EEG-based workers' stress recognition at construction sites

Automation in Construction, Journal Year: 2018, Volume and Issue: 93, P. 315 - 324

Published: May 30, 2018

Language: Английский

---

Machine Learning Framework for the Detection of Mental Stress at Multiple Levels

IEEE Access, Journal Year: 2017, Volume and Issue: 5, P. 13545 - 13556

Published: Jan. 1, 2017

Mental stress has become a social issue and could cause of functional disability during routine work. In addition, chronic implicate several psychophysiological disorders. For example, increases the likelihood depression, stroke, heart attack, cardiac arrest. The latest neuroscience reveals that human brain is primary target mental stress, because perception determines situation threatening stressful. this context, an objective measure for identifying levels while considering considerably improve associated harmful effects. Therefore, in paper, machine learning (ML) framework involving electroencephalogram (EEG) signal analysis stressed participants proposed. experimental setting, was induced by adopting well-known paradigm based on montreal imaging task. induction validated task performance subjective feedback. proposed ML involved EEG feature extraction, selection (receiver operating characteristic curve, t-test Bhattacharya distance), classification (logistic regression, support vector naïve Bayes classifiers) tenfold cross validation. results showed produced 94.6% accuracy two-level identification 83.4% multiple level identification. conclusion, EEG-based potential to quantify objectively into levels. method help developing computer-aided diagnostic tool detection.

Language: Английский

---

A comprehensive survey on multimodal medical signals fusion for smart healthcare systems

Information Fusion, Journal Year: 2021, Volume and Issue: 76, P. 355 - 375

Published: July 5, 2021

Language: Английский

---

A Review on Mental Stress Assessment Methods Using EEG Signals

Sensors, Journal Year: 2021, Volume and Issue: 21(15), P. 5043 - 5043

Published: July 26, 2021

Mental stress is one of the serious factors that lead to many health problems. Scientists and physicians have developed various tools assess level mental in its early stages. Several neuroimaging been proposed literature workplace. Electroencephalogram (EEG) signal important candidate because it contains rich information about states condition. In this paper, we review existing EEG analysis methods on assessment stress. The highlights critical differences between research findings argues variations data contribute several contradictory results. results could be due including lack standardized protocol, brain region interest, stressor type, experiment duration, proper processing, feature extraction mechanism, type classifier. Therefore, significant part related recognition choosing most appropriate features. particular, a complex diverse range features, time-varying, functional, dynamic connections, requires integration understand their associations with Accordingly, suggests fusing cortical activations connectivity network measures deep learning approaches improve accuracy assessment.

Language: Английский

---

Concurrent fNIRS and EEG for Brain Function Investigation: A Systematic, Methodology-Focused Review

Sensors, Journal Year: 2022, Volume and Issue: 22(15), P. 5865 - 5865

Published: Aug. 5, 2022

Electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) stand as state-of-the-art techniques for non-invasive neuroimaging. On a unimodal basis, EEG has poor spatial resolution while presenting high temporal resolution. In contrast, fNIRS offers better resolution, though it is constrained by its One important merit shared the that both modalities have favorable portability could be integrated into compatible experimental setup, providing compelling ground development of multimodal fNIRS-EEG integration analysis approach. Despite growing number studies using concurrent designs reported in recent years, methodological reference past remains unclear. To fill this knowledge gap, review critically summarizes status methods currently used studies, an up-to-date overview guideline future projects to conduct studies. A literature search was conducted PubMed Web Science through 31 August 2021. After screening qualification assessment, 92 involving data recordings analyses were included final review. Specifically, three categories analyses, including EEG-informed fNIRS-informed parallel identified explained with detailed description. Finally, we highlighted current challenges potential directions research.

Language: Английский

---

Connectivity Analysis in EEG Data: A Tutorial Review of the State of the Art and Emerging Trends

Bioengineering, Journal Year: 2023, Volume and Issue: 10(3), P. 372 - 372

Published: March 17, 2023

Understanding how different areas of the human brain communicate with each other is a crucial issue in neuroscience. The concepts structural, functional and effective connectivity have been widely exploited to describe connectome, consisting networks, their structural connections interactions. Despite high-spatial-resolution imaging techniques such as magnetic resonance (fMRI) being used map this complex network multiple interactions, electroencephalographic (EEG) recordings claim high temporal resolution are thus perfectly suitable either spatially distributed temporally dynamic patterns neural activation connectivity. In work, we provide technical account categorization most-used data-driven approaches assess brain-functional connectivity, intended study statistical dependencies between recorded EEG signals. Different pairwise multivariate, well directed non-directed metrics discussed pros–cons approach, time, frequency, information-theoretic domains. establishment conceptual mathematical relationships from these three frameworks, discussion novel methodological approaches, will allow reader go deep into problem inferring networks. Furthermore, emerging trends for description extended forms (e.g., high-order interactions) also discussed, along graph-theory tools exploring topological properties provided by proposed metrics. Applications data reviewed. addition, importance source localization, impacts signal acquisition pre-processing filtering, artifact rejection) on estimates recognized discussed. By going through review, could delve deeply entire process analysis learning, thereby exploiting methodologies within

Language: Английский

---

Stress Assessment Based on Decision Fusion of EEG and fNIRS Signals

IEEE Access, Journal Year: 2017, Volume and Issue: 5, P. 19889 - 19896

Published: Jan. 1, 2017

emergingFusion of electroencephalography (EEG) and functional near infrared spectroscopy (fNIRS) is an emerging approach in the field psychological neurological studies. We developed a decision fusion technique to combine output probabilities EEG fNIRS classifiers. The explored support vector machine as classifier for each modality, optimized classifiers based on their receiver operating characteristic curve values. signal were acquired simultaneously while performing mental arithmetic task under control stress conditions. Experiment results from 20 subjects demonstrated significant improvement detection rate by +7.76% (p <; 0.001) +10.57% 0.0005), compared with sole modality fNIRS, respectively.

Language: Английский

---

An Effective Mental Stress State Detection and Evaluation System Using Minimum Number of Frontal Brain Electrodes

Diagnostics, Journal Year: 2020, Volume and Issue: 10(5), P. 292 - 292

Published: May 9, 2020

Currently, mental stress is a common social problem affecting people. Stress reduces human functionality during routine work and may lead to severe health defects. Detecting important in education industry determine the efficiency of teaching, improve education, reduce risks from errors that might occur due workers' stressful situations. Therefore, early detection using machine learning (ML) techniques essential prevent illness problems, quality industrial safety. The brain main target stress. For this reason, an ML system proposed which investigates electroencephalogram (EEG) signal for thirty-six participants. Extracting useful features efficient (MSD) system. Thus, framework introduces hybrid feature-set feeds five classifiers detect non-stress states, classify levels. To produce reliable, practical, MSD with reduced number electrodes, scheme electrodes placements on different sites scalp selects site has higher impact accuracy Principal Component analysis employed also, extracted such lower model complexity, where optimal principal components examined sequential forward procedure. Furthermore, it examines minimum placed greater evaluation. test effectiveness system, results are compared other feature extraction methods shown literature. They also state-of-the-art recorded detection. highest accuracies achieved study 99.9%(sd = 0.015) 99.26% (sd 0.08) identifying distinguishing between levels, respectively, only two frontal detecting non-stress, three evaluating levels respectively. show reliable as sensitivity 99.9(0.064), 98.35(0.27), specificity 99.94(0.02), 99.6(0.05), precision 99.94(0.06), 98.9(0.23), diagnostics odd ratio (DOR) ≥ 100 This shows compelling performance can be evaluation medical, educational fields. Finally, verified reliability predicting new patients, 98.48% 1.12), 97.78% 1.84), 97.75% 2.05), 0.67), DOR electrodes.

Language: Английский

---

A systematic review on hybrid EEG/fNIRS in brain-computer interface

Biomedical Signal Processing and Control, Journal Year: 2021, Volume and Issue: 68, P. 102595 - 102595

Published: April 2, 2021

Language: Английский

---

The neural correlates of psychosocial stress: A systematic review and meta-analysis of spectral analysis EEG studies

Neurobiology of Stress, Journal Year: 2022, Volume and Issue: 18, P. 100452 - 100452

Published: April 26, 2022

Whereas the link between psychosocial stress and health complications has long been established, influence of on brain activity is not yet completely understood. Electroencephalography (EEG) regularly employed to investigate neural aspects response, but these results have unified. Therefore, in this article, we systematically review current EEG literature which spectral analyses were response interpret with regard three phases (anticipatory, reactive, recovery) can be divided. Our show that measures, alpha power, beta power frontal asymmetry (FAA), are commonly utilized consistently decreases, shows a tendency increase, FAA varies inconsistently. We furthermore found whereas changes independent phase, relative phase trend, other measures such as delta theta gamma theta-alpha ratio less changes. Meta-analyses conducted further revealed significant effect size (hedge's g = 0.6; p 0.001) for an insignificant −0.31; 0.29) 0.01, 0.93). From our results, it concluded some indices, more research needed uncover precise (temporal) mechanisms underlying responses.

Language: Английский

---