Mitsunori Ogihara
University of Miami, FL·Computer Science
Sensors connected to the internet now produce data faster than conventional analysis can handle. This is true of medical scanners, weather stations and industrial machines alike.
- Fields
Computer Science
Engineering
- Topics
real-time analytics
machine learning
artificial intelligence
- Grants
- 1 known grant, through Sep 2029
What they work on
- Develop accelerated methods for analyzing medical images, using AI/ML together with coupled software and programmable hardware so results arrive fast enough for real-time use.
- Build explainable, interpretable AI/ML methods for medical and vision-language models, so users can understand why a model reached its output.
- Create digital twins, computer replicas of dynamic physical systems, that combine physics-based modeling with machine learning and real-time simulation.
- Explore federated learning, semi- and unsupervised learning, programmable architectures and blockchains as general tools for accelerated analytics across healthcare, cybersecurity and environmental applications.
More about the research
Analyzing that data quickly, even in real time, matters for health monitoring, wildfire and weather prediction, cybersecurity and national defense. This center grant studies how to speed up data analysis using artificial intelligence and machine learning (AI/ML) together with specially designed computing hardware.
Why it matters
Faster, interpretable analysis of sensor and imaging data could help hospitals read medical images more quickly, and help agencies and companies monitor disease, predict weather and wildfires, and detect cybersecurity threats in real time. Because the methods are designed to work across fields, industry partners in healthcare, environmental monitoring and business intelligence could adapt them to their own data.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Steven Brunton
University of Washington, WA·Engineering
Develop physics-aware machine learning methods that build physical laws and stability constraints into the models, producing interpretable models that work reliably for aerospace design and control.
Leif Nelson
Boise State University, ID·Computer Science
Deploy and integrate six compute nodes, each with four NVIDIA L40S GPUs, into the existing campus research computing cluster to support data science, machine learning, and AI workloads.
Joseph Camp
Southern Methodist University, TX·Computer Science
Develop an AI curriculum covering federated learning, explainable AI, homomorphic encryption and neural networks, taught through lectures, exercises and simulations and shared via the NAIRR Pilot.
The school
University of Miami: 30 labs on PI Pages, $559M a year on research, 297 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.