R Package: BCIFeatR

Published:

Package: BCIFeatR (Brain-Computer Interface Feature Engineering in R)
Title: Feature Engineering Toolkit for EEG-based BCI
Version: 0.1.0
Author: Yiming Shen
License: MIT + file LICENSE

Overview

BCIFeatR provides a unified, reproducible workflow for extracting and organizing discriminative EEG features for BCI decoding tasks. The package is designed for cross-session and cross-subject studies where stable, interpretable feature representations are essential.

Key Features

  1. Feature Extraction: Time-domain, frequency-domain, and covariance-derived descriptors tailored to motor imagery EEG.
  2. Pipeline Consistency: Standardized preprocessing and feature assembly for train/test reproducibility.
  3. Model-Ready Output: Clean feature matrices that integrate directly with classical ML and domain-adaptation workflows.
  4. Experiment Utility: Utilities for benchmarking and comparing feature sets across sessions.

Installation & Usage

You can install the development version from GitHub:

# install.packages("devtools")
devtools::install_github("Yiming-S/BCIFeatR")

Quick Start

library(BCIFeatR)

# Example workflow (pseudo-minimal)
# features <- extract_bci_features(eeg_data, fs = 250)
# model_df <- as_feature_matrix(features)

View on GitHub