Skip to main content
SpringerLink
Log in

Unsupervised clustering for intrinsic mode functions selection in Hyperspectral image classification

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

In the realm of hyperspectral image classification, traditional methods typically eliminate spectrum noise to enhance spectral features, followed by the application of supervised techniques to improve classification efficiency. However, the use of ensemble empirical model decomposition (EEMD) has gained attention in recent years for its ability to select intrinsic mode functions (IMFs) and reconstruct a new spectrum. Nevertheless, concerns arise regarding the potential suboptimality of selected IMFs and their impact on classification accuracy. To address this issue, our study leverages EEMD to decompose each substance's spectrum into multiple IMFs, which are then clustered using K-means and hierarchical clustering. The proposed unsupervised clustering approach combines IMFs with similar features to create a new spectrum. Notably, our model surpasses the limitations of suboptimal IMF selection, leading to enhanced classification accuracy. Extensive experiments were conducted on hyperspectral data contaminated with high noise signals. The evaluation metrics employed encompassed accuracy as the primary measure. Our model demonstrated superior performance, achieving a significant improvement in accuracy from 0.6640 to 0.9177 compared to previous approaches. In conclusion, our proposed model introduces advancements by incorporating EEMD and unsupervised clustering techniques. The experimental results substantiate its superiority in achieving higher classification accuracy, overcoming the limitations of traditional methods. This study contributes to the field of hyperspectral image classification by offering an effective solution that addresses the challenges posed by suboptimal IMF selection.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Similar content being viewed by others

References

  1. Fan F, Ma Y, Li C, Mei X, Huang J, Ma J (2017) Hyperspectral image denoising with superpixel segmentation and low-rank representation, Inf. Sci. (Ny)., vol. 397–398, pp. 48–68, doi: 10.1016/j.ins.2017.02.044

  2. Chang C-I (2003) Hyperspectral Imaging: Techniques for Spectral Detection and Classification

  3. Ashouri M, Shmueli G, Sin C (2018) Tree-Based Methods for Clustering Time Series Using Domain-Relevant Attributes, SSRN Electron. J., doi:https://doi.org/10.2139/ssrn.3282849

  4. Aydemir MS, Bilgin G (2019) Semisupervised Hyperspectral Image Classification Using Deep Features. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 12(9):3615–3622. https://doi.org/10.1109/JSTARS.2019.2921033

    Article  Google Scholar 

  5. Cavallo B, D’Apuzzo L, Squillante M (2015) A Multi-Criteria Decision Making Method for Sustainable Development of Naples Port City-Area. Quality & Quantity 49(4):1647–1659. https://doi.org/10.1007/s11135-014-0077-9

    Article  Google Scholar 

  6. Tao X, Wang R, Chang R, Li C, Liu R, Zou J Spectral clustering algorithm using density-sensitive distance measure with global and local consistencies, Knowledge-Based Syst., Pub Date : 2019-04-01 , DOI: 10.1016/j.knosys.2019.01.026

  7. Sun S, Pang Y, Wang J et al (2016) EEMD harmonic detection method based on the new wavelet threshold denoising pretreatment. Power System Protection and Control 44(2):42–48

    Google Scholar 

  8. Hawinkel P, Swinnen E, Lhermitte S, Verbist B, VanOrshoven J, Muys B (2015) A time series processing tool to extract climate-driven interannual vegetation dynamics using Ensemble Empirical Mode Decomposition (EEMD), Remote Sens. Environ., doi: https://doi.org/10.1016/j.rse.2015.08.024.

  9. Li Y, Li Y, Chen X, Yu J (2017) Denoising and feature extraction algorithms using NPE combined with VMD and their applications in ship-radiated noise, Symmetry (Basel)., doi: 10.3390/sym9110256.

  10. Du Y, Wang J, Jin X (2013) Defect detection of ultrasonic guided wave pipeline using de-noising method based on wavelet modulus maximum. Journal of Electronic Measurement and Instrument 27(7):683–688

    Article  Google Scholar 

  11. Wang K, Yong B (2016) Application of the Frequency Spectrum to Spectral Similarity Measures, Remote Sens, vol. 8, no. 4, p. 344, doi: 10.3390/rs8040344

  12. Lv X, Ming D, Chen YY, Wang M (2019) Very high resolution remote sensing image classification with SEEDS-CNN and scale effect analysis for superpixel CNN classification. Int. J. Remote Sens. 40(2):506–531. https://doi.org/10.1080/01431161.2018.1513666

    Article  Google Scholar 

  13. Krishnan A, Saxena S (2019) Hyperspectral Imaging Analysis and Applications for Food Quality 195–205

  14. He Z, Shen Y, Wang Q, Wang Y (2014) Optimized ensemble EMD-based spectral features for hyperspectral image classification, IEEE Trans. Instrum. Meas. doi: https://doi.org/10.1109/TIM.2014.2298153.

  15. Jensen JO, Ren H, Amico FMD, Du Y, and Chang C-I (2003) New hyperspectral discrimination measure for spectral similarity, doi: 10.1117/12.487044

  16. Ramirez A, Arce GR, Sadler BM (2012) Hyperspectral pixel classification from coded-aperture compressive imaging, doi: 10.1117/12.926417

  17. Jiang J, Ma J, Wang Z, Chen C (2018) Hyperspectral Image Classification in the Presence of Noisy Labels, IEEE Trans. Geosci. Remote Sens., vol. PP, pp. 1–15, doi: 10.1109/TGRS.2018.2861992

  18. Wang A, Wang Y, Chen Y (2019) Hyperspectral image classification based on convolutional neural network and random forest. Remote Sens. Lett. 10(11):1086–1094. https://doi.org/10.1080/2150704X.2019.1649736

    Article  Google Scholar 

  19. Wang W, Chau K, Xu D, Chen X (2015) Improving Forecasting Accuracy of Annual Runoff Time Series Using ARIMA Based on EEMD Decomposition, doi: 10.1007/s11269-015-0962-6

  20. Shen Y and Zhang M (2012) Hyperspectral image classification based on ensemble empirical mode decomposition, doi: 10.1007/978-3-642-27329-2_72.

  21. Ghodratigohar M, Ghanadian H, AlOsman H (2020) A Remote Respiration Rate Measurement Method for Non-Stationary Subjects Using CEEMDAN and Machine Learning. IEEE Sens. J. 20(3):1400–1410. https://doi.org/10.1109/JSEN.2019.2946132

    Article  Google Scholar 

  22. Zhang Y, Lian J, Liu F (2016) An improved filtering method based on EEMD and wavelet-threshold for modal parameter identification of hydraulic structure. Mech. Syst. Signal Process. 68–69:316–329. https://doi.org/10.1016/j.ymssp.2015.06.020

    Article  Google Scholar 

  23. Boudraa AO, Cexus JC, Saidi Z (2005) EMD-Based Signal Noise Reduction, Int J Signal Process, doi: https://doi.org/10.1063/1.3271040

  24. Wu Z, Huang NE (2009) Ensemble Empirical Mode Decomposition: a Noise-Assisted Data Analysis Method, Advances in Adaptive Data AnalysisVol. 01, No. 01, pp. 1-41, doi: 10.1142/S1793536909000047

  25. Peng T, Zhou J, Zhang C, Zheng Y (2017) Multi-step ahead wind speed forecasting using a hybrid model based on two-stage decomposition technique and AdaBoost-extreme learning machine, Energy Convers Manag, doi: https://doi.org/10.1016/j.enconman.2017.10.021

  26. Gavrovska A, Slavkovic M, Reljin I, Reljin B (2013) Application of wavelet and EMD-based denoising to phonocardiograms, Signals, Circuits and Systems (ISSCS), pp: 1-4.DOI: https://doi.org/10.1109/isscs.2013.6651264

  27. Li J, Tong Y, Guan L, Wu S, Li D (2018) A UV-visible absorption spectrum denoising method based on EEMD and an improved universal threshold fi lter. RSC Adv. 8:8558–8568. https://doi.org/10.1039/C7RA13202F

    Article  Google Scholar 

  28. Ren H, Wang YL, Huang MY, Chang YL, Kao HM (2014) Ensemble empirical mode decomposition parameters optimization for spectral distance measurement in hyperspectral remote sensing data, Remote Sens., doi: https://doi.org/10.3390/rs6032069

  29. Li Y, Liu RW, Liu Z, Liu J (2019) Similarity Grouping-Guided Neural Network Modeling for Maritime Time Series Prediction. IEEE Access 7:72647–72659. https://doi.org/10.1109/ACCESS.2019.2920436

    Article  Google Scholar 

  30. Rakshit M, Das S (2018) An efficient ECG denoising methodology using empirical mode decomposition and adaptive switching mean filter, Biomed. Signal Process. Control, vol. 40, pp. 140–148, doi: 10.1016/j.bspc.2017.09.020.

  31. Yang G, Liu Y, Wang Y, Zhu Z (2015) EMD interval thresholding denoising based on similarity measure to select relevant modes. Signal Processing 109:95–109. https://doi.org/10.1016/j.sigpro.2014.10.038

    Article  Google Scholar 

  32. Xie F, Lei C, Li F, Huang D, Yang J (2019) Unsupervised hyperspectral feature selection based on fuzzy c-means and grey wolf optimizer. Int. J. Remote Sens. 40(9):3344–3367. https://doi.org/10.1080/01431161.2018.1541366

    Article  Google Scholar 

  33. Yan Q, Ding Y, Zhang JJ, Xia Y, Zheng CH (2019) A discriminated similarity matrix construction based on sparse subspace clustering algorithm for hyperspectral imagery. Cogn. Syst. Res. 53:98–110. https://doi.org/10.1016/j.cogsys.2018.01.003

    Article  Google Scholar 

  34. Zheng L, Qu Y, Qian X, Cheng G (2018) A hierarchical co-clustering approach for entity exploration over Linked Data. Knowledge-Based Syst. 141:200–210. https://doi.org/10.1016/j.knosys.2017.11.017

    Article  Google Scholar 

  35. Likas A, Vlassis N, Verbeek JJ (2003) The global k-means clustering algorithm. Pattern Recognit. 36(2):451–461. https://doi.org/10.1016/S0031-3203(02)00060-2

    Article  Google Scholar 

  36. Karypis G, Han EH, Kumar V (1999) Chameleon: Hierarchical clustering using dynamic modeling, Computer (Long. Beach. Calif). doi: 10.1109/2.781637

Download references

Funding

The funders had no say with regard to the analyses, interpretation, or decision to submit the manuscript for publication

Author information

Authors and Affiliations

  1. Department of Mechanical, Electrical & Information Engineering, Putian University, Putian, 351100, Fujian, China

    Zhiqiang Liu

Authors
  1. Zhiqiang Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhiqiang Liu.

Ethics declarations

Conflict of interest

Conflict of interest declaration: The authors declare that they have no financial or other conflicts of interests in relation to this manuscript.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, Z. Unsupervised clustering for intrinsic mode functions selection in Hyperspectral image classification. Multimed Tools Appl 83, 37387–37407 (2024). https://doi.org/10.1007/s11042-023-16884-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-023-16884-8

Keywords

Search

Navigation