A5070305120- Electric Power System Optimization
- Magnetic Field Sensors Techniques
- Blind Source Separation Techniques
- Digital Media Forensic Detection
- Advanced Data Compression Techniques
- Gait Recognition and Analysis
- Mechanical stress and fatigue analysis
- Human Pose and Action Recognition
- Structural Load-Bearing Analysis
- Anomaly Detection Techniques and Applications
- Sensor Technology and Measurement Systems
- Hand Gesture Recognition Systems
- Radiomics and Machine Learning in Medical Imaging
- Advanced Electrical Measurement Techniques
- Optimal Power Flow Distribution
- Speech and Audio Processing
- COVID-19 diagnosis using AI
- Engineering Structural Analysis Methods
- Smart Grid Energy Management
China State Construction Engineering (China)
2025
China Agricultural University
2016
PG&E Corporation (United States)
2000
In this paper, a systematical study on the influence of strengthening parameters flexural performance RC beams using NSM application was carried out. Experimental results consist two reference and 25 divided into groups systems with various embedded bars configurations were presented. Additionally, theoretical analysis conducted to enrich research affecting strength failure mode beams. The accuracy formulas has been verified through experimental results, average value ratio between values is...
Motivation: A machine learning model capable of accurately estimating brain age could have a large clinical impact. Goal(s): To apply radiomics analysis to morphological MR images and train subjects’ from features. Approach: T1- T2-weighted 725 healthy adults were used extract 18324 features bilateral caudate, putamen, hippocampus, stacking regressor model. Results: Our estimated the with mean absolute error 4.77±0.35 years using T1-(45%) T2-weighted(55%). Impact:...
We investigate the statistical and computational limits of prompt tuning for transformer-based foundation models. Our key contributions are on \textit{single-head} transformers with only a \textit{single} self-attention layer: (i) is universal, (ii) supports efficient (even almost-linear time) algorithms under Strong Exponential Time Hypothesis (SETH). Statistically, we prove that such simplest possible universal approximators sequence-to-sequence Lipschitz functions. In addition, provide an...