Neural Signatures Within and Between Chess Puzzle Solving and Standard Cognitive Tasks for Brain-Computer Interfaces: A Low-Cost Electroencephalography Study

2025/05/12 by Matthew Russell, Samuel Youkeles, Russell, Matthew +7
Neuroscience · #EEG and Brain-Computer Interfaces #FOS: Computer and information sciences #Human-Computer Interaction (cs.HC)

paper · pdf · doi:10.48550/arxiv.2505.07592

openalex publication_date 2025/05/12 · openalex created_date 2025/10/14 · openalex updated_date 2026/07/28

Abstract

Consumer-grade electroencephalography (EEG) devices show promise for Brain-Computer Interface (BCI) applications, but their efficacy in detecting subtle cognitive states remains understudied. We developed a comprehensive study paradigm which incorporates a combination of established cognitive tasks (N-Back, Stroop, and Mental Rotation) and adds a novel ecological Chess puzzles task. We tested our paradigm with the MUSE 2, a low-cost consumer-grade EEG device. Using linear mixed-effects modeling we demonstrate successful distinctions of within-task workload levels and cross-task cognitive states based on the spectral power data derived from the MUSE 2 device. With machine learning we further show reliable predictive power to differentiate between workload levels in the N-Back task, and also achieve effective cross-task classification. These findings demonstrate that consumer-grade EEG devices like the MUSE 2 can be used to effectively differentiate between various levels of cognitive workload as well as among more nuanced task-based cognitive states, and that these tools can be leveraged for real-time adaptive BCI applications in practical settings.

Citations

• Stress Monitoring Using Low-Cost Electroencephalogram Devices: A Systematic Literature Review
• performance: An R Package for Assessment, Comparison and Testing of Statistical Models
• effectsize: Estimation of Effect Size Indices and Standardized Parameters
• Autoreject: Automated artifact rejection for MEG and EEG data
• Imbalanced-learn: A Python Toolbox to Tackle the Curse of Imbalanced\n Datasets in Machine Learning
• To transform or not to transform: using generalized linear mixed models to analyse reaction time data
• The concurrent validity of the N -back task as a working memory measure
• Working memory span tasks: A methodological review and user’s guide
• Mental and physical effort affect vigilance differently
• BCI2000: A General-Purpose Brain-Computer Interface (BCI) System
• Age differences in short-term retention of rapidly changing information.
• EEG alpha oscillations: The inhibition–timing hypothesis

Related

• Brain Computer Interface (BCI) based on Electroencephalographic (EEG) patterns due to new cognitive tasks
• Neuro-Informed Joint Learning Enhances Cognitive Workload Decoding in Portable BCIs
• EEG-based Brain-Computer Interfaces (BCIs): A Survey of Recent Studies\n on Signal Sensing Technologies and Computational Intelligence Approaches and\n their Applications
• Design and Implementation of EEG-Mechatronic System Interface for Computational Intelligence
• Neural Networks Meet Neural Activity: Utilizing EEG for Mental Workload Estimation