EEG Signals for Cognitive Workload Recognition Under Noisy Conditions

40 participants contributed approximately 20 minutes of EEG data each, recorded during puzzle-solving and arithmetic tasks. The dataset, created by Fariya Bintay Shafi and last updated in April 2026, is designed to simulate real-world cognitive workload scenarios. It deliberately includes physiological and environmental artifacts to provide a realistic testing ground for robust algorithm development.

Use Cases

• EEG signal denoising and artifact rejection based on captured noise sources like ECG, EMG, and EOG.
• Cognitive workload classification and regression modeling based on task conditions (resting vs. workload).
• Brain-computer interface validation under field conditions based on realistic environmental artifacts.
• Performance-based stratification of models based on participant subgroup classifications (Good vs. Bad counters).

Strengths

• Contains recordings from 40 participants, providing a basis for statistical analysis.
• Deliberately includes a broad range of realistic noise sources (ECG, EMG, EOG, respiratory artifacts, power line interference).
• Provides approximately 20 minutes of EEG data per participant, segmented into resting and working phases.
• Includes subjective performance ratings for 40 participants, enabling subgroup analysis.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Last updated 2026-04-24 18:47:02; freshness should be verified.

Provenance

Source

figshare

Collection Method

EEG signals were acquired using the KT88-3200 system with 16 channels at a sampling rate of 200 Hz from participants engaged in tasks.

Freshness

2026-04-24 18:47:02