Deep learning methods have been widely used in PolSAR image classification. To learn the polarimetric information, many deep learning methods expect to learn high-level semantic features from original PolSAR data. However, only original data cannot learn multiple scattering features and complex structures for extremely heterogeneous terrain objects. In addition, deep learning methods always cause edge confusion due to the high-level features. To overcome these shortages, we propose a double-channel CNN network combined with an edge-preserving MRF model(DCCNN-MRF) for PolSAR image classification. Firstly, to combine complex matrix data and multiple scattering features together, a double-channel convolution network(DCCNN) is developed, which consists of a Wishart-based complex matrix and multi-feature subnetworks. The Wishart-based complex matrix network can learn the statistical characteristics and channel correlation well, and the multi-feature network can learn high-level semantic features well. Then, a unified network framework is designed to fuse two kinds of features to enhance advantageous features and reduce redundant ones. Finally, an edge preserving MRF model is designed to combine with the DCCNN network. In the MRF model, a sketch map-based edge energy function is designed by defining adaptive weighted neighborhood for edge pixels. Experiments are conducted on four real PolSAR data sets with different sensors and bands. Experimental results demonstrate the effectiveness of the proposed DCCNN-MRF method.

With the extension of the post-catch circulation time, a series of changes had taken place in the soft tissue of the live clams, resulting in the decline of its quality. This study investigated the quality changes of clams (Ruditapes philippinarum) in cold chain and was mainly focused on the rehydration process, which included gradient heating rehydration (GR) and sudden heating rehydration (SR). It was found that the GR had a better effect on the quality of clams than the SR. The GR stage clams showed a higher survival rate, glycogen content and adenylate energy charge (A.E.C) value than the SR stage clams. Conversely, the GR stage clams showed lower lactic acid content and K-value than the SR stage clams. The results indicated that the gradient heating rehydration was beneficial to the quality of clams. The transportation and rehydration strategies benefited both producers and shellfish merchants to save total cost.

This study aimed to examine the association of blood triglyceride levels with fasting blood glucose levels and type 2 diabetes (T2D) prevalence in Chinese adults with normal triglyceride levels (<1.7 mmol/L), using linear regression and binary logistic regression, respectively. This cross-sectional study included 16,706 Chinese adults, among which 1,067 had T2D. Triglycerides were positively associated with fasting plasma glucose after multivariate adjustment (β=0.034, P<0.001). One natural log unit increase in blood triglycerides was associated with a 61% higher multivari-ate-adjusted risk of T2D (odds ratio [OR], 1.61; 95% confidence interval [CI], 1.19-2.17; P=0.002). The positive associations remained when participants who were treated with lipid-lowering or an-ti-diabetic drugs were excluded. The optimal cut-off of triglycerides for T2D was 1.09 mmol/L (obtained using Receiver Operating Characteristic curve analysis). Participants with triglycerides of ≥1.09 mmol/L had a 28% higher risk of T2D (OR, 1.28; 95% CI, 1.07-1.53; P=0.006) compared to those with triglycerides below the cut-off. In conclusion, this study showed that, in people with normal triglyceride levels, triglycerides at the upper normal range correlated with increased T2D diagnosis risk, with an optimal cut-off of 1.09 mmol/L. Therefore, adults with high “normal” triglyceride levels (1.09-1.69 mmol/L) may need to be closely monitored for the development of T2D.