An optimized feature selection approach using sand Cat Swarm optimization for hyperspectral image classification
Yükleniyor...
Tarih
2024
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Elsevier
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Integrating metaheuristic algorithms and optimization techniques with remote sensing technology has accelerated the advent of advanced methodologies for analyzing hyperspectral images (HSIs). These images, rich in detail across a broad spectral range, are pivotal for diverse applications. However, the high dimensionality of data poses challenges for obtaining optimal results therefore, a preprocessing step is necessary to reduce the dimensionality of the data to select the most effective features before the application of machine learning models. This study introduces a novel methodology that integrates Back Propagation (BP) and Variable Adaptive Momentum (BPVAM) with Sand Cat Swarm Optimization (SCSO) for the classification of hyperspectral images. Utilizing SCSO for the optimal feature selection followed by BPVAM generated more accurate classification maps. The fusion of the unique strengths of SCSO with the flexibility of BPVAM has significantly boosted the precision, efficiency, and adaptability of HSI classification. The effectiveness of our method is demonstrated using two benchmark hyperspectral datasets and validated through a comprehensive comparison with other benchmark optimization techniques, including Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO). Our findings indicate that our approach enhances classification accuracy that is comparable to the stateof-the-art methods in the domain of hyperspectral data analysis.
Açıklama
Anahtar Kelimeler
Hyperspectral Image Classification, Sand Cat Swarm Optimization Algorithm Optimization, Backpropagation With Variable Adaptive Momentum, Feature Selection
Kaynak
Infrared physics and technology
WoS Q Değeri
Q2
Scopus Q Değeri
Q2
Cilt
141
Sayı
Künye
Hameed, A. A., Jamil, A., & Seyyedabbasi, A. (2024). An optimized feature selection approach using sand Cat Swarm optimization for hyperspectral image classification. Infrared Physics & Technology, 141, 105449.
