{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:17:12Z","timestamp":1774365432721,"version":"3.50.1"},"reference-count":45,"publisher":"MDPI AG","issue":"14","license":[{"start":{"date-parts":[[2023,7,13]],"date-time":"2023-07-13T00:00:00Z","timestamp":1689206400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Remote Sensing"],"abstract":"<jats:p>Object classification in hyperspectral images involves accurately categorizing objects based on their spectral characteristics. However, the high dimensionality of hyperspectral data and class imbalance pose significant challenges to object classification performance. To address these challenges, we propose a framework that incorporates dimensionality reduction and re-sampling as preprocessing steps for a deep learning model. Our framework employs a novel subgroup-based dimensionality reduction technique to extract and select the most informative features with minimal redundancy. Additionally, the data are resampled to achieve class balance across all categories. The reduced and balanced data are then processed through a hybrid CNN model, which combines a 3D learning block and a 2D learning block to extract spectral\u2013spatial features and achieve satisfactory classification accuracy. By adopting this hybrid approach, we simplify the model while improving performance in the presence of noise and limited sample size. We evaluated our proposed model on the Salinas scene, Pavia University, and Kennedy Space Center benchmark hyperspectral datasets, comparing it to state-of-the-art methods. Our object classification technique achieves highly promising results, with overall accuracies of 99.98%, 99.94%, and 99.46% on the three datasets, respectively. This proposed approach offers a compelling solution to overcome the challenges of high dimensionality and class imbalance in hyperspectral object classification.<\/jats:p>","DOI":"10.3390\/rs15143532","type":"journal-article","created":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T00:39:41Z","timestamp":1689295181000},"page":"3532","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["A Deep Learning-Based Hyperspectral Object Classification Approach via Imbalanced Training Samples Handling"],"prefix":"10.3390","volume":"15","author":[{"given":"Md Touhid","family":"Islam","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur 5200, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3475-4217","authenticated-orcid":false,"given":"Md Rashedul","family":"Islam","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur 5200, Bangladesh"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4429-6590","authenticated-orcid":false,"given":"Md Palash","family":"Uddin","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Hajee Mohammad Danesh Science and Technology University, Dinajpur 5200, Bangladesh"},{"name":"School of Information Technology, Deakin University, Geelong, VIC 3220, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5145-7276","authenticated-orcid":false,"given":"Anwaar","family":"Ulhaq","sequence":"additional","affiliation":[{"name":"School of Computing, Mathematics and Engineering, Charles Sturt University, Port Macquarie, NSW 2444, Australia"}]}],"member":"1968","published-online":{"date-parts":[[2023,7,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.jrid.2014.12.001","article-title":"Imaging spectrum of neurocysticercosis","volume":"1","author":"Zhao","year":"2015","journal-title":"Radiol. Infect. Dis."},{"key":"ref_2","unstructured":"Mallapragada, S., Wong, M., and Hung, C.C. (2018, January 9\u201312). Dimensionality reduction of hyperspectral images for classification. Proceedings of the Ninth International Conference on Information, Tokyo, Japan."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1179\/174313110X12771950995716","article-title":"An introduction to hyperspectral imaging and its application for security, surveillance and target acquisition","volume":"58","author":"Yuen","year":"2010","journal-title":"Imaging Sci. J."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Lv, W., and Wang, X. (2020). Overview of hyperspectral image classification. J. Sens., 2020.","DOI":"10.1155\/2020\/4817234"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1080\/02564602.2020.1740615","article-title":"PCA-based feature reduction for hyperspectral remote sensing image classification","volume":"38","author":"Uddin","year":"2021","journal-title":"IETE Tech. Rev."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Jayaprakash, C., Damodaran, B.B., Sowmya, V., and Soman, K. (2018, January 22\u201323). Dimensionality reduction of hyperspectral images for classification using randomized independent component analysis. Proceedings of the 2018 5th IEEE International Conference on Signal Processing and Integrated Networks (SPIN), Noida, India.","DOI":"10.1109\/SPIN.2018.8474266"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.18287\/2412-6179-2018-42-6-1035-1045","article-title":"Comparison of hyperspectral and multi-spectral imagery to building a spectral library and land cover classification performanc","volume":"42","author":"Boori","year":"2018","journal-title":"Comput. Opt."},{"key":"ref_8","first-page":"325","article-title":"Comparison of Feature Reduction Techniques for Change Detection in Remote Sensing","volume":"Volume 2","author":"Aparna","year":"2022","journal-title":"Evolution in Signal Processing and Telecommunication Networks, Proceedings of Sixth International Conference on Microelectronics, Electromagnetics and Telecommunications (ICMEET 2021), Bhubaneswar, India, 27\u201328 August 2021"},{"key":"ref_9","first-page":"115","article-title":"Principal component analysis for hyperspectral image classification","volume":"62","author":"Rodarmel","year":"2002","journal-title":"Surv. Land Inf. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1080\/07038992.2016.1160772","article-title":"Minimum noise fraction versus principal component analysis as a preprocessing step for hyperspectral imagery denoising","volume":"42","author":"Luo","year":"2016","journal-title":"Can. J. Remote Sens."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"713","DOI":"10.1109\/LGRS.2009.2024175","article-title":"Segmented principal component analysis for parallel compression of hyperspectral imagery","volume":"6","author":"Du","year":"2009","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3216","DOI":"10.1016\/j.patcog.2015.04.013","article-title":"Segmented minimum noise fraction transformation for efficient feature extraction of hyperspectral images","volume":"48","author":"Lixin","year":"2015","journal-title":"Pattern Recognit."},{"key":"ref_13","unstructured":"Tsuge, S., Shishibori, M., Kuroiwa, S., and Kita, K. (2001, January 7\u201310). Dimensionality reduction using non-negative matrix factorization for information retrieval. Proceedings of the 2001 IEEE International Conference on Systems, Man and Cybernetics. e-Systems and e-Man for Cybernetics in Cyberspace (Cat. No. 01CH37236), Tucson, AZ, USA."},{"key":"ref_14","first-page":"1","article-title":"A short-term load forecasting method based on GRU-CNN hybrid neural network model","volume":"2020","author":"Wu","year":"2020","journal-title":"Math. Probl. Eng."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Liu, G., Xiao, L., and Xiong, C. (2017, January 21\u201324). Image classification with deep belief networks and improved gradient descent. Proceedings of the 2017 IEEE International Conference on Computational Science and Engineering (CSE) and IEEE International Conference on Embedded and Ubiquitous Computing (EUC), Guangzhou, China.","DOI":"10.1109\/CSE-EUC.2017.74"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"192","DOI":"10.1109\/LGRS.2005.846011","article-title":"On the impact of PCA dimension reduction for hyperspectral detection of difficult targets","volume":"2","author":"Farrell","year":"2005","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_17","first-page":"13","article-title":"Dimensionality reduction: A comparative","volume":"10","author":"Postma","year":"2009","journal-title":"J. Mach. Learn. Res."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1117\/12.518835","article-title":"Segmented PCA-based compression for hyperspectral image analysis","volume":"Volume 5268","author":"Du","year":"2004","journal-title":"Proceedings of the Chemical and Biological Standoff Detection"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"26","DOI":"10.5589\/m08-007","article-title":"Evaluation and comparison of dimensionality reduction methods and band selection","volume":"34","author":"Chen","year":"2008","journal-title":"Can. J. Remote Sens."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/978-3-642-23241-1_6","article-title":"Nonnegative matrix factorization: Models, algorithms and applications","volume":"2","author":"Zhang","year":"2012","journal-title":"Data Mining Found. Intell. Paradig."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1304","DOI":"10.1109\/TMI.2018.2883301","article-title":"Hyperspectral tissue image segmentation using semi-supervised NMF and hierarchical clustering","volume":"38","author":"Kumar","year":"2018","journal-title":"IEEE Trans. Med Imaging"},{"key":"ref_22","first-page":"684","article-title":"Hyperspectral image classification using support vector machines","volume":"9","author":"Harikiran","year":"2020","journal-title":"IAES Int. J. Artif. Intell."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Petersson, H., Gustafsson, D., and Bergstrom, D. (2016, January 12\u201315). Hyperspectral image analysis using deep learning\u2014A review. Proceedings of the 2016 IEEE Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA), Oulu, Finland.","DOI":"10.1109\/IPTA.2016.7820963"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Rissati, J., Molina, P., and Anjos, C. (2020, January 22\u201326). Hyperspectral image classification using random forest and deep learning algorithms. Proceedings of the 2020 IEEE Latin American GRSS & ISPRS Remote Sensing Conference (LAGIRS), Santiago, Chile.","DOI":"10.1109\/LAGIRS48042.2020.9165588"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"103296","DOI":"10.1016\/j.infrared.2020.103296","article-title":"Hyperspectral image classification using CNN with spectral and spatial features integration","volume":"107","author":"Vaddi","year":"2020","journal-title":"Infrared Phys. Technol."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"107962","DOI":"10.1016\/j.foodcont.2021.107962","article-title":"Hyperspectral image classification using CNN: Application to industrial food packaging","volume":"125","author":"Medus","year":"2021","journal-title":"Food Control"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, H., and Shen, Q. (2017). Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sens., 9.","DOI":"10.3390\/rs9010067"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/LGRS.2020.3043710","article-title":"A fast and compact 3-D CNN for hyperspectral image classification","volume":"19","author":"Ahmad","year":"2020","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1109\/LGRS.2019.2918719","article-title":"HybridSN: Exploring 3-D\u20132-D CNN feature hierarchy for hyperspectral image classification","volume":"17","author":"Roy","year":"2019","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"ref_30","first-page":"25","article-title":"Handling imbalanced datasets: A review","volume":"30","author":"Kotsiantis","year":"2006","journal-title":"GESTS Int. Trans. Comput. Sci. Eng."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"687","DOI":"10.1142\/S0218001409007326","article-title":"Classification of imbalanced data: A review","volume":"23","author":"Sun","year":"2009","journal-title":"Int. J. Pattern Recognit. Artif. Intell."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"311","DOI":"10.1080\/00401706.2000.10486056","article-title":"Resampling methods: A practical guide to data analysis","volume":"42","author":"Chaubey","year":"2000","journal-title":"Technometrics"},{"key":"ref_33","unstructured":"Somasundaram, A., and Reddy, U.S. (2016, January 8\u201310). Data imbalance: Effects and solutions for classification of large and highly imbalanced data. Proceedings of the 1st International Conference on Research in Engineering, Computers and Technology (ICRECT 2016), Tiruchirappalli, India."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"105292","DOI":"10.1016\/j.knosys.2019.105292","article-title":"Dealing with class imbalance in classifier chains via random undersampling","volume":"192","author":"Liu","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"ref_35","first-page":"1017","article-title":"Oversampling method for imbalanced classification","volume":"34","author":"Zheng","year":"2015","journal-title":"Comput. Inform."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Alsowail, R.A. (2021, January 23\u201324). An Insider Threat Detection Model Using One-Hot Encoding and Near-Miss Under-Sampling Techniques. Proceedings of the International Joint Conference on Advances in Computational Intelligence: IJCACI 2021, online.","DOI":"10.1007\/978-981-19-0332-8_13"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"323","DOI":"10.1016\/S0950-3293(01)00017-9","article-title":"Principal component analysis in sensory analysis: Covariance or correlation matrix?","volume":"12","author":"Borgognone","year":"2001","journal-title":"Food Qual. Prefer."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"23633","DOI":"10.1007\/s11042-020-09151-7","article-title":"Minimum redundancy maximum relevance (mRMR) based feature selection from endoscopic images for automatic gastrointestinal polyp detection","volume":"79","author":"Billah","year":"2020","journal-title":"Multimed. Tools Appl."},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1023","DOI":"10.1080\/01431160600887706","article-title":"Spectrally segmented principal component analysis of hyperspectral imagery for mapping invasive plant species","volume":"28","author":"Tsai","year":"2007","journal-title":"Int. J. Remote Sens."},{"key":"ref_41","unstructured":"Chakraborty, T., and Trehan, U. (2021). Spectralnet: Exploring spatial-spectral waveletcnn for hyperspectral image classification. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"71886","DOI":"10.1109\/ACCESS.2022.3188853","article-title":"Multibranch 3d-dense attention network for hyperspectral image classification","volume":"10","author":"Yin","year":"2022","journal-title":"IEEE Access"},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"1083","DOI":"10.1049\/ipr2.12087","article-title":"Hyperspectral image classification using 3D 2D CNN","volume":"15","author":"Diakite","year":"2021","journal-title":"IET Image Process."},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Mounika, K., Aravind, K., Yamini, M., Navyasri, P., Dash, S., and Suryanarayana, V. (2021, January 7\u20139). Hyperspectral image classification using SVM with PCA. Proceedings of the 2021 6th IEEE International Conference on Signal Processing, Computing and Control (ISPCC), Solan, India.","DOI":"10.1109\/ISPCC53510.2021.9609461"},{"key":"ref_45","unstructured":"Gra\u00f1a, M., Veganzons, M., and Ayerdi, B. (2023, July 11). Hyperspectral Remote Sensing Scenes. Available online: https:\/\/www.ehu.eus\/ccwintco\/index.php\/Hyperspectral_Remote_Sensing_Scenes."}],"container-title":["Remote Sensing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/14\/3532\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:11:36Z","timestamp":1760127096000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2072-4292\/15\/14\/3532"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,13]]},"references-count":45,"journal-issue":{"issue":"14","published-online":{"date-parts":[[2023,7]]}},"alternative-id":["rs15143532"],"URL":"https:\/\/doi.org\/10.3390\/rs15143532","relation":{},"ISSN":["2072-4292"],"issn-type":[{"value":"2072-4292","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,13]]}}}