Doctoral Dissertations

Keywords and Phrases

ADAS; Braking Intent; EEG; Functional Connectivity; Machine Learning; Spiking Neural Networks

Abstract

Despite the technological breakthroughs in advanced driver assist systems, distracted driving persists as a major challenge to roadway safety. This investigation advances the body of knowledge towards a solution by developing an individualized driver-state detection method using electroencephalogram (EEG) and neuromorphic computing to provide a less invasive and more energy efficient ADAS solution. It furthermore explores the changes in brain functional connectivity under distracted conditions to better understand brain state information that could be used for neuro-feedback intervention systems. The first contribution introduces the concept of using Convolutional Spiking Neural Networks (CSNNs) for recognition of patterns with movement-intention predictive power contained within EEG data and applies this concept to the problem of predicting driver braking intent through identification of the contingent negative variation (CNV). The second contribution extends the first results into a methodology of rapidly creating high-performance, individualized models at the chip level. This overcomes the short-comings of a generalized group-level model by reducing driver-specific performance uncertainty through an individual-focused approach. The final contribution expands upon the preceding results by investigating the broader brain activation patterns during distracted driving, namely by observing the time-dependent patterns of brain functional networks during both normal and distracted driving using ”dynamic” functional connectivity analysis and noting the differences between the two in both a qualitative and quantitative manner. This allows for a more comprehensive understanding of the brain functional connectivity changes that occur during distracted driving and provides ideas for future augmentations of the proposed ADAS advancements through more generalized distracted driving detection.

Advisor(s)

Krishnamurthy, K.
Nadendla, V. Sriram Siddhardh

Committee Member(s)

Bristow, Douglas A.
Olbricht, Gayla R.
Song, Yun Seong

Department(s)

Mechanical and Aerospace Engineering

Degree Name

Ph. D. in Mechanical Engineering

Publisher

Missouri University of Science and Technology

Publication Date

Summer 2025

Journal article titles appearing in thesis/dissertation

Paper I: Pages 12-43 appeared in Nature’s Scientific Reports.

Paper II: Pages 44-82 appeared in Journal of Neural Engineering.

Paper III: Pages 83-123 are intended for submission in the journal of Human Brain Mapping.

Pagination

xii, 138 pages

Note about bibliography

Includes_bibliographical_references_(pages 136-137)

Rights

© 2025 Nathan Alan Lutes , All Rights Reserved

Document Type

Dissertation - Open Access

File Type

text

Language

English

Thesis Number

T 12540

Download

Share

 
COinS