A5016260664- Probabilistic and Robust Engineering Design
- Optimal Experimental Design Methods
- Advanced Multi-Objective Optimization Algorithms
- Radiomics and Machine Learning in Medical Imaging
- MRI in cancer diagnosis
- stochastic dynamics and bifurcation
- Machine Learning in Materials Science
- Nonlinear Dynamics and Pattern Formation
- Advanced Graph Neural Networks
- Power System Optimization and Stability
- Model Reduction and Neural Networks
- Complex Network Analysis Techniques
- Medical Imaging Techniques and Applications
- Advanced Neuroimaging Techniques and Applications
- Manufacturing Process and Optimization
- Advanced machining processes and optimization
- Functional Brain Connectivity Studies
- Complex Systems and Decision Making
- Smart Grid Security and Resilience
- Infrastructure Resilience and Vulnerability Analysis
- Power Systems and Renewable Energy
- Chaos control and synchronization
- Atrial Fibrillation Management and Outcomes
- Dementia and Cognitive Impairment Research
- Supply Chain Resilience and Risk Management
Arizona State University
2024-2025
Advanced Imaging Research (United States)
2024-2025
Binghamton University
2018-2022
North China Electric Power University
2013
Background The aim of this study was to examine the potential added value including neuropsychiatric symptoms (NPS) in machine learning (ML) models, along with demographic features and Alzheimer's disease (AD) biomarkers, predict decline or non-decline global domain-specific cognitive scores among community-dwelling older adults. Objective To evaluate impact adding NPS AD biomarkers on ML model accuracy predicting Methods conducted setting Mayo Clinic Study Aging, participants aged ≥ 50...
The interconnectivity between constituent nodes gives rise to cascading failure in most dynamic networks, such as a traffic jam transportation networks and sweeping blackout power grid systems. Basin stability (BS) has recently garnered tremendous traction quantify the reliability of dynamical In it quantifies capability regain synchronous state after being perturbated. It is noted that detection vulnerable node or generator with lowest BS N−1 critical toward optimal decision making on...
Abstract The recent COVID-19 pandemic reveals the vulnerability of global supply chains: unforeseen crunches and unpredictable variability in customer demands lead to catastrophic disruption production planning management, causing wild swings productivity for most manufacturing systems. Therefore, a smart resilient system (S&RMS) is promised withstand such unexpected perturbations adjust promptly mitigate their impacts on system’s stability. However, modeling resilience disruptive events...
Time delay arises in a variety of real-world complex systems. A high-fidelity simulation generally renders high accuracy to simulate the dynamic evolution such systems and appraise quantity interest for process design response optimization. Identification limit states exemplifies applications, which outlines boundary that separates distinct regions (e.g., stability region) parameter space. While experiments is common procedure evaluate decision functions sketch boundary, it crucially relies...
Abstract In this study, we carry out robust optimal design for the machining operations, one key process in wafer polishing chip manufacturing, aiming to avoid peculiar regenerative chatter and maximize material removal rate (MRR) considering inherent uncertainty. More specifically, characterize cutting tool dynamics using a delay differential equation (DDE) enlist temporal finite element method (TFEM) derive its approximate solution stability index given settings or variables. To further...
Based on a brief review current harmonics generation mechanism for grid-connected inverter under distorted grid voltage, the harmonic disturbances and uncertain items are immersed into original state-space differential equation of inverter. A new algorithm global rejection based nonlinear backstepping control with multivariable internal model principle is proposed exogenous uncertainties. type class constructed. application law nominal system, adaptive state feedback controller combined...
Weakly-supervised diffusion models (DM) in anomaly segmentation, leveraging image-level labels, have attracted significant attention for their superior performance compared to unsupervised methods. It eliminates the need pixel-level labels training, offering a more cost-effective alternative supervised However, existing methods are not fully weakly-supervised because they heavily rely on costly hyperparameter tuning inference. To tackle this challenge, we introduce Anomaly Segmentation with...
Amyloid PET imaging plays a crucial role in the diagnosis and research of Alzheimer’s disease (AD), allowing non-invasive detection amyloid-β plaques brain. However, low spatial resolution scans limits accurate quantification amyloid deposition due to partial volume effects (PVE). In this study, we propose novel approach addressing PVE using latent diffusion model for recovery (LDM-RR) imaging. We leverage synthetic data generation pipeline create high-resolution digital phantoms training....
Abstract In computer simulation and optimal design, sequential batch sampling offers an appealing way to iteratively stipulate points based upon existing selections efficiently construct surrogate modeling. Nonetheless, the issue of near duplicates poses tremendous quandary for learning. It refers situation that selected critical cluster together in each batch, which are individually but not collectively informative towards design. Near severely diminish computational efficiency as they...
Amyloid PET imaging plays a crucial role in the diagnosis and research of Alzheimer's disease (AD), allowing non-invasive detection amyloid-β plaques brain. However, low spatial resolution scans limits accurate quantification amyloid deposition due to partial volume effects (PVE). In this study, we propose novel approach addressing PVE using latent diffusion model for recovery (LDM-RR) imaging. We leverage synthetic data generation pipeline create high-resolution digital phantoms...