No abstract

No abstract

Detecting the damaged building regions is vital to humanitarian assistance and disaster recovery after a disaster. Deep-learning-techniques based on aerial and Unmanned Aerial Vehicle (UAV) images have been extensively applied in the literature to detect damaged building regions, which are approved to be effective methods for fast response actions and rescue work. However, most of the existing building damaged region detection methods only consider the extraction accuracy of damaged regions from aerial or UAV images, which are not real-time and can hardly meet the practical application of emergency response. To address this problem, a new real-time building damaged region detection based on improved YOLOv5 and adapted to an embedded system from UAV images is proposed, which is named as DB-YOLOv5. First, residual dilated convolution module(Res-DConv) is employed to extract the spatial features, which can increase the receptive field. Then, a feature fusion module(BDSCAM) is designed to enhance the expressive ability of object feature, which could improve the classification performance of detector. Finally, a Double-Head method, an integration system of fully connected and convolution head for bounding box regression and classification, executes the localization task. The proposed DB-YOLOv5 method was evaluated using post-disaster UAV images collected over Ludian, China in 2013 and Beichuan, China in 2008. We found that the experimental results This work was supported by the National Natural Science Foundation of China (42101358) and Opening Research Fund of National Engineering Laboratory for Surface Transportation Weather Impacts Prevention under Grant 201801.(Yunlong Wang and Wenqing Feng contributed equally to this work.

No abstract

Background: Hyperbaric oxygen (HBO) therapy can prevent further spinal cord injury (SCI) caused by spinal cord ischemia-reperfusion injury to the maximum extent, which has been reported increasingly in recent years. However its security and effectiveness still lack of high-quality medical evidence. In this study, we will perform a systematic review of previously published randomized controlled trials (RCTs) to evaluate the efficacy and safety of HBO therapy for SCI. Methods: All potential RCTs on HBO therapy for SCI will be searched from the following electronic databases: PubMed, Embase, Cochrane Library, Web of Science, China National Knowledge Infrastructure, Chinese Science and Technology Periodical Database, Wanfang database and Chinese Biomedical Literature Database. We will search all electronic databases from their initiation to the September 30, 2020 in spite of language and publication date. Two contributors will independently select studies from all searched literatures, extract data from included trials, and evaluate study quality for all eligible RCTs using Cochrane risk of bias tool, respectively. Any confusion will be resolved by consulting contributor and a consensus will be reached. We will utilize RevMan 5.3 software to pool the data and to conduct the data analysis. Results: The quality of the assessments will be assessed through Grading of Recommendations Assessment, Development, and Evaluation. Data will be disseminated through publications in peer-reviewed journals. Conclusion: This study will provide evidence to evaluate the efficacy and safety of HBO therapy for SCI at evidence-based medicine level. Trial registration number: INPLASY 2020100084.