Hulya Seferoglu
University of Illinois Chicago, IL·Engineering·Early-career
Self-driving cars, drones, smartphones and sensors produce huge amounts of data. Many applications need this data processed in real time.
- Fields
Engineering
Computer Science
- Topics
coded computation
distributed computing
edge computing
- Grants
- 1 known grant, through Feb 2027
What they work on
- Characterize the cost-benefit trade-offs of coded computation, which adds redundancy to tolerate slow or failed workers, in practical edge computing systems.
- Develop networking algorithms and protocols that adapt coded computation to the uneven and changing resources of end devices, edge servers and cloud.
- Apply coded computation to distributed machine learning at the edge to cut communication cost and provide resilience, privacy and security.
- Design delay-sensitive coded computation schemes that balance latency, amount of redundancy, privacy and security.
More about the research
A self-driving car may generate about 10 GB per mile, too much to send to a distant cloud quickly. One alternative is to spread computing across the devices themselves, nearby edge servers and the cloud. Shared computing must still be fast, reliable and secure when some machines are slow, fail or cannot be trusted.
Why it matters
Time-sensitive Internet of Things applications, such as self-driving cars, drones, robots and health monitors, need fast, secure processing that a distant cloud cannot always provide. Practical coded computation could let these systems pool computing, storage and battery across nearby devices and edge servers while staying resilient and private.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Mingyue Ji
University of Florida, FL·Engineering·Early-career
Develop reconfigurable radio hardware and CAP-MIMO antenna designs, whose sub-apertures can be split between tasks, so one system can sense surroundings and communicate at once in the INSTINCT system.
Lena Mashayekhy
University of Delaware, DE·Computer Science·Early-career
Develop a data-driven method to find mobility patterns of Internet of Things devices that lead to quality-of-service violations in multiaccess edge computing systems.
Somali Chaterji
Purdue University, IN·Computer Science·Early-career
Develop on-device machine learning analytics for farm sensors that adapt to each device's computing power, changing network conditions and competition from co-located applications.
The school
University of Illinois Chicago: 42 labs on PI Pages, $532M a year on research, 359 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.