BCI.js

Get Started

Perform online and offline processing in Node.js with our NPM package, or get started directly in your browser with the jsDelivr CDN.

Node.js

npm install bcijs

Browser

<script src="https://cdn.jsdelivr.net/npm/bcijs@1.8.0/dist/bci.min.js"></script>

Signal Processing

Isolate specific brainwaves with methods such as the fast fourier transform, common spatial pattern, FastICA, and more.

Find more examples in our GitHub repo and our docs.

const bci = require('bcijs');

// Generate 1 second of sample data
let sampleRate = 512;
let duration = 1;
let amplitudes = [8, 4];
// 10 Hz (alpha), 20 Hz (beta) 
let frequencies = [10, 20];

let signal = bci.generateSignal(
    amplitudes,
    frequencies,
    sampleRate,
    duration
);

// Compute relative band power in alpha and beta frequency bands
let powers = bci.bandpower(
    signal,
    sampleRate,
    ['alpha', 'beta'],
    {relative: true}
);

console.log(powers); // [ 0.8000001014839981, 0.19999985303285062 ]

const bci = require('bcijs');

(async () => {
    // Load EEG data from CSV 
    // CSV methods are Node.js specific
    let left = await bci.loadCSV('data/left.csv');
    let right = await bci.loadCSV('data/right.csv');

    // Learn a CSP filter for the EEG data
    // CSP methods run in Node.js and the browser
    let cspParams = bci.cspLearn(left, right);

    // Project the loaded data with the learned CSP parameters
    let cspLeft = bci.cspProject(cspParams, left);
    let cspRight = bci.cspProject(cspParams, right);
})();

Machine Learning

Epoch data, build features, and train a classifier to identify different thoughts and states of mind.