To research the relationship between Childhood obesity and infant feeding patterns, the Electrical Engineering Department at California Polytechnic State University has designed a SmartBottle device attaching to the bottom of a baby bottle to monitor the infant feeding process. This project mainly focuses on the software and firmware design, as well as the neural network design of the SmartBottle device. The SmartBottle device is designed to identify infant feeding activities and to record related data for overweight and obesity research on children. This device includes a 6-dimensional inertial sensor that contains a 3-axis digital accelerometer and a 3-axis digital gyroscope. The measurement of this inertial sensor is passed into a neural network to identify drinking events and to measure the bottle-feeding angle. This device also includes a load sensor, a real-time clock, and an SD card to measure feeding amounts, record feeding time, and store real-time data.
To obtain training data for the NN, device firmware was written to record feeding event data with the aid of a lab assistant familiar with typical feeding actions. Once a large set of data was collected, it was separated into two groups for neural network training and testing. The resulting neural network was repeatedly evaluated by lab assistants and rebuilt until it fully satisfied all the requirements. Finally, according to users’ preferences, the last step was to optimize the software and have it ready to be used for laboratory-based research.
| Identifer | oai:union.ndltd.org:CALPOLY/oai:digitalcommons.calpoly.edu:theses-3960 |
| Date | 01 May 2021 |
| Creators | Guan, Jiajun |
| Publisher | DigitalCommons@CalPoly |
| Source Sets | California Polytechnic State University |
| Detected Language | English |
| Type | text |
| Format | application/pdf |
| Source | Master's Theses |
Page generated in 0.0021 seconds