Driver Drowsiness Detection Based on Steering Wheel Data Applying Adaptive Neuro-Fuzzy Feature Selection

Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

Abstract

This paper presents a novel feature selection method to design a non-invasive driver drowsiness detection system based on steering wheel data. The proposed feature selector can select the most related features to the drowsiness level to improve the classification accuracy. This method is based on the combination of the filter and wrapper feature selection algorithms using adaptive neuro-fuzzy inference system (ANFIS). In this method firstly, four different filter indexes are applied on extracted features from steering wheel data. After that, output values of each filter index are imported as inputs to a fuzzy inference system to determine the importance degree of each feature and select the most important features. Then, the selected features are imported to a support vector machine (SVM) for binary classification to classify the driving conditions in two classes of drowsy and awake. Finally, the classifier accuracy is exploited to adjust parameters of an adaptive fuzzy system using a particle swarm optimization (PSO) algorithm. The experimental data were collected from about 20.5 h of driving in the simulator. The results show that the drowsiness detection system is working with a high accuracy and also confirm that this method is more accurate than the recent available algorithms.
Spracheenglisch
Aufsatznummer943
Seitenumfang14
FachzeitschriftSensors
Jahrgang19
Ausgabennummer4
DOIs
StatusVeröffentlicht - 22 Feb 2019

Fingerprint

sleep
Sleep Stages
Fuzzy inference
wheels
Feature extraction
Wheels
inference
filters
Fuzzy systems
Adaptive algorithms
Particle swarm optimization (PSO)
fuzzy systems
Support vector machines
selectors
Classifiers
Simulators
classifiers
simulators
optimization
output

Schlagwörter

    ASJC Scopus subject areas

    • Fahrzeugbau
    • Analytische Chemie
    • !!Instrumentation
    • !!Atomic and Molecular Physics, and Optics
    • !!Electrical and Electronic Engineering
    • !!Biochemistry

    Fields of Expertise

    • Mobility & Production

    Treatment code (Nähere Zuordnung)

    • Basic - Fundamental (Grundlagenforschung)

    Dies zitieren

    Driver Drowsiness Detection Based on Steering Wheel Data Applying Adaptive Neuro-Fuzzy Feature Selection. / Arefnezhad, Sadegh; Samiee, Sajjad; Eichberger, Arno; Nahvi, Ali.

    in: Sensors , Jahrgang 19, Nr. 4, 943, 22.02.2019.

    Publikation: Beitrag in einer FachzeitschriftArtikelForschungBegutachtung

    @article{c390ea2e097d454ea63af116bed7f098,
    title = "Driver Drowsiness Detection Based on Steering Wheel Data Applying Adaptive Neuro-Fuzzy Feature Selection",
    abstract = "This paper presents a novel feature selection method to design a non-invasive driver drowsiness detection system based on steering wheel data. The proposed feature selector can select the most related features to the drowsiness level to improve the classification accuracy. This method is based on the combination of the filter and wrapper feature selection algorithms using adaptive neuro-fuzzy inference system (ANFIS). In this method firstly, four different filter indexes are applied on extracted features from steering wheel data. After that, output values of each filter index are imported as inputs to a fuzzy inference system to determine the importance degree of each feature and select the most important features. Then, the selected features are imported to a support vector machine (SVM) for binary classification to classify the driving conditions in two classes of drowsy and awake. Finally, the classifier accuracy is exploited to adjust parameters of an adaptive fuzzy system using a particle swarm optimization (PSO) algorithm. The experimental data were collected from about 20.5 h of driving in the simulator. The results show that the drowsiness detection system is working with a high accuracy and also confirm that this method is more accurate than the recent available algorithms.",
    keywords = "Adaptive neuro-fuzzy inference system, driver drowsiness detection, feature selection, particle swarm optimization, adaptive neuro-fuzzy inference system (ANFIS), particle swarm optimization (PSO), Feature selection, Driver drowsiness detection, Particle swarm optimization (PSO), Adaptive neuro-fuzzy inference system (ANFIS)",
    author = "Sadegh Arefnezhad and Sajjad Samiee and Arno Eichberger and Ali Nahvi",
    year = "2019",
    month = "2",
    day = "22",
    doi = "10.3390/s19040943",
    language = "English",
    volume = "19",
    journal = "Sensors",
    issn = "1424-8220",
    publisher = "MDPI AG",
    number = "4",

    }

    TY - JOUR

    T1 - Driver Drowsiness Detection Based on Steering Wheel Data Applying Adaptive Neuro-Fuzzy Feature Selection

    AU - Arefnezhad, Sadegh

    AU - Samiee, Sajjad

    AU - Eichberger, Arno

    AU - Nahvi, Ali

    PY - 2019/2/22

    Y1 - 2019/2/22

    N2 - This paper presents a novel feature selection method to design a non-invasive driver drowsiness detection system based on steering wheel data. The proposed feature selector can select the most related features to the drowsiness level to improve the classification accuracy. This method is based on the combination of the filter and wrapper feature selection algorithms using adaptive neuro-fuzzy inference system (ANFIS). In this method firstly, four different filter indexes are applied on extracted features from steering wheel data. After that, output values of each filter index are imported as inputs to a fuzzy inference system to determine the importance degree of each feature and select the most important features. Then, the selected features are imported to a support vector machine (SVM) for binary classification to classify the driving conditions in two classes of drowsy and awake. Finally, the classifier accuracy is exploited to adjust parameters of an adaptive fuzzy system using a particle swarm optimization (PSO) algorithm. The experimental data were collected from about 20.5 h of driving in the simulator. The results show that the drowsiness detection system is working with a high accuracy and also confirm that this method is more accurate than the recent available algorithms.

    AB - This paper presents a novel feature selection method to design a non-invasive driver drowsiness detection system based on steering wheel data. The proposed feature selector can select the most related features to the drowsiness level to improve the classification accuracy. This method is based on the combination of the filter and wrapper feature selection algorithms using adaptive neuro-fuzzy inference system (ANFIS). In this method firstly, four different filter indexes are applied on extracted features from steering wheel data. After that, output values of each filter index are imported as inputs to a fuzzy inference system to determine the importance degree of each feature and select the most important features. Then, the selected features are imported to a support vector machine (SVM) for binary classification to classify the driving conditions in two classes of drowsy and awake. Finally, the classifier accuracy is exploited to adjust parameters of an adaptive fuzzy system using a particle swarm optimization (PSO) algorithm. The experimental data were collected from about 20.5 h of driving in the simulator. The results show that the drowsiness detection system is working with a high accuracy and also confirm that this method is more accurate than the recent available algorithms.

    KW - Adaptive neuro-fuzzy inference system

    KW - driver drowsiness detection

    KW - feature selection

    KW - particle swarm optimization

    KW - adaptive neuro-fuzzy inference system (ANFIS)

    KW - particle swarm optimization (PSO)

    KW - Feature selection

    KW - Driver drowsiness detection

    KW - Particle swarm optimization (PSO)

    KW - Adaptive neuro-fuzzy inference system (ANFIS)

    UR - http://www.scopus.com/inward/record.url?scp=85062431874&partnerID=8YFLogxK

    U2 - 10.3390/s19040943

    DO - 10.3390/s19040943

    M3 - Article

    VL - 19

    JO - Sensors

    T2 - Sensors

    JF - Sensors

    SN - 1424-8220

    IS - 4

    M1 - 943

    ER -