Congratulations to Mosbah! The Yi-Min Wang and Pi-Yu Chung Research Award is an annual award recognizing doctoral students in Electrical and Computer Engineering for excellence in research. Mosbah was one of two students receiving this award at the 2026 Student Awards and Recognition Banquet – Celebrating Success.
A new approach to spinal stimulation therapy under development at Carle Illinois College of Medicine could offer more effective relief for patients with chronic pain, especially those in rural areas. The innovative approach leverages real-time data on the patient’s emotional state as well as physical biomarkers to optimize pain relief through more personalized delivery of spinal stimulation.
For decades, spinal stimulation has been used to treat chronic pain. A small, implanted device delivers mild electrical impulses to the spine, disrupting pain signals by activating specific nerve fibers. Open-loop stimulators deliver a manually programmed level of electricity regardless of the patient’s unique characteristics. Closed-loop systems are more advanced, allowing for more personalized stimulation based on biomarkers detected in the patient.
CI MED student Prateek Dullur is part of a cross-disciplinary team at the University of Illinois Urbana-Champaign working to improve on existing closed-loop technology. “Prior research has investigated closed-loop systems built on objective biomarkers (e.g., movement and position) or subjective ones (such as mood and pain levels). A personalized approach incorporating both modalities has not yet been developed. We believe this approach is the future of closed-loop algorithms,” Dullur said.
Specifically, the team is working with experts from the University of Illinois Urbana-Champaign who specialize in advanced neural engineering and artificial intelligence. “Part of this work is inspired by seizure forecasting and closed-loop stimulation in epilepsy, which the DEPEND lab (headed by CI MED and Electrical and Computer Engineering Professor Ravishankar Iyer) has validated in a collaboration with the Mayo Clinic. We believe applying a similar architecture to chronic pain and spinal cord stimulation could hold tremendous promise,” Dullur said.
“Ultimately, we aim to provide improved quality of life to patients with chronic pain that is refractory to medication or other treatment,” said Dullur, who presented the team’s work at the Congress of Neurological Surgeons Annual Meeting in Los Angeles in October. “By improving our models, we hope to contribute to the fundamental understanding of chronic pain. This work may take us one step closer towards providing better daily outcomes and lowering the chance of device failure due to tolerance, which is a major concern with existing devices,” he said.
The team is building its proposed computer model for a personalized closed-loop spinal stimulation system. They’re also expanding their work to explore the effectiveness of spinal stimulation for treating rural patients living with chronic pain.
“We are conducting a retrospective study with patients in the Carle Foundation Hospital network. We believe these joint efforts may lead to novel insights into treating chronic pain in under-resourced settings,” Dullur said.
In addition to Dullur, the research team includes: Dr. Suguna Pappu, a CI MED faculty member and Carle Health neurosurgeon; CI MED students Meenakshi Singhal, Mehreen Ali, Brian Hong, and Neema Darabi; from the U. of I. Department of Electrical Engineering Professor Ravishankar Iyer (CI MED professor of Biomedical and Translational Sciences) and graduate student Yurui Cao; and from the Department of Bioengineering, Professor Yuan Yang, an expert in neural engineering and neural modeling.
Available at: https://medicine.illinois.edu/news/ci-med-illinois-researchers-develop-personalized-spinal-stimulation-therapy-for-chronic-pain-sufferers
Archit Patke, Ph.D., a recent graduate from Prof. Iyer’s DEPEND Group, was named a 2025 Machine Learning Commons Rising Star for his groundbreaking work improving the performance and reliability of GPUs that power today’s AI systems. His research boosts efficiency by teaching machines to work smarter — not harder — while uncovering the causes of GPU failures in advanced hardware like NVIDIA’s A100 and H100. Already recognized by major tech companies and adopted in open-source platforms, Patke’s achievements highlight Illinois’ leadership in next-generation AI innovation.
DEPEND PhD student, Yurui, received the first place award at the poster contest held by the Illinois AI and Health Summit!
The Mayo Clinic & Illinois Alliance is pleased to introduce doctoral student, Yurui Cao, as the latest recipient of the Fellowship for Technology-Based Healthcare! Yurui is working with Illinois advisor, Professor Ravi Iyer, and Mayo Clinic advisor, Dr. Gregory Worrel, to develop machine learning tools for understanding the mechanisms underlying brain stimulation and its interaction with epilepsy and behavior.
Read more about the Fellowship program here!
KubeCon is the annual conference on Kubernetes where industry and academic researchers share state-of-the art cloud-native software development and modern operations and deployment techniques.
Accurately estimating CPU & memory requirements for workloads is hard! So, it is common for users to over-provision pods, which leads to under-utilized clusters, and the need to scale up cluster size to accommodate workloads. Recently added in-place pod resize feature brings the ability to right-size over-provisioned pods without restarting them. This talk will illustrate how cluster autoscaler currently handles pods pending due to insufficient resources, then introduce a change to the autoscaling workflow that right-sizes over-provisioned pods, and show how it can help schedule pending pods more quickly while lowering costs & carbon footprint. Haoran will talk about the latest research that leverages machine learning and reinforcement learning techniques to achieve multi-dimensional autoscaling, and discuss how this cutting-edge work can help proactively scale workloads to achieve optimal cluster utilization while meeting application SLOs by more precisely provisioning the pods.
Haoran’s line of work on machine learning for resource management has been published at multiple conferences: FIRM (OSDI 2020), SIMPPO (SoCC 2022), AWARE (ATC 2023)
Link to the talk: https://sched.co/1R2nS
His research is focused on improving the realism of the CARLA simulator that’s widely used for autonomous vehicles.
Click here to view presentation!
We recognize all of your hard work and wish you the best in your future endeavors!
