A5058416787- Infrastructure Maintenance and Monitoring
- Asphalt Pavement Performance Evaluation
- Non-Destructive Testing Techniques
- Geotechnical Engineering and Underground Structures
- Geophysical Methods and Applications
- Marine and coastal plant biology
- Concrete Corrosion and Durability
- Marine Biology and Ecology Research
- Transport Systems and Technology
- Marine Bivalve and Aquaculture Studies
- Real-time simulation and control systems
- Advanced DC-DC Converters
- Structural Health Monitoring Techniques
- Remote Sensing and LiDAR Applications
- Surface Roughness and Optical Measurements
- Image and Object Detection Techniques
- Wireless Sensor Networks and IoT
- Wind Turbine Control Systems
- Advanced Neural Network Applications
- Polar Research and Ecology
- Monoclonal and Polyclonal Antibodies Research
- Immunotherapy and Immune Responses
- Vehicle License Plate Recognition
- Tunneling and Rock Mechanics
- Multilevel Inverters and Converters
Shenyang Jianzhu University
2022-2025
Chinese Academy of Fishery Sciences
2022-2023
Ministry of Agriculture and Rural Affairs
2023
Tianjin University
2023
Shanghai Ocean University
2022
Guangdong Provincial Academy of Building Research Group
2021
Southwest Jiaotong University
2014-2020
Guangzhou Academy of Building Research (China)
2019
Oklahoma State University
2017
Science and Technology Department of Sichuan Province
2014
Abstract The CrackNet, an efficient architecture based on the Convolutional Neural Network (CNN), is proposed in this article for automated pavement crack detection 3D asphalt surfaces with explicit objective of pixel‐perfect accuracy. Unlike commonly used CNN, CrackNet does not have any pooling layers which downsize outputs previous layers. fundamentally ensures accuracy using newly developed technique invariant image width and height through all consists five includes more than one million...
A few recent developments have demonstrated that deep-learning-based solutions can outperform traditional algorithms for automated pavement crack detection. In this paper, an efficient deep network called CrackNet-V is proposed pixel-level detection on 3D asphalt images. Compared with the original CrackNet, has a deeper architecture but fewer parameters, resulting in improved accuracy and computation efficiency. Inspired by uses invariant spatial size through all layers such supervised...
CrackNet is the result of an 18-month collaboration within a 10-person team to develop deep learning–based pavement crack detection software that demonstrated successes in terms consistency for both precision and bias. This paper proposes improved architecture called II enhanced learning capability faster performance. The proposed represents two major modifications on original CrackNet. First, feature generator, which provides handcrafted features through fixed nonlearnable procedures, no...
The classification of pavement crack heavily relies on the engineers' experience or hand-crafted algorithms. Convolutional Neural Network (CNN) has demonstrated to be useful for image classification, which provides an alternative traditional imaging This paper proposes a novel method using deep CNN automatically classify patches cropped from 3D images. In all, four supervised CNNs with different sizes receptive field are successfully trained. experimental results demonstrate that all...
Climate change is altering geographic and phylogeographic distribution of macroalgae, laying great impacts on their conservation sustainable utilization. The potential two dominant cultured seaweeds-Neoporphyra haitanensis Neopyropia yezoensis was predicted under present three representative concentration pathways (RCP 2.6, 4.5, 8.5) for 2050 s using the maximum entropy model (MaxEnt). area receiver operating characteristic curve (AUC) 0.998 N. 0.992 yezoensis, indicating high modelling...
Due to the complexity and diversity of pavement surfaces, cracking detection is a challenging task even for human operators. The automation generally requires robust algorithms with high level intelligence. From such perspective, Deep Learning, promising branch Artificial Intelligence, can serve as an advanced approach intelligence by learning from huge amount historical data enhancing capability behaving correctly under unforeseen complex environments. This paper proposes convolutional...
Pavement cracking is a significant symptom of pavement deterioration and deficiency. Conventional manual inspections road condition are gradually replaced by novel automated inspection systems. As result, great amount surface information digitized these systems with high resolution. With data, cracks can be detected using crack detection algorithms. In this paper, fully algorithm for segmenting enhancing proposed, which consists four major procedures. First, preprocessing procedure employed...
The prompt and accurate detection of tunnel lining cracks is essential for maintaining the safety reliability tunnels. Deep learning-based approaches have significantly advanced automated crack detection, delivering improved efficiency precision in inspection. Nevertheless, intricate characteristics cracks, manifesting as fine, elongated, irregular structures, pose substantial challenges deep semantic segmentation networks, hindering their ability to achieve comprehensive identification....
Automated pavement condition survey is of critical importance to road network management. There are three primary tasks involved in surveys, namely data collection, processing and evaluation. Artificial intelligence (AI) has achieved many breakthroughs almost every aspect modern technology over the past decade, undoubtedly offers a more robust approach automated survey. This article aims provide comprehensive review on collection systems, algorithms evaluation methods proposed between 2010...
The accurate detection of tunnel lining cracks and prompt identification their primary causes are critical for maintaining availability. advancement deep learning, particularly in the domain convolutional neural network (CNN) image segmentation, has made crack more feasible. However, CNN-based technique commonly prioritizes increasing algorithmic complexity to enhance accuracy, posing a challenge balancing accuracy efficiency algorithm. Motivated by superior performance Unet this paper...
Abstract Cracks are an indicator for a bridge’s structural health and functional failures. Crack detection is one of the major tasks needed to maintain serviceability bridge. At present, most commonly used crack technology manual inspection, which has disadvantages being highly labor-intensive time-consuming. In this paper, method based on convolutional neural network (CNN) proposed. To automate quantitative measurements identified crack, hybrid image processing proposed, as well. First,...
To study the real dynamic response regularity of asphalt pavement structure under load, a road test was conducted for three types typical pavement. Dynamic and static deflection basins were established. The characteristics basin studied. set-in strain sensors at bottom surface layer collected falling weight deflectometer (FWD) load. Results show that is deeper than basin, but range latter larger former. two differ. change trends with an increase in FWD load reflect nonlinear characteristics....
In order to study the strength forming mechanism and influencing factors of half-warm mix asphalt (HWMA), stability Marshall samples is tested under different test conditions such as gradations, quantities, methods, number compaction passes, maintenance period, forms maintenance. The results show that (1) suspension dense gradation satisfactory for early HWMA, its varies with quantity; (2) passes period are two major external forming, increase in reduces significantly when on both sides...
Railway condition survey is limited by available time, particularly for high-speed railway due to the need use its full capacity every day. Therefore, at high-automation level becomes necessary. In addition, different from highway pavement assessment, safety primary factor survey. The frequency usually daily or weekly, while runway surveys are commonly conducted on annual basis. Rail profile measurement in transverse direction, missing broken fastener detection and slab surface crack...
As to conduct the wind power generation experimental research in laboratory, a feasible scheme which simulates characteristics of turbine using synchronous motor controlled by servo controller was proposed. The operational principle analyzed and mathematical model built. simulation system has been designed on basis studying vector control system. consists B&R Programmed Computer Controller (PCC), controller, hysterics absorption dynamometer. adapted simulate performance characteristic...
Pavement distress data has been widely collected through pavement survey to evaluate roadway condition. Despite rapid advancements in automated collection, the implementation of used condition index (PCI) still requires extensive manual labor either tradition or image-based PCI inspections. This paper proposes a deep-learning (DL) based automatic cracking detection algorithm and further evaluates potential for with obtained results on asphalt pavement. The two- three-dimensional (2D 3D)...
Abstract The purpose of this study was to develop stable microsatellite markers and evaluate the genetic background cultivated Sargassum fusiforme. Based on transcriptome data obtained by high-throughput sequencing, eleven polymorphic were developed using four S. fusiforme populations from China. One population Dongtou (DT) three wild Muye Island (MY), Pingyu (PY) Nanji (NJ). had highest diversity, with 90.91% loci Shannon’s information index ( I ) 0.606, which much higher than those =...
Abstract Neopyropia yezoensis is a typical intertidal seaweed and major mariculture crops in China. The culture area of N. has been largely increasing the past decade. Whether large-scale cultivation genetic impact on wild populations remains unknown. Here, eleven polymorphic microsatellite markers were developed applied for structure analysis 22 from along coast divided into 4 groups based Bayesian model-based analysis. A significant difference was present between cultivated ones. 13 two...