Paoletti, Mercedes EugeniaMogollón Gutiérrez, ÓscarMoreno Álvarez, SergioSancho, José CarlosHaut, Juan M.2024-11-182024-11-182023Mercedes E Paoletti, Oscar Mogollon-Gutierrez, Sergio Moreno-Álvarez, Jose Carlos Sancho, Juan M Haut. "A comprehensive survey of imbalance correction techniques for hyperspectral data classification". IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 24 May 2023, 5297-5314. https://doi.org/10.1109/JSTARS.2023.32795061939-1404, eISSN: 2151-1535https://doi.org/10.1109/JSTARS.2023.3279506https://hdl.handle.net/20.500.14468/24408The registered version of this article, first published in “ IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 2023", is available online at the publisher's website: IEEE, https://doi.org/10.1109/JSTARS.2023.3279506 La versión registrada de este artículo, publicado por primera vez en “ IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 16, 2023", está disponible en línea en el sitio web del editor: IEEE, https://doi.org/10.1109/JSTARS.2023.3279506Land-cover classification is an important topic for remotely sensed hyperspectral (HS) data exploitation. In this regard, HS classifiers have to face important challenges, such as the high spectral redundancy, as well as noise, present in the data, and the fact that obtaining accurate labeled training data for supervised classification is expensive and time-consuming. As a result, the availability of large amounts of training samples, needed to alleviate the so-called Hughes phenomenon, is often unfeasible in practice. The class-imbalance problem, which results from the uneven distribution of labeled samples per class, is also a very challenging factor for HS classifiers. In this article, a comprehensive review of oversampling techniques is provided, which mitigate the aforementioned issues by generating new samples for the minority classes. More specifically, this article pursues a twofold objective. First, it reviews the most relevant oversampling methods that can be adopted according to the nature of HS data. Second, it provides a comprehensive experimental study and comparison, which are useful to derive practical conclusions about the performance of oversampling techniques in different HS image-based applications.eninfo:eu-repo/semantics/openAccess12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informáticaartículo