Non-intrusive Distraction Pattern Detection Using Behavior Triangulation Method

Shokoufeh Monjezi Kouchak, Ashraf Gaffar

Research output: Chapter in Book/Report/Conference proceedingConference contribution

3 Scopus citations

Abstract

Driver distraction is the primary cause of car accidents among USA teenage drivers. Predicting distractive driver behaviour and adapting the car systems accordingly is one solution to this problem. We use neural networks to find a correlation between driving patterns and car system variables. We conducted an experiment to induce distractive tasks to drivers and collected corresponding data patterns, then used them to train the network. With our triangulation algorithm, we reused the trained network to predict driver behaviour using the data patterns from part 1. Our neural network accurately predicts driver distraction when fed with system variables alone.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
EditorsFernando G. Tinetti, Quoc-Nam Tran, Leonidas Deligiannidis, Mary Qu Yang, Mary Qu Yang, Hamid R. Arabnia
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages811-816
Number of pages6
ISBN (Electronic)9781538626528
DOIs
StatePublished - Dec 4 2018
Event2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017 - Las Vegas, United States
Duration: Dec 14 2017Dec 16 2017

Other

Other2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017
CountryUnited States
CityLas Vegas
Period12/14/1712/16/17

Keywords

  • driver distraction
  • Human- car-interaction
  • Neural Network

ASJC Scopus subject areas

  • Computer Science (miscellaneous)
  • Artificial Intelligence
  • Computer Networks and Communications
  • Computer Science Applications
  • Safety, Risk, Reliability and Quality

Fingerprint Dive into the research topics of 'Non-intrusive Distraction Pattern Detection Using Behavior Triangulation Method'. Together they form a unique fingerprint.

  • Cite this

    Kouchak, S. M., & Gaffar, A. (2018). Non-intrusive Distraction Pattern Detection Using Behavior Triangulation Method. In F. G. Tinetti, Q-N. Tran, L. Deligiannidis, M. Q. Yang, M. Q. Yang, & H. R. Arabnia (Eds.), Proceedings - 2017 International Conference on Computational Science and Computational Intelligence, CSCI 2017 (pp. 811-816). [8560899] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/CSCI.2017.140