Demo Scripts

Hands-Free Spotify Control

This demo demonstrates how to control Spotify hands-free using jaw clench and eye movement detections with our real-time classifiers.

Key Features:

  • Play, pause, and navigate playlist on Spotify through simple, intuitive jaw and eye gestures.

  • Works seamlessly with our real-time classifier system for a hands-free music experience.

Prerequisites and Setup

  1. Spotify Developer Setup:

    • Go to the Spotify Developer Dashboard and log in.

    • Create a new app. In the app settings, add a Redirect URI, e.g., http://localhost:8888/callback, for OAuth. Enable the “Web API” and “Web Playback SDK” permissions under scopes.

    • Retrieve your Client ID and Client Secret from the app settings for use in authentication.

  2. Environment Setup: Make sure you have the spotipy library installed. You can install it using:

    pip install spotipy

Steps

  1. Add Your Spotify Credentials: Replace the placeholders in the script with your Spotify credentials as shown below:

    sp = spotipy.Spotify(auth_manager=SpotifyOAuth(
    client_id="YOUR_CLIENT_ID",
    client_secret="YOUR_CLIENT_SECRET",
    redirect_uri="http://localhost:8888/callback",
    scope="user-modify-playback-state user-read-playback-state"
))

  2. Define Music Control Functions: Use the Spotify Web API to create functions for music control actions, such as play, pause, next track, and volume control.

  3. Create a Handler for Real-Time Predictions: Implement a handler function to connect classifier outputs (jaw clench and eye movements) to your music control functions. This function will interpret real-time predictions and map them to Spotify control actions.

  4. Run the Demo: Open Spotify, run the script to start recording and activate live predictions, and control your music hands-free!

Source Code

 1################ IMPORTS #############################################
 2import asyncio
 3from idun_guardian_sdk import GuardianClient
 4import spotipy
 5from spotipy.oauth2 import SpotifyOAuth
 6
 7#################### Configuration ####################
 8# Recording settings
 9RECORDING_TIMER = int(60 * 5) # 5 minutes
10LED_SLEEP = False
11
12# Device ID
13my_api_token = "INSERT_HERE"
14device_address = "INSERT_HERE"
15
16# Spotify configuration for music control
17sp = spotipy.Spotify(auth_manager=SpotifyOAuth(
18    client_id="INSERT_HERE",
19    client_secret="INSERT_HERE",
20    redirect_uri="http://localhost:8888/callback",
21    scope="user-modify-playback-state user-read-playback-state"
22    ))
23
24#################### Music control ####################
25def toggle_music():
26    """
27    Pause or start the music playback
28    """
29    playback = sp.current_playback()
30
31    if playback and playback['is_playing']:
32        sp.pause_playback()
33    else:
34        sp.start_playback()
35
36def next_track():
37    """
38    Play the next track
39    """
40    sp.next_track()
41
42def previous_track():
43    """
44    Play the previous track
45    """
46    sp.previous_track()
47
48#################### Handler functions ####################
49def pred_handler(event):
50    """
51    Handler for the live prediction data
52    """
53    # Jaw clench -> toggle playlist
54    if any('predictionResponse' in key for key in event.message):
55        jaw_clenches = event.message["predictionResponse"]
56        binary_jaw_clenches = [0 if jaw_clench == 'Nothing' else 1 for jaw_clench in jaw_clenches]
57
58        if any([pred > 0 for pred in binary_jaw_clenches]):
59            print('Jaw clench detected', flush=True)
60            toggle_music()
61
62    # HEOG -> switch track
63    if any("heogClassificationsResponse" in key for key in event.message):
64        heog = event.message["heogClassificationsResponse"]
65
66        if any([pred == 1 for pred in heog]):
67            print('Left HEOG detected', flush=True)
68            previous_track()
69
70        if any([pred == 2 for pred in heog]):
71            print('Right HEOG detected', flush=True)
72            next_track()
73
74
75#################### Main ####################
76if __name__ == "__main__":
77    
78    # Create client
79    client = GuardianClient(api_token=my_api_token, address=device_address)
80
81    # Subscribe to live predictions
82    client.subscribe_realtime_predictions(jaw_clench=True, fft=False, bin_heog=True, handler=pred_handler)
83
84    # Start the recording
85    asyncio.run(
86        client.start_recording(
87            recording_timer=RECORDING_TIMER, led_sleep=LED_SLEEP, calc_latency=False
88        )
89    )
90
91    # Prints and downloads
92    rec_id = client.get_recording_id()
93    print("RecordingId", rec_id)

Download the script (spotify_control.py)

Control Philips Hue Lights with our Eye Movement Classifier

This demo demonstrates how to turn on/off Philips Hue lights by looking left and right.

Key Features:

  • Turn on and off Philips Hue lights by looking left and right.

  • Works seamlessly with our real-time classifier system to control Philips Hue state using brain power.

Prerequisites and Setup

  1. Install the Philips Hue SDK phue: :

    pip install phue

  2. Install the IDUN Guardian SDK: :

    pip install idun_guardian_sdk

  3. Philips Hue Bridge Setup: :

    • Connect your Philips Hue Bridge to your network and find its IP address.

    • Press the button on the bridge to pair it with your network.

    • Retrieve the bridge IP address.

    • Configure the IP address and username of the bridge in the script.

    BRIDGE_IP = 'YOUR_BRIDGE_IP'
BRIDGE_USERNAME = 'YOUR_BRIDGE_USERNAME'

  4. Connect to the Philips Hue Bridge: :

    bridge.connect()

  5. Define Light Control Functions: :

    def handle_left_eye_movement():
    lamp = "Ceiling Lamp 1"
    bridge.set_light(lamp, 'on', True)
    time.sleep(2)
    bridge.set_light(lamp, 'on', False)


def handle_right_eye_movement():
    lamp = "Ceiling Lamp 2"
    bridge.set_light(lamp, 'on', True)
    time.sleep(2)
    bridge.set_light(lamp, 'on', False)

  6. Create a Handler for Real-Time Predictions: :

    def handle_eye_movement(data):
    prediction = data.message
    for p in prediction['heogClassificationsResponse']:
        if p == 1:
            handle_left_eye_movement()
        if p == 2:
            handle_right_eye_movement()

  7. Connect to the IDUN Guardian Device and start data streaming: :

    client = GuardianClient()
client.subscribe_realtime_predictions(bin_heog=True, handler=handle_eye_movement)
asyncio.run(client.start_recording(recording_timer=RECORDING_TIMER))

Source Code

 1import asyncio
 2import time
 3
 4from phue import Bridge
 5
 6from idun_guardian_sdk import GuardianClient
 7
 8"""
 9# Install phue
10pip install phue
11
12# Install the idun guardian sdk
13pip install idun-guardian-sdk
14
15# Replace 'BRIDGE_IP_ADDRESS' with the IP of your Hue Bridge
16bridge = Bridge('BRIDGE_IP_ADDRESS')
17
18# First-time connection: Press the button on the Bridge and run this code
19try:
20    bridge.connect()
21    print(f"Connected! Save this username for future use: {bridge.username}")
22except Exception as e:
23    print(f"Error connecting to the Bridge: {e}")
24    
25# Subsequent connections    
26# Replace with the IP address of your Bridge and your previously saved username
27bridge = Bridge('BRIDGE_IP_ADDRESS', username='YOUR_SAVED_USERNAME')
28
29# Now you can control the lights without pressing the button again
30bridge.set_light(1, 'on', True)
31"""
32
33BRIDGE_IP = ''
34BRIDGE_USERNAME = ''
35
36bridge = Bridge(BRIDGE_IP, username=BRIDGE_USERNAME)
37bridge.connect()
38
39RECORDING_TIMER: int = 60 * 15  # set a recording length in seconds
40
41
42def handle_left_eye_movement():
43    lamp = "Ceiling Lamp 1"
44    bridge.set_light(lamp, 'on', True)
45    time.sleep(2)
46    bridge.set_light(lamp, 'on', False)
47
48
49def handle_right_eye_movement():
50    lamp = "Ceiling Lamp 2"
51    bridge.set_light(lamp, 'on', True)
52    time.sleep(2)
53    bridge.set_light(lamp, 'on', False)
54
55
56def handle_eye_movement(data):
57    prediction = data.message
58    for p in prediction['heogClassificationsResponse']:
59        # debug: 1 = left, 2 = right, 0 = none
60        # print(p)
61
62        if p == 1:
63            handle_left_eye_movement()
64
65        if p == 2:
66            handle_right_eye_movement()
67
68
69if __name__ == '__main__':
70    client = GuardianClient()
71    client.subscribe_realtime_predictions(bin_heog=True, handler=handle_eye_movement)
72    asyncio.run(client.start_recording(recording_timer=RECORDING_TIMER))
73    rec_id = client.get_recording_id()

Download the script (philips_hue_eye_movement_demo.py)