CogniMeter: EEG-Based Brain States Monitoring

Hou, Xiyuan; Liu, Yisi; Lim, Wei Lun; Lan, Zirui; Sourina, Olga; Müeller-Wittig, Wolfgang; Wang, Lipo

doi:10.1007/978-3-662-53090-0_6

Cited by 10 publications

(8 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Initially, studies that dealt with the determination of workload were conducted in the laboratory using different task batteries (Gevins et al, 1998;Gevins and Smith, 2000;McEvoy et al, 2001;Berka et al, 2007;Grimes et al, 2008;Baldwin and Penaranda, 2012;Brouwer et al, 2012Brouwer et al, , 2014Christensen and Estepp, 2013;Weiland et al, 2013;Gerjets et al, 2014;Hogervorst et al, 2014;Ke et al, 2014;Hou et al, 2016;Gardony et al, 2017;Rosen and Reiner, 2017;Puma et al, 2018). Meanwhile, investigations of cognitive workload with more realistic tasks became more popular (Kohlmorgen et al, 2007;Lei and Roetting, 2011;Aricò et al, 2018;Dehais et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Indexing Mental Workload During Simulated Air Traffic Control Tasks by Means of Dual Frequency Head Maps

et al. 2020

View full text Add to dashboard Cite

In our digitized society, advanced information and communication technology and highly interactive work environments impose high demands on cognitive capacity. Optimal workload conditions are important for assuring employee's health and safety of other persons. This is particularly relevant in safety-critical occupations, such as air traffic control. For measuring mental workload using the EEG, we have developed the method of Dual Frequency Head Maps (DFHM). The method was tested and validated already under laboratory conditions. However, validation of the method regarding reliability and reproducibility of results under realistic settings and real world scenarios was still required. In our study, we examined 21 air traffic controllers during arrival management tasks. Mental workload variations were achieved by simulation scenarios with different number of aircraft and the occurrence of a priority-flight request as an exceptional event. The workload was assessed using the EEG-based DFHM-workload index and instantaneous self-assessment questionnaire. The DFHM-workload index gave stable results with highly significant correlations between scenarios with similar traffic-load conditions (r between 0.671 and 0.809, p ≤ 0.001). For subjects reporting that they experienced workload variation between the different scenarios, the DFHM-workload index yielded significant differences between traffic-load levels and priority-flight request conditions. For subjects who did not report to experience workload variations between the scenarios, the DFHM-workload index did not yield any significant differences for any of the factors. We currently conclude that the DFHM-workload index reveals potential for applications outside the laboratory and yields stable results without retraining of the classifiers neither regarding new subjects nor new tasks.

show abstract

Section: Introductionmentioning

confidence: 99%

Indexing Mental Workload During Simulated Air Traffic Control Tasks by Means of Dual Frequency Head Maps

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Other studies show that 82% accuracy achievement using higherorder spectra (HOS) as stress recognition with genetic algorithm for optimal selection of features and classification of support vector machine (SVM) [9]. For two stages of stress recognition, the authors in [10] chose to combine fractal dimensions and statistical features. The accuracy recorded was 85.71% using SVM as a classifier.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Fractal Dimension and Wavelet Transform Methods in Classification of Stress State from EEG Signals

Hamid¹,

Saad²,

Haris³

2022

IJCDS

View full text Add to dashboard Cite

Stress is a significant issue in everyday life that affects both physical and mental health. There are different approaches to stress classification. This research examines the implementation of the fractal dimension (FD) method as one of the features for stress state classification using brain signals. Consequently, the comparison between FD and wavelet transform has been conducted using electroencephalogram (EEG) signals recorded during the Stroop Colour Word Test (SCWT). The comparison results show that the FD is better in the classification of the stress state. The highest F1 score has been obtained using FD with quadratic support vector machine (SVM) in average 83.03% for the comparison between baseline session and different stress states. Besides, FD with medium Gaussian SVM has the highest F1 score, on average 83.36%, for comparison between various stress states.

show abstract

“…To this end, we propose a stable feature selection algorithm based on ICC score ranking [128][129][130][131]. The proposed algorithm consists of three steps: ICC assessment, ICC score ranking, and iterative feature selection.…”

Section: Stable Feature Selectionmentioning

confidence: 99%

“…The major problem of a BCI without re-calibration is arguably the lower recognition accuracy compared to a re-calibrated BCI. In this chapter, we propose a stable feature selection algorithm [128][129][130][131] Comparisons between our stable features and the state-of-the-art features show that our stable features yield better accuracy than the best-performing of the state-of-the-art by 0.62 % -8.47 % on the training set, and by 0.23 % -6.16 % on the test set. We stress that the benefit of using stable features is to mitigate the accuracy decrease to a lesser extent compared to not using stable features.…”

Section: Chapter 3 Stable Feature Selection For Eeg-based Emotion Recmentioning

confidence: 99%

“…CogniMeter [130] is designed to integrate the monitoring of three mental states into one web-based interface: the emotion [176], mental workload [177] and stress [178]. The application can provide real time visualization of the emotion, mental workload and stress level recognized from the EEG signals, and could potentially benefit the investigation of human factors if deployed in user study [9].…”

Section: Cognimetermentioning

confidence: 99%

See 1 more Smart Citation

EEG-based emotion recognition using machine learning techniques

Lan¹

Self Cite

View full text Add to dashboard Cite

Electroencephalography (EEG)-based emotion recognition attempts to detect the affective states of humans directly via spontaneous EEG signals, bypassing the peripheral nervous system. In this thesis, we explore various machine learning techniques for EEG-based emotion recognition, and focus on the three research gaps outlined as follows. 1. Stable feature selection for recalibration-less affective Brain-Computer Interfaces 2. Cross-subject transfer learning for calibration-less affective Brain-Computer Interfaces 3. Unsupervised feature learning for affective Brain-Computer Interfaces We propose several novel methods in this thesis to address the three research gaps and validate our proposed methods by experiments. Extensive comparisons between our methods and other existing methods justify the advantages of our methods.

show abstract

CogniMeter: EEG-Based Brain States Monitoring

Cited by 10 publications

References 31 publications

Indexing Mental Workload During Simulated Air Traffic Control Tasks by Means of Dual Frequency Head Maps

Indexing Mental Workload During Simulated Air Traffic Control Tasks by Means of Dual Frequency Head Maps

Comparison of Fractal Dimension and Wavelet Transform Methods in Classification of Stress State from EEG Signals

EEG-based emotion recognition using machine learning techniques

Contact Info

Product

Resources

About