Journal of Energy, Environmental & Chemical Engineering

| Peer-Reviewed |

Sulfur Dioxide Detection Signal Denoising Based on Support Vector Machine

Received: 22 January 2019    Accepted: 26 February 2019    Published: 19 March 2019
Views:       Downloads:

Share This Article

Abstract

A system for detecting sulfur dioxide (SO2) based on differential optical absorption spectrometry theory was studied. The detection system can eliminate the noise from light source and light path by using the double optical path. Background noise was generated by the photoelectric device. It also effects the quantitative analysis. The Support Vector Machine (SVM) is proposed to process the SO2 ultraviolet absorption spectrum. The SO2 ultraviolet absorption spectra at 220nm-340nm were obtained by using the SO2 detection system in this article. Then the spectral was denoised by the SVM. The experimental results showed that the absorption line was more smoothness after denoising by the SVM, and the SNR and mean square error were 48.9398 and 1×10-7, respectively. The de-noising data was applied to the SO2 detection system, the linearity of the measurement was good with the coefficients of more than 0.9971. Compare the result with the wavelet and Empirical Mode Decomposition (EMD) denoising methods, which illustrates that SVM has better effects. It shows that the SVM method applied to noise reduction of SO2 detection system is superior.

DOI 10.11648/j.jeece.20180304.11
Published in Journal of Energy, Environmental & Chemical Engineering (Volume 3, Issue 4, December 2018)
Page(s) 54-60
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Sulfur Dioxide, Denoising, Support Vector Machine, Wavelet, Empirical Mode Decomposition

References
[1] GUO H B, HUANG S J, Air pollutants and asthma patient visits: indication of source influence. SCI TOTAL ENVIRON, 2018, 625: 355-362.
[2] YU Y J, YU Z L, SUN P, et al. Effects of ambient air pollution from municipal solid waste landfill on children's non-specific immunity and respiratory health. Environmental Pollution, 2018, 236: 382-390.
[3] ZHAO Y, DUAN L, XING J, et al. Soil acidification in China: Is controlling SO2 emissions enough?. ENVIRON SCI TECH LET, 2009, 43(21): 8021-8026.
[4] LIU Y Y, XU X Y, HEN Y, et al. An integrated micro-chip with Ru/Al2O3 /ZnO as sensing material for SO2 detection. SENSOR ACTUAT B-CHEM, 2018, 262: 26-34.
[5] LIU W Q, CUI Z C, LIU J G, et al. Measurement of atmospheric trace gases by spectroscopic and chemical techniques. Chinese Journal of Quantum Electronics, 2004, 21(2): 202-210.
[6] QI J, DONG X P, ZHENG J D, et al. An algorithm of filtering background noise of optical fiber gas senor. Chinese Journal of Lasers, 2011, 38(11): 195-200.
[7] WANG Y T, WANG Y T. Research on de-noising of fluorescence detecting signal based on wavelet transform. Metrology& Measurement Technique, 2009, 36(01): 1-2, 5.
[8] BIAN H L, CHEN G F. Anti-aliasing algorithm of nonstationary harmonic signal measurement based on interpolation in frequency domain using short time Fourier transform. Chinese Journal of Scientific Instrument, 2008, 29(2): 284-288.
[9] WANG S T, LI M M, LI P, et al. Signal processing method based on empirical mode decomposition in the SO2 concentration monitoring. Acta Optica Sinica, 2014, 43(02): 14-19.
[10] ZHAO X M, Patel T H, ZUO M J. Multivariate EMD and full spectrum based condition monitoring for rotating machinery. Mechanical Systems and Signal Processing, 2012, 27(1): 712-728.
[11] ZHU B Z, HAN D, WANG P, et al. Forecasting carbon price using empirical mode decomposition and evolutionary least squares support vector regression. Applied Energy, 2017, 191:521-530.
[12] HAO Z, ZHAO H L, ZHANG C, et al. Estimating winter wheat area based on an SVM and the variable fuzzy set method. REMOTE SENSING LETTERS, 2019, 10(4): 343-352.
[13] PEND H B, CHEN G H, CHEN X X, et al. Hybrid classification of coal and biomass by laser-induced breakdown spectroscopy combined with K-means and SVM. PLASMA SCIENCE & TECHNOLOGY, 2019, 21(3): UNSP 034008.
[14] RAPUR J. S., TIWARI, R.. On-line Time Domain Vibration and Current Signals Based Multi-fault Diagnosis of Centrifugal Pumps Using Support Vector Machines. JOURNAL OF NONDESTRUCTIVE EVALUATION, 2019, 38(1): 6.
[15] BAHRAM C. B., Moradi Ehsan, Golshan Mohammad, et al. An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines. SCI TOTAL ENVIRON, 2019, 651: 2087-2096.
[16] ZHOU Y. L., CHANG F. J., CHANG L. C, et al. Multi-output support vector machine for regional multi-step-ahead PM2.5 forecasting. SCI TOTAL ENVIRON, 2019, 651: 230-240.
[17] LI C B, LIN S S, XU F Q, et al. Short-term wind power prediction based on data mining technology and improved support vector machine method: A case study in Northwest China. JOURNAL OF CLEANER PRODUCTION, 2018, 205: 909-922.
[18] Fabelo Himar, Ortega Samuel, Casselden Elizabeth, et al. SVM Optimization for Brain Tumor Identification Using Infrared Spectroscopic Samples. Sensors (Basel, Switzerland), 2018, 18(12).
[19] ROUTRAY S, Ray A K, Mishra C, et al.. Efficient hybrid image denoising scheme based on SVM classification [J]. Optik-International Journal for Light and Electron Optics, 2018, 157: 503-511.
[20] SHAHDOOSTI H R, HAZAVEI S M. Combined rippled and total variation image denoising methods using twin support vector machines [J]. Multimedia Tools & Applications, 2017, 12: 1-19.
[21] CHEN C Y, LIN M L, ZHANG J. Study on signal filtering based on support vector machine [J]. Journal of Xi’an Jiaotong University, 2006, 40(4): 427-431.
[22] JI Q C, LUO X H. Filter design and hardware implementation based on SVM [J]. Transducer and Microsystem Technologies, 2018, 37(03): 95-98, 102.
[23] VAPNIK V. The Nature of Statistical Learning Theory [M]. New York: Springer-Verlag, 1995.
[24] SMOLA A J, SCHOLKOPF B. A tutorial on support vector regression [J]. Statistics and Computing, 2004, 14(3): 199-222.
[25] KEERTHI S S, LIN C J. Asymptotic behaviors of support vector machines with Gaussian kernel [J]. Neural Computation, 2003, 15(7): 1667-1689.
[26] LI H, LIN Q Z, WANG Q J, et al. Research on spectrum denoising methods based on the combination of wavelet package transformation and mathematical morphology [J]. Spectroscopy and Spectral Analysis, 2010, 30(3): 644-648.
Author Information
  • Institute of Electrical Engineering, Yanshan University, Qinhuangdao, China

  • Institute of Electrical Engineering, Yanshan University, Qinhuangdao, China

Cite This Article
  • APA Style

    Zhifang Wang, Shutao Wang. (2019). Sulfur Dioxide Detection Signal Denoising Based on Support Vector Machine. Journal of Energy, Environmental & Chemical Engineering, 3(4), 54-60. https://doi.org/10.11648/j.jeece.20180304.11

    Copy | Download

    ACS Style

    Zhifang Wang; Shutao Wang. Sulfur Dioxide Detection Signal Denoising Based on Support Vector Machine. J. Energy Environ. Chem. Eng. 2019, 3(4), 54-60. doi: 10.11648/j.jeece.20180304.11

    Copy | Download

    AMA Style

    Zhifang Wang, Shutao Wang. Sulfur Dioxide Detection Signal Denoising Based on Support Vector Machine. J Energy Environ Chem Eng. 2019;3(4):54-60. doi: 10.11648/j.jeece.20180304.11

    Copy | Download

  • @article{10.11648/j.jeece.20180304.11,
      author = {Zhifang Wang and Shutao Wang},
      title = {Sulfur Dioxide Detection Signal Denoising Based on Support Vector Machine},
      journal = {Journal of Energy, Environmental & Chemical Engineering},
      volume = {3},
      number = {4},
      pages = {54-60},
      doi = {10.11648/j.jeece.20180304.11},
      url = {https://doi.org/10.11648/j.jeece.20180304.11},
      eprint = {https://download.sciencepg.com/pdf/10.11648.j.jeece.20180304.11},
      abstract = {A system for detecting sulfur dioxide (SO2) based on differential optical absorption spectrometry theory was studied. The detection system can eliminate the noise from light source and light path by using the double optical path. Background noise was generated by the photoelectric device. It also effects the quantitative analysis. The Support Vector Machine (SVM) is proposed to process the SO2 ultraviolet absorption spectrum. The SO2 ultraviolet absorption spectra at 220nm-340nm were obtained by using the SO2 detection system in this article. Then the spectral was denoised by the SVM. The experimental results showed that the absorption line was more smoothness after denoising by the SVM, and the SNR and mean square error were 48.9398 and 1×10-7, respectively. The de-noising data was applied to the SO2 detection system, the linearity of the measurement was good with the coefficients of more than 0.9971. Compare the result with the wavelet and Empirical Mode Decomposition (EMD) denoising methods, which illustrates that SVM has better effects. It shows that the SVM method applied to noise reduction of SO2 detection system is superior.},
     year = {2019}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - Sulfur Dioxide Detection Signal Denoising Based on Support Vector Machine
    AU  - Zhifang Wang
    AU  - Shutao Wang
    Y1  - 2019/03/19
    PY  - 2019
    N1  - https://doi.org/10.11648/j.jeece.20180304.11
    DO  - 10.11648/j.jeece.20180304.11
    T2  - Journal of Energy, Environmental & Chemical Engineering
    JF  - Journal of Energy, Environmental & Chemical Engineering
    JO  - Journal of Energy, Environmental & Chemical Engineering
    SP  - 54
    EP  - 60
    PB  - Science Publishing Group
    SN  - 2637-434X
    UR  - https://doi.org/10.11648/j.jeece.20180304.11
    AB  - A system for detecting sulfur dioxide (SO2) based on differential optical absorption spectrometry theory was studied. The detection system can eliminate the noise from light source and light path by using the double optical path. Background noise was generated by the photoelectric device. It also effects the quantitative analysis. The Support Vector Machine (SVM) is proposed to process the SO2 ultraviolet absorption spectrum. The SO2 ultraviolet absorption spectra at 220nm-340nm were obtained by using the SO2 detection system in this article. Then the spectral was denoised by the SVM. The experimental results showed that the absorption line was more smoothness after denoising by the SVM, and the SNR and mean square error were 48.9398 and 1×10-7, respectively. The de-noising data was applied to the SO2 detection system, the linearity of the measurement was good with the coefficients of more than 0.9971. Compare the result with the wavelet and Empirical Mode Decomposition (EMD) denoising methods, which illustrates that SVM has better effects. It shows that the SVM method applied to noise reduction of SO2 detection system is superior.
    VL  - 3
    IS  - 4
    ER  - 

    Copy | Download

  • Sections