This is an open-source repo of the codes and hardware schematics used in the FitNibble paper: FitNibble: A Field Study to Evaluate the Utility and Usability of Automatic Diet Monitoring in Food Journaling using an Eyeglasses-based Wearable
- Firmware: which runs on a Rigado 350 nRf52 BLE module. This code is responsible for sensor data acquisition and feature extraction.
- HW Schematics: for BLE module boards and the proximity sensor (VCLN4040) breakout board.
- iOS App: used to communicate with the BLE module and the server running real-time ML classification.
- ML Pipeline: the pipeline used to build DNN eating detection models.
- Server script: running real-time activity classification and collecting app activity data.
- Sensor visualization: A Processing script for real-time sensing data visualization + firmware streaming sensors' data via the serial UART protocol.