Abstract
This paper examines the design of an optical fiber sensor that monitors ground beef online, as it cooks, in order to determine the quality of the meat; in particular, if premature browning has occurred. The experimental work involved cooking fresh meat and meat that has been stored in a freezer for, one week, one month and three months, and recording the reflected spectra and temperature during the cooking process in order to develop a classifier, based on pattern recognition techniques that can determine premature browning and the degree to which the meat has been cooked. A comparison of this sensor is made with traditional research methods of detecting premature browning, to demonstrate that it would be more commercially viable as an online solution.
| Original language | English |
|---|---|
| Pages (from-to) | 1685-1691 |
| Number of pages | 7 |
| Journal | IEEE Sensors Journal |
| Volume | 7 |
| Issue number | 12 |
| DOIs | |
| Publication status | Published - Dec 2007 |
Keywords
- Artificial neural network
- Backpropagation learning
- Food processing industry
- Multilayer perceptrons
- Online color measurement
- Optical fiber sensors
- Premature browning detection
- Principal component analysis
- Self organizing maps
- Spectral classification