schrodingho/FM_ZSL_IoT

Source Code for ECAI 2024 Paper "Leveraging Foundation Models for Zero-Shot IoT Sensing"

32
/ 100
Emerging

This project helps researchers and engineers analyze data from Internet of Things (IoT) sensors, like activity trackers or smart home devices, even for activities or events they haven't specifically trained their systems on. You feed it raw sensor data (e.g., from mmWave, IMU, or Wi-Fi) along with descriptions of what those signals represent, and it classifies new, previously 'unseen' activities. This is useful for anyone working with IoT sensor data who needs to adapt quickly to new scenarios without extensive re-training.

Use this if you need to classify or detect events from IoT sensor data for categories or situations that were not included in your original training data.

Not ideal if your IoT sensing tasks are entirely within well-defined, pre-trained categories and do not require recognizing novel events.

IoT-sensing activity-recognition predictive-maintenance smart-environments human-computer-interaction
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 0 / 25

How are scores calculated?

Stars

15

Forks

Language

Python

License

MIT

Last pushed

Feb 27, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/schrodingho/FM_ZSL_IoT"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.