Spatial Deep Learning Approach to Older Driver Classification

• Published in: IEEE access 2024, Vol.12, p.191219-191230
• Main Authors: Boateng, Charles, Ghoreishi, Seyedeh Gol Ara, Yang, Kwangsoo, Jan, Muhammad Tanveer, Tappen, Ruth, Jang, Jinwoo, Newman, David, Moshfeghi, Sonia, Jackson, Kelley, Resnick, Rhian, Furht, Borko, Rosselli, Monica, Conniff, Joshua
• Format: Article
• Language: English
• Subjects: Classification; Data augmentation; Datasets; Deep learning; Feature extraction; Global Positioning System; Heterogeneity; Indexes; Insurance; Machine learning; Older adults; older driver classification; Older people; Risk assessment; Roads; Safety; Safety measures; Spatial deep learning; Telematics; Traffic safety; Trajectory; trajectory data mining; Vehicles
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2024.3516572

Given telemetry datasets (e.g., GPS location, speed, direction, distance.), the Older Driver Classification (ODC) problem identifies two groups of drivers: normal and abnormal. The ODC problem is essential in many societal applications, including road safety, insurance risk assessment, and targeted interventions for elderly drivers with dementia or Mild Cognitive Impairment (MCI). The problem is challenging because of the volume and heterogeneity of temporally-detailed vehicle datasets. This paper proposes a novel spatial deep-learning approach that leverages Grid-Index based data augmentation to enhance the detection of abnormal driving behaviors. Through extensive experiments and a real-world case study, the proposed approach consistently identifies abnormal drivers with high accuracy. The findings demonstrate the potential of grid-based methods to improve telematics-based driving behavior analysis significantly. This approach offers valuable implications for enhancing road safety measures, optimizing insurance risk assessments, and developing targeted interventions for at-risk drivers.