emoPAD Universe

Cross-Platform Support

emoPAD Universe supports the following operating systems:

Auto-Start

After installing this skill, the following operations will be performed automatically:

1. 1. Check and install required Python dependencies
2. Start emoPAD service (listening on http://127.0.0.1:8766)
3. Start emoNebula auto-report (popup window displaying emotion nebula chart every 5 minutes)

No manual start needed, ready to use after installation.

Tools

emopad_status

Get current emotion PAD status and sensor connection status

Description: Returns values for three dimensions: Pleasure, Arousal, Dominance, and connection status of EEG, PPG, GSR sensors

Parameters: None

Returns: Formatted emotion status text, including sensor connection status

emopad_snapshot

Generate current emotion nebula chart

Description: Generate 3D PAD cube visualization screenshot

Parameters: None

Returns:

• - Status message
• PNG image data

emopadstartnebula

Start emoNebula auto-report

Description: Automatically generate and display emotion nebula chart in popup window every 5 minutes. Requires at least 2 sensors connected to display image, otherwise shows data missing reminder.

Parameters: None

Returns: Status message

emopadstopnebula

Stop emoNebula auto-report

Description: Stop automatically displaying emotion nebula chart

Parameters: None

Returns: Status message

Configuration

CODEBLOCK0

Dependencies

• - mne
• heartpy
• neurokit2
• bleak
• pyvista
• pyserial
• scipy
• numpy
• PyWavelets
• fastapi
• uvicorn
• pillow
• requests
• pyyaml

Hardware Support

Currently Supported Devices

Future Planned Support

• - Muse series EEG devices
• Emotiv EEG devices
• Oura Ring smart ring
• Whoop smart wristband
• Other mainstream EEG devices and wearable devices

About Emotion PAD Calculation

Important Note: Currently, emotion PAD calculation is based on heuristic methods, mapping relationships summarized from extensive literature.

Characteristics of this method:

• - ✅ Based on statistical patterns from scientific literature
• ✅ Suitable for emotion recognition in general population
• ⚠️ Temporarily cannot reflect individual differences

Future Improvements: Will introduce personalized calibration training modules in new versions, through user-specific data training, to achieve true personalized emotion recognition.