Gather and label data
Record gas fingerprints and environmental context, then pair them with user votes about food and cooking methods.
Model development
Teaching Scentinel what is happening in the kitchen.
Scentinel is currently collecting sensor histories and human labels. There is not yet enough verified data to publish dependable live predictions, so the dashboard reports these outputs as unavailable rather than guessing.
Development path
From observations to useful predictions
Improve models and run inference
Train and validate improved models while publishing kitchen activity, food predictions, and confidence from the best available model.
Why votes matter
Sensor readings need human context.
A gas fingerprint can show that the air changed, but it cannot initially explain why. Votes connect a sensor window to known kitchen activity, food, and cooking methods, creating labels that the model can learn from.
Contribute a labelPlanned outputs
What will appear on the dashboard
- Kitchen activity
- Estimated likelihood that cooking activity is occurring.
- Food prediction
- The food class most consistent with the recent gas fingerprint.
- Confidence
- How strongly the model supports its displayed prediction.