|
| 1 | +import { Card, CardContent, CardHeader, CardTitle } from "@/components/ui/card"; |
| 2 | + |
| 3 | +const projects = [ |
| 4 | + { |
| 5 | + title: "Smart Artificial Pancreas Systems", |
| 6 | + description: ( |
| 7 | + <> |
| 8 | + In collaboration with the <strong className="dark:text-white">UVA Center of Diabetes</strong>, we are pioneering "trainable" artificial pancreas systems that leverage |
| 9 | + machine learning to personalize diabetes management for individuals with <strong className="dark:text-white">Type 1 Diabetes</strong>. By harnessing vast amounts of continuous |
| 10 | + glucose monitoring (CGM) and insulin delivery data, we're developing smarter, fully automated closed-loop control algorithms. Our goal is to improve |
| 11 | + patient outcomes and enhance quality of life by providing more precise and adaptive insulin delivery. |
| 12 | + </> |
| 13 | + ), |
| 14 | + }, |
| 15 | + { |
| 16 | + title: "Single-Cell Signaling Dynamics", |
| 17 | + description: ( |
| 18 | + <> |
| 19 | + Our team is creating novel learning frameworks to analyze how individual cells respond to different stimuli. By focusing on signaling molecules |
| 20 | + and transcription factors, we aim to uncover how cells make heterogeneous and context-dependent decisions. We integrate high-dimensional single-cell |
| 21 | + measurements with live-cell trajectory data using advanced techniques like <strong>stochastic flow matching</strong> and <strong>spectral operator analysis</strong>. |
| 22 | + This research advances our understanding of cellular behavior at the single-cell level, potentially leading to new therapeutic strategies in precision medicine. |
| 23 | + </> |
| 24 | + ), |
| 25 | + }, |
| 26 | + { |
| 27 | + title: "Explainable AI for Glaucoma Risk Assessment", |
| 28 | + description: ( |
| 29 | + <> |
| 30 | + We are developing <strong>GUIDE</strong> (Glaucoma Understanding and Integrated Data Evaluation), an explainable AI framework that uses <strong>foundation models</strong> |
| 31 | + to integrate clinical data, imaging, electronic health records, and social determinants of health. Our goal is to provide personalized glaucoma risk assessments, |
| 32 | + enhance fairness, and reduce health disparities through transparent and robust multimodal models. By employing <strong>hierarchical fusion models</strong> and focusing |
| 33 | + on <strong>contextual transparency</strong>, we aim to transform glaucoma management and improve patient outcomes. |
| 34 | + </> |
| 35 | + ), |
| 36 | + }, |
| 37 | + { |
| 38 | + title: "Operator-Theoretic Methods in Dynamical Systems", |
| 39 | + description: ( |
| 40 | + <> |
| 41 | + Employing operator theory, particularly within the <strong>Koopman framework</strong>, we analyze the spectral characteristics of complex dynamical systems. |
| 42 | + This work advances reduced-order modeling and innovative control strategies, improving <strong>Model Predictive Control (MPC)</strong> and model-based learning |
| 43 | + for high-dimensional, nonlinear systems. Our approach addresses challenges like instabilities from continuous spectra and sensitivity to initial conditions, |
| 44 | + enhancing the performance of <strong>model-based reinforcement learning</strong> and <strong>physics-informed machine learning (ML)</strong> methods. |
| 45 | + </> |
| 46 | + ), |
| 47 | + }, |
| 48 | + { |
| 49 | + title: "Complex Networks and Graph Data Analysis", |
| 50 | + description: ( |
| 51 | + <> |
| 52 | + We investigate the dynamics of complex networks to understand how topological features influence processes such as information spread, disease transmission, |
| 53 | + and network robustness. By leveraging <strong>machine learning</strong>, <strong>dynamical systems theory</strong>, and <strong>reinforcement learning</strong>, |
| 54 | + we design and optimize network architectures for desired functionalities in communication networks, power grids, and social systems. Our research enhances the |
| 55 | + capabilities of <strong>Graph Neural Networks (GNNs)</strong> by incorporating high-order structures, capturing nuanced relationships, and improving community detection. |
| 56 | + </> |
| 57 | + ), |
| 58 | + }, |
| 59 | +]; |
| 60 | + |
| 61 | +export function ProjectsCard() { |
| 62 | + return ( |
| 63 | + <Card className="dark:bg-gray-800 dark:border-gray-700"> |
| 64 | + <CardHeader> |
| 65 | + <CardTitle className="dark:text-white">Current Projects</CardTitle> |
| 66 | + </CardHeader> |
| 67 | + <CardContent className="space-y-8"> |
| 68 | + {projects.map((project, index) => ( |
| 69 | + <div key={index}> |
| 70 | + <h3 className="font-semibold mb-2 text-zinc-700 dark:text-zinc-300">{project.title}</h3> |
| 71 | + <p className="text-sm dark:text-gray-300">{project.description}</p> |
| 72 | + </div> |
| 73 | + ))} |
| 74 | + </CardContent> |
| 75 | + </Card> |
| 76 | + ); |
| 77 | +} |
0 commit comments