🧬

eNI

Neural Interface

Biosignal processing library for neural and physiological signal acquisition. EEG, EMG, ECG processing for brain-computer interfaces and neurofeedback.

Intelligence LayerC/C++, PythonResearch

View on GitHub

Key Features

Multi-Modal Acquisition — EEG (256ch), EMG (16ch), ECG (12-lead)

Real-Time DSP — IIR/FIR, FFT, wavelets at 1 kHz

Feature Extraction — Time, frequency, time-frequency domains

BCI Paradigms — P300, SSVEP, motor imagery

eAI Integration — Seamless ML pipeline

Artifact Rejection — Auto eye-blink/muscle removal

Data Export — EDF+, BDF, CSV, HDF5

Architecture

Application (BCI Control, Neurofeedback, Prosthetics)
├── Classification (eAI: SVM, LDA, CNN, LSTM)
├── Feature Extraction (Time, Frequency, Connectivity)
├── Signal Processing (Filtering, FFT, ICA, CSP)
└── Signal Acquisition (ADS1299, ADS1298, OpenBCI)

Code Example

#include <eni/eni.h>
#include <eni/filter.h>

eni_config_t cfg = {
    .channels = 8,
    .sample_rate = 250,
    .adc_chip = ENI_ADC_ADS1299,
    .reference = ENI_REF_AVERAGE
};
eni_acq_t *acq = eni_acq_init(&cfg);

eni_filter_t *bp = eni_filter_bandpass(
    8.0, 30.0, cfg.sample_rate, 4);

float samples[8], filtered[8], features[16];
eni_acq_read(acq, samples);
eni_filter_apply(bp, samples, filtered, 8);
eni_feature_band_power(filtered, 8, 250, features);

API Highlights

Function	Description
`eni_acq_init()`	Initialize signal acquisition
`eni_filter_bandpass()`	Create bandpass IIR filter
`eni_fft()`	Compute FFT of signal segment
`eni_feature_band_power()`	Extract frequency band powers

← Back to All Products