Skip to main content

SiFi Bridge Python

SiFi Bridge Python is a Python API for controlling SiFi Labs biosensor devices programmatically. Build custom applications, automate experiments, and integrate physiological data into your research workflow.

Features​

  • Object-Oriented API - Clean, Pythonic interface for device control
  • Real-Time Data Streaming - Access sensor data as NumPy-compatible arrays
  • Flexible Configuration - Control all sensor parameters programmatically
  • Multiple Output Formats - Stream to CSV, LSL, TCP, or custom handlers
  • Multi-Device Support - Manage multiple devices simultaneously
  • Easy Integration - Works seamlessly with NumPy, Pandas, scikit-learn, and ML frameworks

Installation​

Install via pip:

pip install sifi-bridge-py

Or from source:

git clone https://github.com/SiFiLabs/sifi-bridge-py.git
cd sifi-bridge-py
pip install -e .

See the Installation Guide for detailed instructions.

Quick Start​

Connect to a device and stream ECG data in just a few lines:

import sifi_bridge_py as sbp

# Create bridge and connect
sb = sbp.SifiBridge()
sb.connect(sbp.DeviceType.BIOPOINT_V1_3)

# Configure ECG sensor
sb.configure_ecg(state=True, fs=500)
sb.start()

# Read 10 packets
for i in range(10):
    packet = sb.get_ecg()
    print(f"ECG data: {packet['data']['ecg'][:5]}...")

# Cleanup
sb.stop()
sb.disconnect()

See the Quick Start Guide for more examples.

Use Cases​

Data Collection & Export​

# Record data to CSV for 60 seconds
sb = sbp.SifiBridge(publishers="csv://./data/")
sb.connect()
sb.configure_sensors(ecg=True, emg=True, imu=True)
sb.start()

time.sleep(60)

sb.stop()
sb.disconnect()

Real-Time Analysis​

# Process ECG in real-time
import numpy as np

sb = sbp.SifiBridge()
sb.connect()
sb.configure_ecg(state=True, fs=500)
sb.start()

while True:
    packet = sb.get_ecg()
    ecg_data = np.array(packet['data']['ecg'])

    # Your analysis here
    heart_rate = calculate_heart_rate(ecg_data)
    print(f"HR: {heart_rate} bpm")

Lab Streaming Layer (LSL)​

# Stream to LSL for integration with other tools
sb = sbp.SifiBridge(publishers="lsl://")
sb.connect()
sb.configure_sensors(ecg=True, emg=True)
sb.start()

# Data automatically streams to LSL
# Access from EEGLAB, OpenViBE, etc.

Machine Learning Integration​

# Collect training data for ML
import pandas as pd

data_buffer = []
sb = sbp.SifiBridge()
sb.connect()
sb.configure_emg(state=True, fs=2000)
sb.start()

# Collect 1000 packets
for _ in range(1000):
    packet = sb.get_emg()
    data_buffer.append(packet['data']['emg'])

# Convert to DataFrame for ML
df = pd.DataFrame(data_buffer)
# Train your model...

Key Concepts​

Device Connection​

Connect to devices by type or specific address:

# Auto-connect to any BioPoint
sb.connect(sbp.DeviceType.BIOPOINT_V1_3)

# Connect by MAC address
sb.connect("AA:BB:CC:DD:EE:FF")

# List available devices first
devices = sb.list_devices(sbp.ListSources.BLE)
sb.connect(devices[0])

Sensor Configuration​

Configure each sensor independently:

# ECG at 500 Hz
sb.configure_ecg(state=True, fs=500)

# EMG at 2000 Hz
sb.configure_emg(state=True, fs=2000)

# PPG with custom LED intensity
sb.configure_ppg(state=True, fs=100, led_intensity=200)

# IMU at 100 Hz
sb.configure_imu(state=True, fs=100)

Data Acquisition​

Multiple ways to get data:

# Get any packet
packet = sb.get_data()

# Get specific sensor
ecg = sb.get_ecg()
emg = sb.get_emg()
imu = sb.get_imu()
ppg = sb.get_ppg()

# With timeout
packet = sb.get_data(timeout=1.0)

Device Commands​

Control LEDs, motors, and feedback:

# LED control
sb.send_command(sbp.DeviceCommand.OPEN_LED_1)
sb.send_command(sbp.DeviceCommand.CLOSE_LED_1)

# Vibration motor
sb.send_command(sbp.DeviceCommand.START_MOTOR, intensity=5)
sb.send_command(sbp.DeviceCommand.STOP_MOTOR)

# Event markers
sb.send_command(sbp.DeviceCommand.EVENT_MARKER, marker=42)

Comparison with CLI​

FeaturePython APICLI
Use CaseCustom applications, automationInteractive exploration, quick data collection
Coding RequiredYesNo
IntegrationSeamless with NumPy, Pandas, MLExport to CSV, LSL, TCP
FlexibilityFull programmatic controlCommand-based
Best ForDevelopers, researchers with codingResearchers without coding, quick tests

Both interfaces use the same underlying library and offer the same capabilities.

Support​