Underwater image enhancement using Divide-and-Conquer network.

Underwater image enhancement has become the requirement for more people to have a better visual experience or to extract information. However, underwater images often suffer from the mixture of color distortion and blurred quality degradation due to the external environment (light attenuation, background noise and the type of water). To solve the above problem, we design a Divide-and-Conquer network (DC-net) for enhancing underwater image, which mainly consists of a texture network, a color network and a refinement network. Specifically, the multi-axis attention block is presented in the texture network, which combine different region/channel features into a single stream structure. And the color network employs an adaptive 3D look-up table method to obtain the color enhanced results. Meanwhile, the refinement network is presented to focus on image features of ground truth. Compared to state-of-the-art (SOTA) underwater image enhance methods, our proposed method can obtain the better visual quality of underwater images and better qualitative and quantitative performance. The code is publicly available at https://github.com/zhengshijian1993/DC-Net.

The effect of TEMPOL pretreatment on postoperative cognitive function, inflammatory response, and oxidative stress in aged rats under sevoflurane anesthesia.

INTRODUCTION: The heterocyclic compound 4-hydroxy-(2,2,6,6-Tetramethylpiperidin-1-yl)oxyl (TEMPOL) has a protective effect on neurological function in brain tissues damaged by ischemia and hypoxia. This study explored the effects of TEMPOL pretreatment on postoperative cognitive function in aged rats under sevoflurane anesthesia, focusing on inflammatory response and oxidative stress. METHODS: Sixty male rats were divided into normal control (C), sevoflurane anesthesia (S), TEMPOL pretreatment (T), and sevoflurane anesthesia + TEMPOL pretreatment (ST) groups (15 per group). Groups T and ST rats received continuous intraperitoneal TEMPOL (100 mg/kg) for 3 days, while groups C and S rats were injected with 0.9% saline. After pretreatment, groups S and ST received 3% sevoflurane anesthesia. RESULTS: Rats in group S exhibited a longer swimming distance, longer escape latency, lower frequency of platform crossing, and shorter dwell time in the targeted quadrant than those in groups C and T. Rats in group ST exhibited a shorter swimming distance, shorter escape latency, higher frequency of platform crossing, and longer dwell time in the targeted quadrant than those in group S. The expressions of interleukin-6, tumor necrosis factor-α, inducible nitric oxide synthase, and Ym1/2 messenger ribonucleic acid were higher in groups S and ST rats than in groups C and T rats and lower in group ST rats than in group S rat (p < .05). Superoxide dismutase (SOD), total antioxidant capacity (T-AOC), and glutathione peroxidase (GSH-Px) were lower, while malondialdehyde (MDA) was higher in groups S and ST rats than in groups C and T rats (p < .05). Group ST showed higher SOD, T-AOC, and GSH-Px, and lower MDA than group S (p < .05). CONCLUSIONS: TEMPOL pretreatment attenuated postoperative cognitive impairment induced by sevoflurane anesthesia in aged rats. This may be attributed to the downregulation of NR2B-CREB-BDNF pathway, reducing the inflammatory response and oxidative stress damage in hippocampal tissue.

Remaining Useful Life Prediction of Rolling Bearings Based on Multi-Scale Attention Residual Network.

The remaining useful life (RUL) prediction of rolling bearings based on vibration signals has attracted widespread attention. It is not satisfactory to adopt information theory (such as information entropy) to realize RUL prediction for complex vibration signals. Recent research has used more deep learning methods based on the automatic extraction of feature information to replace traditional methods (such as information theory or signal processing) to obtain higher prediction accuracy. Convolutional neural networks (CNNs) based on multi-scale information extraction have demonstrated promising effectiveness. However, the existing multi-scale methods significantly increase the number of model parameters and lack efficient learning mechanisms to distinguish the importance of different scale information. To deal with the issue, the authors of this paper developed a novel feature reuse multi-scale attention residual network (FRMARNet) for the RUL prediction of rolling bearings. Firstly, a cross-channel maximum pooling layer was designed to automatically select the more important information. Secondly, a lightweight feature reuse multi-scale attention unit was developed to extract the multi-scale degradation information in the vibration signals and recalibrate the multi-scale information. Then, end-to-end mapping between the vibration signal and the RUL was established. Finally, extensive experiments were used to demonstrate that the proposed FRMARNet model can improve prediction accuracy while reducing the number of model parameters, and it outperformed other state-of-the-art methods.

Attention-Based Multiscale Feature Pyramid Network for Corn Pest Detection under Wild Environment.

A serious outbreak of agricultural pests results in a great loss of corn production. Therefore, accurate and robust corn pest detection is important during the early warning, which can achieve the prevention of the damage caused by corn pests. To obtain an accurate detection of corn pests, a new method based on a convolutional neural network is introduced in this paper. Firstly, a large-scale corn pest dataset has been constructed which includes 7741 corn pest images with 10 classes. Secondly, a deep residual network with deformable convolution has been introduced to obtain the features of the corn pest images. To address the detection task of multi-scale corn pests, an attention-based multi-scale feature pyramid network has been developed. Finally, we combined the proposed modules with a two-stage detector into a single network, which achieves the identification and localization of corn pests in an image. Experimental results on the corn pest dataset demonstrate that the proposed method has good performance compared with other methods. Specifically, the proposed method achieves 70.1% mean Average Precision (mAP) and 74.3% Recall at the speed of 17.0 frames per second (FPS), which balances the accuracy and efficiency.

Research on Data Fusion Scheme for Wireless Sensor Networks with Combined Improved LEACH and Compressed Sensing.

There are a lot of redundant data in wireless sensor networks (WSNs). If these redundant data are processed and transmitted, the node energy consumption will be too fast and will affect the overall lifetime of the network. Data fusion technology compresses the sampled data to eliminate redundancy, which can effectively reduce the amount of data sent by the node and prolong the lifetime of the network. Due to the dynamic nature of WSNs, traditional data fusion techniques still have many problems. Compressed sensing (CS) theory has introduced new ideas to solve these problems for WSNs. Therefore, in this study we analyze the data fusion scheme and propose an algorithm that combines improved clustered (ICL) algorithm low energy adaptive clustering hierarchy (LEACH) and CS (ICL-LEACH-CS). First, we consider the factors of residual energy, distance, and compression ratio and use the improved clustered LEACH algorithm (ICL-LEACH) to elect the cluster head (CH) nodes. Second, the CH uses a Gaussian random observation matrix to perform linear compressed projection (LCP) on the cluster common (CM) node signal and compresses the N-dimensional signal into M-dimensional information. Then, the CH node compresses the data by using a CS algorithm to obtain a measured value and sends the measured value to the sink node. Finally, the sink node reconstructs the signal using a convex optimization method and uses a least squares algorithm to fuse the signal. The signal reconstruction optimization problem is modeled as an equivalent l1-norm problem. The simulation results show that, compared with other data fusion algorithms, the ICL-LEACH-CS algorithm effectively reduces the node's transmission while balancing the load between the nodes.

Expression and clinical significance of Caveolin-1 in prostate Cancer after transurethral surgery.

BACKGROUND: Prostate cancer is a common malignancy of the male genitourinary system that occurs worldwide. The current research aims to investigate caveolin-1 expression in prostate cancer tissue and its relationship with pathological grade, clinical pathologic staging, and preoperative prostate-specific antigen (PSA) levels. METHODS: From January 2012 to December 2014, samples from 47 patients with prostate cancer who had received transurethral prostatic resection (TURP) and 20 patients with benign prostatic hyperplasia were collected at the First Affiliated Hospital of Guangxi Medical University. Caveolin-1 was detected by streptavidin-perosidase (SP) immunohistochemical staining in pathological tissue slices. The results were statistically analyzed for pathological grade, clinical stage, and preoperative PSA level. RESULTS: The expression of caveolin-1 was significantly higher in prostate cancer samples than in benign prostatic hyperplasia samples (P < 0.05), and caveolin-1 expression was significantly different among the pathological grades of poorly, moderately and well-differentiated prostate cancer (P < 0.05). The difference in caveolin-1 expression was significant for different clinical stages (T1-T2 and T3-T4) of prostate cancer (P < 0.05). The difference in caveolin-1 expression was not significant among samples with different preoperative PSA levels (0-10, 10-100 and > 100 µg/L) (P > 0.05). CONCLUSIONS: Caveolin-1 is closely related to the pathological grade and clinical stage of prostate cancer after transurethral surgery, and it may be a novel tumor marker for prostate cancer. The expression of caveolin-1 is not associated with preoperative serum PSA levels.