Jia Liu
Ohio State University, OH·Engineering·Early-career
Phones, tablets and other wireless devices increasingly handle demanding data tasks: streaming live map updates, sharing images, and running machine learning models. Wireless networks and data-processing algorithms were mostly designed separately, so neither works as efficiently as it could for these new uses.
- Fields
Engineering
Computer Science
Mathematics & Statistics
- Topics
wireless networks
edge computing
wireless edge
- Grants
- 2 known grants, through Sep 2027
What they work on
- Develop communication-efficient distributed optimization methods at the wireless physical layer, so machine learning training and inference across edge devices use less communication.
- Design joint queueing and computing scheduling at the medium access control layer, which decides when each device transmits, using queueing theory and stochastic analysis.
- Create admission control and resource virtualization schemes at the transport layer to support data- and model-parallel AI analytics in wireless edge networks.
- Design methods that keep crowd-sourced imagery fresh and merge it into real-time updates of a geospatial digital twin, a live digital model of a physical environment.
- Develop incentive mechanisms that ensure truthful reporting by crowd contributors and mitigate self-reinforcing bias in crowd-sourced digital twin updates.
More about the research
The two projects tackle this mismatch from different angles. One designs the theory and algorithms that let wireless networks support machine learning efficiently. The other designs ways to keep live digital maps of the physical world current using data contributed by ordinary people.
Why it matters
Better co-design of wireless networks and machine learning could improve the speed and efficiency of AI applications, such as computer vision and recommendation systems, that run on mobile devices. Timely, truthful, crowd-sourced digital maps could help emergency responders and infrastructure managers see current conditions, including in places that sensors, satellites and drones cover poorly.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Mitsunori Ogihara
University of Miami, FL·Computer Science
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.
Zhi-Li Zhang
University of Minnesota, MN·Computer Science
Develop an O-RAN-based framework in which 5G networks use vehicle trajectory and speed to proactively cut delays from poor radio signals and base-station handovers during remote driving.
Miao Pan
University of Houston, TX·Computer Science
Design software-hardware co-designed model pruning and adaptive quantization schemes that exploit the sparsity of model updates to reduce computation and memory access during federated learning on a single 5G mobile device.
The school
Ohio State University: 71 labs on PI Pages, $1.6B a year on research, 882 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.