A5101706851- Topic Modeling
- Advanced Neural Network Applications
- Groundwater flow and contamination studies
- Natural Language Processing Techniques
- Enhanced Oil Recovery Techniques
- Sentiment Analysis and Opinion Mining
- Microbial bioremediation and biosurfactants
- Appendicitis Diagnosis and Management
- Industrial Vision Systems and Defect Detection
- Domain Adaptation and Few-Shot Learning
- Emotion and Mood Recognition
- Biometric Identification and Security
- Multi-Agent Systems and Negotiation
- Advanced Text Analysis Techniques
- Software Engineering Techniques and Practices
- Artificial Intelligence in Healthcare and Education
- Network Security and Intrusion Detection
- Dental Radiography and Imaging
- Multisensory perception and integration
- User Authentication and Security Systems
- Intracerebral and Subarachnoid Hemorrhage Research
- Surface Roughness and Optical Measurements
- Medical Imaging and Analysis
- Coronary Interventions and Diagnostics
- COVID-19 diagnosis using AI
First People's Hospital of Foshan
2024
Guangxi University
2022-2023
Shenzhen Institutes of Advanced Technology
2022-2023
Xiamen University
2019-2022
Harbin Institute of Technology
2021
Peng Cheng Laboratory
2021
Xiamen University of Technology
2018
Jimei University
2018
Recently, coronary heart disease has attracted more and attention, where segmentation analysis for vascular lumen contour are helpful treatment. And intravascular optical coherence tomography (IVOCT) images used to display shapes in clinic. Thus, an automatic method IVOCT is necessary reduce the doctors' workload while ensuring diagnostic accuracy. In this paper, we proposed a deep residual network of multi-scale feature fusion based on attention mechanism (RSM-Network, Residual Squeezed...
Planar primitives tend to be incorrectly detected or incomplete in complex scenes where adhesions exist between different objects, resulting topology errors the reconstructed models. We propose a semantic-guided building reconstruction method known as (SGR), which is capable of achieving independence and integrity models two key stages. In first stage, space partition represented by 2.5D convex cell restoring planar that are easily lost can further infer potential structural adaptivity. The...
Jianzhu Bao, Chuang Fan, Jipeng Wu, Yixue Dang, Jiachen Du, Ruifeng Xu. Proceedings of the 59th Annual Meeting Association for Computational Linguistics and 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.
Aim: To investigate the application of ultrasound along with clinical features for differential diagnosis low-grade appendiceal mucinous neoplasm (LAMN) and acute suppurative appendicitis (ASA).Material methods: The data 76 patients histopathologically confirmed LAMN (31 patients) ASA (45 were retrospectively analyzed. Univariate analysis binary logistic regression influencing factors conducted to identify ASA. AUROC was calculated analyze diagnostic efficacy these independent factors. A...
Recent works have validated the benefit of integrating spatial information into deep networks to improve pixel-level prediction tasks such as monocular depth estimation. However, how efficiently and robustly integrate cues retains an open problem. In this paper, we introduce Side Prediction Aggregation (termed SPA) method enhance embedding scene structural from low-level high-level layers. To estimation accuracy, proposed is further equipped with continuous Spatial Refinement Loss SRL) at...
Summary Face anti‐spoofing has attracted many attentions in security applications, such as mobile payment and entrance guard. Until now, face technique is still a challenging task. Mainstream image‐based spoofing algorithms usually use global motion or texture information to distinguish whether an input live fake. However, the performance of these methods are sensitive light changes, images acquired from different sensors. The main reason that spoofed image always slight local areas,...
In this paper we present the results of AI-Debater 2023 Challenge held by Chinese Conference on Affect Computing (CCAC 2023), and introduce related datasets. We organize two tracks to handle argumentative generation tasks in different scenarios, namely, Counter-Argument Generation (Track 1) Claim-based Argument 2). Each track is equipped with its distinct dataset baseline model respectively. total, 32 competing teams register for challenge, from which received 11 successful submissions....
High-quality scalp EEG datasets are extremely valuable for motor imagery (MI) analysis. However, due to electrode size and montage, different inevitably experience channel information loss, posing a significant challenge MI decoding. A 2D representation that focuses on the time domain may loss spatial in EEG. In contrast, 3D based topography suffer from introduce noise through padding methods. this paper, we propose framework called Reference Electrode Standardization Interpolation Network...
The tooth arrangements of human beings are challenging to accurately observe when relying on dentists' naked eyes, especially for dental caries in children, which is difficult detect. Cone-beam computer tomography (CBCT) used as an auxiliary method measure patients' teeth, including children. However, subjective and irreproducible manual measurements required during this process, wastes much time energy the dentists. Therefore, a fast accurate segmentation algorithm that can replace repeated...
Deep networks have recently been applied to medical assistant diagnosis. The brain is the largest and most complex structure in central nervous system, which also complicated images such as computed tomography (CT) scan. While reading CT image, radiologists generally search across image find lesions, characterize measure them, then describe them radiological report. To automate this process, we quantitatively analyze cerebral hemorrhage dataset propose a Multi-scale Feature with...
To comprehensively reveal the effects of endogenous heavy metals on desorption and release n-hexadecane in calcareous soils from a karst area, present work conducted kinetic experiments column experiments. This study also focused relationship between under various environmental factors including pH, ionic strength (IS), rhamnolipid (RL). Results demonstrated that higher content Pb solution with lower pH level created additional absorption sites for n-hexadecane, thereby inhibiting soil...
Abstract Petroleum hydrocarbon pollutants in karst areas have aroused widespread concern due to their toxicity. It is crucial gain knowledge on transport and retention of petroleum hydrocarbons areas. Calcareous soils were contaminated by cadmium/naphthalene the industrial agricultural activities, however, fates these calcareous been rarely studied. In this study, n-hexadecane was selected as a model hydrocarbon. Batch experiments conducted explore adsorption behavior...