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.

An efficient image descriptor for image classification and CBIR

“…1) The Feature selection technique which is applied by PCA algorithm, has been used for several reasons such as reducing the computation volume and training times, simplification of models and etc. [22]. 2) The LBP descriptor is a strong feature for texture classification.…”

Driver Drowsiness Detection and Warning System

“…This system model uses characteristic features such as yawning, dizziness, also conventional driving mode which are detected using machine learning with deep leaning techniques, which can be installed as an operating system inside the cars. Sadegh Arefnezhad et al [6] have taken different features from steering wheel in which four different filter indexes are applied and from which certain features are selected using adaptive neuro-fuzzy inference system (ANFIS). These extracted features are, then given to Support Vector Machine (SVM) which divides the output to drowsy state or wake state, which is given to Particle Swarm Optimization (PSO) algorithm in order to exploit accuracy of the model.…”

CAN-bus Verileri kullanarak Agresif Sürüş Tespiti için Temel Sınıflandırma Algoritmalarının Performans Değerlendirmesi

“…Authors in their study get a performance over 82%. Moreover, Fuzzy classification method is preferred in some of studies (Imkamon at al, 2008;Wu at al, 2012;Songkroh at al, 2014;Fazio at al, 2016;Arefnezhad at al, 2019;Wesseleny at al,2019). Determination of aggressive driving without CAN bus data is achieved by the studies in (Waitkus at al, 2014;Li at al, 2014;Vignali at al, 2019;de Naurois at al, 2019).…”