A physiological data‐driven model for learners' cognitive load detection using HRV‐PRV feature fusion and optimized XGBoost classification

Guo, Junqi; Dai, Yunrong; Wang, Chixiang; Wu, Hao; Xu, Tianyou; Lin, Kai

doi:10.1002/spe.2730

Cited by 7 publications

(1 citation statement)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…HRV has been shown to be an objective estimation of learners’ cognitive load in a learning environment [ 61 , 62 ]. For controlling preinterventional stress, the participants sat quietly for 20 minutes.…”

Section: Methodsmentioning

confidence: 99%

Using a 360° Virtual Reality or 2D Video to Learn History Taking and Physical Examination Skills for Undergraduate Medical Students: Pilot Randomized Controlled Trial

Chao¹,

Chuang²,

Hsin³

et al. 2021

JMIR Serious Games

View full text Add to dashboard Cite

Background Learning through a 360° virtual reality (VR) or 2D video represents an alternative way to learn a complex medical education task. However, there is currently no consensus on how best to assess the effects of different learning materials on cognitive load estimates, heart rate variability (HRV), outcomes, and experience in learning history taking and physical examination (H&P) skills. Objective The aim of this study was to investigate how learning materials (ie, VR or 2D video) impact learning outcomes and experience through changes in cognitive load estimates and HRV for learning H&P skills. Methods This pilot system–design study included 32 undergraduate medical students at an academic teaching hospital. The students were randomly assigned, with a 1:1 allocation, to a 360° VR video group or a 2D video group, matched by age, sex, and cognitive style. The contents of both videos were different with regard to visual angle and self-determination. Learning outcomes were evaluated using the Milestone reporting form. Subjective and objective cognitive loads were estimated using the Paas Cognitive Load Scale, the National Aeronautics and Space Administration Task Load Index, and secondary-task reaction time. Cardiac autonomic function was assessed using HRV measurements. Learning experience was assessed using the AttrakDiff2 questionnaire and qualitative feedback. Statistical significance was accepted at a two-sided P value of <.01. Results All 32 participants received the intended intervention. The sample consisted of 20 (63%) males and 12 (38%) females, with a median age of 24 (IQR 23-25) years. The 360° VR video group seemed to have a higher Milestone level than the 2D video group (P=.04). The reaction time at the 10th minute in the 360° VR video group was significantly higher than that in the 2D video group (P<.001). Multiple logistic regression models of the overall cohort showed that the 360° VR video module was independently and positively associated with a reaction time at the 10th minute of ≥3.6 seconds (exp B=18.8, 95% CI 3.2-110.8; P=.001) and a Milestone level of ≥3 (exp B=15.0, 95% CI 2.3-99.6; P=.005). However, a reaction time at the 10th minute of ≥3.6 seconds was not related to a Milestone level of ≥3. A low-frequency to high-frequency ratio between the 5th and 10th minute of ≥1.43 seemed to be inversely associated with a hedonic stimulation score of ≥2.0 (exp B=0.14, 95% CI 0.03-0.68; P=.015) after adjusting for video module. The main qualitative feedback indicated that the 360° VR video module was fun but caused mild dizziness, whereas the 2D video module was easy to follow but tedious. Conclusions Our preliminary results showed that 360° VR video learning may be associated with a better Milestone level than 2D video learning, and that this did not seem to be related to cognitive load estimates or HRV indexes in the novice learners. Of note, an increase in sympathovagal balance may have been associated with a lower hedonic stimulation score, which may have met the learners’ needs and prompted learning through the different video modules. Trial Registration ClinicalTrials.gov NCT03501641; https://clinicaltrials.gov/ct2/show/NCT03501641

show abstract

Section: Methodsmentioning

confidence: 99%

Using a 360° Virtual Reality or 2D Video to Learn History Taking and Physical Examination Skills for Undergraduate Medical Students: Pilot Randomized Controlled Trial

Chao¹,

Chuang²,

Hsin³

et al. 2021

JMIR Serious Games

View full text Add to dashboard Cite

show abstract

The Validity of Heart Rate Variability (HRV) in Educational Research and a Synthesis of Recommendations

Kim,

Park,

Lee

2024

Educ Psychol Rev

View full text Add to dashboard Cite

This study provides a comprehensive overview of methodological aspects when using heart rate variability (HRV) measures in educational research. Following PRISMA 2020 guidelines, we searched four databases for relevant studies published until March 5, 2024. From the 48 studies reviewed, we extracted data across three analytical categories: (1) area of study interest and participant populations, (2) data collection and analysis methodologies, and (3) the concurrent and predictive validity of HRV measurement for educational research. Study quality was evaluated using QualSyst assessment criteria. Most studies measured stress and enlisted undergraduate students as participants. Data were predominately collected using wearable devices, measuring HRV for durations of less than 30 min, and in varied contexts, including during exams, while learning, and in experiments. The parameters analyzed varied within both time and frequency domains. HRV data had a moderate level of concurrent validity as a measure of stress in an educational context. The concurrent validity of HRV data for measuring attention remains uncertain with insufficient evidence. Limited correlations appeared between stress and performance. The findings, potentials, and limitations of HRV measures are discussed, and synthesized recommendations for educational research using HRV data are provided.

show abstract

Sleep staging classification based on a new parallel fusion method of multiple sources signals

Hei¹,

Yuan²,

Fan³

et al. 2022

Physiol. Meas.

View full text Add to dashboard Cite

Approach: First, the heart rate variability (HRV) is extracted from EOG with the Weight Calculation Algorithm (WCA) and an “HYF” RR interval detection algorithm. Second, three feature sets were extracted from HRV segments and EOG segments: time-domain features, frequency domain features and nonlinear-domain features. The frequency domain features and nonlinear-domain features were extracted by using Discrete Wavelet Transform (DWT), Autoregressive (AR), and Power Spectral entropy (PSE), and Refined Composite Multiscale Dispersion Entropy (RCMDE). Third, a new “Parallel Fusion Method” (PFM) for sleep stage classification is proposed. Three kinds of feature sets from EOG and HRV segments are fused by using PFM. Fourth, Extreme Gradient Boosting (XGBoost) and Support Vector Machine (SVM) classification models is employed for sleep staging. Main results: Our experimental results show significant performance improvement on automatic sleep staging on the target domains achieved with the new sleep staging approach. The performance of the proposed method is testedby evaluating the average accuracy, Kappa coefficient. The average accuracy of sleep classification results by using XGBoost classification model with PFM is 82.7% and the kappa coefficient is 0.711, also by using SVM classification model with the PFM is 83.7%, and the kappa coefficient is 0.724. Experimental results show that the performance of the proposed method is competitive with the most current methods and results, and the recognition rate of S1 stage is significantly improved. Significance： As a consequence, it would enable one to improve the quality of automatic sleep staging models when the EOG and HRV signals are fused, which can be beneficial for monitor sleep quality and keep abreast of health conditions. Besides, our study provides good research ideas and methods for scholars, doctors and individuals.

show abstract

A physiological data‐driven model for learners' cognitive load detection using HRV‐PRV feature fusion and optimized XGBoost classification

Cited by 7 publications

References 44 publications

Using a 360° Virtual Reality or 2D Video to Learn History Taking and Physical Examination Skills for Undergraduate Medical Students: Pilot Randomized Controlled Trial

Using a 360° Virtual Reality or 2D Video to Learn History Taking and Physical Examination Skills for Undergraduate Medical Students: Pilot Randomized Controlled Trial

The Validity of Heart Rate Variability (HRV) in Educational Research and a Synthesis of Recommendations

Sleep staging classification based on a new parallel fusion method of multiple sources signals

Contact Info

Product

Resources

About