A5074146436- Speech Recognition and Synthesis
- Natural Language Processing Techniques
- Topic Modeling
- Speech and dialogue systems
- Speech and Audio Processing
- Structural Health Monitoring Techniques
- Infrastructure Maintenance and Monitoring
- Advancements in Battery Materials
- Music and Audio Processing
- Advanced Battery Materials and Technologies
- Prostate Cancer Diagnosis and Treatment
- Supercapacitor Materials and Fabrication
- 3D Surveying and Cultural Heritage
- Wireless Power Transfer Systems
- Energy Harvesting in Wireless Networks
- Health Systems, Economic Evaluations, Quality of Life
- Advanced Battery Technologies Research
- Neural Networks and Applications
- Seismic Performance and Analysis
- Structural Engineering and Vibration Analysis
- Non-Destructive Testing Techniques
- Advanced ceramic materials synthesis
- Cardiac, Anesthesia and Surgical Outcomes
- Semiconductor materials and devices
- Advanced materials and composites
Heilongjiang University
2025
South China University of Technology
2019-2025
Cell Technology (China)
2024-2025
Shandong Academy of Sciences
2025
Qilu University of Technology
2025
Ministry of Education of the People's Republic of China
2025
Powerchina Huadong Engineering Corporation (China)
2023-2025
PowerChina (China)
2025
Soochow University
2022-2025
Tongji University
2024
Abstract This article implements the state‐of‐the‐art deep learning technologies for a civil engineering application, namely recognition of structural damage from images. Inspired by ImageNet Challenge and development computer hardware, concept Structural is proposed herein with four naïve baseline tasks: component type identification, spalling condition check, level evaluation, determination. A relatively small number images (2,000) are selected manually labeled according to tasks. In order...
Five diverse technology companies show how it's done.
This article looks at the knowledge graphs of five diverse tech companies, comparing similarities and differences in their respective experiences building using graphs, discussing challenges that all knowledge-driven enterprises face today. The collection discussed here covers breadth applications, from search, to product descriptions, social networks.
Hitherto, it remains a great challenge to stabilize electrolyte-electrode interfaces and impede lithium dendrite proliferation in lithium-metal batteries with high-capacity nickel-rich LiNx Coy Mn1-x-y O2 (NCM) layer cathodes. Herein, special molecular-level-designed polymer electrolyte is prepared by the copolymerization of hexafluorobutyl acrylate methylene bisacrylamide construct dual-reinforced stable interfaces. Verified X-ray photoelectron spectroscopy depth profiling, there are...
Abstract Employing Deep Learning (DL) technologies to solve Civil Engineering problems is an emerging topic in recent years. However, due the lack of labeled data, it difficult obtain accurate results with DL. One commonly used method tackle this issue use affine transformation augment data set, but can only generate new images that are highly correlated original ones. Moreover, unlike normal natural objects, distribution structural much more complex and mixed. To address these challenges,...
Abstract In recent years, applying deep learning (DL) to assess structural damages has gained growing popularity in vision‐based health monitoring (SHM). However, both data deficiency and class imbalance hinder the wide adoption of DL practical applications SHM. Common mitigation strategies include transfer learning, oversampling, undersampling, yet these ad hoc methods only provide limited performance boost that varies from one case another. this work, we introduce variant generative...
With the rapid development of machine learning (ML) and deep (DL) in computer vision, adopting these tools vision-based structural health monitoring (SHM) damage assessment is attracting interest engineering. However, several critical issues become impediments, namely, no general automated detection framework, insufficient labeled data, lack collaboration, inconsistent research approaches. Thus, this paper, authors propose a Pacific Earthquake Engineering Research (PEER) Hub ImageNet...
Abstract In bridge health monitoring (BHM), crack identification and width measurement are two of the most important indices for evaluating functionality bridges. order to reduce labor cost in field detection, researchers have proposed a variety deep learning (DL)‐based detection techniques recognition. However, some problems still exist extending these practical applications, such as data annotation difficulty, limited model generalization ability, inaccuracy DL actual measurement. this...
Abstract Visual understanding on construction sites by deep learning, such as semantic segmentation, is hardly mentioned in the literature due to severe lack of labeled data sets. To resolve this issue, we collect and label 859 images, including 12 classes objects activities, from different sites. We then adopt DeepLabV3+ set with modifications. leverage Cityscape pretrain model, fine‐tune it our collected set. Moreover, multiple augmentation techniques are utilized expand training Our model...
Bolt loosening is a critical factor that triggers collapse of wind turbine tower structures, and fast accurate bolt detection significant importance. This paper proposes two-stage framework, which combines the traditional manual torque method commonly used in engineering with deep learning model to reduce cost inspection rate missed inspection. A graphical marks was collect synthetic datasets, reducing time required training test sets real environments. The You Only Look Once (YOLO)-based...
Abstract Using deep learning (DL) to recognize building and infrastructure damage via images is becoming popular in vision‐based structural health monitoring (SHM). However, many previous studies solely work on the existence of directly treat problem as a single‐attribute classification or separately focus finding location area localization segmentation problem. Abundant information from multiple sources intertask relationships are not fully exploited. In this study, SHM first reformulated...
Purpose.: To determine the biocompatibility of a new wireless intraocular pressure (IOP) transducer (WIT) in rabbit eyes and to correlate its measurements with other pressure-measuring devices. Methods.: The WIT is ring-shaped device that allows IOP through radiofrequency. It was implanted into six New Zealand White rabbits after extracapsular lens extraction. A sham eye no used as control. animals were observed examined by microscopy at various intervals up 25 months surgery. measured...
Recent data suggest that increasing rates of hospitalization after prostate biopsy are mainly due to infections from fluoroquinolone-resistant bacteria. We report the initial results a statewide quality improvement intervention aimed at reducing infection related hospitalizations transrectal biopsy.From March 2012 through May 2014 on patient demographics, comorbidities, prophylactic antibiotics and post-biopsy complications were prospectively entered into an electronic registry by trained...
This paper presents a novel robust method for single target tracking in RGB-D images, and also contributes substantial new benchmark dataset evaluating trackers. While object's color distribution is reasonably motion-invariant, this not true the target's depth distribution, which continually varies as moves relative to camera. It therefore nontrivial design models can fully exploit (potentially very rich) information tracking. For reason, much of previous literature relies on tracking, while...
Background and Aims HCC is a leading cause of cancer‐related deaths globally with poor outcome limited therapeutic options. Although the myelocytomatosis ( MYC ) oncogene frequently dysregulated in HCC, it thought to be undruggable. Thus, current study aimed identify critical downstream metabolic network develop therapies for MYC‐driven HCC. Approach Results Liver cancer was induced mice hepatocyte‐specific disruption Myc control by administration diethylnitrosamine. Liquid chromatography...