首页 > 论文 > 光学学报 > 39卷 > 5期(pp:530003--1)

基于Lasso方法的污染气体自适应探测算法

Adaptive Feature Extraction Algorithm Based on Lasso Method for Detecting Polluted Gas

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

摘要

在开放光路条件下, 污染气体与大气成分的光谱特征相互混叠, 难以直接对污染气体进行识别。提出了一种自适应特征提取算法, 预先生成各种大气条件下的光谱特征, 利用Lasso算法进行快速特征优选, 选择最优目标/背景组合重构背景光谱, 提取目标特征。为了验证所提算法的有效性, 开展了不同背景下的甲烷遥测实验、不同相对湿度条件下的氨气遥测实验, 以及室内近距离乙烯探测实验。将所提算法与Harig算法进行对比, 结果表明:所提算法能更好地扣除背景, 具有较强的实用性。

Abstract

Under the open light path condition, the spectral characteristics of polluted gases and atmospheric components are overlapped, making it difficult to directly identify the polluted gases. This study proposes an adaptive feature extraction method, which pre-generates the spectral features under various atmospheric conditions. The rapid feature extraction is performed using the Lasso algorithm for selecting the optimal target-background combination, reconstructing the background spectrum, and extracting the target features. The effectiveness of the proposed algorithm is verified via the methane remote detection under different backgrounds; the ammonia gas detection is also performed under different relative humidity conditions along with the indoor close-range ethylene detection. The proposed method is compared with the Harig′s method. The results show that the proposed method can well eliminate background and possesses strong practicability.

Newport宣传-MKS新实验室计划
补充资料

中图分类号:TP722.5

DOI:10.3788/aos201939.0530003

所属栏目:光谱学

基金项目:国家自然科学基金(41505020)、国家高技术研究发展计划(CXJJ-16S006)

收稿日期:2018-10-23

修改稿日期:2019-01-06

网络出版日期:2019-01-29

作者单位    点击查看

崔方晓:中国科学院合肥物质科学研究院安徽光学精密机械研究所, 安徽 合肥 230031
李大成:中国科学院合肥物质科学研究院安徽光学精密机械研究所, 安徽 合肥 230031
吴军:中国科学院合肥物质科学研究院安徽光学精密机械研究所, 安徽 合肥 230031
王安静:中国科学院合肥物质科学研究院安徽光学精密机械研究所, 安徽 合肥 230031
李扬裕:中国科学院合肥物质科学研究院安徽光学精密机械研究所, 安徽 合肥 230031

联系人作者:李大成(dcli@aiofm.ac.cn)

【1】John R C, Leonardo C P, William O, et al. Open path FTIR detection of threat chemicals in air and on surfaces[J]. Proceedings of SPIE, 2011, 8012: 801209.

【2】Samer S, Peter R, Jrn-Hinnrich G, et al. Detection and tracking of gas clouds in an urban area by imaging infrared spectroscopy[J]. Proceedings of SPIE, 2013, 8743: 874317.

【3】Kim Y C, Yu H G, Lee J H, et al. Hazardous gas detection for FTIR-based hyperspectral imaging system using DNN and CNN[J]. Proceedings of SPIE, 2017, 10433: 1043317.

【4】Harig R, Matz G. Toxic cloud imaging by infrared spectrometry: a scanning FTIR system for identification and visualization[J]. Field Analytical Chemistry & Technology, 2001, 5(1/2): 75-90.

【5】Cui F X, Fang Y H. Infrared back ground compression method based on brightness temperature spectrum[J]. Acta Optica Sinica, 2013, 33(11): 1130001.
崔方晓, 方勇华. 基于亮温光谱的红外背景压缩方法[J]. 光学学报, 2013, 33(11): 1130001.

【6】Harig R, Keens A, Rusch P, et al. Hyperspectral sensor for analysis of gases in the atmosphere(HYGAS)[J]. Proceedings of SPIE, 2010, 7695: 76950B.

【7】Gittins C M. Detection and characterization of chemical vapor fugitive emissions by nonlinear optimal estimation: theory and simulation[J]. Applied Optics, 2009, 48(23): 4545.

【8】Cui F X, Fang Y H, Lan T G, et al. Remote sensing of pollutant gases using brightness temperature and principal component analysis[J]. Spectroscopy and Spectral Analysis, 2011, 31(10): 2794-2797.
崔方晓, 方勇华, 兰天鸽, 等. 基于亮温光谱和主成分分析的大气污染气体探测[J]. 光谱学与光谱分析, 2011, 31(10): 2794-2797.

【9】Burr T, Hengartner N. Overview of physical models and statistical approaches for weak gaseous plume detection using passive infrared hyperspectral imagery[J]. Sensors, 2006, 6(12): 1721-1750.

【10】Zhu X F, Tian Y, Xu Q. Sparse methods in spectroscopy[J]. Computers and Applied Chemistry, 2017, 34(8): 588-596.
朱新峰, 田叶, 徐琴. 光谱学中的稀疏化方法[J]. 计算机与应用化学, 2017, 34(8): 588-596.

【11】Efron B, Hastie T, Johnstone I, et al. Least angle regression[J]. The Annals of Statistics, 2004, 32(2): 407-451.

引用该论文

Cui Fangxiao,Li Dacheng,Wujun,Wang Anjing,Li Yangyu. Adaptive Feature Extraction Algorithm Based on Lasso Method for Detecting Polluted Gas[J]. Acta Optica Sinica, 2019, 39(5): 0530003

崔方晓,李大成,吴军,王安静,李扬裕. 基于Lasso方法的污染气体自适应探测算法[J]. 光学学报, 2019, 39(5): 0530003

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