Driver State Detection Based on Cardiovascular System and Driver Reaction Information Using a Graphical Model

Nguyễn, Thanh Tùng; Aoki, Hirofumi; Son, Le Anh; Hirano, Akira; Aoki, Kunimoto; Inagami, Makoto; Suzuki, Tatsuya

doi:10.4236/jtts.2021.112009

Cited by 3 publications

(1 citation statement)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, the algorithm is better at gathering relevant data about the topic under investigation, classification accuracy improves, and fewer characteristics are required for real-time classification [16]. Convolutional neural network (CNN) architectures like LeNet, AlexNet, VGGNet, ResNet, Inception, DenseNet, and EfficientNet, recurrent neural networks (RNN), long-short-term memory (LSTM), and gated recurrent units are examples of popular deep supervised learning methods (GRU) [27][28][29][30]. For instance, a new drowsiness detection approach was presented in [31].…”

Section: Supervised Learningmentioning

confidence: 99%

Comparative Study of Machine Learning Algorithms in Classifying HRV for the Driver’s Physiological Condition

Abdul Razak,

Sayed Ismail,

Yogarayan

et al. 2023

Civ Eng J

View full text Add to dashboard Cite

Heart Rate Variability (HRV) may be used as a psychological marker to assess drivers’ states from physiological signals such as an electrocardiogram (ECG), electroencephalogram (EEG), and photoplethysmography (PPG). This paper reviews HRV acquisition methods from drivers and machine learning approaches for driver cardiac health based on HRV classification. The study examines four publicly available ECG datasets and analyzes their HRV features, including time domain, frequency domain, short-term measures, and a combination of time and frequency domains. Eight machine learning classifiers, namely K-Nearest Neighbor, Decision Tree, Naive Bayes, Linear Discriminant Analysis, Support Vector Machine, Random Forest, Gradient Boost, and Adaboost, were used to determine whether the driver's state is normal or abnormal. The results show that K-Nearest Neighbor and Decision Tree classifiers had the highest accuracy at 92.86%. The study concludes by assessing the performance of machine learning algorithms in classifying HRV for the driver's physiological condition using the Man-Whitney U test in terms of accuracy and F1 score. We have statistical evidence to support that the prediction quality is different when HRV analysis applies these three sets: (i) time domain measures or frequency domain measures; (ii) frequency domain measures or short-term measures; and (iii) combining time and frequency domains or only frequency domains. Doi: 10.28991/CEJ-2023-09-09-013 Full Text: PDF

show abstract

Section: Supervised Learningmentioning

confidence: 99%

Comparative Study of Machine Learning Algorithms in Classifying HRV for the Driver’s Physiological Condition

Abdul Razak,

Sayed Ismail,

Yogarayan

et al. 2023

Civ Eng J

View full text Add to dashboard Cite

show abstract

Relating Driver Behaviour and Response to Messages through HMI in Autonomous and Connected Vehicular Environment

Iskandarani

2022

Cogent Engineering

View full text Add to dashboard Cite

Effect of Driver Response on Efficiency of Vehicular Communication using Penalty Cost Function (EVCPCF)

Iskandarani¹

2023

TOTJ

View full text Add to dashboard Cite

Background and objective: This study examines and takes into account three key timing factors that have an impact on the effectiveness of human-machine interfaces (HVI). A threshold-based mechanism is created to account for both cooperative driving and advanced vehicle control system (AVCS) scenarios. For AVCS and cooperative driving, the developed model takes into account on-board machine interface time, human interface time, and transmission time.. Methods: A threshold function that represents the penalty cost of a slow driver reaction is presented in order to enable adaptive intelligence, enhance HVI design, and increase vehicle safety. The Penalty Cost Function (PCF) is used to make vehicle control systems intervene and take control in situations where the driver is responding slowly to safety and warning messages. Additionally, this study demonstrates that AVCS-based vehicular systems are more responsive overall and are less impacted by the PCF function than cooperative systems. Results: The mathematical models created through this work allowed for a limiting efficiency value and capping for each driving scenario, according to comparative plots. This will improve the creation of more reliable control systems as part of a vehicle's mechatronics, which will affect how vehicles communicate with one another in a cooperative setting. MATLAB simulation was used to verify the mathematical model. The simulation covered two limiting cases of 0.33 and 0.5 and used incrementing numbers of vehicles (10, 20, 30, 40, 50) to check the impact of increasing vehicle numbers on communication efficiency and examine that both AVCS and AVCS with cooperative will have close levels and converge at limiting values. Conclusion: The successfully completed simulation demonstrated that throughput decreased as the number of vehicles increased, although in the limiting case, both scenarios and the driving system changed virtually by the same percentage.

show abstract

Driver State Detection Based on Cardiovascular System and Driver Reaction Information Using a Graphical Model

Cited by 3 publications

References 48 publications

Comparative Study of Machine Learning Algorithms in Classifying HRV for the Driver’s Physiological Condition

Comparative Study of Machine Learning Algorithms in Classifying HRV for the Driver’s Physiological Condition

Relating Driver Behaviour and Response to Messages through HMI in Autonomous and Connected Vehicular Environment

Effect of Driver Response on Efficiency of Vehicular Communication using Penalty Cost Function (EVCPCF)

Contact Info

Product

Resources

About