A5054356181- Fire dynamics and safety research
- Combustion and Detonation Processes
- Advanced Neural Network Applications
- Remote-Sensing Image Classification
- Oil Spill Detection and Mitigation
- Risk and Safety Analysis
- Fire Detection and Safety Systems
- Advanced Image and Video Retrieval Techniques
- Advanced Surface Polishing Techniques
- Pickering emulsions and particle stabilization
- Human Mobility and Location-Based Analysis
- Advanced Image Processing Techniques
- Medical Image Segmentation Techniques
- Video Surveillance and Tracking Methods
- Advanced machining processes and optimization
- Marine and Coastal Research
- Image and Object Detection Techniques
- Advanced Biosensing Techniques and Applications
- UAV Applications and Optimization
- Advanced Vision and Imaging
- Authorship Attribution and Profiling
- Coal Properties and Utilization
- Industrial Vision Systems and Defect Detection
- Knowledge Management and Technology
- Advanced Machining and Optimization Techniques
China University of Petroleum, East China
2018-2024
Zhuhai People's Hospital
2022
Jinan University
2022
Air Force Engineering University
2020-2021
Chang'an University
2020-2021
Chongqing University
2016-2021
Beihang University
2018
Chinese People's Liberation Army
2011
Memorial University of Newfoundland
2002
Hydrogen–gasoline hybrid refueling stations can minimize construction and management costs save land resources are gradually becoming one of the primary modes for hydrogen stations. However, catastrophic consequences may be caused as both gasoline flammable explosive. It is crucial to perform an effective risk assessment prevent fire explosion accidents at This study conducted a area hydrogen–gasoline station based on improved Accident Risk Assessment Method Industrial Systems (ARAMIS). An...
Industrial robotics is a continuously developing area of in-depth research, as industrial robots have demonstrated to possess advantages in the robotic automation solutions applications. In this paper, novel automatic seam bead grinding robot manipulator with integration machining and measuring proposed an experimentation platform developed for removal weld beads at welded pipe ends. Also, motion planning methodology, which consists operation process approach method, presented appropriate...
The influence of the initial fuel temperature on burning behavior crude oil pool fire in ice cavities was experimentally studied this paper. Bohai with temperatures 283, 293, and 303 K burned an cavity diameter 6–8 cm. mass loss rate exhibits three stages: decrease stage, growth decay stage. plays a significant role A heat transfer model is established to predict rate, which agrees well experimental value.
Background Many fundus imaging modalities measure ocular changes. Automatic retinal vessel segmentation (RVS) is a significant image-based method for the diagnosis of ophthalmologic diseases. However, precise challenging task when detecting micro-changes in images, e.g., tiny vessels, edges, lesions and optic disc edges. Methods In this paper, we will introduce novel double branch fusion U-Net model that allows one branches to be trained by weighting scheme emphasizes harder examples improve...
Oriented object detection in remote sensing images (RSIs) is a significant yet challenging Earth Vision task, as the objects RSIs usually emerge with complicated backgrounds, arbitrary orientations, multi-scale distributions, and dramatic aspect ratio variations. Existing oriented detectors are mostly inherited from anchor-based paradigm. However, prominent performance of high-precision real-time overshadowed by design limitations tediously rotated anchors. By using simplicity efficiency...
Driven by the wave of urbanization in recent decades, research topic about migrant behavior analysis draws great attention from both academia and government. Nevertheless, subject to cost data collection lack modeling methods, most existing studies use only questionnaire surveys with sparse samples non-individual level statistical achieve coarse-grained behaviors. In this paper, a partially supervised cross-domain deep learning model named CD-CNN is proposed for migrant/native recognition...
Object detection is regarded as a significant research branch of optical remote sensing image analysis. Aimed at the characteristics targets such direction diversity, small scales, and dense arrangements, state-of-the-art detectors used in images are primarily extended from some general natural approaches based on deep convolutional neural networks (DCNNs). Nevertheless, intended for commonly an anchor mechanism perform regression tasks Cartesian coordinate system, which requires complex...
Oriented object detection in optical remote sensing images (ORSIs) is a challenging task since the targets ORSIs are displayed an arbitrarily oriented manner and on small scales, densely packed. Current state-of-the-art models used primarily evolved from anchor-based direct regression-based paradigms. Nevertheless, they still encounter design difficulty handcrafted anchor definitions learning complexities localization regression. To tackle these issues, this paper, we proposed novel...
Recently, deep learning-based techniques have shown great power in image inpainting especially dealing with squared holes. However, they fail to generate plausible results inside the missing regions for irregular and large holes as there is a lack of understanding between existing counterparts. To overcome this limitation, we combine two non-local mechanisms including contextual attention module (CAM) an implicit diversified Markov random fields (ID-MRF) loss multi-scale architecture which...