Translator Disclaimer
Paper
11 March 2020 Brix percentage estimation using artificial intelligence approaches
Author Affiliations +
Proceedings Volume 11331, Fourth International Conference on Photonics Solutions (ICPS2019); 113310I (2020) https://doi.org/10.1117/12.2552892
Event: Fourth International Conference on Photonic Solutions (ICPS 2019), 2019, Chiang Mai, Thailand
Abstract
In this paper, a measurement system using absorption spectroscopy was designed and realized. Using alternative measurement method, the system could perform with minimum calibration requirement. Features of sucrose solutions with Brix percentage from 12 oBrix to 16 oBrix were measured and extracted. Moreover, three artificial intelligent methods, namely artificial neural networks, artificial neural networks with principal component analysis, and genetic algorithm, were applied to predict unknown concentrations. The key difference between methods was the assumption on residual error’s statistical characteristics. Experimental results showed that the correlation and collinearity in structure of measured data were essential for higher prediction accuracy in artificial intelligent methods. In our experiments, genetic algorithm provided the most accurate predictions.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Quang Thai Pham and Tien Dat Pham "Brix percentage estimation using artificial intelligence approaches", Proc. SPIE 11331, Fourth International Conference on Photonics Solutions (ICPS2019), 113310I (11 March 2020); https://doi.org/10.1117/12.2552892
PROCEEDINGS
9 PAGES


SHARE
Advertisement
Advertisement
Back to Top