Core Contributors
Faculty
I want to quantify glymphatic flows and understand them in terms of physical mechanisms like pressure, stress, forces, momentum, and energy – at brain-wide and local scales. I want to use that understanding to suggest behaviors and interventions that can promote healthy glymphatic function and improve clinical outcomes. I want to link physical mechanisms to the neurological processes that control, and are controlled by, them. Tight coupling between models and experiments drives us forward.
Techniques:
- Automated particle tracking
- Automated front tracking
- Image processing
- Physics-informed neural networks
- Reduced-order modeling
- Glymphatic flow simulation & theory
- Fluid dynamics experiments
Sleep State analysis based on multi-modal data
We develop signal processing, image processing, and machine learning methods for information extraction from neurophysiological data. Our current focus in BrainFlowZZZ is sleep state analyis based in multi-model data incuding EEG/EcoG, EMG, fiber photometry. We also work on a variety of microscopic image analysis problems.
Techniques: Deep learning, time series analysis, image analysis, estimation theory, bayesian inference, optimization algorithms
Focuses on refining, simplifying, and automating existing data analysis workflows in the U19 project.
Our work includes the following: Develop anatomical shape analysis methods with improved segmentation and statistical shape characterization; Seek patterns in CSF flow that link to brain state; Classify sleep states in mice and humans via AI; Seek further insight into sleep state by incorporating hemodynamic data; Share novel tools and transformational data with the wider scientific community.
Techniques: computer vision, machine learning, time series analysis, multimodal learning and date mining
Staff
PhD Students
Focuses on refining, simplifying, and automating existing data analysis workflows in the U19 project.
Our work includes the following: Develop anatomical shape analysis methods with improved segmentation and statistical shape characterization; Seek patterns in CSF flow that link to brain state; Classify sleep states in mice and humans via AI; Seek further insight into sleep state by incorporating hemodynamic data; Share novel tools and transformational data with the wider scientific community.
Techniques: computer vision, machine learning, time series analysis, multimodal learning and date mining
Specializes in multi-model data research, focusing on analyzing physiological signals such as EEG, EMG, Fiber Photometry, and Norepinephrine data for sleep staging. I study the interrelations to advance digital biomarker discovery. My work involves leveraging AI for biomedical signal processing, particularly in developing machine learning models for sleep stage classification.
Techniques: signal processing, machine learning & deep learning, multimodal data analysis, digital biomarker discovery, AI-driven health sensing applications, brain-computer interfaces (BCI)
Undergraduate Researchers
Our aim is to quantify cerebral vessel pulsatility in awake and anesthetized mice using computational analysis of experimental data. We segment and calculate the average diameter of the blood vessel for each frame of 3 hour-long in vivo mouse recordings. These vessel diameter changes, along with ECG signals, can be used to calculate slow vasomotion and cardiac pulsatility.
Techniques: Image processing, edge detection, vessel diameter measurement, data analysis
Techniques: Developing and utilizing various machine learning models for data analysis goals including numerical predictions, labeling, and sample clustering, programming in Python, Java, and C for helper research tools development.