Related Experiment Video
Updated: May 14, 2026
07:08
Estimate the Cognitive Load Using Electrocardiographic Measure: A Human-AI Collaborative Task
Published on: December 5, 2025
SS-RIME: A Scale-Stabilized Approach to EEG Cognitive Workload Classification
Kais Khaldi1, Afrah Alanazi2, Inam Alanazi2
1Department of Computer Science, College of Computer and Information Sciences, Jouf University, Sakaka 72388, Saudi Arabia.
Sensors (Basel, Switzerland)
|May 13, 2026
Summary
A new EEG analysis method, SS-RIME, accurately decodes cognitive workload by stabilizing frequency and weighting brain signals. This robust, explainable framework is ideal for real-time human-machine interaction and neuroergonomics.
Area of Science:
- Neuroscience
- Cognitive Science
- Biomedical Engineering
Background:
- Accurate cognitive workload assessment from EEG is crucial for neuroergonomics and human-machine interaction.
- Existing methods like EMD and CEEMDAN have limitations including instability and amplitude sensitivity.
- There is a need for a physiologically grounded and interpretable EEG feature extraction framework.
Purpose of the Study:
- To introduce Scale-Stabilized Relative Intrinsic Mode Energy (SS-RIME), a novel EEG feature extraction framework.
- To address limitations of existing methods by integrating frequency stabilization and spectral weighting.
- To provide a robust, explainable, and computationally efficient solution for cognitive workload decoding.
Main Methods:
- Developed SS-RIME integrating instantaneous frequency stabilization, delta/theta spectral weighting, and cross-IMF energy normalization.
- Applied SS-RIME to 64-channel EEG data recorded during N-back tasks.
- Compared SS-RIME performance against classical machine learning and deep learning models (EEGNet, DeepConvNet, ShallowConvNet).
Main Results:
- SS-RIME achieved high accuracies: 99.12% (0 vs. 2-back), 97.84% (0 vs. 3-back), 92.31% (2 vs. 3-back).
- Demonstrated strong cross-subject generalization.
- Identified theta-dominant IMFs in frontal midline regions as key discriminative components.
- Inference time was below 20 ms per epoch, indicating computational efficiency.
Conclusions:
- SS-RIME offers a theoretically motivated and physiologically informed approach for EEG-based cognitive workload decoding.
- The framework is robust, explainable, and suitable for real-time applications.
- SS-RIME outperforms existing EMD/CEEMDAN and deep learning methods, addressing key methodological gaps.
