K En Yakın Komşular Tabanlı Sıvı Sınıflandırması İçin Yansıma Katsayıları ve Parametrelerin Etkilerinin Değerlendirilmesi

Öz

Bu çalışmada sıvı ölçümlerinde mikrodalga spektroskopi yöntemi kullanılmış ve sıvıların sınıflandırılmasında K en yakın komşular algoritması kullanılmıştır. Bu amaçla, öncelikle sınıflandırma deneylerinde kullanılan her bir sıvının yansıma parametresini ölçmek için bir vektör ağ analizörü, bir yama anteni ve bir şişeden oluşan deney düzeneği oluşturulmuştur. Bu çalışmanın amacı, hem önerilen sistemle alınan ölçümleri etkileyebilecek parametreleri hem de sıvıların sınıflandırılmasında performansı etkileyebilecek algoritma parametrelerini ve bu parametrelerin etkilerini incelemektir. Sıvıların antene olan mesafesinin ölçüm sonucunu etkileyip etkilemediğini, etkiliyorsa etkisini incelemek için anten ile sıvı arasında farklı mesafeler bırakılarak ölçümler yapılmıştır. Sınıflandırmayı etkileyebilecek en yakın komşu algoritmasının parametrelerini incelemek için, yama anten kullanılarak ölçülen farklı sıvıların saçılma parametreleri mikrodalga veri seti olarak kullanılmıştır. Ayrıca kap tipinin etkisi analiz edilmiştir. Farklı sayıda en yakın komşu ve farklı mesafe ölçütleri kullanıldığında doğruluk oranı ölçülerek ağırlıklandırılarak ve algoritma ağırlıklandırılmadan performans testleri yapılmıştır. Sonuçlar, ağırlıklandırma uygulanarak yapılan sınıflandırmanın, en yakın komşu sayısına ve kullanılan uzaklık ölçütlerine bakılmaksızın ağırlıklandırma yapılmadan yapılan sınıflandırmaya göre daha başarılı olduğunu ortaya koymaktadır.

Anahtar Kelimeler

• Mikrodalga ölçümü
• dairesel yama anten
• K en yakın komşu algoritması
• sıvı sınıflandırması
• mesafe ölçüsü
• ağırlıklandırma
• en yakın komşu sayısı

Analysis of the Parameters that Affect the Measurements of Reflection Coefficients and Evaluation of the Effects of Parameters for K Nearest Neighbors-Based Liquid Classification

Öz

In this study, microwave spectroscopy method has been used in liquid measurements and K nearest neighbors algorithm has been used for classifying liquids. For this aim, firstly an experimental setup consisting of a vector network analyzer, a patch antenna and a bottle have been built to measure the reflection parameter of each liquid used in classification experiments. The aim of this study is to examine both the parameters that may affect the measurements taken with the proposed system and the algorithm parameters that may affect the performance in the classification of liquids and the effects of these parameters. Measurements have been taken by leaving different distances between the antenna and the liquid in order to examine whether the distance of the liquids to the antenna affects the measurement result, and if so, what effect. For examining the parameters of K nearest neighbors algorithm that may affect the classification, the scattering parameters of different liquids measured using the patch antenna have been used as microwave dataset. In addition, the effect of container type has been analyzed. Performance tests have been conducted by weighting and without weighting the algorithm, by measuring the accuracy rate when different numbers of nearest neighbors and different distance metrics have been used. The results reveal that the classification made by applying weighting is more successful than the classification made without weighting regardless of the number of nearest neighbors and used distance metrics.

Anahtar Kelimeler

• Microwave measurement
• Circular patch antenna
• K nearest neighbors algorithm
• liquid classification
• distance metric
• weighting
• number of nearest neighbors

Kaynakça

1. Aydın, E. A., & Kaya Keleş, M. (2017). Breast cancer detection using K‐nearest neighbors data mining method obtained from the bow‐tie antenna dataset. International Journal of RF and Microwave Computer‐Aided Engineering, 27(6), e21098.
2. Bhatia, N. (2010). Survey of nearest neighbor techniques. arXiv preprint arXiv:1007.0085.
3. Borisov, V., & Karpenko, A. (2001). Using of the Michelson microwave interferometer for the measurement of permittivity of thin-layer materials. Russian journal of nondestructive testing, 37(8), 597-599.
4. Chakrabarti, S., Cox, E., Frank, E., Güting, R. H., Han, J., Jiang, X., . . . Neapolitan, R. E. (2008). Data mining: know it all: Morgan Kaufmann.
5. Chen, H., Hu, Z., Wang, P., Xu, W., & Hou, Y. (2020). Application of spectral droplet analysis method in flammable liquids identification. Paper presented at the 2019 International Conference on Optical Instruments and Technology: Optical Sensors and Applications.
6. Chen, Q., Kang, G., Zhou, T., & Wang, J. (2017). Fire hazard analysis of alcohol aqueous solution and Chinese liquor based on flash point. Paper presented at the IOP Conference Series: Materials Science and Engineering.
7. Cheremisinoff, N. P. (1999). Handbook of industrial toxicology and hazardous materials: CRC Press.
8. Chicco, D., & Jurman, G. (2020). The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation. BMC Genomics, 21, 6.

9. Doad, P., & Bartere, M. (2013). A Review: Study of Various Clustering Techniques. International Journal of Engineering Research & Technology, 2(11), 3141-3145.
10. Hayasaka, T., Lin, A., Copa, V. C., Lopez, L. P., Loberternos, R. A., Ballesteros, L. I. M., . . . Lin, L. (2020). An electronic nose using a single graphene FET and machine learning for water, methanol, and ethanol. Microsystems & Nanoengineering, 6(1), 1-13.
11. Jain, A. K., Duin, R. P. W., & Mao, J. (2000). Statistical pattern recognition: A review. IEEE Transactions on pattern analysis and machine intelligence, 22(1), 4-37.
12. Jawad, H., Lanteri, J., Migliaccio, C., Pichot, C., Platt, I. G., Tan, A. E.-C., . . . Woodhead, I. M. (2017). Microwave modeling and experiments for non destructive control improved quality of fruit. Paper presented at the 2017 IEEE Conference on Antenna Measurements & Applications (CAMA).
13. Jepsen, P. U., Jensen, J. K., & Møller, U. (2008). Characterization of aqueous alcohol solutions in bottles with THz reflection spectroscopy. Optics express, 16(13), 9318-9331.
14. Jiang, Y., Ju, Y., & Yang, L. (2016). Nondestructive in-situ permittivity measurement of liquid within a bottle using an open-ended microwave waveguide. Journal of Nondestructive Evaluation, 35(1), 7.
15. Jose, K., Varadan, V., & Varadan, V. (2001). Wideband and noncontact characterization of the complex permittivity of liquids. Microwave and Optical Technology Letters, 30(2), 75-79.
16. Kresse, W., & Danko, D. M. (2012). Springer handbook of geographic information: Springer Science & Business Media.
17. Larose, D. T., & Larose, C. D. (2014). Discovering knowledge in data: an introduction to data mining (Vol. 4): John Wiley & Sons.
18. Li, Z., Haigh, A., Soutis, C., Gibson, A., & Sloan, R. (2017a). Evaluation of water content in honey using microwave transmission line technique. Journal of Food Engineering, 215, 113-125.
19. Li, Z., Haigh, A., Soutis, C., Gibson, A., & Sloan, R. (2017b). Microwaves sensor for wind turbine blade inspection. Applied Composite Materials, 24(2), 495-512.
20. Li, Z., Haigh, A., Soutis, C., Gibson, A., & Sloan, R. (2018). A simulation-assisted non-destructive approach for permittivity measurement using an open-ended microwave Waveguide. Journal of Nondestructive Evaluation, 37(3), 1-10.
21. Moghadas, H., & Mushahwar, V. K. (2018). Passive microwave resonant sensor for detection of deep tissue injuries. Sensors and Actuators B: Chemical, 277, 69-77.
22. Orachorn, P., Chankow, N., & Srisatit, S. (2019). An Alternative Method for Screening Liquid in Bottles at Airports Using Low Energy X-ray Transmission Technique. Radiation environment and medicine: covering a broad scope of topics relevant to environmental and medical radiation research, 8(2), 77-84.
23. Rey, T., Kordon, A., & Wells, C. (2012). Applied data mining for forecasting using SAS: SAS Institute.
24. Saçlı, B., Aydınalp, C., Cansız, G., Joof, S., Yilmaz, T., Çayören, M., . . . Akduman, I. (2019). Microwave dielectric property based classification of renal calculi: Application of a kNN algorithm. Computers in biology and medicine, 112, 103366.
25. Slaughter, R., Mason, R., Beasley, D., Vale, J., & Schep, L. (2014). Isopropanol poisoning. Clinical toxicology, 52(5), 470-478.
26. Tan, X., Huang, S., Zhong, Y., Yuan, H., Zhou, Y., Xiao, Q., . . . Qi, C. (2017). Detection and identification of flammable and explosive liquids using THz time-domain spectroscopy with principal component analysis algorithm. Paper presented at the 2017 10th UK-Europe-China Workshop on Millimetre Waves and Terahertz Technologies (UCMMT).
27. Venkatesh, M., & Raghavan, G. (2005). An overview of dielectric properties measuring techniques. Canadian biosystems engineering, 47(7), 15-30.
28. Wirasuta, I. M. A. G., Dewi, N. K. S. M., Purwaningsih, N. K. P. A., Heltyani, W. E., Aryani, N. L. P. I., Sari, N. M. K., . . . Ramona, Y. (2019). A rapid method for screening and determination test of methanol content in ethanol-based products using portable Raman spectroscopy. Forensic Chemistry, 16, 100190.
29. Yurchenko, A. V., Novikov, A., & Kitaeva, M. V. (2012). A resonator microwave sensor for measuring the parameters of Solar-quality silicon. Russian journal of nondestructive testing, 48(2), 109-114.