemia Serum Recognition Using Fluorescence Spectroscopic Analysis Based on Probabilistic Neural Networks

paper | 更新时间：2020-08-12

- Hypertriglyceridemia Serum Recognition Using Fluorescence Spectroscopic Analysis Based on Probabilistic Neural Networks
- Chinese Journal of Luminescence Vol. 32, Issue 11, Pages: 1192-1196(2011)
- 作者机构：
  
  1. 华东交通大学机电工程学院,江西南昌,330013
  2. 南京航空航天大学理学院,江苏南京,210016
- 作者简介：
- 基金信息：
- DOI：
  CLC： O433.4
- Received：04 June 2011，
  
  Revised：24 July 2011，
  
  Published Online：22 November 2011，
  
  Published：22 November 2011
- 稿件说明：
移动端阅览
李鹏, 王乐新, 赵志敏. 基于概率神经网络的荧光光谱法识别高甘油三脂血清[J]. 发光学报, 2011,32(11): 1192-1196

LI Peng, WANG Le-xin, ZHAO Zhi-min. Hypertriglyceridemia Serum Recognition Using Fluorescence Spectroscopic Analysis Based on Probabilistic Neural Networks[J]. Chinese Journal of Luminescence, 2011,32(11): 1192-1196
李鹏, 王乐新, 赵志敏. 基于概率神经网络的荧光光谱法识别高甘油三脂血清[J]. 发光学报, 2011,32(11): 1192-1196 DOI：

LI Peng, WANG Le-xin, ZHAO Zhi-min. Hypertriglyceridemia Serum Recognition Using Fluorescence Spectroscopic Analysis Based on Probabilistic Neural Networks[J]. Chinese Journal of Luminescence, 2011,32(11): 1192-1196 DOI：

摘要

针对因正常和高甘油三脂血清荧光光谱混叠致使其识别率不高的问题

首先测量了正常和高甘油三脂血清样品在260

370

580 nm激发光下产生的荧光光谱

并以荧光强度作为样品的初始特征;其次

采用主成分分析法对初始特征进行分析和提取

获得了样品的特征向量;最后

构建了4层概率神经网络

并对正常和高甘油三脂血清样品进行了识别。对采用不同荧光光谱进行血清样品识别的效果进行了对比

结果表明

采用260 nm和370 nm荧光光谱识别正常和高甘油三脂血清的正确率分别为100%和95%。实验验证了研究方案的可行性和效果

对发展荧光光谱技术在识别高甘油三脂血症中的应用具有重要的意义和价值。

Abstract

The fluorescence spectra overlap of normal serum and hypetriglyceridemia serum will result in low recognition rate. The paper reports a recognition method of hypertriglyceridemia serum using fluorescence spectroscopic analysis based on principal component analysis and probabilistic neural networks. Firstly

fluorescence spectra of normal serum and hypertriglyceridemia serum were measured with the excitation wavelengths of 260

370

580 nm. And the sample's initial feature vector was defined according to fluorescence intensities. Secondly

principal component analysis was used to extract the initial feature vector and establish new sample's feature vector according to the cumulate reliability (>95%). Finally

the four-layer probabilistic neural network was founded for serum samples' recognition. Study designed seven groups of experimental scheme by choosing different fluorescence spectrum for recognition effect comparison. The result showed that recognition rates of the normal serum and hypertriglyceridemia serum were 100% and 95% respectively using fluorescence spectra with the excitation wavelengths of 260 nm and 370 nm. The feasibility and effect of the recognition scheme were demonstrated. The study provides an important guidance for developing the recognition technique of hypertriglyceridemia serum using fluorescence spectroscopic analysis based on probabilistic neural networks.

关键词

Keywords

references

Hao Suli, Liu Jinxiu, Xu Kangsen. Study on ELSD determination of structural fat emulsion injection for structural trigly-cerides [J]. Chin. J. Phar. Anal. (药物分析杂志), 2004, 24 (3):301-303 (in Chinese).[2] Aodeng Gaowa, Jin Yingchun. Spectroscopic studies on the interaction between fenbufen and bovine serum albumin [J]. Chin. J. Lumin. (发光学报), 2011, 32 (4):404-410 (in Chinese).[3] Wang Lexin, Zhao Zhimin. Resonance scattering spectra of normal serums and abnormal serums [J]. Chin. J. Lumin. (发光学报), 2011, 32 (2):200-204 (in Chinese).[4] Ling Mingsheng, Qian Zhiyu, Liang Chaoying. Research on blood glucose concentration monitoring by fluorescence spectrum [J]. Chinese Journal of Quantum Electronics (量子电子学报), 2007, 24 (5):635-639 (in Chinese).[5] Hu Youbo, Li Donggang, Li Junwei, et al. Determination of selenium in blood by hydride generation atomic fluorescence spectrometry [J]. Chemical Engineer (化学工程师), 2007(7):25-26 (in Chinese).[6] Li Yongzhi, Yang Jingyu, Wu Songsong. A class-information-incorporated kernel principal component analysis method [J]. PR & AI (模式识别与人工智能), 2008, 21 (3):410-415 (in Chinese).[7] Specht D F. Probabilistic neural networks [J]. Neural Networks, 1990, 3 (1):109-118.[8] Lee J J, Kim D, Chang S K. An improved application technique of the adaptive probabilistic neural network for predicting concrete strength [J]. Computational Materials Science, 2009, 44 (3):988-998.[9] Kim D, Kim D H, Chang S. Application of probabilistic neural network to design breakwater armor blocks [J]. Ocean Engineering, 2008, 35 (3-4):294-300.

Views

132

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Recent Advances in Optical Microcavity Enhanced Fluorescence and Raman Spectroscopy

Research on Products Quality Stability Based on Near Infrared Spectroscopy and Feature Extraction of PCA Radar Chart

Mechanism of Interaction Between Levofloxacin and Pepsin by Spectroscopic and Molecular Docking Methods

Multi-color Prediction Model Based on BP-NN Optimized by GA and PCA

Synthesis of 4-Thio-5-iodouridine and The Interaction Between It and Human Serum Albumin

Related Author

JIANG Yijian

YAN Yinzhou

YAO Yao

ZHANG Lei

GAO Rui

ZHANG Hai-tao

QIN Yu-hua

LI Meng-ting

Related Institution

School of Physics and Optoelectronic Engineering， Beijing University of Technology

College of Information Science and Technology, Qingdao University of Science and Technology

Technical Research Center, China Tobacco Yunnan Industrial Co., Ltd.

College of Information Science and Engineering, China Ocean University

School of Pharmaceutical Sciences, Zhengzhou University

AI问答

Address：No.3888 Dong Nanhu Road, Changchun, Jilin, China Postal code：130033
Tel：0431-86176862 Email：fgxbt@126.com
Technical support is provided by Beijing Founder electronics co., LTD 吉ICP备11002662号-17 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰