Abstract
We propose a novel supervised classification algorithm for spatially dependent data, built as an extension of kernel discriminant analysis, that we named Spatial Kernel Discriminant Analysis (SKDA). Our algorithm is based on a kernel estimate of the spatial probability density function, which integrates a second kernel to take into account spatial dependency of data. In fact, classical data mining algorithms assume that data samples are independent and identically distributed. However, this assumption is not verified when dealing with spatial data characterized by spatial autocorrelation phenomenon. To make an accurate analysis, it is necessary to exploit this rich source of information and to capture this property. We have applied our algorithm to a relevant domain, which consist of the classification of remotely sensed hyperspectral images. In order to assess the efficiency of our proposed method, we conducted experiments on two remotely sensed images datasets (Indian Pines and Pavia University) with different characteristics and scenarios. The experimental results show that our method is competitive and achieves higher classification accuracy compared to other contextual classification methods.
Similar content being viewed by others
References
Ahmed, M.S., N’diaye, M., Attouch, M.K., Dabo-Niang, S.: k-nearest neighbors prediction and classification for spatial data. arXiv preprint arXiv:1806.00385 (2018)
Appice, A., Guccione, P., Malerba, D.: A novel spectral-spatial co-training algorithm for the transductive classification of hyperspectral imagery data. Pattern Recogn. 63, 229–245 (2017). https://doi.org/10.1016/j.patcog.2016.10.010
Baumgardner, M.F., Biehl, L.L., Landgrebe, D.A.: 220 band aviris hyperspectral image data set: June 12, 1992 indian pine test site (2015). https://doi.org/10.4231/R7RX991C. https://purr.purdue.edu/publications/1947/1
Bel, L., Allard, D., Laurent, J.M., Cheddadi, R., Bar-Hen, A.: CART algorithm for spatial data: application to environmental and ecological data. Comput. Stat. Data Anal. 53(8), 3082–3093 (2009). https://doi.org/10.1016/j.csda.2008.09.012
Benediktsson, J.A., Ghamisi, P.: Spectral–spatial classification of hyperspectral remote sensing images. Artech House (2015)
Bogorny, V., Valiati, J., Camargo, S., Engel, P., Kuijpers, B., Alvares, L.O.: Mining maximal generalized frequent geographic patterns with knowledge constraints. In: null, pp. 813–817. IEEE (2006)
Boumeddane, S., Hamdad, L., Dabo-Niang, S., Haddadou, H.: Spatial kernel discriminant analysis: Applied for hyperspectral image classification. In: Proceedings of the 11th International Conference on Agents and Artificial Intelligence, ICAART 2019, Volume 2, Prague, Czech Republic, February 19–21, 2019, pp. 184–191 (2019). https://doi.org/10.5220/0007372401840191
Chen, Y., Jiang, H., Li, C., Jia, X., Ghamisi, P.: Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans. Geosci. Remote Sens. 54(10), 6232–6251 (2016). https://doi.org/10.1109/TGRS.2016.2584107
Cheng, T., Wang, J., Haworth, J., Heydecker, B., Chow, A.: A dynamic spatial weight matrix and localized space-time autoregressive integrated moving average for network modeling. Geogr. Anal. 46(1), 75–97 (2014)
Dabo-Niang, S., Hamdad, L., Ternynck, C., Yao, A.F.: A kernel spatial density estimation allowing for the analysis of spatial clustering: application to monsoon asia drought atlas data. Stoch. Environ. Res. Risk Assess. 28(8), 2075–2099 (2014)
Dabo-Niang, S., Ternynck, C., Yao, A.F.: A new spatial regression estimator in the multivariate context. Comptes Rendus Mathematique 353(7), 635–639 (2015)
Dabo-Niang, S., Ternynck, C., Yao, A.F.: Nonparametric prediction of spatial multivariate data. J. Nonparametr. Stat. 28(2), 428–458 (2016)
Fauvel, M., Tarabalka, Y., Benediktsson, J.A., Chanussot, J., Tilton, J.C.: Advances in spectral–spatial classification of hyperspectral images. Proc. IEEE 101(3), 652–675 (2013). https://doi.org/10.1109/JPROC.2012.2197589
Ghamisi, P., Benediktsson, J.A., Cavallaro, G., Plaza, A.: Automatic framework for spectral–spatial classification based on supervised feature extraction and morphological attribute profiles. IEEE J Sel. Topics Appl. Earth Observ. Remote Sens. 7(6), 2147–2160 (2014). https://doi.org/10.1109/JSTARS.2014.2298876
Ghamisi, P., Chen, Y., Zhu, X.X.: A self-improving convolution neural network for the classification of hyperspectral data. IEEE Geosci. Remote Sens. Lett. 13(10), 1537–1541 (2016). https://doi.org/10.1109/LGRS.2016.2595108
Ghamisi, P., Plaza, J., Chen, Y., Li, J., Plaza, A.J.: Advanced spectral classifiers for hyperspectral images: a review. IEEE Geosci. Remote Sens. Mag. 5(1), 8–32 (2017)
Gramacki, A.: Nonparametric Kernel Density Estimation and Its Computational Aspects. Springer, New York (2018)
Hang, R., Liu, Q., Hong, D., Ghamisi, P.: Cascaded recurrent neural networks for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 57(8), 5384–5394 (2019). https://doi.org/10.1109/TGRS.2019.2899129
He, L., Li, J., Plaza, A., Li, Y.: Discriminative low-rank gabor filtering for spectral–spatial hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 55(3), 1381–1395 (2017). https://doi.org/10.1109/TGRS.2016.2623742
Hu, W., Huang, Y., Li, W., Zhang, F., Li, H.: Deep convolutional neural networks for hyperspectral image classification. J. Sens. 2015, 258619:1–258619:12 (2015). https://doi.org/10.1155/2015/258619
Kang, X., Li, S., Benediktsson, J.A.: Spectral-spatial hyperspectral image classification with edge-preserving filtering. IEEE Trans. Geosci. Remote Sens. 52(5), 2666–2677 (2014). https://doi.org/10.1109/TGRS.2013.2264508
Kobos, M., Mandziuk, J.: Classification based on combination of kernel density estimators. In: Artificial Neural Networks—ICANN 2009, 19th International Conference, Limassol, Cyprus, September 14–17, 2009, Proceedings, Part II, pp. 125–134 (2009). https://doi.org/10.1007/978-3-642-04277-5_13
Lee, J., Li, S.: Extending moran’s index for measuring spatiotemporal clustering of geographic events. Geogr. Anal. 49(1), 36–57 (2017)
LeSage, J.P., Pace, R.K.: Spatial dependence in data mining. In: Data mining for scientific and engineering applications, pp. 439–460. Springer (2001)
Li, Y., Zhang, H., Xue, X., Jiang, Y., Shen, Q.: Deep learning for remote sensing image classification: a survey. Wiley Interdiscip. Rev. Data Min. Knowl. Discov. (2018). https://doi.org/10.1002/widm.1264
Miller, H.J.: Tobler’s first law and spatial analysis. Ann. Assoc. Am. Geogr. 94(2), 284–289 (2004)
Mou, L., Ghamisi, P., Zhu, X.X.: Deep recurrent neural networks for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 55(7), 3639–3655 (2017). https://doi.org/10.1109/TGRS.2016.2636241
Mou, L., Ghamisi, P., Zhu, X.X.: Unsupervised spectral-spatial feature learning via deep residual conv-deconv network for hyperspectral image classification. IEEE Trans. Geosci. Remote Sens. 56(1), 391–406 (2018). https://doi.org/10.1109/TGRS.2017.2748160
Mukhopadhyay, S., Ghosh, A.K.: Bayesian multiscale smoothing in supervised and semi-supervised kernel discriminant analysis. Comput. Stat. Data Anal. 55(7), 2344–2353 (2011). https://doi.org/10.1016/j.csda.2011.02.001
N’diaye, M., Dabo-Niang, S., Ngom, P., Thiam, N., Fall, M., Brehmer, P.: Nonparametric prediction for spatial dependent functional data: application to demersal coastal fish off Senegal, pp. 31–49 (2020)
O’Sullivan, D.: Geographically weighted regression: the analysis of spatially varying relationships, by as fotheringham c. brunsdon, and m. charlton. Geogr. Anal. 35(3), 272–275 (2003)
Pu, H., Chen, Z., Wang, B., Jiang, G.: A novel spatial-spectral similarity measure for dimensionality reduction and classification of hyperspectral imagery. IEEE Trans. Geosci. Remote Sens. 52(11), 7008–7022 (2014). https://doi.org/10.1109/TGRS.2014.2306687
Shekhar, S., Evans, M.R., Kang, J.M., Mohan, P.: Identifying patterns in spatial information: a survey of methods. Wiley Interdisc. Rew.: Data Mining Knowl. Discov. 1(3), 193–214 (2011). https://doi.org/10.1002/widm.25
Shekhar, S., Jiang, Z., Ali, R.Y., Eftelioglu, E., Tang, X., Gunturi, V.M.V., Zhou, X.: Spatiotemporal data mining: a computational perspective. ISPRS Int. J. Geo-Inf. 4(4), 2306–2338 (2015). https://doi.org/10.3390/ijgi4042306
Stojanova, D., Ceci, M., Appice, A., Malerba, D., Dzeroski, S.: Dealing with spatial autocorrelation when learning predictive clustering trees. Ecol. Inf. 13, 22–39 (2013). https://doi.org/10.1016/j.ecoinf.2012.10.006
Ternynck, C.: Spatial regression estimation for functional data with spatial dependency. J. Soc. Française Stat. 155(2), 138–160 (2014)
van der Walt, C.M., Barnard, E.: Variable kernel density estimation in high-dimensional feature spaces. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, February 4–9, 2017, San Francisco, pp. 2674–2680 (2017). http://aaai.org/ocs/index.php/AAAI/AAAI17/paper/view/14737
Wang, Y., Zhang, Y., Song, H.: A spectral-texture Kernel-based classification method for hyperspectral images. Remote Sens. 8(11), 919 (2016). https://doi.org/10.3390/rs8110919
Zhao, M., Li, X.: An application of spatial decision tree for classification of air pollution index. In: Proceedings of the 2011 19th International Conference on Geoinformatics, pp. 1–6. IEEE (2011)
Acknowledgements
The authors would like to thank Dr Pedram Ghamisi for kindly providing us the standard training and test sets for Indian Pines and Pavia University datasets.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Boumeddane, S., Hamdad, L., Haddadou, H. et al. A kernel discriminant analysis for spatially dependent data. Distrib Parallel Databases 39, 583–606 (2021). https://doi.org/10.1007/s10619-020-07309-8
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10619-020-07309-8