Makine Öğrenmesi Yöntemleri ile Tahıl Yüzey Sınıflaması

Year 2020, Ejosat Special Issue 2020 (ICCEES), 54 - 59, 05.10.2020

Huseyin Duysak , Umut Özkaya , Enes Yiğit

https://doi.org/10.31590/ejosat.802719

Cited By: 1

Abstract

Bu çalışmada buğday yüzey çeşitlerinin sınıflandırılması için radar yardımıyla elde edilen sinyaller makine öğrenmesi yöntemleri ile analizi gerçekleştirilmiştir. 18-40 GHz frekans arasında vektör ağ analizörü kullanılarak radar geri saçılım sinyalleri kaydedilmiştir. Toplamda 5681 adet A tarama sinyallerinin ölçümleri kaydedilmiştir. Önerilen yöntem çerçevesi iki bölümden oluşmaktadır. Birinci bölümde geri saçılım sinyalleri üzerinde Hızlı Fourier Dönüşümü (HFD), Ayrık Kosinüs Dönüşümü (AKD), Ayrık Dalgacık Dönüşümü (ADD) uygulanarak Birinci Derece İstatistiksel özellikler elde edilmiştir. Bu özellikler Destek Vektör Makinesi (DVM) ile sınıflandırma işlemi gerçekleştirilmiştir. Önerilen yöntemin ikinci bölümünde sinyaller üzerinde Kısa Zamanlı Fourier Dönüşümü (KZFD) uygulanarak karmaşık formda iki boyutlu matrisler elde edilmiştir. Bu matrislerin büyüklüğü baz alınarak özellik çıkarımı için Gri Değer Eş Oluşum Matrisi (GDEOM) ve Gri Değer Koşu Uzunluğu Matrisi (GDKUM) elde edilerek özellik çıkarım işlemi tamamlanmıştır. DVM ile sınıflandırma işlemi gerçekleştirilmiştir. 10-k çapraz doğruluma işlemi uygulanmıştır. En yüksek performans KZFD+ GDEOM+DVM ile elde edilmiştir.

Keywords

Radar, Ölçüm, Makine Öğrenimi, Sınıflama

Grain Surface Classification via Machine Learning Methods

Abstract

In this study, radar signals were analyzed to classify grain surface types by using machine learning methods. Radar backscatter signals were recorded using a vector network analyzer between 18-40 GHz. A total of 5681 measurements of A scan signals were collected. The proposed method framework consists of two parts. First Order Statistical features are obtained by applying Fast Fourier Transform (FFT), Discrete Cosine Transform (DCT), Discrete Wavelet Transform (DWT) on backscatter signals in the first part of the framework. Classification process of these features was carried out with Support Vector Machine (SVM). In the second part of the proposed framework, two dimensional matrices in complex form were obtained by applying Short Time Fourier Transform (STFT) on the signals. Gray-Level Co-Occurrence Matrix (GLCM) and Gray-Level Run-Length Matrix (GLRLM) were obtained and feature extraction process was completed. Classification process was carried out with DVM. 10-k cross validation was applied. The highest performance was achieved with STFT+GLCM+SVM.

Keywords

Radar, Measurement, Machine Learning, Classification

References

• H. Duysak and E. Yigit, “Machine learning based quantity measurement method for grain silos,” Measurement, vol. 152, p. 107279, 2020, doi: https://doi.org/10.1016/j.measurement.2019.107279.
• M. Vogt and M. Gerding, “Silo and Tank Vision: Applications, Challenges, and Technical Solutions for Radar Measurement of Liquids and Bulk Solids in Tanks and Silos,” IEEE Microwave Magazine, vol. 18, no. 6, pp. 38–51, 2017, doi: 10.1109/MMM.2017.2711978.
• A. P. Turner et al., “Stored Grain Volume MeasurementUsing a Low Density Point Cloud,” Applied Engineering in Agriculture, vol. 33, no. 1, pp. 105–112, Jan. 2017, doi: 10.13031/aea.11870.
• H. Duysak and E. Yiğit, “Level Measurement in Grain Silos with Extreme Learning Machine Algorithm,” in 2019 Scientific Meeting on Electrical-Electronics & Biomedical Engineering and Computer Science (EBBT), 2019, pp. 1–4, doi: 10.1109/EBBT.2019.8742047.
• E. Yigit, “A novel compressed sensing based quantity measurement method for grain silos,” Computers and Electronics in Agriculture, vol. 145, pp. 179–186, Feb. 2018, doi: 10.1016/j.compag.2017.12.041.
• Frigo, M. and S. G. Johnson, "FFTW: An Adaptive Software Architecture for the FFT,"Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, Vol. 3, 1998, pp. 1381-1384. [6]. Rader, C. M., "Discrete Fourier Transforms when the Number of Data Samples Is Prime,"Proceedings of the IEEE, Vol. 56, June 1968, pp. 1107-1108.
• Mei Jiansheng, Li Sukang. Tan Xiaomei,” A Digital Watermarking Algorithm Based On DCT and DWT”, Proceedings of the 2009 International Symposium on Web Information Systems and Applications (WISA’09) Nanchang, P. R. China, May 22-24, 2009, pp. 104-107.
• Nilanjan Dey, Tanmay Bhattacharya, S.R. Bhadra Chowdhury, “A Session based Multiple Image Hiding Technique using DWT and DCT”, International Journal of Computer Applications (0975 – 8887), Volume 38– No.5, January 2012.
• Fu, B., Mettel, M. R., Kirchbuchner, F., Braun, A., & Kuijper, A. (2018, November). Surface Acoustic Arrays to Analyze Human Activities in Smart Environments. In European Conference on Ambient Intelligence (pp. 115-130). Springer, Cham.
• R. M. Haralick, K. Shanmugam, and I. Dinstein,“Textural features for image classification”, IEEETrans. System Man. Cybernetics, vol. SMC-3, pp. 610–621, 1973.
• Rizk, Y., Mitri, N., & Awad, M. (2013, August). A local mixture based SVM for an efficient supervised binary classification. In IJCNN (pp. 1-8).