About me
I’m a researcher and software developer working at the intersection of neuroscience, signal processing and machine learning. I work as an Assistant Professor at the Rochester Institute of Technology (RIT), where I develop causal cross-frequency models to better detect electro-hemodynamic dynamics in the brain, and I teach courses on neuroscience, neuroimaging and artificial intelligence.
Before RIT, I was a Postdoctoral Researcher in Biomedical Engineering at the University of California, Irvine, where I worked on statistical tests for phase-amplitude coupling and on connectivity methods to locate seizure-generating tissue. I received my PhD in Engineering Sciences from Oslo Metropolitan University in 2021, with a dissertation on time-spectral modeling of biomedical signals. I have also worked for some time as a data scientist in industry.
My research combines statistical modeling, signal processing and machine learning to extract meaningful patterns from complex neurological data, including scalp EEG, intracranial EEG and fNIRS recordings. My technical interests include:
- Scientific computing
- Signal processing
- Bayesian statistical modeling
- Machine learning
- Data visualization
- Low-resource computing
I also built high-performance tools for scientific computing (mainly before agentic programming), mostly in the Python, R and JavaScript ecosystems: real-time signal processing algorithms, interactive web applications for scientific visualization, statistical packages for biomedical data, and cross-platform applications for complex data modeling. I still built software tools, but I emphasized more in the algorithmic and numerical correctness than code.
On the blog, I write about software development practices in scientific computing, signal processing or data analysis techniques that are transversal for my research, but not more engineering-focused than science.
You can find my publication list](@/publications/_index.md) and CV on this site, or reach me at mapcgns@rit.edu.