Search

Due to the complex background, small and dense targets, and large scale continuous changes in remote sensing images, universal object detectors are difficult to adapt well, resulting in poor detection performance. To address the above issues, a multi-branch feature mapping based remote sensing image object detection algorithm is proposed based on the YOLOv5s model. Firstly, a RepVGG module combined with gated channel transformation is designed using structural reparameterization technology. Its series structure is used to replace the C3 module of the original backbone network, aggregating global contextual information and enhancing feature expression and extraction capabilities. Secondly, the adaptive exponential weighted pooling method and the sampling method of inverse process reconstruction feature fusion network are used to maximize the retention of feature information and improve the detection performance of smaller targets. Finally, the combination of EIoU and Focal Loss is introduced as the loss function of the model to optimize the regression rate of the prediction box and the loss weight distribution of difficult and easy samples, further improving the positioning accuracy. The experimental results on the DIOR and NWPU VHR-10 datasets show that the average accuracy of the proposed algorithm reaches 92.2% and 92.5%, respectively, which is 3.5 percentage points and 5.6 percentage points higher than YOLOv5s, achieving better detection performance. At the same time, the real-time performance also meets the requirements of remote sensing image object detection in actual scenes.

Recent study has shown that deep feature matching methods in metric learning, combined with large-scale and diverse training data, can significantly enhance the generalization ability of person re-identification. However, many existing methods generate large memory and computational costs, such as classification parameters or class memory learning. To address these issues, a new generalization person re-identification method based on correlation graph sampler(CGS) is proposed. The basic idea of CGS is to construct a nearest neighbor relationship graph for all classes using local sensitive Hashing (LSH) and feature metrics at the beginning of training. This ensures that each small batch of training samples is composed of randomly selected base classes and near-neighboring classes that are similar to the base classes to provide informative and challenging learning examples and improve the discriminative learning ability of person re-identification models. The sampling principle of CGS is influenced by the quality of features extracted by the backbone network, and therefore, the sampling ability of CGS can be enhanced with the training of the backbone network and has learnability. Through cross-evaluation of this method on large-scale datasets(including CUHK03, Market-1501, and MSMT17), extensive experimental results demonstrate the effectiveness of this method and showcase its potential in person re-identification applications. [ABSTRACT FROM AUTHOR]

ObjectiveTo discuss the characteristics of psychological assistance hotline calls and operators' coping strategies of before and after the COVID-19 outbreak， in order to further improve the assistance ability of the psychological crisis hotline.MethodsA retrospective study was conducted on the demographics characteristics， call problems， coping strategies， and call time trends recorded by Changchun psychological assistance hotline information registration platform before the epidemic in Changchun City （January 20， 2019-April 20， 2019） and during the epidemic period （January 20， 2020-April 20， 2020）.ResultsThe differences between gender， age， marital status， location， and occupation type before and during the epidemic were statistically significant （χ2=11.205， 234.240， 152.083， 265.458， 353.385， P

In this work, we have fabricated a novel Fenton-like ferrihydrite/MoS2 (Fh/MoS2) composite and verified that the introduction of a small amount of iron on the surface of MoS2 can directly promote the exposure of Mo4+, finally enhancing the catalytic activity of the catalyst. Even though the content of iron element is only 1.19% in the composite, the reaction rate constant of Fh/MoS2 system for the degradation of environmental pollutants, such as organic dyes, antibiotic, and ionic liquid, is all much better than that of pure MoS2 system, which is attributed to much more generation of reactive oxygen species derived from synergistic effect of Fe3+/Fe2+ and Mo4+/Mo6+ redox cycles. The results of XPS and low-temperature EPR confirm that the exposure amount of Mo4+ active sites of 10% Fh/MoS2 is greatly increased, which is conducive to the conversion of Fe3+ to Fe2+ in the reaction process, thus effectively promoting the activation of H2O2. [ABSTRACT FROM AUTHOR]

Antler ossified tissue has been widely used for the extraction of bioactive peptides. In this study, collagen was prepared from antler ossified tissue via acetic acid and pepsin. Five different proteases were used to hydrolyze the collagen and the hydrolysate treated by neutrase (collagen peptide named ACP) showed the highest DPPH radical clearance rate. The extraction process of ACP was optimized by response surface methodology, and the optimal conditions were as follows: a temperature of 52 °C, a pH of 6.1, and an enzyme concentration of 3200 U/g, which resulted in the maximum DPPH clearance rate of 74.41 ± 0.48%. The peptides (ACP-3) with the strongest antioxidant activity were obtained after isolation and purification, and its DPPH free radical clearance rate was 90.58 ± 1.27%; at the same time, it exhibited good scavenging activity for ABTS, hydroxyl radical, and superoxide anion radical. The study investigated the protective effect of ACP-3 on oxidative damage in HaCaT cells. The findings revealed that all groups that received ACP-3 pretreatment exhibited increased activities of SOD, GSH-Px, and CAT compared to the model group. Furthermore, ACP-3 pretreatment reduced the levels of ROS and MDA in HaCaT cells subjected to H2O2-induced oxidative damage. These results suggest that collagen peptides derived from deer antler ossified tissue can effectively mitigate the oxidative damage caused by H2O2 in HaCaT cells, thereby providing a foundation for the utilization of collagen peptides in pharmaceuticals and cosmetics. [ABSTRACT FROM AUTHOR]