Quad-Tree-Based Driver Classification Using Deep Learning for Mild Cognitive Impairment Detection

Given GPS points on a transportation network, the goal of the Quad-tree Based Driver Classification (QBDC) problem is to identify whether drivers have Mild Cognitive Impairment (MCI). The QBDC problem is challenging due to the large volume and complexity of the data. This paper proposes a quad-tree...

Full description

Saved in:
Bibliographic Details
Main Authors: Seyedeh Gol Ara Ghoreishi, Charles Boateng, Sonia Moshfeghi, Muhammad Tanveer Jan, Joshua Conniff, Kwangsoo Yang, Jinwoo Jang, Borko Furht, David Newman, Ruth Tappen, Monica Rosselli, Kelley L. Jackson
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10955159/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850203046002294784
author Seyedeh Gol Ara Ghoreishi
Charles Boateng
Sonia Moshfeghi
Muhammad Tanveer Jan
Joshua Conniff
Kwangsoo Yang
Jinwoo Jang
Borko Furht
David Newman
Ruth Tappen
Monica Rosselli
Kelley L. Jackson
author_facet Seyedeh Gol Ara Ghoreishi
Charles Boateng
Sonia Moshfeghi
Muhammad Tanveer Jan
Joshua Conniff
Kwangsoo Yang
Jinwoo Jang
Borko Furht
David Newman
Ruth Tappen
Monica Rosselli
Kelley L. Jackson
author_sort Seyedeh Gol Ara Ghoreishi
collection DOAJ
description Given GPS points on a transportation network, the goal of the Quad-tree Based Driver Classification (QBDC) problem is to identify whether drivers have Mild Cognitive Impairment (MCI). The QBDC problem is challenging due to the large volume and complexity of the data. This paper proposes a quad-tree based approach to the QBDC problem by analyzing driving patterns using a real-world dataset. We propose a geo-regional quad-tree structure to capture the spatial hierarchy of driving trajectories and introduce new driving features representation for input into a convolutional neural network (CNN) for driver classification. The experimental results demonstrate the effectiveness of the proposed algorithm, achieving an F1 score of 95% that significantly outperforms the baseline models. These results highlight the potential of geo-regional quad-tree structures to extract interpretable features and describe complex driving patterns. This approach offers significant implications for driver classification, with the potential to improve road safety and cognitive health monitoring.
format Article
id doaj-art-24a154aa5acf473d8fbc0e676f8b83f3
institution OA Journals
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-24a154aa5acf473d8fbc0e676f8b83f32025-08-20T02:11:37ZengIEEEIEEE Access2169-35362025-01-0113631296314210.1109/ACCESS.2025.355870610955159Quad-Tree-Based Driver Classification Using Deep Learning for Mild Cognitive Impairment DetectionSeyedeh Gol Ara Ghoreishi0https://orcid.org/0009-0007-3244-932XCharles Boateng1https://orcid.org/0009-0009-7930-5360Sonia Moshfeghi2Muhammad Tanveer Jan3https://orcid.org/0000-0002-3870-0526Joshua Conniff4Kwangsoo Yang5https://orcid.org/0000-0003-4293-9908Jinwoo Jang6https://orcid.org/0000-0002-3657-698XBorko Furht7David Newman8https://orcid.org/0000-0003-0423-6267Ruth Tappen9Monica Rosselli10https://orcid.org/0000-0003-2656-9505Kelley L. Jackson11College of Eng and Computer Science, Florida Atlantic University, Boca Raton, FL, USACollege of Eng and Computer Science, Florida Atlantic University, Boca Raton, FL, USACollege of Eng and Computer Science, Florida Atlantic University, Boca Raton, FL, USACollege of Eng and Computer Science, Florida Atlantic University, Boca Raton, FL, USACollege of Science, Florida Atlantic University, Boca Raton, FL, USACollege of Eng and Computer Science, Florida Atlantic University, Boca Raton, FL, USACollege of Eng and Computer Science, Florida Atlantic University, Boca Raton, FL, USACollege of Eng and Computer Science, Florida Atlantic University, Boca Raton, FL, USACollege of Nursing, Florida Atlantic University, Boca Raton, FL, USACollege of Nursing, Florida Atlantic University, Boca Raton, FL, USACollege of Science, Florida Atlantic University, Boca Raton, FL, USACollege of Nursing, Florida Atlantic University, Boca Raton, FL, USAGiven GPS points on a transportation network, the goal of the Quad-tree Based Driver Classification (QBDC) problem is to identify whether drivers have Mild Cognitive Impairment (MCI). The QBDC problem is challenging due to the large volume and complexity of the data. This paper proposes a quad-tree based approach to the QBDC problem by analyzing driving patterns using a real-world dataset. We propose a geo-regional quad-tree structure to capture the spatial hierarchy of driving trajectories and introduce new driving features representation for input into a convolutional neural network (CNN) for driver classification. The experimental results demonstrate the effectiveness of the proposed algorithm, achieving an F1 score of 95% that significantly outperforms the baseline models. These results highlight the potential of geo-regional quad-tree structures to extract interpretable features and describe complex driving patterns. This approach offers significant implications for driver classification, with the potential to improve road safety and cognitive health monitoring.https://ieeexplore.ieee.org/document/10955159/Spatiotemporal dataGPS datatrajectory analysisdriving behaviorolder driver classificationquad-tree decomposition
spellingShingle Seyedeh Gol Ara Ghoreishi
Charles Boateng
Sonia Moshfeghi
Muhammad Tanveer Jan
Joshua Conniff
Kwangsoo Yang
Jinwoo Jang
Borko Furht
David Newman
Ruth Tappen
Monica Rosselli
Kelley L. Jackson
Quad-Tree-Based Driver Classification Using Deep Learning for Mild Cognitive Impairment Detection
IEEE Access
Spatiotemporal data
GPS data
trajectory analysis
driving behavior
older driver classification
quad-tree decomposition
title Quad-Tree-Based Driver Classification Using Deep Learning for Mild Cognitive Impairment Detection
title_full Quad-Tree-Based Driver Classification Using Deep Learning for Mild Cognitive Impairment Detection
title_fullStr Quad-Tree-Based Driver Classification Using Deep Learning for Mild Cognitive Impairment Detection
title_full_unstemmed Quad-Tree-Based Driver Classification Using Deep Learning for Mild Cognitive Impairment Detection
title_short Quad-Tree-Based Driver Classification Using Deep Learning for Mild Cognitive Impairment Detection
title_sort quad tree based driver classification using deep learning for mild cognitive impairment detection
topic Spatiotemporal data
GPS data
trajectory analysis
driving behavior
older driver classification
quad-tree decomposition
url https://ieeexplore.ieee.org/document/10955159/
work_keys_str_mv AT seyedehgolaraghoreishi quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT charlesboateng quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT soniamoshfeghi quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT muhammadtanveerjan quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT joshuaconniff quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT kwangsooyang quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT jinwoojang quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT borkofurht quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT davidnewman quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT ruthtappen quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT monicarosselli quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection
AT kelleyljackson quadtreebaseddriverclassificationusingdeeplearningformildcognitiveimpairmentdetection