|Generate QR code
Open Access
Subscription Access
Application of Non-Negative Sparse Matrix Transformation in Hyperspectral Analysis
Abstract
A variety of pictures in hyperspectral fields requires a reduction in dimensionality, which often needs unique algorithms such as principal component analysis and minimum noise fraction (MNF). This article investigates the improved method of non-negative sparse matrix transformation based on the maximum likelihood covariance estimation and the Frobenius norm to better achieve dimensionality reduction. Non-negativity is presented based on the sparse matrix, which reduces the calculation time and improves efficiency. In order to verify the non-negative sparse matrix transforms (n-SMT) algorithm, samples eroded by disease were selected in the experiment and classified to identify the different parts of leaves after dimension reduction. Besides the n-SMT method, the MNF algorithm is also applied to all the samples. This article compares the two algorithms’ operating time and verifies the accuracy of classification after the n-SMT algorithm.
About the Authors
Z. Deng
Changchun University of Science and Technology, School of Optoelectronic Engineering
China
China
Changchun
Y. Fu
Changchun University of Science and Technology, School of Optoelectronic Engineering
China
China
Changchun
S. Zhao
Changchun University of Science and Technology, School of Optoelectronic Engineering
China
China
Changchun
Y. Gao
Changchun University of Science and Technology, School of Optoelectronic Engineering
China
China
Changchun
J. Cui
Changchun University of Science and Technology, School of Optoelectronic Engineering
China
China
Changchun
References
1. X. Jia, B. C. Kuo, M. M. Crawford, Proc. IEEE, 101, No. 3, 676–697 (2013).
2. D. Landgrebe, IEEE Signal Proc. Magazine, 19, No. 1, 17–28 (2002).
3. W. Jing, C. I. Chang, IEEE Trans. Geosci. Remote, 44, No. 6, 1586–1600 (2006).
4. M. Fauvel, Y. Tarabalka, J. A. Benediktsson, J. Chanussot, J. Tilton, Proc. IEEE, 101, No. 3, 652–675 (2013).
5. C. A. Manogue, T. Dray, Mod. Phys. Lett. A, 14, No. 2, 99–103 (2013).
6. D. Zhang, Y. Le Y, Int. Conf. Comput. Intelligence & Industrial Application (2010).
7. L. R. Bachega, C. A. Bouman, Int. Conf. Image Proc. IEEE (2010).
8. A. L. Bertozzi, A. Flenner, Multiscale Model Sim., 10, No. 3, 1090–1118 (2012).
9. J. Theiler, G. Cao, et al., IEEE J. Sel. Top. Signal Process, 5, No. 3, 424–437 (2011).
10. G. Cao, L. Bachega, et al., IEEE Trans. Image Process, 20, No. 3, 625–640 (2011).
11. N. Kochan, G. Y. Tütüncü, G. Giner, Expert Syst. Appl., 167, No. 3, 114200 (2020).
12. J. Fan, L. Yuan, An. Stat., 39, No. 6, 3320–3356 (2011).
13. D. D. Lee, H. S. Seung, et al., Nature, 401, 788–791 (1999).
14. P. O. Hoyer J Mach. Learn Res., 5, No. 9, 1457–1469 (2004).
15. A. Copar, M. Zitnik, B. Zupan, Biodata Min., 10, No. 1, 41 (2017).
16. Y. L. Xie, P. K. Hopke, P. Paatero, J. Chem., 12, No. 6, 357–364 (2015).
17. H. Zhi, X. Yu, G. Wang, Z. Wang, Fifth Int. Conf. Fuzzy System and Knowledge Discovery, FKSD 2008, IEEE, 4, 10–20, Jinan, Shandong, China (2008)
18. D. Bo, M. M. Lin, M. T. Chu, Numer. Algorithms, 65, No. 2, 251–274 (2014).
19. Y. Chen, A. Wiesel, A. O. I. Hero, IEEE Trans. Signal Process, 59, No. 9, 4097–4107 (2011).
20. M. Pal, G. Foody, IEEE Trans. Geosci. Remote, 48, No. 5, 2297–2307 (2010).
21. Z. Emre, E. Tülin, M. E. Karslgil, 13th European Signal Processing Conference IEEE (2015).
22. Y. Bazi, F. Melgani, IEEE Trans. Geosci. Remote, 44, No. 11, 3374–3385 (2003).
23. K. Hajian-Tilaki, Caspian J. Int. Med., 4, No. 2, 627–635 (2013).
24. S. D. Walter, State Med., 24, No. 13, 2025–2040 (2005).
Review
For citations:
Deng Z., Fu Y., Zhao S., Gao Y., Cui J. Application of Non-Negative Sparse Matrix Transformation in Hyperspectral Analysis. Zhurnal Prikladnoii Spektroskopii. 2022;89(3):436.
Views: 160
Email this article 