No abstract

No abstract

Many deep learning models, such as convolutional neural network (CNN) and recurrent neural network (RNN), have been successfully applied to extracting deep features for hyperspectral tasks. Hyperspectral image classification allows distinguishing the characterization of land covers by utilizing their abundant information. Motivated by the attention mechanism of the human visual system, in this study, we propose a spectral-spatial attention network for hyperspectral image classification. In our method, RNN with attention can learn inner spectral correlations within a continuous spectrum, while CNN with attention is designed to focus on saliency features and spatial relevance between neighboring pixels in the spatial dimension. Experimental results demonstrate that our method can fully utilize the spectral and spatial information to obtain competitive performance.

No abstract

No abstract

We report both experimentally and theoretically that enhanced acoustic transmission can occur in the subwavelength region through a thin but stiff structured plate without any opening. This exotic acoustic phenomenon is essentially distinct from the previous related studies originated from, either collectively or individually, the interaction of the incident wave with openings in previous structures. It is attributed to the structure-induced resonant excitation of the nonleaky Lamb modes that exist intrinsically in the uniform elastic plate. Our finding should have an impact on ultrasonic applications.

No abstract

It is important to study the antioxidant activities of polysaccharides and their derivatives for the development of natural antioxidants.