首页 > 论文 > 光学学报 > 40卷 > 7期(pp:0730002--1)

XGBoost在气体红外光谱识别中的应用

Application of XGBoost in Gas Infrared Spectral Recognition

  • 摘要
  • 论文信息
  • 参考文献
  • 被引情况
  • PDF全文
分享:

摘要

为解决气体红外光谱识别问题,引入提升算法中较新的研究成果——极端梯度提升(XGBoost)算法。选用实测的三氯甲烷、对二甲苯、四氯乙烯气体的红外光谱数据进行实验。首先在对原始数据进行预处理后,通过特征工程提取光谱特征,生成特征向量;然后建立XGBoost模型,并对模型参数进行调优;最后基于分类准确率指标,将所提模型与随机森林(RF)、支持向量机(SVM)、前馈神经网络(FNN)、卷积神经网络(CNN)模型进行对比。实验结果表明,XGBoost在气体红外光谱识别领域有着广阔的应用前景。

Abstract

To address the problem of gas infrared spectral identification, a new lifting algorithm named eXtreme gradient boosting (XGBoost) is introduced. Infrared spectral data of chloroform, p-xylene, and tetrachloroethylene are selected for experiments. After these original data are preprocessed, the spectral features are first extracted by feature engineering to generate feature vectors. Then, the XGBoost model is established and its parameters are optimized. Finally, based on a classification accuracy index, the XGBoost model is compared with random forest (RF), support vector machine (SVM), feedforward neural network (FNN), and convolutional neural network (CNN). The experimental results show that XGBoost has a broad application prospect in the field of gas infrared spectral identification.

中国激光微信矩阵
补充资料

中图分类号:O433

DOI:10.3788/AOS202040.0730002

所属栏目:光谱学

收稿日期:2019-12-03

修改稿日期:2019-12-30

网络出版日期:2020-04-01

作者单位    点击查看

陶孟琪:中国科学院安徽光学精密机械研究所环境光学与技术重点实验室, 安徽 合肥 230031中国科学技术大学, 安徽 合肥 230026
刘家祥:中国科学院安徽光学精密机械研究所环境光学与技术重点实验室, 安徽 合肥 230031
吴越:中国科学院安徽光学精密机械研究所环境光学与技术重点实验室, 安徽 合肥 230031中国科学技术大学, 安徽 合肥 230026
宁志强:中国科学院安徽光学精密机械研究所环境光学与技术重点实验室, 安徽 合肥 230031中国科学技术大学, 安徽 合肥 230026
方勇华:中国科学院安徽光学精密机械研究所环境光学与技术重点实验室, 安徽 合肥 230031中国科学技术大学, 安徽 合肥 230026

联系人作者:方勇华(yhfang@aiofm.ac.cn)

【1】Sheehe S L, Jackson S I. Identification of species from visible and near-infrared spectral emission of a nitromethane-air diffusion flame [J]. Journal of Molecular Spectroscopy. 2019, 364: 111185.

【2】Han Y Z, Zhang Y X, Chang S J, et al. Recognition for the nonlinear fluorescence spectra based on optimal wavelet transform and artificial neural network [J]. Journal of Optoelectronics·Laser. 2005, 16(6): 718-721.
韩应哲, 张延炘, 常胜江, 等. 基于最佳小波变换和神经网络的气体非线性荧光光谱的识别 [J]. 光电子·激光. 2005, 16(6): 718-721.

【3】Bai P, Xie W J, Liu J H. Method of infrared spectrum analysis of hydrocarbon mixed gas based on multilevel and SVM-subset [J]. Spectroscopy and Spectral Analysis. 2008, 28(2): 299-302.
白鹏, 谢文俊, 刘君华. 层次式SVM子集含烃类混合气体光谱分析方法 [J]. 光谱学与光谱分析. 2008, 28(2): 299-302.

【4】Bai P, Wang J H, Wang H K, et al. A method of mixed gas component infrared spectrum recognition based on SVM regression model [J]. Acta Photonica Sinica. 2008, 37(4): 754-757.
白鹏, 王建华, 王宏柯, 等. 基于SVM回归模型的混合气体组分种类光谱识别方法 [J]. 光子学报. 2008, 37(4): 754-757.

【5】Liu M J, Feng W W, Shi F R, et al. Fast algorithm for feature extraction and identification of infrared spectra of polluted gases [J]. Spectroscopy and Spectral Analysis. 2006, 26(10): 1854-1857.
刘美娟, 冯巍巍, 史丰荣, 等. 污染气体红外光谱特征的快速提取与识别 [J]. 光谱学与光谱分析. 2006, 26(10): 1854-1857.

【6】Yu D H. Research on gas recognition and concentration detection algorithm based on infrared spectrum [D]. Chengdu: University of Electronic Science and Technology of China. 2018, 13-58.
余段辉. 基于红外光谱的气体识别与浓度检测算法研究 [D]. 成都: 电子科技大学. 2018, 13-58.

【7】Chen T Q, Guestrin C. XGBoost: a scalable tree boosting system . [C]∥Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, August 13-17, 2016, San Francisco, California. New York: ACM. 2016, 785-794.

【8】Zopluoglu C. Detecting examinees with item preknowledge in large-scale testing using extreme gradient boosting (XGBoost) [J]. Educational and Psychological Measurement. 2019, 79(5): 931-961.

【9】Torlay L, Perrone-Bertolotti M, Thomas E, et al. Machine learning: XGBoost analysis of language networks to classify patients with epilepsy [J]. Brain Informatics. 2017, 4: 159-169.

【10】Li D Z, Wang C, Li Y Y. Evaluation of fan blade icing based on XGBoost algorithm [J]. Electric Power Science and Engineering. 2019, 35(9): 43-48.
李大中, 王超, 李颖宇. 基于XGBoost算法的风机叶片结冰状态评测 [J]. 电力科学与工程. 2019, 35(9): 43-48.

【11】Zhang X, Luo A. XGBOOST based stellar spectral classification and quantized feature [J]. Spectroscopy and Spectral Analysis. 2019, 39(10): 3292-3296.
张枭, 罗阿理. 基于XGBOOST的恒星光谱分类特征数值化 [J]. 光谱学与光谱分析. 2019, 39(10): 3292-3296.

【12】Zhang W W, Liu D, Jia X Y. Three classified coupon prediction based on XGBoost algorithm [J]. Journal of Nanjing University of Aeronautics & Astronautics. 2019, 51(5): 643-651.
张微薇, 刘盾, 贾修一. 基于XGBoost的三分类优惠券预测方法 [J]. 南京航空航天大学学报. 2019, 51(5): 643-651.

【13】Mo H, Sun H J, Liu J J, et al. Developing window behavior models for residential buildings using XGBoost algorithm [J]. Energy and Buildings. 2019, 205: 109564.

【14】, et al. Automatic baseline correction of gas spectra based on baseline drift model [J]. Spectroscopy and Spectral Analysis. 2018, 38(12): 300-305.
, 等. 基于基线漂移模型的气体光谱自动基线校正 [J]. 光谱学与光谱分析. 2018, 38(12): 300-305.
Wang X, Lu S L, Li Y, Wang X, Lü S L, Li Y, et al. Automatic baseline correction of gas spectra based on baseline drift model [J]. Spectroscopy and Spectral Analysis. 2018, 38(12): 3946-3951.
王昕, 吕世龙, 李岩, 王昕, 吕世龙, 李岩, 等. 基于基线漂移模型的气体光谱自动基线校正 [J]. 光谱学与光谱分析. 2018, 38(12): 3946-3951.

【15】Liu J, Koenig J L. A new baseline correction algorithm using objective criteria [J]. Applied Spectroscopy. 1987, 41(3): 447-449.

【16】Zhao Y S, Xue X M, Song X J, et al. Comparison and analysis of FT-IR spectra for six broad-leaved wood species [J]. Journal of Forestry Engineering. 2019, 33(5): 40-45.
赵阅书, 薛晓明, 宋小娇, 等. 6种阔叶树材红外光谱特征的比较 [J]. 林业工程学报. 2019, 33(5): 40-45.

【17】Yang S Q, Yan L J, Liu N, et al. Asphalt index based on characteristic spectral analysis of infrared spectrum [J]. Journal of Jiangsu University(Natural Science Edition). 2019, 40(2): 244-248.
杨三强, 颜立景, 刘娜, 等. 基于红外光谱图特征峰分析的沥青指标 [J]. 江苏大学学报(自然科学版). 2019, 40(2): 244-248.

【18】Zhuang L, Song X J, Xu Y H. Study on the infrared spectral characteristic of tetracentron sinense wood [J]. Hubei Agricultural Sciences. 2017, 56(7): 1334-1339, 1344.
庄琳, 宋小娇, 徐燕红. 水青树木材红外光谱特征研究 [J]. 湖北农业科学. 2017, 56(7): 1334-1339, 1344.

引用该论文

Tao Mengqi,Liu Jiaxiang,Wu Yue,Ning Zhiqiang,Fang Yonghua. Application of XGBoost in Gas Infrared Spectral Recognition[J]. Acta Optica Sinica, 2020, 40(7): 0730002

陶孟琪,刘家祥,吴越,宁志强,方勇华. XGBoost在气体红外光谱识别中的应用[J]. 光学学报, 2020, 40(7): 0730002

您的浏览器不支持PDF插件,请使用最新的(Chrome/Fire Fox等)浏览器.或者您还可以点击此处下载该论文PDF