Journals / Türk Uzaktan Algılama ve CBS Dergisi / 2023 / Cilt: 4 Sayı: 2

Kernel Extreme Learning Machine for Hyperspectral Image Classification

Çekirdek Tabanlı Aşırı Öğrenme Makinesi ile Hiperspektral Görüntü Sınıflandırma

Pages
198–212
Publication Date
2023-09-28
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Highest classification accuracies were achieved by support vector machines with overall accuracies of 91,64% and 83,45% for the original dataset and dimensionality reduction applied data, respectively.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Hyperspectral images have been actively used in many real-life applications, primarily in remote sensing, since it provides detailed and rich spectral information.
📊
Key Findings & Data:In this study, the ability of kernel extreme learning machine for the classification of hyperspectral image was investigated and the classification performance was compared with two machine learning algorithms (support vector machines and random forest). “Indian Pines” hyperspectral dataset was used in this experimental study and there are 16 land cover classes in the study area.
💡
Conclusion & Impact:Highest classification accuracies were achieved by support vector machines with overall accuracies of 91,64% and 83,45% for the original dataset and dimensionality reduction applied data, respectively.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Uzaktan algılama · Aşırı öğrenme makinesi · Hiperspektral

Abstract

Hyperspectral images have been actively used in many real-life applications, primarily in remote sensing, since it provides detailed and rich spectral information. There are several challenges in hyperspectral image classification because of the high spectral dimension and the complex structure and hence the advanced classification algorithms (ensemble learning and kernel-based methods) are usually preferred. In this study, the ability of kernel extreme learning machine for the classification of hyperspectral image was investigated and the classification performance was compared with two machine learning algorithms (support vector machines and random forest). “Indian Pines” hyperspectral dataset was used in this experimental study and there are 16 land cover classes in the study area. The principal component analysis was used for the dimensionality reduction and first 40 principal components were selected. The classification was performed for both original dataset and dimensionality reduction applied data. Highest classification accuracies were achieved by support vector machines with overall accuracies of 91,64% and 83,45% for the original dataset and dimensionality reduction applied data, respectively. Furthermore, the original data achieved higher performance with respect to dimensionality reduction applied data in terms of overall accuracy for all methods.

Özet

Hiperspektral görüntüler, zengin spektral bilgi içerdiklerinden dolayı uzaktan algılama başta olmak üzere birçok alanda etkin bir şekilde kullanılmaktadır. Yüksek spektral boyutu ve karmaşık yapılarından dolayı, hiperspektral görüntülerin sınıflandırılmasında bazı sıkıntılar yaşanmaktadır ve bu nedenle sınıflandırma işlemlerinde ileri düzey algoritmalar (topluluk öğrenme algoritmaları, çekirdek tabanlı yöntemler vb.) tercih edilmektedir. Bu çalışma kapsamında, çekirdek tabanlı aşırı öğrenme makinesinin (ÇAÖM) hiperspektral görüntü sınıflandırmadaki kabiliyeti araştırılmış ve sınıflandırma performansı, iki farklı makine öğrenme algoritması (destek vektör makineleri ve rastgele orman) ile karşılaştırılmıştır. Çalışma kapsamında “Indian Pines” hiperspektral veri seti kullanılmıştır ve çalışma alanında 16 adet arazi örtüsü sınıfı bulunmaktadır. Boyut indirgeme amacıyla veriye temel bileşenler analizi yöntemi uygulanmıştır. Sınıflandırma işlemi hem orijinal hiperspektral verisine hem de temel bileşenler analizi ile boyutu indirgenmiş veriye uygulanmıştır. Boyut indirgeme işlemi sonucunda ilk 40 temel bileşen bant olarak seçilmiştir. En yüksek sınıflandırma doğrulukları hem orijinal veri seti için (%91,64) hem de boyutu indirgenmiş veri seti için (%83,45) DVM yöntemi ile elde edilmiştir. Ayrıca, orijinal veri setinin sınıflandırılması ile elde edilen doğrulukların boyutu indirgenmiş verinin sınıflandırması ile elde edilen doğruluklardan daha yüksek olduğu tespit edilmiştir.

🔖

Cite This Article

ÜSTÜNER, M. (2023). Kernel Extreme Learning Machine for Hyperspectral Image Classification. Türk Uzaktan Algılama ve CBS Dergisi, Cilt: 4 Sayı: 2, 198–212. https://ajindex.com/articles/963473

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (12)

  1. Adam, E., Mutanga, O., Odindi, J., & Abdel-Rahman, E. M. (2014). Land-use/cover classification in a heterogeneous coastal landscape using RapidEye imagery: evaluating the performance of random forest and support vector machines classifiers. International Journal of Remote Sensing, 35(10), 3440-3458.
  2. Akar, Ö., & Güngör, O. (2012). Classification of multispectral images using Random Forest Algorithm. Journal of Geodesy and Geoinformation, 1(2), 105-112.
  3. Baumgardner, M. F., Biehl, L. L., & Landgrebe, D. A. (2015). 220 band aviris hyperspectral image data set: June 12, 1992 Indian pine test site 3. Purdue University Research Repository, 10(7), 991. doi:/10, 4231, R7RX991C. Bazi, Y., & Melgani, F. (2006). Toward an optimal SVM classification system for hyperspectral remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 44(11), 3374-3385.
  4. Bazi, Y., Alajlan, N., Melgani, F., AlHichri, H., Malek, S., & Yager, R. R. (2014). Differential evolution extreme learning machine for the classification of hyperspectral images. IEEE Geoscience and Remote Sensing Letters, 11(6), 1066-1070.
  5. Belgiu, M., & Drăguţ, L. (2016). Random forest in remote sensing: A review of applications and future directions. ISPRS Journal of Photogrammetry and Remote Sensing, 114, 24-31.
  6. Bioucas-Dias, J. M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., & Chanussot, J. (2012). Hyperspectral unmixing overview: Geometrical, statistical, and sparse regression-based approaches. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(2), 354-379.
  7. Bioucas-Dias, J. M., Plaza, A., Camps-Valls, G., Scheunders, P., Nasrabadi, N., & Chanussot, J. (2013). Hyperspectral remote sensing data analysis and future challenges. IEEE Geoscience and Remote Sensing Magazine, 1(2), 6-36.
  8. Bilgin, G. (2009). Hiperspektral görüntülerin eğiticisiz bölütlenmesi (Doktora tezi). Yıldız Teknik Üniversitesi,
  9. İstanbul,
  10. Türkiye. Camps-Valls, G., Gómez-Chova, L., Calpe-Maravilla, J., Martín-Guerrero, J. D., Soria-Olivas, E., Alonso-Chordá, L., & Moreno, J. (2004). Robust support vector method for hyperspectral data classification and knowledge discovery. IEEE Transactions on Geoscience and Remote Sensing, 42(7), 1530-1542.
  11. Camps-Valls, G., & Bruzzone, L. (2005). Kernel-based methods for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 43(6), 1351-1362.
  12. Cao, F., Yang, Z., Ren, J., Chen, W., Han, G., & Shen, Y. (2019). Local block multilay