Multivariate Multiscale Entropy: An Approach to Estimating Vigilance of Driver

Various driver’s vigilance estimation techniques currently exist in literature. But none of them detects the vigilance of driver in complexity domain. As a result, we have proposed the recently introduced multivariate multiscale entropy (MMSE) method to fill this research gap. In this research, we have applied the MMSE technique to differential entropy features of electroencephalogram (EEG) and electrooculogram (EOG) signals for detecting vigilance of driver in complexity domain. The MMSE has also been employed to PERCLOS (Percentage of Eye Closure) values to analyse cognitive states (awake, tired and drowsy) in complexity domain. The contribution of this research is to show how a new feature called MMSE can efficiently classify the awake, tired and drowsy state of the driver in complexity domain. Another contribution is to demonstrate the distinguishing ability of the MMSE by validating it with applying multivariate sample entropy feature of cognitive states to support vector machine (SVM). The experimental MMSE analysis curves show statistically significant differences (p < 0.01) in terms of complexity among brain EEG signals, forehead EEG signals and EOG signals. Moreover, the difference in the multivariate sample entropy across all scales in awake (1.0828 ± 0.4664), tired (0.7841 ± 0.3183) and drowsy (0.2938 ± 0.1664) states are statistically significant (p <0.01). Also, the SVM, a machine learning technique, has discriminated the cognitive states with the promising classification accuracy of 76.2%. As a result, the MMSE analysis of cognitive states can be implemented practically for vigilance detection by building a programmable vigilance detection system.

Multivariate Multiscale Entropy: An Approach to Estimating Vigilance of Driver

This research has been done using recently introduced multivariate multiscale entropy method with a view to estimating vigilance of drivers during driving in simulated environment. In this driving simulation experiment, twenty one subjects including twelve men and nine women were participated. Multivariate multiscale entropy (MMSE) has been applied to this multimodal Seed dataset for estimating vigilance from electroencephalogram (EEG) and electrooculogram (EOG) signals in order to build a vigilance detection system. The experimental MMSE analysis curves show statistically signi cant di erences (p < 0.01) in terms of complexity among brain EEG signals, forehead EEG signals and EOG signals. Moreover, the di erence in the multivariate sample entropy across all scales in awake (1.0828 0.4664), tired (0.7841 0.3183) and drowsy (0.2938 0.1664) states are statistically signi cant (p <0.01). Also, the support vector machine (SVM), a machine learning technique, has discriminated the cognitive states (awake, tired and drowsy) with the promising classi cation accuracy of 76.2%. As a result, the MMSE analysis of cognitive states can be implemented practically for vigilance detection by building a programmable vigilance detection system .

QUANTIFICATION OF MENTAL STRESS USING COMPLEXITY ANALYSIS OF EEG SIGNALS

Detection of mental stress has been receiving great attention from the researchers for many years. Many studies have analyzed electroencephalogram signals in order to estimate mental stress using linear methods. In this paper, a novel nonlinear stress assessment method based on multivariate multiscale entropy has been introduced. Since the multivariate multiscale entropy method characterizes the complexity of nonlinear time series, this research determines the mental stress of human during cognitive workload using complexity of electroencephalogram (EEG) signals. To perform this work, 36 subjects including 9 men and 27 women were participated in the cognitive workload experiment. Multivariate multiscale entropy method has been applied to electroencephalogram data collected from those subjects for estimating mental stress in terms of complexity. The complexity feature of brain electroencephalogram signals collected during resting and cognitive workload has shown statistically significant ([Formula: see text]) differences across brain regions and mental tasks which can be implemented practically for building stress detection system. In addition, the complexity profile of electroencephalogram signals has shown that higher stress is reflected in good counting compared to bad counting. Moreover, the support vector machine (SVM) has shown promising classification between resting and mental counting states by providing 80% sensitivity, 100% specificity and 90% classification accuracy.

Potential Mediators of Load-Related Changes in Movement Complexity in Young, Healthy Adults

Context Movement screening has become increasingly popular among tactical professionals. This popularity has motivated the design of interventions that cater to improving outcomes on the screens themselves, which are often scored in reference to an objective norm. In contrast to the assumptions underlying this approach, dynamical systems theory suggests that movements arise as a function of continuously evolving constraints and that optimal movement strategies may not exist. To date, few data address behavioral complexity in the fundamental movement tasks commonly used in clinical screenings. Objective To provide evidence of complex variability during movement screens and test the role of modifiable—that is, trainable—constraints in mediating loss of complexity during experimental-task manipulations. Design Crossover study. Setting Research laboratory. Patients or Other Participants Twenty-five male (age = 23.96 ± 3.74 years, height = 178.82 ± 7.51 cm, mass = 79.66 ± 12.66 kg) and 25 female (age = 22.00 ± 2.02 years, height = 165.40 ± 10.24 cm, mass = 63.98 ± 11.07 kg) recreationally active adults. Intervention(s) Participants performed tests of balance, range of motion, and strength. Additionally, they performed cyclical movement tasks under a control (C) condition and while wearing an 18.10-kg weight vest (W). Main Outcome Measure(s) Ground reaction forces were sampled at 1000 Hz and used to calculate center of pressure during cyclical movement tests. Multivariate multiscale entropy (MMSE) for the center-of-pressure signal was then calculated. Condition effects (C versus W) were analyzed using paired t tests, and penalized varying-coefficients regression was used to identify models predicting entropy outcomes from balance, range of motion, and strength. Results The MMSE decreased during the W condition (MMSEC &gt; MMSEW; t49 range = 3.17–5.21; all P values &lt; .01). Conclusions Moderate evidence supported an association between modifiable constraints and behavioral complexity, but a role in mediating load-related loss of complexity was not demonstrated.