A regression approach based on separability maximization for modeling a continuous-valued stress index from electrocardiogram data

Ribeiro, Rui; Cunha, João Paulo Silva

doi:10.1016/j.bspc.2018.06.006

Cited by 14 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of the H10 sensor for measuring resting heart rate and the validity to measure RR heart rate variability intervals at rest has been confirmed and its ability to produce RR interval recordings consistent with an ECG has been supported (Giles, Draper, & Neil, 2016). HRV data was processed for correction of artefact and irregularities: all RR intervals lower than 300ms and greater than 3000ms, all RR intervals that change by more than 400ms with respect to the previous valid RR interval, and all RR intervals that change by more than 25% with respect to the mean of the five last valid RR intervals (Ribeiro, 2018). The time domain measures used in this study were standard deviation of the normal to normal R-R intervals (SDNN), and the frequency domain indices were low frequency content (LF) which is ranged from 0.04 to 0.15 Hz.…”

Section: Methodsmentioning

confidence: 93%

“…Prior to HRV feature extraction, a filter was applied to the raw RR interval data to remove artifacts: all RR intervals lower than 300ms and greater than 3000ms, all RR intervals that change by more than 400ms with respect to the previous valid RR interval, and all RR intervals that change by more than 25% with respect to the mean of the five last valid RR intervals were removed. The remaining RR intervals are referred to as normal-to-normal (NN) interval (Ribeiro, 2018).…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Effect of Guided Tactical Breathing with Biofeedback on Acute Stress Attenuation and Marksmanship Performance of Novice Shooters

Lotfabadi

Granek

et al. 2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

The current study introduced a novel approach to inducing stress, and examining effects of wearable and mobile technology-assisted tactical breathing with real-time heartrate biofeedback, on the attenuation of acute stress, post-stressor recovery and performance. 39 participants with no prior experience with firearms participated in a marksmanship task engaging stationary targets with a semi-automatic rifle, at a controlled indoor shooting range. Novice shooters applying guided tactical breathing with biofeedback following exposure to the shooting task, were able to maintain lower arousal (uninhibited parasympathetic system). Findings suggested significant effect of intervention with biofeedback on stress attenuation, however no significant improvement of marksmanship performance among novice shooters resulting from the intervention was found. This study provides insights into app-led tactical breathing training to control arousal levels during stress, recommending strategies on further evaluation of the effectiveness of mobile and wearable technologies on stress attenuation for varying levels of marksmanship skill and individual difference.

show abstract

Section: Methodsmentioning

confidence: 93%

Section: Discussionmentioning

confidence: 99%

Effect of Guided Tactical Breathing with Biofeedback on Acute Stress Attenuation and Marksmanship Performance of Novice Shooters

Lotfabadi

Granek

et al. 2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

show abstract

“…RR intervals less than 0.3 s or greater than 2 s were regarded as outliers ( 57 ). RR intervals that differed more than 25% from the mean of the three preceding valid RR intervals were also considered as outliers ( 58 ). These aberrant RR values were replaced by the mean value of the three preceding and the three following RR intervals ( 59 ).…”

Section: Methodsmentioning

confidence: 99%

Measurement and Real-Time Recognition of Driver Trust in Conditionally Automated Vehicles: Using Multimodal Feature Fusions Network

Cao

Song

et al. 2023

Transportation Research Record: Journal of the Transportation R

View full text Add to dashboard Cite

Trust calibration is essential to prevent misuse and disuse of automated vehicles (AVs). Accurate measurement and real-time identification of driver trust is an important prerequisite for achieving trust calibration. Currently, in conditionally automated driving, most researchers utilize self-reported ratings as the ground truth to evaluate driver trust and explore objective trust indicators. However, inconsistencies between the subjective rating and objective behaviors were reported, indicating that trust measurements cannot rely solely on self-reported ratings. To fill this research gap, a method of subjective and objective combination was proposed to measure and identify driver trust in AVs. Thirty-four drivers were involved in a sequence of takeover events. Monitoring ratio and subjective trusting ratings were collected, and combined to measure driver trust levels (i.e., higher and lower trust). Compared with the subjective measurement, the hybrid measurement can more reliably evaluate driver trust in AVs. More importantly, we established a real-time driver trust recognition model for AVs using label smoothing-based convolutional neural network and long short-term memory network fusing multimodal physiological signals (i.e., galvanic skin response and electrocardiogram) and interactive experiences (i.e., takeover-related lead time, takeover frequencies and system usage time). Four common models were developed to compare with the proposed model: Gaussian naive Bayes, support vector machine, convolutional neural network, and long short-term memory network. The comparison results suggest that the performance of our model outperforms others with an F1-score of 75.3% and an area under curve value of 0.812. These findings could have implications for the development of trust monitoring systems in conditionally automated driving.

show abstract

“…Typically, a certain time period is set, and the characteristics are computed during that period. The research on stress detection using HRV typically use a window length measured in minutes [9], [10]. Therefore, the ability to make inferences about cognitive stress is limited to a minimum delay of one minute, which is not feasible for real-time stress detection.…”

Section: Introductionmentioning

confidence: 99%

Mental Stress Prediction Using Machine Learning on Real Time Dataset

Vanisha P. Vaidya

2024

jes

View full text Add to dashboard Cite

Mental stress is a significant issue affecting individuals across all age groups in today's society. The impact of stress extends beyond mental well-being and can lead to various chronic illnesses, including depression, malignancy, and cardiovascular disease (CVD). Addressing mental stress and implementing strategies for stress management and prevention are crucial not only for mental well-being but also for reducing the risk of associated chronic illnesses. In this paper, we are focussing of the problem of mental stress in today's society and the significance of early prediction and management. The use of Random Forest (RF) method with enhanced band pass filtration technique on ECG data for predicting stress levels is a promising approach. Achieving a 96.73% accuracy in stress categorization, along with improvements over prior research results, highlights the effectiveness of the proposed model. The main contribution of the research work is that the results of the model are validated using real-time datasets which further strengthens its reliability and applicability in practical scenarios.

show abstract

A regression approach based on separability maximization for modeling a continuous-valued stress index from electrocardiogram data

Cited by 14 publications

References 21 publications

Effect of Guided Tactical Breathing with Biofeedback on Acute Stress Attenuation and Marksmanship Performance of Novice Shooters

Effect of Guided Tactical Breathing with Biofeedback on Acute Stress Attenuation and Marksmanship Performance of Novice Shooters

Measurement and Real-Time Recognition of Driver Trust in Conditionally Automated Vehicles: Using Multimodal Feature Fusions Network

Mental Stress Prediction Using Machine Learning on Real Time Dataset

Contact Info

Product

Resources

About