James Madison University Student Team’s Innovative AI Powered Solution to Reduce Drunk Driving. Over the course of several years, a dedicated team of students from James Madison University (JMU) has been on a mission to combat drunk driving and save lives. Their groundbreaking innovation combines cutting-edge technology with a commitment to public safety.
The journey began when a group of JMU students recognized the urgent need to address drunk driving fatalities. Their interdisciplinary collaboration involved students from engineering, computer science, and behavioral sciences. Together, they embarked on a mission to create a solution that would reduce the number of alcohol-related accidents on our roads.
Contact Us
Advisor Team Bios
Rod MacDonald
Professor MacDonald has over 25 years of experience developing simulation models as decision support tools for local, state, and federal agencies, as well as for numerous businesses ranging from Boeing to small medical groups. His expertise lies in creating these models to aid in decision-making processes across various domains.
Dr. Ahmad Salman
Dr. Ahmad Salman is an Associate Professor in the Department of Integrated Science and Technology at JMU. His research focuses on cryptography for secure communications in lightweight devices, as well as techniques for conserving battery power in those devices. He explores topics such as cyber-physical systems, the Internet of Things (IoT), and post-quantum cryptography. One of his projects involves developing a node that collects data (such as temperature and pH levels) from streams and sends it to a drone for analysis, without disturbing the surrounding ecosystem. Additionally, he investigates security and privacy concerns related to tracking devices used in hospitals while ensuring compliance with privacy regulations like HIPAA.
Chase Coleman
Chase Coleman graduated in the Spring of 2024 and majored in Computer Science while minoring in both Robotics and Mathematics. He currently works as a technology consultant at Capgemini Government Solutions, where he also interned during his time at JMU. He specializes in cloud system architecture with multiple professional certifications in AWS and Azure.
Chase greatly contributed to the beginning years of the HGN project by developing the first machine learning model to analyze users' test results. To facilitate testing, Chase programmed and installed a prototype user interface into a vehicle using a Raspberry Pi. He also utilized his AWS expertise to architect a cloud-based backend that provided computational support for the lightweight HGN Tester prototype. The research Chase gathered during IRB-approved test trials is now aiding the team in developing a deep learning model to further improve the HGN Tester's accuracy.
Patrick Dodds
Patrick Dodds is a senior majoring in Computer Science, graduating in the Spring 2025. Last summer, he interned at Booz Allen Hamilton, where he contributed to advanced projects requiring expertise in computing. He holds CompTIA Security+ and AWS Cloud Practitioner certifications, reflecting his focus on cybersecurity and cloud computing.
Patrick’s experience includes working with AWS servers and EC2 instances to build scalable solutions. He has also developed TinyML applications using Raspberry Pi and Jetson Nano. On the Horizontal Gaze Nystagmus (HGN) project he is working on integrating the software into the hardware in a jetson nano to be able to run the test and have a facial recognition integrated as well. Additionally, Patrick has skills in embedded systems, machine learning, programming LED lighting systems, blending software, and hardware integration.
Abdullah Alghoniemy
Abdullah Alghoniemy is a second-year Master’s student in Computer Science at JMU. Over the past year, he interned as a Software Engineer at Ellucian, an EdTech company in Reston, VA. He also contributed to a research project at JMU, developing a machine learning-based solution to forecast real-time parking availability and recommend parking options to users before reaching their destination. On the horizontal gaze nystagmus project, Abudllah is leading the development of machine learning algorithms to improve the accuracy of detecting horizontal gaze nystagmus.
Publications
Horizontal Gaze Nystagmus Transmission Interlock System
Article Web Link: Horizontal Gaze Nystagmus Transmission Interlock System
Coleman et al., "Horizontal Gaze Nystagmus Transmission Interlock System," 2023 Systems and Information Engineering Design Symposium (SIEDS), Charlottesville, VA, USA, 2023, pp. 43-48, doi: 10.1109/SIEDS58326.2023.10137888
Article Web Link: Enhancing Road Safety with AI: A Secure Personalized System for Detecting Impairment through Horizontal Gaze Nystagmus
Coleman, J. Coulthard, P. Dodds, A. Salman and R. MacDonald, "Enhancing Road Safety with AI: A Secure System for Detecting Impairment through Horizontal Gaze Nystagmus," 2024 Systems and Information Engineering Design Symposium (SIEDS), Charlottesville, VA, USA, 2024, pp. 118-123, doi: 10.1109/SIEDS61124.2024.10534664.
Interested in learning more about licensing?
This innovation is supported by James Madison Innovations, Inc. (JMI)
James Madison Innovations, Inc. (JMI), is a JMU 501(c)(3) non-profit corporation for intellectual property management and licensing organization, the two entities connect researchers, entrepreneurs, and professionals in industry and support services to bolster the entrepreneurial infrastructure and promote innovation in the Valley. Learn More