Advertisement

A novel technique to detect a suboptimal threshold of neighborhood rough sets for hyperspectral band selection

  • Barnali Barman
  • Swarnajyoti PatraEmail author
Methodologies and Application
  • 49 Downloads

Abstract

Neighborhood rough sets (NRS), an extension of rough sets, are widely used for feature selection. Although NRS have the advantage of dealing with the continuous data, success of the NRS-based feature selection techniques is strongly dependent on a predefined threshold value which determines the size of neighborhood granule. In this paper, we have proposed a novel technique to detect a suitable threshold of NRS for hyperspectral band selection. Our proposed technique analyzes the changes in boundary regions to select a suitable threshold value that keeps less uncertain boundary samples into positive region and more uncertain boundary samples into boundary region of the decision attribute. The effectiveness of the proposed technique is assessed by using different data sets.

Keywords

Feature selection Hyperspectral images Neighborhood rough sets Support vector machine 

Notes

Acknowledgements

The first named author is supported by University Grants Commission, New Delhi (Grant No. F./2015-16/NFO-2015-17-OBC-ASS-46084).

Compliance with ethical standards

Conflict of interest

The authors declare that there is no conflict of interests regarding the publication of this paper.

Informed consent

Consent to submit has been received explicitly from all co-authors, as well as from the responsible authorities tacitly or explicitly at the institute/organization where the work has been carried out before the work is submitted.

Research involving human participants and/or animals

Our research does not include human participants or animals.

References

  1. Cao X, Li X, Li Z, Jiao L (2017) Hyperspectral band selection with objective image quality assessment. Int J Remote Sens 38(12):3656–3668CrossRefGoogle Scholar
  2. Chang CC, Lin CJ (2012) Libsvm: a library for support vector machine. http://www.csie.ntu.edu.tw/~cjlin/libsvm
  3. Feng l, Tan AH, Lim MH, Jiang SW (2016) Band selection of hyperspectral images using probabilistic memetic algorithm. Soft Comput 20(12):4685–4693CrossRefGoogle Scholar
  4. Gu Y, Wang C, Wang S, Zhang Y (2011) Kernel-based regularized-angle spectral matching for target detection in hyperspectral imagery. Pattern Recognit Lett 32(2):114–119CrossRefGoogle Scholar
  5. Hu Q, Yu D, Liu J, Wu C (2008) Neighborhood rough set based heterogeneous feature subset selection. Inf Sci 178(18):3577–3594MathSciNetCrossRefzbMATHGoogle Scholar
  6. Liu L, Huang W, Wang C (2018) Hyperspectral image classification with kernel-based least-squares support vector machines in sum space. IEEE J Sel Top Appl Earth Obs Remote Sens 11(4):1144–1157CrossRefGoogle Scholar
  7. Liu Y, Chen Y, Tan K, Xie H, Wang L, Yan X, Xie W, Xu Z (2016a) Maximum relevance, minimum redundancy band selection based on neighborhood rough set for hyperspectral data classification. Meas Sci Technol 27(12):125,501CrossRefGoogle Scholar
  8. Liu Y, Xie H, Chen Y, Tan K, Wang L, Xie W (2016b) Neighborhood mutual information and its application on hyperspectral band selection for classification. Chemom Intell Lab 157:140–151CrossRefGoogle Scholar
  9. Liu Y, Xie H, Tan K, Chen Y, Xu Z, Wang L (2016c) Hyperspectral band selection based on consistency-measure of neighborhood rough set theory. Meas Sci Technol 27(5):55,501–55,514CrossRefGoogle Scholar
  10. Liu Y, Xie H, Wang L, Tan K (2016d) Hyperspectral band selection based on a variable precision neighborhood rough set. Appl Opt 55(3):462–472CrossRefGoogle Scholar
  11. Lu Z, Qin Z, Zhang Y, Fang J (2014) A fast feature selection approach based on rough set boundary regions. Pattern Recognit Lett 36:81–88CrossRefGoogle Scholar
  12. Meher SK (2015) Knowledge-encoded granular neural networks for hyperspectral remote sensing image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 8(6):2439–2446CrossRefGoogle Scholar
  13. Pan R, Wang X, Yi C, Zhang Z, Fan Y, Bao W (2017) Multi-objective optimization method for thresholds learning and neighborhood computing in a neighborhood based decision-theoretic rough set model. Neurocomputing 266:619–630CrossRefGoogle Scholar
  14. Patra S, Bruzzone L (2015) A rough set based band selection technique for the analysis of hyperspectral images. In: IEEE international geoscience and remote sensing symposium (IGARSS), pp 497–500Google Scholar
  15. Patra S, Modi P, Bruzzone L (2015) Hyperspectral band selection based on rough set. IEEE Trans Geosci Remote Sens 53(10):5495–5503CrossRefGoogle Scholar
  16. Pawlak Z (1982) Rough sets. Int J Inf Comput Sci 11(5):341–356CrossRefzbMATHGoogle Scholar
  17. Serpico SB, Moser G (2007) Extraction of spectral channels from hyperspectral images for classification purposes. IEEE Trans Geosci Remote Sens 45(2):484–495CrossRefGoogle Scholar
  18. Shi H, Shen Y, Liu Z (2003) Hyperspectral bands reduction based on rough sets and fuzzy c-means clustering. In: Proceedings of the 20th IEEE instrumentation & measurement technology conference, 2003. IMTC’03, vol 2, pp 1053–1056. IEEEGoogle Scholar
  19. Singla A, Patra S (2018) A fast partition-based batch-mode active learning technique using SVM classifier. Soft Comput 22(14):4627–4637CrossRefGoogle Scholar
  20. Sun K, Geng X, Ji L (2014) An efficient unsupervised band selection method based on an autocorrelation matrix for a hyperspectral image. Int J Remote Sens 35(21):7458–7476CrossRefGoogle Scholar
  21. Swiniarski RW, Skowron A (2003) Rough set methods in feature selection and recognition. Pattern Recognit Lett 24(6):833–849CrossRefzbMATHGoogle Scholar
  22. Wei W, Zhang Y, Tian C (2015) Latent subclass learning-based unsupervised ensemble feature extraction method for hyperspectral image classification. Remote Sens Lett 6(4):257–266CrossRefGoogle Scholar
  23. Wen JH, Zhao YQ, Zhang XF, Yan WD, Lin W (2014) Local discriminant non-negative matrix factorization feature extraction for hyperspectral image classification. Int J Remote Sens 35(13):5073–5093CrossRefGoogle Scholar
  24. Xie F, Lin Y, Ren W (2011) Optimizing model for land use/land cover retrieval from remote sensing imagery based on variable precision rough sets. Ecol Model 222(2):232–240CrossRefGoogle Scholar
  25. Yang C, Qiu J, Zhang W (2013) Knowledge granulation based roughness measure for neighborhood rough sets. In: 2013 Third international conference on intelligent system design and engineering applications (ISDEA), pp 917–920. IEEEGoogle Scholar
  26. Ye Z, Li H, Song Y, Benediktsson JA, Tang YY (2017) Hyperspectral image classification using principal components-based smooth ordering and multiple 1-D interpolation. IEEE Trans Geosci Remote Sens 55(2):1199–1209CrossRefGoogle Scholar
  27. Zhang Y, Cao G, Li X, Wang B (2018) Cascaded random forest for hyperspectral image classification. IEEE J Sel Top Appl Earth Obs Remote Sens 11(4):1082–1094CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Computer Science and Engineering DepartmentTezpur UniversityTezpurIndia

Personalised recommendations