A5074986791- Traffic Prediction and Management Techniques
- Direction-of-Arrival Estimation Techniques
- Advanced Adaptive Filtering Techniques
- Advanced Graph Neural Networks
- Advanced Image and Video Retrieval Techniques
- Pancreatic function and diabetes
- Image and Signal Denoising Methods
- Multimodal Machine Learning Applications
- Energy Load and Power Forecasting
- Radar Systems and Signal Processing
- Mesenchymal stem cell research
- Tissue Engineering and Regenerative Medicine
- Robotics and Sensor-Based Localization
- Sparse and Compressive Sensing Techniques
Northeastern University
2024
Tianjin Medical University General Hospital
2023
University of Notre Dame
2022
MSCs have been demonstrated to a great benefit for type 1 diabetes mellitus (T1DM) due their strong immunosuppressive and regenerative capacity. However, the comprehensive mechanism is still unclear. Our previous study indicated that transforming growth factor beta induced (TGFBI) highly expressed in human umbilical cord-derived mesenchymal stem or stromal cells (hUC-MSCs), which are also implicated T1DM. In this study, we found infusion of TGFBI knockdown hUC-MSCs displayed impaired...
Earth Mover's Distance (EMD) is an important similarity measure between two distributions, used in computer vision and many other application domains. However, its exact calculation computationally memory intensive, which hinders scalability applicability for large-scale problems. Various approximate EMD algorithms have been proposed to reduce computational costs, but they suffer lower accuracy may require additional usage or manual parameter tuning. In this paper, we present a novel...
Predicting and quantifying the impact of traffic accidents is necessary critical to Intelligent Transport Systems (ITS). As a state-of-the-art technique in graph learning, current neural networks heavily rely on Fourier transform, assuming homophily among neighborhood. However, assumption makes it challenging characterize abrupt signals such as accidents. Our paper proposes an wavelet network (AGWN) model predict their time durations using only one single snapshot.