- Organic Electronics and Photovoltaics
- Organic Light-Emitting Diodes Research
- Industrial Vision Systems and Defect Detection
- Image Processing Techniques and Applications
- Image Retrieval and Classification Techniques
- Advanced Image and Video Retrieval Techniques
- Magnetic Bearings and Levitation Dynamics
- Conducting polymers and applications
- Thermography and Photoacoustic Techniques
- Nonlinear Optical Materials Studies
- Video Surveillance and Tracking Methods
- Porphyrin and Phthalocyanine Chemistry
- Image Processing and 3D Reconstruction
- Video Analysis and Summarization
- Gear and Bearing Dynamics Analysis
- Advanced Measurement and Detection Methods
- Advanced Neural Network Applications
- Machine Fault Diagnosis Techniques
- Advanced Algorithms and Applications
- Traffic Prediction and Management Techniques
- Remote Sensing in Agriculture
- High voltage insulation and dielectric phenomena
- Nonlinear Optical Materials Research
- Transportation Planning and Optimization
- Remote Sensing and LiDAR Applications
Shandong University
2024-2025
Tongji University
2014-2024
Shanghai Tenth People's Hospital
2018-2024
Nanjing Agricultural University
2021-2022
State Grid Corporation of China (China)
2022
Electric Power Research Institute
2021
University of Illinois Urbana-Champaign
2020
Syracuse University
2020
Western Washington University
2020
Harbin Institute of Technology
2020
We propose a multi-lingual multi-task architecture to develop supervised models with minimal amount of labeled data for sequence labeling. In this new architecture, we combine various transfer using two layers parameter sharing. On the first layer, construct basis provide universal word representation and feature extraction capability all models. second level, adopt different sharing strategies schemes. This proves be particularly effective low-resource settings, when there are less than 200...
Manling Li, Alireza Zareian, Ying Lin, Xiaoman Pan, Spencer Whitehead, Brian Chen, Bo Wu, Heng Ji, Shih-Fu Chang, Clare Voss, Daniel Napierski, Marjorie Freedman. Proceedings of the 58th Annual Meeting Association for Computational Linguistics: System Demonstrations. 2020.
Due to the high precision and non-contact characteristics, infrared thermography has been widely used in equipment inspection ensure safety of electric power systems. A fundamental step toward automatic diagnosis is detection thermal images. Therefore, this paper presents a deep learning approach detect parts real-time. Specifically, we propose convolutional neural network that predicts coordinates, orientation angle, class type each part. prior concerning consistency between also...
Works like a charm: A soluble charm-bracelet-type poly(N-vinylcarbazole) functionalized with reduced graphene oxide (RGO-PVK) was synthesized by treating carbanion intermediates of PVK RGO (see scheme). This material exhibited excellent broadband optical limiting responses at both λ=532 and 1064 nm.
To relieve perceived pain in patients undergoing colonoscopy, we developed an endoscopist-patient co-participative VR tool (EPC-VR) based on A Neurocognitive Model of Attention to Pain. It allows the patient play a game actively and supports endoscopist triggering distraction mechanism divert patient's attention away from medical procedure. We performed comparative clinical study with 40 patients. Patients' perception affective responses were evaluated, results support effectiveness EPC-VR:...
Petroleum coke was pretreated by HNO3 before urea modification and KOH activation to synthesize N-doped porous carbons. The as-synthesized samples were carefully characterized various techniques. This series of demonstrate high CO2 uptake at 1 bar up 4.13 mmol/g 25 °C 6.24 0 °C, respectively. In addition, these sorbents possess CO2/N2 selectivity, stable reusability, moderate heat adsorption, dynamic capture capacity under simulated flue gas conditions. Further comparison shows that...
Rolling bearings usually work in tough conditions, which makes the collected vibration signals complex and fault features weak. Hence, feature extraction methods for rolling have become a research focus. In this paper, new method termed optimal variational mode decomposition (VMD) is proposed to extract bearing features. Firstly, since envelope entropy very sensitive signal features, used as fitness function, an objective function whale optimization algorithm (WOA). Secondly, WOA has...
A donor−acceptor−donor molecule, PcZn−Pim−PcZn triad, which would be applied to improve the light absorption efficiency and achieve efficient charge-separation states for appropriately long times, was prepared by reacting 3,4,9,10-perylene-tetracarboxylic dianhydride (Pim) with tBu3(NH2)PcZn at 190 °C. The process is anticipated occur via excited singlet state of zinc phthalocyanines (1PcZn*) perylene (1Pim*), depending on excitation wavelength used in polar nonpolar solvents. lifetime...
Infrared Thermography is an important way for electrical equipment live detection to monitor the status. In this paper, intelligent infrared image fault diagnosis method proposed. We first use a modified deep learning detect arbitrary capture angle part, and then features are extracted according result. With temperature value extracted, quantitative achieved by taking advantage of data mining methods. images captured substation used verify performance. The experimental results show that...
The function of microRNA-34a (miR-34a) in transdifferentiation glioma stem cells (GSCs) into vascular endothelial (VECs) was explored by focusing on Notch ligand Delta-like 1 (Dll1). MiR-34a mimics transfected CD133 + cell U251. angiogenesis feature miR-34a U251 investigated and the expressions CD31, CD34, Vwf, 1, Dll1 were quantified. Length branching vessel-like structures significantly higher than control cells. VEC overexpressed further confirmed vWF. Transfection decreased expression...