Abstract
Driver drowsiness and stress are major causes of traffic deaths and injuries, which ultimately wreak havoc on world economic loss. Researchers are in full swing to develop various algorithms for both drowsiness and stress recognition. In contrast to existing works, this paper proposes a generic model using multiple-objective genetic algorithm optimized deep multiple kernel learning support vector machine that is capable to recognize both driver drowsiness and stress. This algorithm simplifies the research formulations and model complexity that one model fits two applications. Results reveal that the proposed algorithm achieves an average sensitivity of 99%, specificity of 98.3% and area under the receiver operating characteristic curve (AUC) of 97.1% for driver drowsiness recognition. For driver stress recognition, the best performance is yielded with average sensitivity of 98.7%, specificity of 98.4% and AUC of 96.9%. Analysis also indicates that the proposed algorithm using multiple-objective genetic algorithm has better performance compared to the grid search method. Multiple kernel learning enhances the performance significantly compared to single typical kernel. Compared with existing works, the proposed algorithm not only achieves higher accuracy but also addressing the typical issues of dataset in simulated environment, no cross-validation and unreliable measurement stability of input signals.
Highlights
Introduction and Literature ReviewThe World Health Organization (WHO) has reported that the annual road traffic deaths and injuries remain unacceptably high as 1.35 million and 50 million respectively [1]
Four parts would be discussed in detail: (i) the performance of the proposed generic model multiple-objective genetic algorithm (MOGA) optimized D-multiple kernel learning (MKL)-support vector machine (SVM) was evaluated; (ii) study of the effectiveness of MOGA comparing with pure D-MKL-SVM; (iii) comparing the performance between MKL and single typical kernel and (iv) comparing the performance of proposed algorithm and related works
Owning to the fact that existing works on driver drowsiness and stress recognition have room for improvement, which suffer from the following concerns: (i) input signals of poor measurement stability, (ii) performance evaluation without cross-validation and (iii) collecting data using a simulated environment, this paper proposed a generic model using the multiple-objective genetic algorithm (MOGA) optimized deep multiple kernel learning support vector machine (D-MKL-SVM)
Summary
The World Health Organization (WHO) has reported that the annual road traffic deaths and injuries remain unacceptably high as 1.35 million and 50 million respectively [1]. It has highlighted the road traffic is the 8th leading cause of death for people of all ages. More important, it ranks number one when it comes to the age group of 5–29 years old, which can wreak havoc on economic and social development. With the ever-growing number of cars, the leading cause of death will soar from the 9th to the 7th position by Sensors 2020, 20, 1474; doi:10.3390/s20051474 www.mdpi.com/journal/sensors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
