Download PDFOpen PDF in browser

Prediction of Drowsy Driving Using EEG and Facial Expression by Machine Learning

11 pagesPublished: March 13, 2019

Abstract

Careless driving is the most common cause of traffic accidents. Being in a drowsy state is a cause of careless driving, which can lead to a serious accident. Therefore, in this study, we focus on predicting drowsy driving. Studies on the prediction of drowsy driving focus on the prediction aspect only . However, users have various demands, like not wanting to wear a device while driving, and it is necessary to consider such demands when we introduce the prediction system. Hence, our purpose is to predict drowsy driving that can respond to a user’s demand(s) by combining two approaches of electroencephalogram (EEG ) and facial expressions. Our method is divided into three parts by type of data (facial expressions, EEG, and both), and the users can select the one suitable for their demands. We acquire data with a depth camera and an electroencephalograph and make a machine-learning model to predict drowsy driving. As a result, it is possible to correctly predict drowsy driving in the order of facial expression < EEG < and both combined. Our framework may be applicable to data other than EEG and facial expressions.

Keyphrases: demand, driving, Drowsy, EEG, facial expressions, machine learning

In: Gordon Lee and Ying Jin (editors). Proceedings of 34th International Conference on Computers and Their Applications, vol 58, pages 225--235

Links:
BibTeX entry
@inproceedings{CATA2019:Prediction_of_Drowsy_Driving,
  author    = {Daichi Naito and Ryo Hatano and Hiroyuki Nishiyama},
  title     = {Prediction of Drowsy Driving Using EEG and Facial Expression by Machine Learning},
  booktitle = {Proceedings of 34th International Conference on Computers and Their Applications},
  editor    = {Gordon Lee and Ying Jin},
  series    = {EPiC Series in Computing},
  volume    = {58},
  pages     = {225--235},
  year      = {2019},
  publisher = {EasyChair},
  bibsource = {EasyChair, https://easychair.org},
  issn      = {2398-7340},
  url       = {https://easychair.org/publications/paper/ZqfG},
  doi       = {10.29007/v16j}}
Download PDFOpen PDF in browser