group
What campus are you from?
Daytona Beach
Authors' Class Standing
Michael Culbertson, Junior Poorendra Ramlall, Graduate Student
Lead Presenter's Name
Michael Culbertson
Faculty Mentor Name
Subhradeep Roy
Abstract
Understanding how mental states such as fatigue, workload, and engagement influence driving behavior is key to improving both road safety and the design of intelligent vehicle systems. With recent advances in portable electroencephalography (EEG) technology, it is now possible to study these cognitive states in realistic driving situations rather than only in clinical settings. In this ongoing research, we demonstrate how EEG data collected from human drivers can help identify and differentiate these mental states using data-driven analysis. An important part of this work is the experimental design. We describe how our driving experiments are carefully structured to create conditions that bring out different levels of cognitive demand, allowing us to capture and analyze the corresponding EEG responses. The EEG signals are processed using Quasar Q-State’s machine learning tools to remove noise and classify brain activity related to varying levels of workload, fatigue, and engagement. The models developed from these experiments are expected to help us understand how mental states influence driving performance and interactions with the driving environment. Ultimately, this work aims to build a bridge between human cognition, brain activity, and driver behavior, contributing to the development of safer and more adaptive driving systems.
Did this research project receive funding support from the Office of Undergraduate Research.
No
Designing Experiments to Identify Driver Cognitive States Using EEG
Understanding how mental states such as fatigue, workload, and engagement influence driving behavior is key to improving both road safety and the design of intelligent vehicle systems. With recent advances in portable electroencephalography (EEG) technology, it is now possible to study these cognitive states in realistic driving situations rather than only in clinical settings. In this ongoing research, we demonstrate how EEG data collected from human drivers can help identify and differentiate these mental states using data-driven analysis. An important part of this work is the experimental design. We describe how our driving experiments are carefully structured to create conditions that bring out different levels of cognitive demand, allowing us to capture and analyze the corresponding EEG responses. The EEG signals are processed using Quasar Q-State’s machine learning tools to remove noise and classify brain activity related to varying levels of workload, fatigue, and engagement. The models developed from these experiments are expected to help us understand how mental states influence driving performance and interactions with the driving environment. Ultimately, this work aims to build a bridge between human cognition, brain activity, and driver behavior, contributing to the development of safer and more adaptive driving systems.