No abstract

A novel O-(carboxymethyl)-chitosan (OCMC) nanofiltration (NF) membrane is developed via surface functionalization with graphene oxide (GO) nanosheets to enhance desalting properties. Using ring-opening polymerization between epoxy groups of GO nanosheets and amino groups of OCMC active layer, GO nanosheets are irreversibly bound to the membrane. The OCMC NF membranes surface-functionalized with GO nanosheets are characterized by Fourier-transform infrared spectroscopy, X-ray photoelectron spectroscopy, scanning electron microscopy, atomic force microscopy, contact angle analyzer, and zeta potential analyzer. The membranes exhibit not only higher permeability but also better salt rejections than the pristine membranes and the commercial NF membranes; besides, the desalting properties are enhanced with the concentration of GO nanosheets increasing. Furthermore, the transport mechanism of GO-OCMC NF membranes reveals that the nanoporous structure of GO-OCMC functional layer and size exclusion and electrostatic repulsion of water nanochannels formed by GO nanosheets lead to the membranes possessing enhanced desalting properties.

Deep spectral-spatial features fusion has become a research focus in hyperspectral image (HSI) classification. However, how to extract more robust spectral-spatial features is still a challenging problem. In this article, a novel deep multilayer fusion dense network (MFDN) is proposed to improve the performance of HSI classification. The proposed MFDN simultaneously extracts the spatial and spectral features based on different sample input sizes, which can extract abundant spectral and spatial correlation information. First, the principal component analysis algorithm is performed on hyperspectral data to extract low-dimensional HSI data, and then the spatial features are extracted from the lowdimensional 3-D HSI data through 2-D convolutional, 2-D dense block, and average-pooling layers. Second, the spectral features are extracted directly from the raw 3-D HSI data by means of 3-D convolutional, 3-D dense block, and average-pooling layers. Third, the spatial and spectral features are fused together through 3-D convolutional, 3-D dense block, and average-pooling layers. Finally, the fused spectral-spatial features are sent into two full connection layers to extract high-level abstract features. Furthermore, densely connected structures can help alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and improve the HSI classification accuracy. The proposed fusion network outperforms the other state-of-the-art methods especially with a small number of labeled samples. Experimental results demonstrate that it can achieve outstanding hyperspectral classification performance. Index Terms-Deep learning, densely connected convolutional neural network, hyperspectral image (HSI) classification, multilayer feature fusion. I. INTRODUCTION H YPERSPECTRAL sensors can capture hundreds of narrow spectral channels with very high spectral resolution.

Recently, networks consider spectral-spatial information in multiscale inputs less, even though there are some networks that consider this factor, however these networks cannot guarantee to get optimal features, which are extracted from each scale input. Furthermore, these networks do not consider the complementary and related information among different scale features. To address these issues, a multiscale deep middle-level feature fusion network (MMFN) is proposed in this paper for hyperspectral classification. In MMFN, the network fully fuses the strong complementary and related information among different scale features to extract more discriminative features. The training of network contains two stages: the first stage obtains the optimal models corresponding to different scale inputs and extracts the middle-level features under the corresponding scale model. It can guarantee the multiscale middle-level features are optimal. The second stage fuses the optimal multiscale middle-level features in the convolutional layer, and the subsequent residual blocks can learn the complementary and related information among different scale middle-level features. Moreover, the idea of identity mapping in residual learning can help the network obtain a higher accuracy when the network is deeper. The effectiveness of our method is proved on four HSI data sets and the experimental results show that our method outperforms the other state-of-the-art methods especially with small training samples.

No abstract