Polarity-Considered EEG Microstates for Oddball Stimulus Classification

40 healthy participants' EEG data from an oddball paradigm experiment, analyzed across stimulus modality, condition, and response type. The dataset was created by Tatsumi Tsubaki and last updated on March 18, 2026. It includes polarity-considered microstate labeling sequences used to train machine learning models for stimulus classification.

Use Cases

• Classifying oddball stimuli based on polarity-considered EEG microstate sequences.
• Comparing classification performance between auditory and visual stimulus modalities.
• Evaluating the benefit of cross-modal conditions in key-response tasks using microstate features.
• Training tree-based ensemble models (e.g., Random Forest, XGBoost) for BCI signal classification.

Strengths

• Data from 40 participants provides a basis for analysis.
• Polarity consideration improved classification by approximately 20% in the described study.
• Models achieved an area under the ROC curve above 0.8 and a mean F1 score of 0.83 for a specific task.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• The primary data file is a 3.4 MB DOCX, which may not be a standard format for structured data.

Provenance

Source

figshare

Collection Method

EEG data from an experimental oddball paradigm with 40 healthy participants, processed with microstate analysis.

Freshness

Last updated 2026-03-18 06:42:03