AccScience Publishing / AJWEP / Volume 19 / Issue 5 / DOI: 10.3233/AJW220075
RESEARCH ARTICLE

Multi Kernel Support Vector Machine for Particulate Matter Estimation

Deepak Gaur1* Deepti Mehrotra2 Karan Singh2
Show Less
1 Amity School of Engineering & Technology, Amity University, Noida, UP, India
2 School of Computer & Systems Sciences, Jawaharlal Nehru University, New Delhi, India
AJWEP 2022, 19(5), 89–95; https://doi.org/10.3233/AJW220075
Submitted: 17 January 2020 | Revised: 4 April 2022 | Accepted: 4 April 2022 | Published: 16 September 2022
© 2022 by the Author(s). This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution -Noncommercial 4.0 International License (CC-by the license) ( https://creativecommons.org/licenses/by-nc/4.0/ )
Abstract

The presence of particulate matter, in the atmospheric environment, affects the health of living creatures  as well as the ecosystem. Estimation of particulate matter has become one of the most challenging study for  researchers. There are numerous computer techniques for the estimation of these particles. In this study, a multi  kernel support vector machine (M-SVM) approach is introduced for the categorisation of particulate matter captured  as digital images. Images from the archive of many outdoor scene (AMOS) have been taken for implementation  purpose. The model is trained to predict the level of particulate matter captured as a digital image. An experimental  model with M-SVM classification predicts the particulate matter captured as image among three levels, i.e., whether  an image has a normal level, critical level or highly critical level. Simulated results were found to analyse the  particulate matter with 98% of accuracy, which ensures efficient recognition of our experimental method

Keywords
Particulate matter (PM)
multi kernel support vector machine (M-SVM)
image processing
archive of many outdoor scenes (AMOS) data set
Conflict of interest
The authors declare they have no competing interests.
References

Aiolli, F. and A. Sperduti (2005). Multiclass classification  with multi-prototype support vector machines. Journal of  Machine Learning Research. 6: 817-850.

Al-Yaseen, W.L., Zulaiha A.O. and M.Z.A. Nazri (2017).  Multi-level hybrid support vector machine and extreme  learning machine based on modified K-Means for intrusion  detection system. Expert Systems with Applications, 67: 296-303.

Azid, A., et al. (2018). Assessing indoor air quality using  chemometric models. Polish Journal of Environmental  Studies, 27(6): 2443-2450.

Batuwita, R. and V. Palade (2013). Class Imbalance Learning  Methods for Support Vector Machines. In: Imbalanced  Learning: Foundations, Algorithms and Applications.  Chapter 5, IEEE, pp. 83-99.

Bo, Q., et al. (2018). Particle Pollution Estimation from  Images Using Convolutional Neural Network and Weather  Features. In: Proceedings - International Conference on  Image Processing, ICIP, pp. 3433-3437.

Chen, X., Yaru L. and D. Li (2016). An efficient method for  air quality evaluation via ANN-based image recognition.  Presented at the 2nd International Conference on Artificial  Intelligence and Industrial Engineering (AIIE2016).  Advances in Intelligent System Research, 133: 253-256.

Dong, C., Loy, C.C., He, K. and X. Tang (2016). Image  super-resolution using deep convolutional networks.  IEEE Transactions on Pattern Analysis and Machine  Intelligence, 38(2): 295-307.

Farahmand, A., Abdolhossein S. and J. Shanbehzadeh  (2013). Document Image Noises and Removal Methods.  Proceedings of the International Multi-Conference of  Engineers and Computer Scientists 2013 (IMECS 2013),  Hong Kong, Vol. I. 

Gaur, D., Mehrotra, D. and K. Singh (2020). Particulate  Matter Estimation Based on Haze Degree Factor. In: Pant,  M., Sharma, T., Verma, O., Singla, R. and A. Sikander  (eds). Soft Computing: Theories and Applications.  Advances in Intelligent Systems and Computing, 1053:  769-779. Springer, Singapore. https://doi.org/10.1007/978- 981-15-0751-9_70

Gu, K., Qiao, J. and X. Li (2019). Highly efficient  picture-based prediction of PM2.5 concentration. IEEE  Transactions on Industrial Electronics, 6(4): 3176-3184.

He, K., Sun, J. and X. Tang (2013). Guided image filtering.  IEEE Transactions on Pattern Analysis and Machine  Intelligence, 35(6): 1397-1409.Hsu, Chih-Wei, Chih-Chung Chang and Chih-Jen Lin (2003).  A practical guide to support vector classification. pp. 1396- 1400. http://www.datascienceassn.org

Kim, S.H., et al. (2019). Vision-based deep Q-learning  network models to predict particulate matter concentration  levels using temporal digital image data. Journal of  Sensors, 2019: 9673047.

Liu, C., Tsow, F., Zou, Y. and N. Tao (2016). Particle pollution  estimation based on image analysis. PLoS ONE, 11(2): e0145955.

O’Sullivan, J.D., Stylianou, A., Abrams, A. and R. Pless  (2015). Democratizing the Visualization of 500 Million  Webcam Images. In: Proceedings - Applied Imagery  Pattern Recognition Workshop, pp. 1-5.

Peiris, R.H., Budman, H., Moresoli, C. and R.L. Legge  (2010). Understanding fouling behaviour of ultrafiltration  membrane processes and natural water using principal  component analysis of fluorescence excitation-emission  matrices. Journal of Membrane Science, 357(1-2): 62-72.

Pharr, M. and G. Humphreys (2004). Sampling and  Reconstruction. In: Physically Based Rendering: From  Theory to Implementation. Chapter 7. Morgan Kauffmann  Publishers.

Rebentrost, P., Masoud, M. and S. Lloyd (2014). Quantum  support vector machine for big data classification. Physical  Review Letters, 113: 130503.

Rijal, N., et al. (2018). Ensemble of Deep Neural Networks  for Estimating Particulate Matter from Images. In: 2018  3rd IEEE International Conference on Image, Vision and  Computing, ICIVC 2018. pp. 733-738.

Shad, R., Mesgari, M.S., Abkar, A. and A. Shad (2009).  Predicting air pollution using fuzzy genetic linear  membership kriging in GIS. Computers, Environment and  Urban Systems, 33(6): 472-481.

Smith, K., et al. (2015). CIDRE: An illumination-correction  method for optical microscopy. Nature Methods, 12(5): 404-406.

Thurston, G.D., Ito, K. and R. Lall (2011). A source  apportionment of U.S. fine particulate matter air pollution.  Atmospheric Environment, 45(24): 3924-3946.

Troscianko, J. and M. Stevens (2015). Image calibration and  analysis toolbox -A free software suite for objectively  measuring reflectance, colour and pattern. Methods in  Ecology and Evolution, 6(11): 1320-1331.

Wang, Z. and X. Xue (2013). Multi-Class Support Vector  Machine. In: Support Vector Machines Applications, pp.  23-48.

Weizhen, H., et al. (2014). Using support vector regression  to predict PM 10 and PM 2.5. In IOP Conference Series:  Earth and Environmental Science, 17: 012268.

Zhao, Y. and Y. Abu (2013). Fine particulate matter  concentration level prediction by using tree-based  ensemble classification algorithms. International Journal  of Advanced Computer Science and Applications, 4(5):  21-27.

Zaman, N.A.F.K., Kanniah, K.D. and D.G. Kaskaoutis (2017).  Estimating particulate matter using satellite based aerosol  optical depth and meteorological variables in Malaysia.  Atmospheric Research, 193: 142-162.

Share
Back to top
Asian Journal of Water, Environment and Pollution, Electronic ISSN: 1875-8568 Print ISSN: 0972-9860, Published by AccScience Publishing