Hyperspectral Image Classification with Deep CNN Using an Enhanced Elephant Herding Optimization for Updating Hyper-Parameters

Deep learning approaches based on convolutional neural networks (CNNs) have recently achieved success in computer vision, demonstrating significant superiority the domain of image processing. For hyperspectral (HSI) classification, are an efficient option. Hyperspectral classification often spectral information. Convolutional used for order to achieve greater performance. The complex computation requires hyper-parameters that attain high accuracy outputs, and this process needs more computational time effort. Following up proposed technique, a bio-inspired metaheuristic strategy enhanced form elephant herding optimization is research paper. It allows one automatically search target suitable values network hyper-parameters. To design automatic system (EEHO) with AdaBound optimizer implemented tuning updating (CNN–EEHO–AdaBound). validation should produce highly accurate response high-accuracy outputs high-level HSI takes amount processing time. experiments carried out benchmark datasets (Indian Pines Salinas) evaluation. methodology outperforms state-of-the-art methods performance comparative analysis, findings proving its effectiveness. results show improved by optimising