In-Vehicle Stress Monitoring Based on EEG Signal

Abstract

In recent years, improved road safety by monitoring human factors i.e., stress, mental load, sleepiness, fatigue etc. of vehicle drivers has been addressed in a number of studies. Due to the individual variations and complex dynamic in-vehicle environment systems that can monitor such factors of a driver while driving is challenging. This paper presents a drivers' stress monitoring system based on electroencephalography (EEG) signals enabling individual---focused computational approach that can generate automatic decision. Here, a combination of different signal processing i.e., discrete wavelet transform, largest Lyapunov exponent (LLE) and modified covariance have been applied to extract key features from the EEG signals. Hybrid classification approach Fuzzy-CBR (case-based reasoning) is used for decision support. The study has focused on both long and short-term temporal assessment of EEG signals enabling monitoring in different time intervals. In short time interval, which requires complex computations, the classification accuracy using the proposed approach is 79% compare to a human expert. Accuracy of EEG in developing such system is also compared with other reference signals e.g., Electrocardiography (ECG), Finger temperature, Skin conductance, and Respiration. The results show that in decision making the system can handle individual variations and provides decision in each minute time interval.

A Novel Mutual Information Based Feature Set for Drivers’ Mental Workload Evaluation Using Machine Learning

“…For example, a non-linear approach using fractal dimensions, discrete wavelet transform, non-negative matrix factorization, time and frequency domain analysis, etc. [ 26 , 27 , 28 , 29 , 30 ]. Recently, the use of Deep Learning (DL) techniques increased in this domain to reduce the complexity of adopting the mentioned methods.…”

Development of an EEG Headband for Stress Measurement on Driving Simulators

“…The use of EEG to analyze drivers' stress has attracted the attention of researchers in recent years along with the development of autonomous cars. In [33], the study proposed a combined fuzzy and case-based reasoning (Fuzzy-CBR) classification approach to identify the stress or relaxed states of drivers using EEG signals. The proposed method scored a classification accuracy of 79%.…”

“…Even if linearity and/or measurement error are not provided for commercial devices, most of the scientific literature acquires EEG signals using commercial sensors, and the data are then processed with ML algorithms in order to classify the stress in drivers, especially using driving simulators. Some studies used the help of other bio-sensors to categorize and label the acquired EEG signals [33,34] (again, we point out the importance of a precise time alignment between different sensors); some other studies relied on the drivers' selfreport [35]; other studies classified the mental activity using an arbitrary threshold on the EEG signal level and labeling the categories on the basis of threshold trespassing [36]. In this study, we adopted the analysis of the beta activities to identify the stress in drivers from the acquired EEG signals, and this method is well known in the literature [39][40][41][42].…”