Performance Evaluation of Support Vector Machine and Stacked Autoencoder for Hyperspectral Image Analysis

In the world of remote sensing, hyperspectral imaging has emerged as a powerful tool that captures incredibly detailed information about our environment. These images contain hundreds of spectral bands that reveal what the human eye cannot see, making them invaluable for applications ranging from pr...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE journal of selected topics in applied earth observations and remote sensing Jg. 18; S. 16429 - 16444
Hauptverfasser: Jabir, Brahim, Nadif, Bendaoud, Diez, Isabel De la Torre, Garay, Helena, Noya, Irene Delgado
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Piscataway IEEE 2025
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:
Accuracy
Active learning
Computational modeling
Data models
Datasets
Deep learning
Environmental monitoring
hyperspectral data classification
Hyperspectral imaging
Image analysis
Image classification
Image processing
Machine learning
Noise
Performance evaluation
Precision agriculture
Remote sensing
Spectral bands
stacked autoencoder (SAE)
support vector machine (SVM)
Support vector machines
Training
ISSN:1939-1404, 2151-1535
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In the world of remote sensing, hyperspectral imaging has emerged as a powerful tool that captures incredibly detailed information about our environment. These images contain hundreds of spectral bands that reveal what the human eye cannot see, making them invaluable for applications ranging from precision agriculture to environmental monitoring. However, extracting insights from complex data requires sophisticated analytical approaches. Our research dives into the performance comparison of two popular machine learning approaches: the support vector machine (SVM) and the more recent deep learning-based stacked autoencoder (SAE). We wanted to understand which approach works better under different real-world conditions that researchers and practitioners face. Through extensive experiments across five diverse public hyperspectral datasets, we discovered that the choice between these models is not straightforward, it depends significantly on your specific circumstances. When labeled data are scarce, which is a common challenge in remote sensing, SVM proves more reliable and efficient. Conversely, when abundant training data are available, SAE demonstrates impressive capabilities in learning complex patterns. One interesting finding was how active learning as a technique that intelligently selects the most informative samples for labeling, improved SAE's performance on medium-sized datasets, potentially offering a practical solution to the data scarcity problem. The proposed approaches showed vulnerability to noise, highlighting the importance of preprocessing steps in real-world applications. Although SVM generally requires less computational resources, SAE's potential to handle large and complex datasets makes it an attractive option when the appropriate computing infrastructure is available. The model training also achieved high accuracy, compared to other models published in the literature. The results achieved provide a practical path for researchers and practitioners navigating the complex landscape of hyperspectral image analysis to help them choose the most suitable approach for their specific constraints and requirements.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2025.3580654