Detail publikačního výsledku

CLASSIFICATION OF DRIVER'S DROWSINESS FROM STEERING WHEEL MOTION UNDER REAL TRAFFIC CONDITIONS

HAUPT, D.; HONZÍK, P.; KUČERA, P.; HYNČICA, O.

Originální název

CLASSIFICATION OF DRIVER'S DROWSINESS FROM STEERING WHEEL MOTION UNDER REAL TRAFFIC CONDITIONS

Anglický název

CLASSIFICATION OF DRIVER'S DROWSINESS FROM STEERING WHEEL MOTION UNDER REAL TRAFFIC CONDITIONS

Druh

Stať ve sborníku v databázi WoS či Scopus

Originální abstrakt

To develop a system for drivers drowsiness recognition is a challenging task in the modern car transportation. Many studies have promising results. Unfortunately most data is acquired in the laboratory conditions. Therefore proving drowsiness detection reliability and accuracy in real traffic is difficult. The analyzed data in this paper is acquired from the real traffic and hence it contains all uncertainty. An in-direct measurement from the vehicle CAN bus has been chosen for data acquisition in order to not affect the driver. The data is preprocessed according to the assumptions about drivers behavior and transformed to the frequency domain by means of the orthogonal transform (STFT, CWT and DWT). Subsequently, in the frequency domain, more than 70 000 features are generated. By means of the filter feature selection, 10 best features are chosen for a prediction. Finally, 1-NN model is used for prediction accuracy estimation.

Anglický abstrakt

To develop a system for drivers drowsiness recognition is a challenging task in the modern car transportation. Many studies have promising results. Unfortunately most data is acquired in the laboratory conditions. Therefore proving drowsiness detection reliability and accuracy in real traffic is difficult. The analyzed data in this paper is acquired from the real traffic and hence it contains all uncertainty. An in-direct measurement from the vehicle CAN bus has been chosen for data acquisition in order to not affect the driver. The data is preprocessed according to the assumptions about drivers behavior and transformed to the frequency domain by means of the orthogonal transform (STFT, CWT and DWT). Subsequently, in the frequency domain, more than 70 000 features are generated. By means of the filter feature selection, 10 best features are chosen for a prediction. Finally, 1-NN model is used for prediction accuracy estimation.

Klíčová slova

drowsiness, driver, Wavelet transform, Fourier transform, feature generation, AUC, LOOCV, CV

Klíčová slova v angličtině

drowsiness, driver, Wavelet transform, Fourier transform, feature generation, AUC, LOOCV, CV

Autoři

HAUPT, D.; HONZÍK, P.; KUČERA, P.; HYNČICA, O.

Rok RIV

2014

Vydáno

27.06.2012

ISBN

978-80-214-4540-6

Kniha

MENDEL 2012, 18th International Conference on Soft Computing

Strany od

428

Strany do

433

Strany počet

6

Plný text v Digitální knihovně

http://hdl.handle.net/

BibTex

@inproceedings{BUT93627,
  author="Daniel {Haupt} and Petr {Honzík} and Pavel {Kučera} and Ondřej {Hynčica}",
  title="CLASSIFICATION OF DRIVER'S DROWSINESS FROM STEERING WHEEL MOTION UNDER REAL TRAFFIC CONDITIONS",
  booktitle="MENDEL 2012, 18th International Conference on Soft Computing",
  year="2012",
  pages="428--433",
  isbn="978-80-214-4540-6"
}