A5083353650- Radiomics and Machine Learning in Medical Imaging
- High Entropy Alloys Studies
- Medical Imaging and Analysis
- MRI in cancer diagnosis
- High-Temperature Coating Behaviors
- Advanced Neural Network Applications
- Endometrial and Cervical Cancer Treatments
- Human Pose and Action Recognition
- Additive Manufacturing Materials and Processes
- Face recognition and analysis
- Video Surveillance and Tracking Methods
- Emotion and Mood Recognition
- Titanium Alloys Microstructure and Properties
- Hydrology and Sediment Transport Processes
- Pain Management and Placebo Effect
- Soil erosion and sediment transport
- Brain Tumor Detection and Classification
- Advanced Radiotherapy Techniques
- Heat Transfer and Boiling Studies
- Domain Adaptation and Few-Shot Learning
- COVID-19 diagnosis using AI
- Prostate Cancer Diagnosis and Treatment
- Manufacturing Process and Optimization
- Cell Image Analysis Techniques
- Image Enhancement Techniques
Anhui University of Science and Technology
2025
Anhui Science and Technology University
2025
Air Force Engineering University
2023-2024
Air Force Medical University
2006-2024
Guangdong Research Institute of Water Resources and Hydropower
2009-2023
Central South University
2007-2022
Northeastern University
2019-2022
Guangdong Polytechnic of Science and Technology
2015-2022
Institute of Plasma Physics
2022
Soochow University
2022
Sediment-induced erosion is a primary cause of failure in the flow-passage components Francis turbine units. This study adopted Realizable k–ε turbulence model to numerically simulate effects sediment-induced on guide turbines. Specifically, using flow similarity theory, testing device suitable for studying behavior vanes was designed, and between fields actual validated. The results revealed high degree consistency near-wall velocities sediment volume fractions experienced by both at 0.5...
Many factors affect the quality of injection molding plastic products, including process parameters, mold materials, type and geometry parts, cooling system, pouring etc. A multi-objective optimization method for parameters based on BP neural network NSGA-II algorithm is proposed to address problem product defects caused by unreasonable parameter settings. Taking junction box shell as object, numerical simulation was carried out using Moldflow2019 software a six-factor five-level orthogonal...
In medical institutions, pain is one of the important clues for patients to transmit their conditions effectively, which makes estimation status an exceedingly task. Of late, many methods have been proposed address this However, most them estimate from entire face images or videos instead paying more attention regions relevant pain. We propose a pain-awareness multistream convolutional neural network (CNN) estimation. Specifically, we separate expression, and CNN used learn corresponding...
It is becoming a trend that many strengthening methods are applied at the same time to overcome strength-ductility trade-off. However, combination of precipitation and transformation-induced plasticity (TRIP) rarely used effectively because precipitates will hinder phase transformation. In this work, coherent L12 Face-Centered Cubic (FCC) - Hexagonal Close-Packed (HCP) type martensitic transformation combined in single alloy. With synergistic effect both sides, yield strength aged...
In this paper, we present a new, large-scale database on underwater image, which is called the NWPU image database. This contains 6240 images of 40 objects. Each object captured with 6 different levels turbidity water, 4 lighting conditions and distances. Among them, use value 0 as Ground-truth. addition, shadowless in air clear water. Different from other databases, capture real high lake water instead simulating method ensures that are close possible to environment. We have given baseline...
Pain is a significant indicator that shows people are suffering from an unwell experience and its automatic estimation has attracted much interest in recent years. Of late, most methods designed to capture the dynamic pain information visual signals while few physiological-signal based can provide extra potential cues analyze more accurately. However, it still challenging physiological data patients as requires contact devices patients' cooperation. In this paper, we propose leverage pseudo...
Abstract Pain is a common phenomenon in clinical patients, which indicates patients are suffering from uncomfortable conditions for necessary treatments. So the assessment of pain status becomes significant task current medical institutions. Of late, various conventional hand‐crafted or deep learning methods on face images presented to estimate intensity automatically. However, these approaches usually feed whole into automatic estimation system and explore little information...
Similar to the basic facial expression recognition, one challenge for pain intensity recognition is some individual characteristics, e.g. face shapes, may cause great diversities in same emotion. So it usually very difficult distinguish two adjacent levels of as each has a large variation. In this study, coarse‐to‐fine combination method proposed recognition. The results multi‐scale outputs from multiple base deep network are combined probabilistic way improving discrimination between...
Background: This study aimed to develop a model that automatically predicts the neoadjuvant chemoradiotherapy (nCRT) response for patients with locally advanced cervical cancer (LACC) based on T2-weighted MR images and clinical parameters. Methods: A total of 138 were enrolled, information before treatment collected. Clinical included age, stage, pathological type, squamous cell carcinoma (SCC) level, lymph node status. hybrid extracted domain-specific features from computational radiomics...
Abstract Intensive human activity has caused significant changes in the river morphology and hydrological characteristics of Pearl River Delta. Particularly, in‐channel mining dam construction have induced remarkable levels downward riverbed incision. Although strict control measures been implemented for sand mining, it remains unclear how evolved since abandonment high‐intensity its impact on flow diversion at downstream confluence. This study presents morphological adjustments lower...
MRI is an important tool for accurate detection and targeted biopsy of prostate lesions. However, the imaging appearances some cancers are similar to those surrounding normal tissue on MRI, which referred as MRI-invisible (MIPCas). The MIPCas remains challenging requires extensive systematic identification. In this study, we developed a weakly supervised UNet (WSUNet) detect MIPCas.
Previous contrastive deep clustering methods mostly focus on instance-level information while overlooking the member relationship within groups/clusters, which may significantly undermine their representation learning and capability. Recently, some group-contrastive have been developed, which, however, typically rely samples of entire dataset to obtain pseudo labels lack ability efficiently update group assignments in a batch-wise manner. To tackle these critical issues, we present novel...