Intelligent Sine Cosine Optimization with Deep Transfer Learning Based Crops Type Classification Using Hyperspectral Images

Hyperspectral Remote Sensing (HRS) is an emergent, multidisciplinary paradigm with several applications, which are developed on the basis of material spectroscopy, radiative transfer, and imaging spectroscopy. HRS plays a vital role in agriculture for crops type classification soil prediction. The recently artificial intelligence techniques can be used using HRS. This study develops Intelligent Sine Cosine Optimization Deep Transfer Learning Based Crop Type Classification (ISCO-DTLCTC) model. ISCO-DTLCTC technique comprises initial preprocessing step to extract region interest. information gain-based feature reduction employed reduce dimensionality original hyperspectral images. In addition, fusion 3 deep convolutional neural networks models namely, VGG16, SqueezeNet, Dense-EfficientNet perform extraction process. Furthermore, sine cosine optimization (SCO) algorithm Modified Elman Neural Network (MENN) model applied classification. design SCO helps proficiently select parameters involved MENN performance validation carried out benchmark datasets results inspected under measures. Extensive comparative demonstrated betterment over state art approaches maximum accuracy 99.99%.