News Highlights

Homa Alemzadeh Aids Successful Kick-off Event for IFIP WG10.4’s Intelligent Vehicle Dependability and Security Project

Homa Alemzadeh, assistant professor of electrical and computer engineering at the University of Virginia, shared her expertise in resilient cyber-physical systems with members of the International Federation for Information Processing during the winter meeting of its Working Group on Dependable Computing and Fault Tolerance.

Novel Data Mining Method Identifies Most Promising Drugs to Treat COVID-19

Nikolaos Sidiropoulos, Louis T. Rader Professor of electrical and computer engineering at the University of Virginia, and his collaborators are developing novel data mining and artificial intelligence methods to help in the fight against COVID-19.

Model Predicts Hospitalizations 10-15 Days Ahead with Improved Accuracy

Nikolaos Sidiropoulos, Louis T. Rader Professor of electrical and computer engineering at the University of Virginia, and his collaborators have developed models and methods to predict the evolution of epidemic trends for many regions simultaneously. This helps public health officials and hospital administrators manage scarce resources such as respirators and intensive care unit beds needed for COVID-19 response.

Jundong Li’s Graph Mining Research Aims to Reduce Bias in Decision-Making

Jundong Li, University of Virginia assistant professor of electrical and computer engineering with joint appointments in computer science and the School of Data Science, shared advancements in graph mining at the 29th International Joint Conference on Artificial Intelligence, January 7-15.

Benton H. Calhoun Elected IEEE Fellow for Pioneering Design of Ultra-low-power Circuits

The Institute of Electrical and Electronics Engineers has elected Benton H. Calhoun as a fellow for original and fundamental contributions in integrated circuit design. Calhoun, professor of electrical and computer engineering at the University of Virginia, specializes in energy-efficient, sub-threshold circuit design and applications that enable self-powered wireless sensing systems. These wireless sensing nodes are so low power that they no longer need to use batteries. Instead, they operate on power harvested from their environment.

Homa Alemzadeh and Research Team Present CognitiveEMS Research at NIST Annual Meeting

Homa Alemzadeh and her research team have come a long way since winning a $1.1 million grant in 2018 to build an artificial intelligence assistant to help first responders make good decisions during emergency situations. As first reported in 2018, the project’s goal is to develop a wearable, voice-activated assistant that collects sound data from the incident scene and, in response, provides dynamic feedback that would help the responder by suggesting appropriate medical interventions.

Xu Yi Earns Young Investigator Award for Groundbreaking Photonics Research

Xu Yi, University of Virginia assistant professor of electrical and computer engineering, has earned a Young Investigator Award from the Air Force Office of Scientific Research to conduct groundbreaking research in photonics.

A Superconducting Journey to a Black Hole and Beyond

Until recently, the evidence for black holes had only been obtained indirectly; however, a large black hole consisting of 6.5 billion solar masses and residing 55 million light years away has now been imaged using superconducting detectors. This was a remarkable and common-culture captivating discovery requiring an “integrated telescope” collecting measurements from many radio astronomy observatories and an international cast of collaborating scientists and engineers. Tune in to the Applied Superconductivity Conference to hear Art Lichtenberger’s story within the story.

Yixin Sun Publishes Research on Detecting Malware Injection

Yixin Sun, Anita Jones Career Enhancement Assistant Professor of Computer Science and Electrical and Computer Engineering at the University of Virginia, joined university and industry researchers to develop a new approach to detect malware injection. Sun is first author on the team’s paper, published in the Proceedings of the 2020 IEEE European Symposium on Security and Privacy. The paper presents a new approach to effectively detect stealthy attacks from seemingly legitimate connections to popular web services made by benign programs.

The research team built a fine-grained Program-DNS profile for each benign program to characterize expected DNS behavior. From the Program-DNS profile, the team developed six novel features on a dataset of over 130 million DNS requests collected from a real-world enterprise and 8 million requests from malware-samples executed in a sandbox environment. Their novel features successfully detected 190 malware-injected processes that would have otherwise gone unnoticed. Their study demonstrates that fine-grained Program-DNS profiles can help detect attack campaigns that bypass traditional DNS monitoring safeguards and signature-based detection techniques. Read the paper: https://conferences.computer.org/eurosp/pdfs/EuroSP2020-2psedXWK6U4prXdo7t91Gm/508700a552/508700a552.pdf

Machine Learning Technique Promises Early Detection of Osteoarthritis

Gustavo Rohde, professor of biomedical engineering and electrical and computer engineering at the University of Virginia, is senior author of a collaborative research study in machine learning to identify patients vulnerable to osteoarthritis.