Evaluation of drivers' mental workload based on multi-modal physiological signals DOI Creative Commons

Qiliang ZHANG,

Kunhua YANG,

Xingda Qu

et al.

JOURNAL OF SHENZHEN UNIVERSITY SCIENCE AND ENGINEERING, Journal Year: 2022, Volume and Issue: 39(3), P. 278 - 286

Published: May 1, 2022

Accurately assessing the driver's mental workload is of great significance to reduce traffic accidents caused by overload. This study aims evaluate drivers' in simulated typical driving scenarios, with N-back cognitive tasks used manipulate varied levels task difficulty. We collect data on multi-modal physiological signals including electroencephalogram (EEG), electrocardiogram (ECG), and electrodermal activity (EDA) signals, subjective load National Aeronautics Space Administration index (NASA_TLX) during completion process driver experiment, propose a series classification models based feature analysis pattern recognition signals. These are verified machine learning algorithms random forest, decision tree k-nearest neighbor models. The results show that accuracy varies different modalities EEG-based yield highest among single-modal models, followed EDA-based ECG-based Multi-modal-based generally perform better than forest algorithm three-modal EEG, ECG EDA has accuracy.

Language: Английский

Analysis of EEG, Cardiac Activity Status, and Thermal Comfort According to the Type of Cooling Seat during Rest in Indoor Temperature DOI Creative Commons

Yunchan Shin,

Minjung Lee, Honghyun Cho

et al.

Applied Sciences, Journal Year: 2020, Volume and Issue: 11(1), P. 97 - 97

Published: Dec. 24, 2020

In this study, electroencephalogram (EEG) and cardiac activity status of the human body while using various types seats during rest were analyzed in indoor summer conditions. Thermal comfort was also evaluated through a subjective survey. The EEG, status, survey indicated that use ventilation cold water-cooling effective. This effectiveness because θ-wave α-wave activation, sensorimotor rhythm, β-wave reduction, left hemisphere demonstrating conditions applied suitable for rest. According to analysis questionnaire survey, provided more pleasant state than basic seat, improving subject’s warmth comfort, concentration. addition, seat highest satisfaction level, being most favorable condition

Language: Английский

Citations

15
Simplified Prediction Method for Detecting the Emergency Braking Intention Using EEG and a CNN Trained with a 2D Matrices Tensor Arrangement DOI
Hermes J. Mora, Esteban J. Pino

International Journal of Human-Computer Interaction, Journal Year: 2022, Volume and Issue: 39(3), P. 587 - 600

Published: April 18, 2022

The driver's mental state is frequently detected employing EEG signals which are usually converted into grayscale images to train a Machine Learning algorithm that classifies his status. This work aims achieve simplified and accurate method detect the emergency braking intention Convolutional Neural Network (CNN). Three main problems: computer resources, network accuracy, training time defined accomplish this aim. While CNN an efficient image-based classifier, it increases computing resources processing time. Therefore, we solved these problems by through 2D matrices tensor designed with very large database without transforming running on free cloud platform. However, well aware physical fatigue while driving load. Consequently, measured reaction proves increment over time, negatively affecting participants' performance. linear correlation between target non-target classes reveals most events can be well-differentiated from not anomalous driving. CCN accuracy 84% just four electrodes-scalp, comparable reported grayscale-based methods.

Language: Английский

Citations

8
The influence of unpleasant emotional arousal on military performance: An experimental study using auditory stimuli during a shooting task DOI Creative Commons
Leandro L. Di Stasi, Evelyn Gianfranchi, Miguel Pérez-Garcı́a

et al.

International Journal of Industrial Ergonomics, Journal Year: 2022, Volume and Issue: 89, P. 103295 - 103295

Published: April 18, 2022

Due to the intrinsic difficulties associated with simulating extreme events, it remains unclear how unpleasant emotional arousal might affect shooting performance among well-trained high-risk operators. To address this issue, an infantry rifle squad performed two simulated exercises of different complexity (low vs. high) while exposed emotionally charged sound clips. A control group underwent same experimental procedure without presence any externally validate our method inoculation, we collected infantrymen's salivary cortisol and perceived valence levels over phases (i.e., baseline, shooting, recovery). The dependent variables were their (shot-to-hit ratio instructor's evaluation) degree task complexity. Furthermore, explored variations participants' nasal skin temperature during exercises. Salivary concentrations varied time only for stimuli. While had effect on overall infantrymen (e.g., precision movements shooting), accuracy was not affected. Emotional did influence temperature. Overall, results suggest that inoculation based clips could serve as a complementary (reliable ethically appropriate) train operators deal arousal. These findings may also contribute better understanding role in operational effectiveness.

Language: Английский

Citations

8
Task-related, intrinsic oscillatory and aperiodic neural activity predict performance in naturalistic team-based training scenarios DOI Creative Commons
Zachariah R. Cross, Alex Chatburn,

Lee Melberzs

et al.

Scientific Reports, Journal Year: 2022, Volume and Issue: 12(1)

Published: Sept. 28, 2022

Abstract Effective teams are essential for optimally functioning societies. However, little is known regarding the neural basis of two or more individuals engaging cooperatively in real-world tasks, such as operational training environments. In this exploratory study, we recruited forty paired twenty dyads and recorded dual-EEG at rest during realistic scenarios increasing complexity using virtual simulation systems. We estimated markers intrinsic brain activity (i.e., individual alpha frequency aperiodic activity), well task-related theta oscillations. Using nonlinear modelling a logistic regression machine learning model, found that resting-state EEG predicts performance can also reliably differentiate between members within dyad. Task-related easy tasks predicted later on complex to greater extent than prior behaviour. These findings complement laboratory-based research both oscillatory higher-order cognition provide evidence play critical role task team

Language: Английский

Citations

8
Evaluation of drivers' mental workload based on multi-modal physiological signals DOI Creative Commons

Qiliang ZHANG,

Kunhua YANG,

Xingda Qu

et al.

JOURNAL OF SHENZHEN UNIVERSITY SCIENCE AND ENGINEERING, Journal Year: 2022, Volume and Issue: 39(3), P. 278 - 286

Published: May 1, 2022

Accurately assessing the driver's mental workload is of great significance to reduce traffic accidents caused by overload. This study aims evaluate drivers' in simulated typical driving scenarios, with N-back cognitive tasks used manipulate varied levels task difficulty. We collect data on multi-modal physiological signals including electroencephalogram (EEG), electrocardiogram (ECG), and electrodermal activity (EDA) signals, subjective load National Aeronautics Space Administration index (NASA_TLX) during completion process driver experiment, propose a series classification models based feature analysis pattern recognition signals. These are verified machine learning algorithms random forest, decision tree k-nearest neighbor models. The results show that accuracy varies different modalities EEG-based yield highest among single-modal models, followed EDA-based ECG-based Multi-modal-based generally perform better than forest algorithm three-modal EEG, ECG EDA has accuracy.

Language: Английский

Citations

8