Effect of Different Kernel Functions on Hazardous Liquid Detection Using a Patch Antenna and Support Vector Machines

Abstract

Microwave spectroscopy method has become widespread in many applications including liquid classification. In this study, a microwave spectroscopy system that can classify liquids without opening the lid of their containers is proposed. Thus, the operators are prevented from being exposed to harmful substances and wasting time. Everyday liquids such as carbonated drinks, fruit juices, shampoo, cream and alcoholic beverages and hazardous liquids were characterized remotely by the microwave spectroscopy method in which spectroscopic signatures of a total of 52 liquids were used. In order to be able to classify liquids with the highest accuracy, it is also important to determine the most suitable measurement system as well as the correct selection of the classification algorithm and algorithm parameters that show the best performance. In this study, Support Vector Machines algorithm, which is a very successful algorithm in separating binary classes, is used. In addition, the effects of the algorithm on the classification performance have been examined using different kernel functions and cross-validation technique has been used for the performance analysis. As a result of the performance analysis, it is seen that up to 100% success can be achieved when linear or polynomial kernel functions have been preferred.

Keywords

• Hazardous liquids
• Microwave spectroscopy
• Support Vector Machines
• Kernel functions
• Accuracy

References

1. W. Luo, Z. Zhang, H. Liu, C. Zhang. “Terahertz reflection time-domain spectroscopy for measuring alcohol concentration.” Infrared, Millimeter- Wave, and Terahertz Technologies V, International Society for Optics and Photonics, 2018, pp. 1082615. doi:10.1117/12.2500966
2. X. Tan, S. Huang, Y. Zhong, H. Yuan, Y. Zhou, Q. Xiao, L. Guo, S. Tang, Z. Yang, C. Qi. “Detection and identification of flammable and explosive liquids using THz time-domain spectroscopy with principal component analysis algorithm.” 2017 10th UK-Europe-China Workshop on Millimetre Waves and Terahertz Technologies UCMMT , IEEE, 2017, pp. 1-4. doi:10.1109/UCMMT.2017.8068488
3. X. Tan, S. Tang, Z. Yang, J. Xie, J. Tang, F. Xie, C. Qi. “ Detection and identification of liquids using reflection THz time-domain spectroscopy with principal component analysis and support vector machine algorithm.” International Symposium on Ultrafast Phenomena and Terahertz Waves, Optical Society of America, 2018, pp. WI27. doi:10.1364/ISUPTW.2018.WI27
4. W. Zhang, Y. Tang, A. Shi, L. Bao, Y. Shen, R. Shen, Y. Ye. “ Recent developments in spectroscopic techniques for the detection of explosives.” Materials, 11 2018 1364. doi:10.3390/ma11081364
5. M.F. Isaac-Lam. “ Incorporation of Benchtop NMR Spectrometer into the Organic Chemistry Laboratory: Analysis of an Unknown Liquid.” Journal of Chemical Education, 97 2020, pp. 2036-2040. doi:10.1021/acs.jchemed.9b00787
6. E. Gudmundson, A. Jakobsson, I.J. Poplett, J.A. Smith. “ Detection and classification of liquid explosives using NMR.” 2009 IEEE International Conference on Acoustics, Speech and Signal Processing, IEEE, 2009, pp. 3053-3056.
7. M.L. Ramírez-Cedeño, W. Ortiz- Rivera, L.C. Pacheco-Londoño, S.P. Hernández-Rivera. “Remote detection of hazardous liquids concealed in glass and plastic containers.” IEEE Sensors Journal, 10, 2010, pp 693-698. doi:10.1109/JSEN.2009.2036373
8. P. Orachorn, N. Chankow, S. Srisatit. “Development of technique for screening liquids in glass bottle using low energy X-ray transmission.” RMUTT Research Journal Rajamangala University of Technology Thanyaburi, 16, 2017, pp 20-26.

9. S.I.Y. Al-Mously. “ A modified complex permittivity measurement technique at microwave frequency.” International Journal of New Computer Architectures and Their Applications, 2, 2012, pp 389-402.
10. Z. Li, A. Haigh, C. Soutis, A. Gibson, R. Sloan. “A simulation-assisted non- destructive approach for permittivity measurement using an open-ended microwave Waveguide.” Journal of Nondestructive Evaluation, 37, 2018, 39. doi:10.1007/s10921-018-0493-1
11. R.V. Shinde, A.R. Deshmukh, S.A. Ingole, A.C. Kumbharkhane. “Dielectric spectroscopy and hydrogen bonding studies of 1-chloropropane– ethanol mixture using TDR technique, Journal of Advanced Dielectrics.” 9, 2019, 1950018. doi:10.1142/S2010135X19500188
12. V. Gaiduk, S. Nikitov. “Possible mechanisms of dielectric relaxation of liquid water and calculation of the temperature dependence of the complex permittivity of water.” Optics and Spectroscopy, 98, 2005, pp 919-933. doi:10.1134/1.1953988
13. V. Gaĭduk. “Relations between the association of liquid water molecules and the dielectric and raman spectra of H 2 O.” Optics and Spectroscopy, 106, 2009, 24-42. doi:10.1134/S0030400X09010044
14. G. Gennarelli, S. Romeo, M.R. Scarfì, F. Soldovieri. “A microwave resonant sensor for concentration measurements of liquid solutions.” IEEE Sensors Journal, 13, 2013 pp 1857-1864. doi:10.1109/JSEN.2013.2244035
15. M.A. Sairin, N.H. Abd Latiff, S. Abd Aziz, F.Z. Rokhani. “Distinguishing edible oil using dielectric spectroscopy at microwave frequencies of 8.2–12.1 GHz.” 2016 10th International Conference o n Sensing Technology ICST , IEEE, 2016, pp. 1-4. doi:10.1109/ICSensT.2016.7796333
16. L. Zhang, M.A. Schultz, R. Cash, D.M. Barrett, M.J. McCarthy. “Determination of quality parameters of t omato paste using guided microwave spectroscopy.” Food control, 40, 2014, pp 214-223. doi:10.1016/j.foodcont.2013.12.008
17. A.V. Yurchenko, A. Novikov, M.V. Kitaeva. “A resonator microwave sensor for measuring the parameters of Solar-quality silicon.” Russian Journal of Nondestructive Testing, 48, 2012, pp 109-114. doi:10.1134/S1061830912020118
18. A. La Gioia, E. Porter, I. Merunka, A. Shahzad, S. Salahuddin, M. Jones, M. O’Halloran. “Open-ended coaxial probe technique for dielectric measurement of biological tissues: Challenges and common practices.” Diagnostics, 8, 2018, 40. doi:10.3390/diagnostics8020040
19. P. Hamsagayathri, P. Sampath. “Microwave Breast Cancer Screening for Women Welfare, Indian Journal of Public Health Research & Development.” 8, 2017, pp 115-121.
20. R. Wellock, A.D. Walmsley. “Applications of microwave spectroscopy in process analysis.” Spectroscopy Europe, 16, 2004, pp 23- 26.
21. P. Singh, S. Bhamidipati, R. Singh, R. Smith, P. Nelson. “Evaluation of in-line sensors for prediction of soluble and total solids/moisture in continuous processing of fruit juices.” Food Control, 7, 1996, pp 141-148. doi:10.1016/0956-7135 96 00020-5
22. C. Cortes, V. Vapnik, Support-vector networks. “Machine learning.” 20, 1995, pp 273-297.
23. G.M. Foody, A. Mathur. “Toward intelligent training of supervised image classifications: directing training data acquisition for SVM classification.” Remote Sensing of Environment, 93, 2004, pp 107-117.
24. D.D. Gutierrez. “Machine learning and data science: an introduction to statistical learning methods with R.” Technics Publications, 2015. doi:10.1109/ICASSP.2009.4960268
25. E.E. Osuna. “Support vector machines: Training and applications.” Massachusetts Institute of Technology, 1998.
26. Z. Liu, M.J. Zuo, X. Zhao, H. Xu, An. “Analytical Approach to Fast Parameter Selection of Gaussian RBF Kernel for Support Vector Machine.” J. Inf. Sci. Eng., 31, 2015, pp 691-710.
27. T. Kavzoglu, I. Colkesen. “A kernel functions analysis for support vector machines for land cover classification, International Journal of Applied Earth Observation and Geoinformation.” 11, 2009, pp 352-359. doi:10.1016/j.jag.2009.06.002