Short near infrared spectroscopy coupled with partial least square for the detection of adulteration in soybean oil
This paper demonstrates the application of short near infrared spectroscopy to measure the presence of lard adulteration in soybean oil. Partial least square (PLS) regression was used as supervised learning algorithm to quantify the percentage of adulteration in soybean oil. Spectral data obtained w...
| Published in: | AIP Conference Proceedings |
|---|---|
| Main Author: | |
| Format: | Conference paper |
| Language: | English |
| Published: |
American Institute of Physics Inc.
2018
|
| Online Access: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85047361166&doi=10.1063%2f1.5036854&partnerID=40&md5=1ec52a1cce173104352a5638c031f7b3 |
| Summary: | This paper demonstrates the application of short near infrared spectroscopy to measure the presence of lard adulteration in soybean oil. Partial least square (PLS) regression was used as supervised learning algorithm to quantify the percentage of adulteration in soybean oil. Spectral data obtained was divided into training and validation dataset using fixed ratio 7:3. R2 for calibration and prediction are 0.9999 while root mean square error of calibration and prediction are 0.3018 and 0.3246. The result obtained showed the robustness of the predictive model. © 2018 Author(s). |
|---|---|
| ISSN: | 0094243X |
| DOI: | 10.1063/1.5036854 |