A data-driven framework for learners’ cognitive load detection using ECG-PPG physiological feature fusion and XGBoost classification

Wang, Chixiang; Guo, Junqi

doi:10.1016/j.procs.2019.01.234

Cited by 23 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This finding supports the nature of linear correlations among time and frequency domains of HRV indices. Although k-NN was among the most used algorithm in building HRV-based ML models, its lower performance compared to other algorithms was also reported in other studies [26], [53]. This indicated the variance of performance across some supervised classification algorithms.…”

Section: Machine Learning Classifiersmentioning

confidence: 74%

“…Tsunoda et al [25] used traditional and established ECG system devices (BIOPAC 3 channels) to predict when the cognitive performance started to decrease. Some scholars (e.g., [26,27,28] also employed three ECG channels to detect mental stress and cognitive task. One of the few studies that collected HRV data using one wearable sensor is Huang et al, [29].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning models for the Cognitive Stress Detection Using Heart Rate Variability Signals

Izzah¹,

Sutarto²,

Hariyadi³

2022

jti

View full text Add to dashboard Cite

Cognitive domains play a critical role in daily functioning. The prediction of cognitive stress state is important to better monitor work performance. This study aims to explore machine learning models to detect cognitive load or state using heart rate variability (HRV) signals. HRV data were recorded from thirty subjects during rest, two cognitive tasks (d2 Attention and Featuring Switcher task), and recovery. Seven HRV indexes from both time and frequency domains, extracted from raw R-R intervals, were used to identify whether subjects performed cognitive tasks or not. Five classifier models: linear support vector machine (LSVM), kernel SVM radial basis function, k-nearest neighbor (KNN), and random forest (RF), were trained and evaluated using a leave-one-out cross-validation approach. The accuracies and F1-score range from 0.54 to 0.62, with LSVM, showing the best. These acceptable performances indicate the machine learning approach could be used to further distinguish between rest and cognitive state. With the ubiquity of non-invasive and low-cost wearable devices, this finding offers insight to be incorporated into personal work performance monitoring in the digital age.

show abstract

Section: Machine Learning Classifiersmentioning

confidence: 74%

Section: Introductionmentioning

confidence: 99%

Machine Learning models for the Cognitive Stress Detection Using Heart Rate Variability Signals

Izzah¹,

Sutarto²,

Hariyadi³

2022

jti

View full text Add to dashboard Cite

show abstract

“…In addition, regularisation is performed when constructing the regression tree, allowing column sampling to prevent overfitting. In practice, the XGBoost algorithm has shown good results in many prediction fields ( Wang and Guo, 2019 ).…”

Section: Methodsmentioning

confidence: 99%

Automatic Multichannel Electrocardiogram Record Classification Using XGBoost Fusion Model

Huang

Lü

2022

Front. Physiol.

View full text Add to dashboard Cite

There is an increasing demand for automatic classification of standard 12-lead electrocardiogram signals in the medical field. Considering that different channels and temporal segments of a feature map extracted from the 12-lead electrocardiogram record contribute differently to cardiac arrhythmia detection, and to the classification performance, we propose a 12-lead electrocardiogram signal automatic classification model based on model fusion (CBi-DF-XGBoost) to focus on representative features along both the spatial and temporal axes. The algorithm extracts local features through a convolutional neural network and then extracts temporal features through bi-directional long short-term memory. Finally, eXtreme Gradient Boosting (XGBoost) is used to fuse the 12-lead models and domain-specific features to obtain the classification results. The 5-fold cross-validation results show that in classifying nine categories of electrocardiogram signals, the macro-average accuracy of the fusion model is 0.968, the macro-average recall rate is 0.814, the macro-average precision is 0.857, the macro-average F1 score is 0.825, and the micro-average area under the curve is 0.919. Similar experiments with some common network structures and other advanced electrocardiogram classification algorithms show that the proposed model performs favourably against other counterparts in F1 score. We also conducted ablation studies to verify the effect of the complementary information from the 12 leads and the auxiliary information of domain-specific features on the classification performance of the model. We demonstrated the feasibility and effectiveness of the XGBoost-based fusion model to classify 12-lead electrocardiogram records into nine common heart rhythms. These findings may have clinical importance for the early diagnosis of arrhythmia and incite further research. In addition, the proposed multichannel feature fusion algorithm can be applied to other similar physiological signal analyses and processing.

show abstract

“…Other sensing modalities relevant for the estimation of cognitive load include electrocardiography (ECG) and photoplethsmography (PPG) and the use of the corresponding heart rate metrics to classify cognitive workload in a range of scenarios, including driving whilst performing an N-back memory task [9], taking maths tests of varying difficulty [10] and when engaging in a partially automated task with a machine based component [11]. Whilst ECG and PPG are less obtrusive than EEG or gaze tracking in daily life and do offer a wearable solution to cognitive workload tracking, it remains unclear whether the documented increases in heart rate are associated with the stress of performing well during higher cognitive workload tasks [12] [13], or indeed the increased cognitive workload itself.…”

Section: A Cognitive Workload Trackingmentioning

confidence: 99%

In-Ear SpO2 for Classification of Cognitive Workload

Davies¹,

Williams²,

Hammour³

et al. 2021

Preprint

View full text Add to dashboard Cite

Classification of cognitive workload promises immense benefit in diverse areas ranging from driver safety to augmenting human capability through closed loop brain computer interface. The brain is the most metabolically active organ in the body and increases its metabolic activity and thus oxygen consumption with increasing cognitive demand. In this study, we explore the feasibility of in-ear SpO 2 cognitive workload tracking. To this end, we preform cognitive workload assessment in 8 subjects, based on an N-back task, whereby the subjects are asked to count and remember the number of odd numbers displayed on a screen in 5 second windows. The 2 and 3-back tasks lead to either the lowest median absolute SpO 2 or largest median decrease in SpO 2 in all of the subjects, indicating a robust and measurable decrease in blood oxygen in response to increased cognitive workload. Using features derived from in-ear pulse oximetry, including SpO 2 , pulse rate and respiration rate, we were able to classify the 4 N-back task categories, over 5 second epochs, with a mean accuracy of 94.2%. Moreover, out of 21 total features, the 9 most important features for classification accuracy were all SpO 2 related features. The findings suggest that in-ear SpO 2 measurements provide valuable information for classification of cognitive workload over short time windows, which together with the small form factor promises a new avenue for real time cognitive workload tracking.

show abstract

A data-driven framework for learners’ cognitive load detection using ECG-PPG physiological feature fusion and XGBoost classification

Cited by 23 publications

References 21 publications

Machine Learning models for the Cognitive Stress Detection Using Heart Rate Variability Signals

Machine Learning models for the Cognitive Stress Detection Using Heart Rate Variability Signals

Automatic Multichannel Electrocardiogram Record Classification Using XGBoost Fusion Model

In-Ear SpO2 for Classification of Cognitive Workload

Contact Info

Product

Resources

About