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

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.

[1]  Uzay Kaymak,et al.  Fuzzy criteria for feature selection , 2012, Fuzzy Sets Syst..

[2]  Bf Buxton,et al.  An introduction to support vector machines for data mining , 2001 .

[3]  Pablo A. Estévez,et al.  A review of feature selection methods based on mutual information , 2013, Neural Computing and Applications.

[4]  Xuesong Wang,et al.  Driver drowsiness detection based on non-intrusive metrics considering individual specifics. , 2016, Accident; analysis and prevention.

[5]  Julien I.E. Hoffman,et al.  t-Test Variants: Cross-Over Tests, Equivalence Tests , 2019, Basic Biostatistics for Medical and Biomedical Practitioners.

[6]  Azim Eskandarian,et al.  Effect of drowsiness on driving performance variables of commercial vehicle drivers , 2009 .

[7]  Diego Cabrera,et al.  A statistical comparison of neuroclassifiers and feature selection methods for gearbox fault diagnosis under realistic conditions , 2016, Neurocomputing.

[8]  Eghbal G. Mansoori,et al.  On fuzzy feature selection in designing fuzzy classifiers for high-dimensional data , 2016, Evol. Syst..

[9]  H. Naseri,et al.  A real-time lane changing and line changing algorithm for driving simulators based on virtual driver behavior , 2017, J. Simulation.

[10]  Shahram Azadi,et al.  Data Fusion to Develop a Driver Drowsiness Detection System with Robustness to Signal Loss , 2014, Sensors.

[11]  K. Premalatha,et al.  A Survey on Feature Selection Methods in Microarray Gene Expression Data for Cancer Classification , 2017 .

[12]  Anthony D. McDonald,et al.  Real-Time Detection of Drowsiness Related Lane Departures Using Steering Wheel Angle , 2012 .

[13]  Marco Vannucci,et al.  A Fuzzy System for Combining Filter Features Selection Methods , 2016, International Journal of Fuzzy Systems.

[14]  Yu-Kun Lai,et al.  Example-based image colorization via automatic feature selection and fusion , 2017, Neurocomputing.

[15]  Micheal Drieberg,et al.  A Hybrid Approach to Detect Driver Drowsiness Utilizing Physiological Signals to Improve System Performance and Wearability , 2017, Sensors.

[16]  Luis Miguel Bergasa,et al.  Fusion of Optimized Indicators from Advanced Driver Assistance Systems (ADAS) for Driver Drowsiness Detection , 2014, Sensors.

[17]  Nak-Tak Jeong,et al.  Drowsy behavior detection based on driving information , 2016, International Journal of Automotive Technology.

[18]  Mohammad Ali Zare Chahooki,et al.  A Survey on semi-supervised feature selection methods , 2017, Pattern Recognit..

[19]  Ferat Sahin,et al.  A survey on feature selection methods , 2014, Comput. Electr. Eng..

[20]  B. Walczak,et al.  Particle swarm optimization (PSO). A tutorial , 2015 .

[21]  Swarun Kumar,et al.  LTE radio analytics made easy and accessible , 2015, SIGCOMM 2015.

[22]  Sudarson Jena,et al.  Correlation based feature selection with clustering for high dimensional data , 2018, Journal of Electrical Systems and Information Technology.

[23]  Amparo Alonso-Betanzos,et al.  Filter Methods for Feature Selection - A Comparative Study , 2007, IDEAL.

[24]  Jeremy Woolley,et al.  Inquiry into the National Road Safety Strategy 2011–2020 , 2018 .

[25]  Qing Chang,et al.  Feature selection methods for big data bioinformatics: A survey from the search perspective. , 2016, Methods.

[26]  Zuojin Li,et al.  Online Detection of Driver Fatigue Using Steering Wheel Angles for Real Driving Conditions , 2017, Sensors.

[27]  Okyay Kaynak,et al.  A Data-Driven Fuzzy Information Granulation Approach for Freight Volume Forecasting , 2017, IEEE Transactions on Industrial Electronics.

[28]  Emmanuelle Diaz,et al.  Detection and prediction of driver drowsiness using artificial neural network models. , 2017, Accident; analysis and prevention.

[29]  Vipin Kumar,et al.  Feature Selection: A literature Review , 2014, Smart Comput. Rev..

[30]  M. Teshnehlab,et al.  Training ANFIS structure with modified PSO algorithm , 2007, 2007 Mediterranean Conference on Control & Automation.

[31]  Bin Yang,et al.  Drowsiness monitoring by steering and lane data based features under real driving conditions , 2010, 2010 18th European Signal Processing Conference.

[32]  Julio López,et al.  Dealing with high-dimensional class-imbalanced datasets: Embedded feature selection for SVM classification , 2018, Appl. Soft Comput..

[33]  Gang Li,et al.  A Context-Aware EEG Headset System for Early Detection of Driver Drowsiness , 2015, Sensors.

[34]  Shiwu Li,et al.  Drowsiness monitoring based on steering wheel status , 2019, Transportation Research Part D: Transport and Environment.

[35]  Daniel Haupt,et al.  Steering wheel motion analysis for detection of the driver's drowsiness , 2011 .

[36]  Kumar Rajamani,et al.  Real-Time Vision Based Driver Drowsiness Detection Using Partial Least Squares Analysis , 2016, J. Signal Process. Syst..

[37]  Anongnart Srivihok,et al.  Wrapper Feature Subset Selection for Dimension Reduction Based on Ensemble Learning Algorithm , 2015 .

[38]  Jarek Krajewski,et al.  Steering wheel behavior based estimation of fatigue , 2017 .

[39]  Shuilong He,et al.  A novel intelligent method for bearing fault diagnosis based on affinity propagation clustering and adaptive feature selection , 2017, Knowl. Based Syst..

[40]  Fardin Ahmadizar,et al.  A novel multivariate filter method for feature selection in text classification problems , 2018, Eng. Appl. Artif. Intell..

[41]  Rong-Jiang Ma,et al.  Application of Particle Swarm Optimization Algorithm in the Heating System Planning Problem , 2013, TheScientificWorldJournal.

[42]  B. N. Manu,et al.  Facial features monitoring for real time drowsiness detection , 2016, 2016 12th International Conference on Innovations in Information Technology (IIT).