A5000576513- Medical Imaging Techniques and Applications
- Image and Signal Denoising Methods
- Seismic Imaging and Inversion Techniques
- Advanced X-ray and CT Imaging
- Green IT and Sustainability
- Advanced Battery Technologies Research
- Neural Networks and Applications
- Electric Vehicles and Infrastructure
- Radiation Dose and Imaging
- Graph Theory and Algorithms
- Advanced Research in Systems and Signal Processing
- Metaheuristic Optimization Algorithms Research
Northern Arizona University
2024
University of Electronic Science and Technology of China
2020-2024
This paper proposes an integrated approach combining computer networks and artificial neural to construct intelligent network operator, functioning as AI model. State information from is transformed into embedded vectors, enabling the operator efficiently recognize different pieces of accurately output appropriate operations for at each step. The has undergone comprehensive testing, achieving a 100% accuracy rate, thus eliminating operational risks. Additionally, simple simulator created...
The remarkable success of deep learning (DL) in predicting battery health has prompted interest its application recent years. While state-of-the-art DL models have achieved high accuracy prediction, they not been widely adopted industrial workflows, primarily due to their lack interpretability and security. To address this issue, we propose a blockchain-based interpretable prediction algorithm for electric vehicles (EVs) within the Internet Vehicles (IoV). Specifically, proposed method...
This paper proposes an integrated approach combining computer networks and artificial neural to construct intelligent network operator, functioning as AI model. State information from is transformed into embedded vectors, enabling the operator efficiently recognize different pieces of accurately output appropriate operations for at each step. The has undergone comprehensive testing, achieving a 100% accuracy rate, thus eliminating operational risks. Furthermore, novel algorithm proposed...
Recently, cross domain adaptation has been applied into quite a few image restoration tasks. While promising performance achieved, the shift problem between training set (a.k.a., source domain) and testing target in Low-dose Computed Tomography (LDCT) denoising tasks is typically ignored by most existing methods. This prone to degradation of due large discrepancy feature distribution each dataset from various vendors. Therefore, simple yet effective LDCT approach proposed this paper...
Deep learning (DL)-based Low-dose CT (LDCT) image denoising methods may face domain shift problem, where data from different domains (i.e., hospitals) have similar anatomical regions but exhibit intrinsic noise characteristics. Therefore, we propose a plug-and-play model called Lowand High-frequency Alignment (LHFA) to address this issue by leveraging semantic features and aligning distributions of datasets, while maintaining diagnostic quality suppressing noise. Specifically, the LHFA...
Compared with normal-dose computed tomography (NDCT), low-dose CT (LDCT) images have lower potential radiation risk for patients while suffering from the degradation problem by noise. In past decades, deep learning-based (DL-based) methods achieved impressive denoising performances in comparison to traditional methods. However, most existing DL-based typically preform training on a specific pairs of LDCT/NDCT and aim generalize well clinical scenarios LDCT only. It is difficult task...