Selection of Near Infrared Spectral Wavelength Variables Based on Improved Immune Genetic Algorithm

TAO Huan-ming; GAO Mei-feng

doi:10.19969/j.fxcsxb.21012006

您当前的位置：

首页 >

文章列表页 >

Selection of Near Infrared Spectral Wavelength Variables Based on Improved Immune Genetic Algorithm

Scientific Papers | 更新时间：2023-02-13

- Selection of Near Infrared Spectral Wavelength Variables Based on Improved Immune Genetic Algorithm
- Journal of Instrumental Analysis Vol. 40, Issue 10, Pages: 1482-1488(2021)
- 作者机构：
  
  江南大学轻工过程先进控制教育部重点实验室，物联网工程学院，江苏无锡 214122
- 作者简介：
- 基金信息：
- DOI：10.19969/j.fxcsxb.21012006
  CLC：
扫描看全文
陶焕明,高美凤.基于改进免疫遗传算法的近红外光谱变量选择方法[J].分析测试学报,2021,40(10):1482-1488.

TAO Huan-ming,GAO Mei-feng.Selection of Near Infrared Spectral Wavelength Variables Based on Improved Immune Genetic Algorithm[J].Journal of Instrumental Analysis,2021,40(10):1482-1488.
陶焕明,高美凤.基于改进免疫遗传算法的近红外光谱变量选择方法[J].分析测试学报,2021,40(10):1482-1488. DOI： 10.19969/j.fxcsxb.21012006.

TAO Huan-ming,GAO Mei-feng.Selection of Near Infrared Spectral Wavelength Variables Based on Improved Immune Genetic Algorithm[J].Journal of Instrumental Analysis,2021,40(10):1482-1488. DOI： 10.19969/j.fxcsxb.21012006.

摘要

该文在免疫遗传算法（IGA）的基础上，提出一种改进免疫遗传算法（iIGA）用于近红外光谱波长变量的选择。该算法舍去了原算法中固定抗体相似度阈值的思想，取而代之的是抗体相似度阈值自适应，同时引入精英保留策略和贪心算法思想，使得算法朝着正确的方向进行局部性探优。将该算法在玉米的淀粉和蛋白质含量数据集上进行实验测试，建立偏最小二乘（PLS）分析模型，并与IGA、遗传算法（GA）以及全谱方法进行了对比。结果表明，在玉米淀粉含量的预测上，iIGA相较于原IGA算法，预测集均方根误差（RMSEP）从0.312 0降至0.298 0，预测集预测精度提升4.5%；在玉米蛋白质含量的预测上，RMSEP从0.124 4降至0.110 3，预测集预测精度提升11.3%。分别对预测淀粉和蛋白质模型的RMSEP值进行显著性检验，,F,值分别为165.22和182.05，,P,值分别为9.5 × 10,－23,和4.5 × 10,－24,，,P,值均小于0.05，因此，iIGA能显著提升模型预测精度。

Abstract

Based on immune genetic algorithm（IGA），an improved immune genetic algorithm（iIGA） was proposed to select the wavelength variables of near infrared spectra．The idea of fixed antibody similarity threshold in the original algorithm was abandoned in the iIGA，which was replaced with adaptive antibody similarity threshold．Meanwhile，the elitist retention strategy and greedy algorithm idea were introduced，making the algorithm carry out local optimization in the right direction．The algorithm was tested on the corn starch and protein content data sets to establish a partial least squares（PLS） analysis model，and compared with IGA，genetic algorithm （GA） and full spectrum method．Results showed that the root mean square error of prediction set （RMSEP） of iIGA was reduced from 0.312 0 to 0.298 0，compared with those of the original IGA algorithm，the prediction accuracy of prediction set was improved by 4.5%．In the prediction of corn protein content，the RMSEP decreased from 0.124 4 to 0.110 3，the prediction accuracy of prediction set increased by 11.3%．A significant test was carried out for the RMSEP values of starch and protein models，respectively，in which ,F, values were 165.22 and 182.05，,P, values were 9.5 × 10,－23, and 4.5 × 10,－24,，respectively，and ,P ,values were less than 0.05．Therefore，iIGA could significantly improve the prediction accuracy of the model．

关键词

近红外光谱波长选择改进的免疫遗传算法分析模型预测精度

Keywords

near infrared spectrumwavelength selectionimproved immune genetic algorithmanalysis modelprediction accuracy

references

Li C，Zhao T L，Li C，Mei L，Yu E，Dong Y T，Chen J H，Zhu S J．Food Chem.，2017，221：990－996.

Zhang H，Li C C，Huang J，Huang X H，Zhang W C，Zhang X，Wu Z L，Yu X K．Polish J. Environ. Stud.，2018，27（4）：1859－1867.

Liu H J，Li M Z，Zhang J Y，Gao D H，Sun H，Zhang M，Wu J Z．Int. J. Agric. Biol. Eng.，2019，12（5）：149－155.

Qu F F，Ren D，Hou J J，Zhang Z，Lu A X，Wang J H，Xu H L．Spectrosc. Spectral Anal.，2016，36（2）：593－598.

Yun Y H，Li H D，Leslie R E W，Fan W，Wang J J，Cao D S，Xu Q S，Liang Y Z．Spectrochim. Acta A，2013，111：31－36.

Huang C Y，Fan H B，Liu F，Xu G R．J. Instrum. Anal. （黄常毅，范海滨，刘飞，许赣荣．分析测试学报），2014，33（5）：520－526.

Jiang S Q，Sun T．Food Mach. （江水泉，孙通．食品与机械），2020，2：89－93.

Leardi R，Norgaard L．J. Chemom.，2006，18（11）：486－497.

Hu L Q，Yin C L，Ma S，Liu Z M．Food Anal. Methods，2019，12（3）：633－643.

Sun X R，Zhou Z J，Liu C L，Fu X X，Dou Y．Food Sci. （孙晓荣，周子健，刘翠玲，付新鑫，窦颖．食品科学），2018，39（2）：222－226.

Shamsipur M，Zare－Shahabadi V，Hemmateenejad B，Akhond M．J. Chemom.，2006，20（3/4）：146－157.

Liu X，Mao Z K，Zhang X M，Li S W，Jin X．J. Jiangsu Univ.：Nat. Sci. Ed. （刘鑫，冒智康，张小鸣，李绍稳，金秀．江苏大学学报：自然科学版），2020，41（3）：321－327.

Zhou Z W，Luo D L，Shao J，Xu Y，You Y C．Phys. Commun.，2020，41：101103.

Zhang H Y．Assem. Autom.，2019，39（1）：113－123.

Dai X L，Wang P，Gong D W．J. Harbin Eng. Univ. （代小林，王鹏，宫大为．哈尔滨工程大学学报），2018，39（12）：2033－2039.

Zhao X，Zhu Q B，Huang M，Cen H Y．Anal. Methods，2013，5（18）：4811－4817.

Lou G X，Cai Z Y．Cluster Comput.，2019，22（2）：3419－3429.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Selection of Near Infrared Spectral Wavelength Variables Based on Improved Whale Optimization Algorithm and Its Application

Study on a Near Infrared Calibration Transfer Method Based on Sparrow Search Algorithm Combined with Deep Feedforward Neural Network

Related Author

No data

Related Institution

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

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

Address：100 Xianlie Middle Road, Guangzhou Postal code：510070
Tel：020-87684776,37656606 Fax：020-87684776 Email：fxcsxb@china.com
Technical support is provided by Beijing Founder electronics co., LTD 粤ICP备12017312号-3 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