Dr. CHANGRUI LIU | Dr. LILY PHARRIS
Dr. JIAN WANG | Dr. QING WANG
A team of UT Martin students and faculty co-authored “Machine Learning-Based Anomaly Detection for Traffic in IoT-Enabled Transportation Networks” in “Electronics” (Vol. 15, No. 17, Article 3921). The study tested five machine learning methods on a public dataset of internet-connected device traffic, finding that all performed well at spotting attacks, with one method proving best at flagging malicious activity overall and a simpler model performing best at identifying which of eleven specific attack types was occurring.
The team also found that just three pieces of network data accounted for most detection decisions, suggesting lightweight, real-time security systems could be built for connected vehicles and similar devices.
Contributing students, all May 2026 graduates of UT Martin’s cybersecurity program, were Connor Gladish of Adamsville; Molly Corgan of Cary, North Carolina; Jason Moss of Atoka; and Blanca Negrete, of Riverbank, California.
Contributing UTM faculty were Dr. Jian Wang, assistant professor of computer science; Dr. Qing Wang, associate professor of computer science; Dr. Changrui Liu, assistant professor of mathematics and statistics; and Dr. Lily Pharris, assistant professor of computer science.
BRIAN JOHNSON
Brian Johnson, chair of the Department of Psychology and a lecturer in that department, was the guest panelist Oct. 13 for JoVE’s webinar, “Bringing Developmental Psychology to Life with Video.” He discussed his use of JoVE’s science and social psychology videos within his social psychology course over the past few semesters. The developmental psychology videos represent a new series available from the publisher.
The panel discussion was held virtually.
JoVE, formerly the Journal of Visualized Experiments, is the world-leading producer and provider of science videos with the mission to improve scientific research and education. JoVE is a peer-reviewd scientific journal that publishes experimental medhods in video format.
