Driver’s cardiac activity performance evaluation based on non-contact ECG system placed at different seat locations
TL;DR: Combined cECG from seat back and seat base was better than using a single source for sensor and Perspiration effect reveled that the signals from the seat base were more consistent and reliable as compared to seat back signal.
Abstract: Electrocardiography (ECG) is known to be a reasonable measure of driver fatigue. In this study, we have estimated the cECG performance while placing it on seat base and seat back of the driver seat. Ten male licensed volunteers participated in this study for the duration on the one hour on the simulator. cECG electrodes were place at the seat back and other set of cECG electrodes were placed at the seat base. cECG signals were acquired from both seat back and seat base and it was correlated with the conventional ECG system. Based on Magnitude square coherence (MSC) analysis, it was observed that all the ECG signals acquired from different source had good coherence with ECG (p > 0.05). It was observed that the cECG signals acquired from the seat base shown good coherence as compared to the signals acquired from seat back. Perspiration effect reveled that the signals from the seat base were more consistent and reliable as compared to seat back signal (p > 0.05). However, combined cECG from seat back and seat base was better than using a single source for sensor.
Citations
More filters
01 Dec 2018
TL;DR: This paper verify the superiority of the deep learning approaches over machine learning methods for driver fatigue detection using electrocardiography (ECG) using heart rate variability (HRV) derived from ECG, and directly controlled by the autonomic nervous system.
Abstract: Driving fatigue is one of the significant factor cause road accidents which often result in huge socio-economic loss to the country. The real-time, accurate driver fatigue and drowsiness detection can bring down the accident rate. This paper verify the superiority of the deep learning approaches over machine learning methods for driver fatigue detection using electrocardiography (ECG). Heart rate variability (HRV) derived from ECG, and directly controlled by the autonomic nervous system is a promising indicator for real-time driver fatigue estimation. The classification system use time domain, frequency domain and nonlinear HRV features to ensure high accuracy and detection rate. This study conducted on 10 healthy individuals in simulator driving environment. The deep learning architecture based on Stacked Autoencoders achieve an accuracy above 90% to determine the perceived fatigue in drivers.
25 citations
Cites background from "Driver’s cardiac activity performan..."
...Numerous physiological parameters such as electroencephalography (EEG) [8], electrocardiography (ECG) [8], [9], electrooculogram (EOG) and electromyography (EMG) [10] can be used to measure the levels of fatigue in drivers....
[...]
...The capacitive ECG sensors attached to the seat/steering wheel ensure the long-term recording of ECG with minimum discomfort [15], [8], [9]....
[...]
TL;DR: Validation of c ECG with conventional ECG will be very helpful in considering cECG as a good replacement of conventional ECGs to detect non-contact ubiquitous driver performance monitoring.
Abstract: A non-contact capacitive coupled electrocardiography (cECG) system to estimate driver’s fatigue is presented in this paper. Twenty male volunteers participated in this paper on a high fidelity driving simulator. To validate the cECG system, we have correlated it with conventional single lead ECG systems. Effect of perspiration on the cECG signal was also observed. Heart dynamics based on Poincare plot was estimated to observe fatigue. Magnitude square coherence analysis provided good coherence between conventional ECG and cECG signals whereas, signal quality of the cECG signals was observed better as time progressed probably due to effect of perspiration. Significant change (p < 0.05) in HRV dynamics and frequency measure of cECG signals was observed during course of driving. Correlation coefficients between non-linear indices of HRV (SD1, SD2, and SD1/SD2) and frequency measure indices of HRV (LF, HF, and LF/HF) were tested by the Spearman rank correlation test. Result from non-linear and frequency indices analysis of HRV showed significant change (p < 0.05) during course of simulated driving. Validation of cECG with conventional ECG will be very helpful in considering cECG as a good replacement of conventional ECG to detect non-contact ubiquitous driver performance monitoring.
22 citations
Cites background from "Driver’s cardiac activity performan..."
...Decrease in electrodeskin impedance happens due to moistening of underlying skin by sweat-gland activity with the passage of time [64], [65]....
[...]
01 Dec 2018
TL;DR: This work proposed a highly accurate, EEG based driver fatigue classification system which can reduce the rate of fatigue related road accidents using machine learning and deep learning algorithms.
Abstract: Driver fatigue is a major cause of the road accidents that occur throughout the globe. It has been observed that among total number of accidents, 20% are contributed from driver fatigue. Acknowledging the existing data it is clear that a notification system for driver fatigue is of at most importance. Over the past a large number of strategies have been tested out and among them EEG based systems have shown to be the most accurate and reliable to estimate driver’s cognitive state. The direct relation of brain activity to EEG signal explains its high accuracy in a fatigue detection system. Current researches in machine learning as well as deep learning have shown a new perspective in EEG data analysis. This work proposed a highly accurate, EEG based driver fatigue classification system which can reduce the rate of fatigue related road accidents using machine learning and deep learning algorithms. The results showed that the relative power of theta, alpha, beta and delta showed significant correlation to driver fatigue. The selected features were trained and evaluated using 20 well established classifiers in the field of driver fatigue. Among all the classifiers tested, the Fine Tree, Subspace KNN, Fine Gaussian SVM, and Weighted KNN were performed to the highest accuracy levels. Different performance metrics are used for this work and Deep Autoencoder and KNN are identified as the best suitable Deep learning and Machine Learning Algorithms for driver fatigue prediction with an accuracy of 99.7% and 99.6 % respectively.
4 citations
01 Jan 2021
TL;DR: In this paper, a novel approach for real-time fatigue detection based on heart rate variability (HRV) is proposed, which uses physiological features to ensure high accuracy and detection rate.
Abstract: Driving fatigue is a leading cause of road crashes that often result in injury and death. The real-time detection of fatigue and drowsiness on a vehicle can bring down the accident rate in our country. In this paper, a novel approach toward real-time fatigue detection based on heart rate variability (HRV) is proposed. This detection system uses physiological features to ensure high accuracy and detection rate. The deep learning network designed can accurately classify normal and fatigue conditions. HRV analysis in time and frequency domains gives reliable information about normal and fatigue status. The warning system inside the vehicle will alert the driver, and the information will send to the remote monitoring center.
2 citations
01 Jan 2021
TL;DR: In this paper, the estimation of driver fatigue in different age group bus drivers and drivers with and without post-traumatic stress disorder (PTSD) based on seat interface pressure sensor was reported.
Abstract: Driver’s performance on the road is vital from road safety point of view. This paper reports the estimation of driver fatigue in different age group bus drivers and drivers with and without post-traumatic stress disorder (PTSD) based on seat interface pressure sensor. Twenty professional bus drivers participated in this study. Feature such as contact pressure was estimated for the period of one hour on simulated as well as on-road driving condition. Result from seat interface pressure sensor showed significant (p > 0.05) difference in all the groups of the driver considered in this study. It was observed that the majority of the drivers exert more pressure with their right thigh and buttock, and almost every driver has been observed leaning back after onset of the fatigue. Old drivers fatigue rate was higher compared to younger drivers. Finding of this study will be very helpful in designing cabin ergonomics, seats and giving proper training to the drivers to avoid road accidents.
References
More filters
Book•
13 May 1980
TL;DR: This chapter discusses single-Input/Single-Output Relationships, nonstationary data analysis techniques, and procedures to Solve Multiple- Input/Multiple-Output Problems.
Abstract: Discusses engineering applications and recent developments based upon correlation and spectral analysis. Illustrations deal with applications to acoustics, mechanical vibrations, system identification, and fluid dynamics problems in aerospace, automotive, industrial noise control, civil engineering and oceanographic fields, as well as similar problems in other fields. Tackles problems and solutions, assuming reader has required hardware and software to compute estimates of correlation, spectra, coherence, and phase functions.
2,447 citations
23 Jun 2003
TL;DR: It is claimed that the applied measures used in the synchronization between left and right hemisphere rat electroencephalographic channels are valuable for the study of synchronization in real data and in the particular case of EEG signals their use as complementary variables could be of clinical relevance.
Abstract: We agree with the Comment by Duckrow and Albano [Phys. Rev. E 67, 063901 (2003)] that mutual information, estimated with an optimized algorithm, can be a useful tool for studying synchronization in real data. However, we point out that the improvement they found is mainly due to an interesting but nonstandard embedding technique used, and not so much due to the algorithm used for the estimation of mutual information itself. We also address the issue of stationarity of electroencephalographic (EEG) data.
736 citations
TL;DR: In this article, the synchronization between left and right hemisphere rat electroencephalographic (EEG) channels by using various synchronization measures, namely nonlinear interdependences, phase synchronizations, mutual information, cross correlation, and the coherence function, was studied.
Abstract: We study the synchronization between left and right hemisphere rat electroencephalographic (EEG) channels by using various synchronization measures, namely nonlinear interdependences, phase synchronizations, mutual information, cross correlation, and the coherence function. In passing we show a close relation between two recently proposed phase synchronization measures and we extend the definition of one of them. In three typical examples we observe that except mutual information, all these measures give a useful quantification that is hard to be guessed beforehand from the raw data. Despite their differences, results are qualitatively the same. Therefore, we claim that the applied measures are valuable for the study of synchronization in real data. Moreover, in the particular case of EEG signals their use as complementary variables could be of clinical relevance.
716 citations
TL;DR: The smart shirt which measures electrocardiogram (ECG) and acceleration signals for continuous and real time health monitoring is designed and developed and the adaptive filtering method to cancel artifact noise from conductive fabric electrodes in a shirt is also designed and tested.
Abstract: The smart shirt which measures electrocardiogram (ECG) and acceleration signals for continuous and real time health monitoring is designed and developed. The shirt mainly consists of sensors for continuous monitoring the health data and conductive fabrics to get the body signal as electrodes. The measured physiological ECG data and physical activity data are transmitted in an ad-hoc network in IEEE 802.15.4 communication standard to a base-station and server PC for remote monitoring. The wearable sensor devices are designed to fit well into shirt with small size and low power consumption to reduce the battery size. The adaptive filtering method to cancel artifact noise from conductive fabric electrodes in a shirt is also designed and tested to get clear ECG signal even though during running or physical exercise of a person.
354 citations
TL;DR: The theoretical background of fluctuations in heart rate and respiration and the application of existing methods in laboratory and normal working situations are discussed and data acquisition and analysis methods are presented.
314 citations