{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T03:00:42Z","timestamp":1760151642234,"version":"build-2065373602"},"reference-count":53,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T00:00:00Z","timestamp":1649030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61627804"],"award-info":[{"award-number":["61627804"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Feature extraction, aiming to simplify and optimize data features, is a typical hyperspectral image dimensionality reduction technique. As a kernel-based method, kernel minimum noise fraction (KMNF) transformation is excellent at handling the nonlinear features within HSIs. It adopts the kernel function to ensure data linear separability by transforming the original data to a higher feature space, following which a linear analysis can be performed in this space. However, KMNF transformation has the problem of high computational complexity and low execution efficiency. It is not suitable for the processing of large-scale datasets. In terms of this problem, this paper proposes a graphics processing unit (GPU) and Nystr\u00f6m method-based algorithm for Fast KMNF transformation (GNKMNF). First, the Nystr\u00f6m method estimates the eigenvector of the entire kernel matrix in KMNF transformation by the decomposition and extrapolation of the sub-kernel matrix to reduce the computational complexity. Then, the sample size in the Nystr\u00f6m method is determined utilizing a proportional gradient selection strategy. Finally, GPU parallel computing is employed to further improve the execution efficiency. Experimental results show that compared with KMNF transformation, improvements of up to 1.94% and 2.04% are achieved by GNKMNF in overall classification accuracy and Kappa, respectively. Moreover, with a data size of 64 \u00d7 64 \u00d7 250, the execution efficiency of GNKMNF speeds up by about 80\u00d7. The outcome demonstrates the significant performance of GNKMNF in feature extraction and execution efficiency.<\/jats:p>","DOI":"10.3390\/rs14071737","type":"journal-article","created":{"date-parts":[[2022,4,4]],"date-time":"2022-04-04T09:49:41Z","timestamp":1649065781000},"page":"1737","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Novel Method for Fast Kernel Minimum Noise Fraction Transformation in Hyperspectral Image Dimensionality Reduction"],"prefix":"10.3390","volume":"14","author":[{"given":"Tianru","family":"Xue","sequence":"first","affiliation":[{"name":"Key Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0791-4836","authenticated-orcid":false,"given":"Yueming","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"},{"name":"Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China"},{"name":"Research Center for Intelligent Sensing Systems, Zhejiang Laboratory, Hangzhou 311100, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5811-0590","authenticated-orcid":false,"given":"Xuan","family":"Deng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Space Active Opto-Electronics Technology, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China"},{"name":"University of Chinese Academy of Sciences, Beijing 100049, China"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1109\/JSTARS.2014.2329792","article-title":"A study on the effectiveness of different independent component analysis algorithms for hyperspectral image classification","volume":"7","author":"Falco","year":"2014","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1082","DOI":"10.1109\/TGRS.2014.2333539","article-title":"Dimension Reduction Using Spatial and Spectral Regularized Local Discriminant Embedding for Hyperspectral Image Classification","volume":"53","author":"Zhou","year":"2015","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1109\/36.298007","article-title":"Hyperspectral image classification and dimensionality reduction: An orthogonal subspace projection approach","volume":"32","author":"Harsanyi","year":"1994","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1109\/TIP.2016.2617462","article-title":"Discovering Diverse Subset for Unsupervised Hyperspectral Band Selection","volume":"26","author":"Yuan","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"2509","DOI":"10.1109\/TGRS.2016.2645703","article-title":"Dimensionality Reduction and Classification of Hyperspectral Images Using Ensemble Discriminative Local Metric Learning","volume":"55","author":"Dong","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Xue, T., Wang, Y., Chen, Y., Jia, J., Wen, M., Guo, R., Wu, T., and Deng, X. (2021). Mixed Noise Estimation Model for Optimized Kernel Minimum Noise Fraction Transformation in Hyperspectral Image Dimensionality Reduction. Remote Sens., 13.","DOI":"10.3390\/rs13132607"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"118","DOI":"10.1109\/MGRS.2019.2911100","article-title":"Hyperspectral band selection: A review","volume":"7","author":"Sun","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Mag."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Yin, J., Wang, Y., and Zhao, Z. (2010, January 19\u201321). Optimal Band Selection for Hyperspectral Image Classification Based on Inter-Class Separability. Proceedings of the 2010 Symposium on Photonics and Optoelectronics, Chengdu, China.","DOI":"10.1109\/SOPO.2010.5504325"},{"key":"ref_9","unstructured":"Sildomar, T.-M., and Yukio, K. (2007, January 25\u201328). A Particle Swarm Optimization-Based Approach for Hyperspectral Band Selection. Proceedings of the 2007 IEEE Congress on Evolutionary Computation, Singapore."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1109\/TNNLS.2015.2477537","article-title":"Salient band selection for hyperspectral image classification via manifold ranking","volume":"27","author":"Wang","year":"2016","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"1552","DOI":"10.1109\/TGRS.2004.830549","article-title":"Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries","volume":"42","author":"Keshava","year":"2004","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"2659","DOI":"10.1109\/JSTARS.2014.2312539","article-title":"Optimized hyperspectral band selection using particle swarm optimization","volume":"7","author":"Su","year":"2014","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"2631","DOI":"10.1109\/36.803411","article-title":"A joint band prioritization and band-decorrelation approach to band selection for hyperspectral image classification","volume":"37","author":"Chang","year":"1999","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"793","DOI":"10.14358\/PERS.70.7.793","article-title":"Methodology for hyperspectral band selection","volume":"70","author":"Bajcsy","year":"2004","journal-title":"Photogramm. Eng. Remote Sens."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"138","DOI":"10.1109\/LGRS.2010.2053516","article-title":"An efficient method for supervised hyperspectral band selection","volume":"8","author":"Yang","year":"2010","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"4158","DOI":"10.1109\/TGRS.2007.904951","article-title":"Clustering-based hyperspectral band selection using information measures","volume":"45","author":"Pla","year":"2007","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1109\/LGRS.2010.2091673","article-title":"BandClust: An unsupervised band reduction method for hyperspectral remote sensing","volume":"8","author":"Cariou","year":"2010","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1109\/LGRS.2017.2681118","article-title":"Unsupervised hyperspectral band selection by fuzzy clustering with particle swarm optimization","volume":"14","author":"Zhang","year":"2017","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1631\/jzus.C1000304","article-title":"Clustering-based hyperspectral band selection using sparse nonnegative matrix factorization","volume":"12","author":"Li","year":"2011","journal-title":"J. Zhejiang Univ. Sci. C"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Li, S., and Qi, H. (2011, January 11\u201314). Sparse Representation-Based Band Selection for Hyperspectral Images. Proceedings of the 18th IEEE International Conference on Image Processing, Brussels, Belgium.","DOI":"10.1109\/ICIP.2011.6116223"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"2784","DOI":"10.1109\/JSTARS.2015.2417156","article-title":"Band selection using improved sparse subspace clustering for hyperspectral imagery classification","volume":"8","author":"Sun","year":"2015","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Gao, L., Zhao, B., Jia, X., Liao, W., and Zhang, B. (2017). Optimized kernel minimum noise fraction transformation for hyperspectral image classification. Remote Sens., 9.","DOI":"10.3390\/rs9060548"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"2719","DOI":"10.1080\/01431169608949102","article-title":"Principal Components transform with simple, automatic noise adjustment","volume":"17","author":"Roger","year":"1996","journal-title":"Int. J. Remote Sens."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1109\/36.3001","article-title":"A transformation for ordering multispectral data in terms of image quality with implications for noise removal","volume":"26","author":"Green","year":"1988","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"862","DOI":"10.1109\/TGRS.2008.2005729","article-title":"Classification of hyperspectral images with regularized linear discriminant analysis","volume":"47","author":"Bandos","year":"2009","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.patcog.2016.09.006","article-title":"Sequential dimensionality reduction for extracting localized features","volume":"63","author":"Casalino","year":"2017","journal-title":"Pattern Recognit."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.csda.2006.11.006","article-title":"Algorithms and applications for approximate nonnegative matrix factorization","volume":"52","author":"Berry","year":"2007","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"612","DOI":"10.1109\/TIP.2010.2076296","article-title":"Kernel maximum autocorrelation factor and minimum noise fraction transformations","volume":"20","author":"Nielsen","year":"2010","journal-title":"IEEE Trans. Image Process."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Sch\u00f6lkopf, B., Smola, A.J., and M\u00fcller, K.-R. (1997). Kernel Principal Component Analysis. Transactions on Petri Nets and Other Models of Concurrency XV, Springer Science and Business Media LLC.","DOI":"10.7551\/mitpress\/1130.003.0026"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"676","DOI":"10.1109\/JPROC.2012.2229082","article-title":"Feature mining for hyperspectral image classification","volume":"101","author":"Jia","year":"2013","journal-title":"Proc. IEEE"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"186","DOI":"10.1016\/j.patcog.2011.05.014","article-title":"Supervised optimal locality preserving projection","volume":"45","author":"Wong","year":"2012","journal-title":"Pattern Recognit."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","article-title":"Nonlinear Dimensionality Reduction by Locally Linear Embedding","volume":"290","author":"Roweis","year":"2000","journal-title":"Science"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1165","DOI":"10.1109\/JSTARS.2016.2606578","article-title":"Dimensionality reduction of hyperspectral imagery using sparse graph learning","volume":"10","author":"Chen","year":"2016","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3991","DOI":"10.1016\/j.laa.2012.04.033","article-title":"Sparse nonnegative matrix underapproximation and its application to hyperspectral image analysis","volume":"438","author":"Gillis","year":"2013","journal-title":"Linear Algebra Its Appl."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"441","DOI":"10.1109\/TGRS.2004.842292","article-title":"Exploiting manifold geometry in hyperspectral imagery","volume":"43","author":"Bachmann","year":"2005","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"6248","DOI":"10.1080\/01431161.2020.1736732","article-title":"Feature extraction for hyperspectral image classification: A review","volume":"41","author":"Kumar","year":"2020","journal-title":"Int. J. Remote Sens."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"10977","DOI":"10.1109\/JSTARS.2021.3123371","article-title":"Hyperspectral Image Classification Based on Multilevel Joint Feature Extraction Network","volume":"14","author":"Lu","year":"2021","journal-title":"IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Li, Z., Huang, H., Zhang, Z., and Shi, G. (2022). Manifold-Based Multi-Deep Belief Network for Feature Extraction of Hyperspectral Image. Remote Sens., 14.","DOI":"10.3390\/rs14061484"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"6232","DOI":"10.1109\/TGRS.2016.2584107","article-title":"Deep Feature Extraction and Classification of Hyperspectral Images Based on Convolutional Neural Networks","volume":"54","author":"Chen","year":"2016","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"5054","DOI":"10.1109\/TGRS.2020.3011943","article-title":"Attention multibranch convolutional neural network for hyperspectral image classification based on adaptive region search","volume":"59","author":"Feng","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1109\/TGRS.2019.2933609","article-title":"Learning to pay attention on spectral domain: A spectral attention module-based convolutional network for hyperspectral image classification","volume":"58","author":"Mou","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"9600","DOI":"10.1109\/TGRS.2020.3048128","article-title":"Attention-based second-order pooling network for hyperspectral image classification","volume":"59","author":"Xue","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"113089","DOI":"10.1016\/j.eswa.2019.113089","article-title":"M3DNet: A manifold-based discriminant feature learning network for hyperspectral imagery","volume":"144","author":"Li","year":"2020","journal-title":"Expert Syst. Appl."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"3399","DOI":"10.1109\/TGRS.2013.2272760","article-title":"Decision Fusion in Kernel-Induced Spaces for Hyperspectral Image Classification","volume":"52","author":"Li","year":"2014","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_45","doi-asserted-by":"crossref","unstructured":"Shawe-Taylor, J., and Cristianini, N. (2004). Kernel Methods for Pattern Analysis, Cambridge University Press.","DOI":"10.1017\/CBO9780511809682"},{"key":"ref_46","doi-asserted-by":"crossref","unstructured":"Rasti, B., Scheunders, P., Ghamisi, P., Licciardi, G., and Chanussot, J. (2018). Noise reduction in hyperspectral imagery: Overview and application. Remote Sens., 10.","DOI":"10.3390\/rs10030482"},{"key":"ref_47","unstructured":"Nielsen, A.A. (1999, January 27\u201329). An Extension to a Filter Implementation of a Local Quadratic Surface for Image Noise Estimation. Proceedings of the 10th International Conference on Image Analysis and Processing, Venice, Italy."},{"key":"ref_48","unstructured":"Williams, C., and Seeger, M. (2001, January 1). Using the Nystr\u00f6m method to speed up kernel machines. Proceedings of the 14th Annual Conference on Neural Information Processing Systems, Denver, CO, USA."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"2457","DOI":"10.1002\/cpe.1472","article-title":"Exploiting the capabilities of modern GPUs for dense matrix computations","volume":"21","author":"Barrachina","year":"2009","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"4077","DOI":"10.1109\/TGRS.2018.2889731","article-title":"Destriping algorithms based on statistics and spatial filtering for visible-to-thermal infrared pushbroom hyperspectral imagery","volume":"57","author":"Jia","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"ref_51","first-page":"1","article-title":"Removing stripe noise based on improved statistics for hyperspectral images","volume":"19","author":"Jia","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_52","first-page":"1299","article-title":"Aerial hyperspectral remote sensing classification dataset of Xiong\u2019an new area (Matiwan Village)","volume":"24","author":"Cen","year":"2020","journal-title":"J. Remote Sens."},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"5510918","DOI":"10.1109\/TGRS.2021.3096999","article-title":"Tradeoffs in the spatial and spectral resolution of airborne hyperspectral imaging systems: A crop identification case study","volume":"60","author":"Jia","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/7\/1737\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:49:43Z","timestamp":1760136583000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/14\/7\/1737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,4]]},"references-count":53,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2022,4]]}},"alternative-id":["rs14071737"],"URL":"https:\/\/doi.org\/10.3390\/rs14071737","relation":{},"ISSN":["2072-4292"],"issn-type":[{"type":"electronic","value":"2072-4292"}],"subject":[],"published":{"date-parts":[[2022,4,4]]}}}