Key result
Adaptive genetic feature selection for ECG-based cognitive stress classification outperforms PCA, achieving ~0.83 AUC.
Why the study?
Cognitive stress detection using ECG is challenged by the high dimensionality of multichannel analysis, feature redundancy, and classifier performance variability.
Does an adaptive genetic selection strategy improve ECG-based cognitive stress classification in healthy students compared to PCA or no dimensionality reduction?
Does an adaptive genetic selection strategy improve ECG-based cognitive stress classification in healthy students compared to PCA or no dimensionality reduction?
An adaptive genetic selection strategy effectively identifies compact and discriminative ECG feature subsets, improving cognitive stress classification performance.
Answers are grounded in this paper and cite their sources.
Adaptive ECG feature selection boosts cognitive stress classification accuracy; leaves open clinical validation in patients.
Cognitive stress detection based on electrocardiogram (ECG) is challenged by the high dimensionality of multichannel analysis, redundancy between heart rate variability (HRV) and morphological descriptors, and variability in classifier performance. We developed and evaluated a cognitive stress classification framework based on a standardized ECG acquisition protocol, the integration of HRV and morphological descriptors extracted from 12 leads, and an adaptive feature selection strategy using a binary genetic algorithm with explicit penalization of dimensionality. Seventy healthy students aged 18–25 years participated, and cognitive stress was induced using a task based on PMA-R Factor R. The initial dataset included 27 descriptors per lead, and the proposed dimensionality reduction method was compared with two reference schemes: no dimensionality reduction and conventional principal component analysis (PCA) with a 99% cumulative explained variance threshold. Performance was assessed over 30 data splits using five classifiers: logistic regression, linear support vector machine (SVM), radial basis function SVM (SVM-RBF), k-nearest neighbors (KNN), and decision tree. The best trade-off between parsimony and predictive performance was achieved with λ=0.05, yielding a compact subset of 11 features on average and a mean AUC of 0.830. In the final comparison, the adaptive strategy achieved the best overall performance with SVM-RBF (AUC =0.830±0.047; specificity =0.814±0.115), outperforming both the full feature set and PCA. These findings indicate that penalized genetic selection validated across multiple classifiers is an effective strategy for identifying compact, discriminative, and robust feature subsets for ECG-based cognitive stress classification.
No takes yet. Share an insight, caveat, or question.
Ortiz-Santos et al. (2026) studied Cognitive stress (n=70). Adaptive feature selection strategy using a binary genetic algorithm vs. No dimensionality reduction and conventional PCA was evaluated on Mean AUC for cognitive stress classification. An adaptive genetic feature selection strategy for ECG-based cognitive stress classification achieved a mean AUC of 0.830, outperforming both the full feature set and PCA.
Synapse has enriched 10 related papers. Consider them for comparative context: