Fourier-transform infrared spectroscopy and machine learning to predict fatty acid content of nine commercial insects
- PDF / 898,805 Bytes
- 8 Pages / 595.276 x 790.866 pts Page_size
- 58 Downloads / 239 Views
ORIGINAL PAPER
Fourier‑transform infrared spectroscopy and machine learning to predict fatty acid content of nine commercial insects Zhongdong Liu1,9 · Ahmed Rady2 · Nuwan K. Wijewardane3 · Qianqian Shan4 · Huili Chen5 · Shengru Yang6 · Jinlong Li7 · Mengxing Li3,8,10 Received: 26 April 2020 / Accepted: 7 October 2020 © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Insects used as food and feed has attracted considerable attention for their nutritional profiles in recent years. Fatty acid profile, such as unsaturated fatty acid content, ratio of unsaturated to saturated fatty acids, determines the quality of insect products. Multiple previous studies have used spectroscopy technologies and machine learning algorithms to predict fatty acid content in various foods and feeds. However, these approaches were not applied for predicting fatty acid content in insects before. In this study, 50 insect samples containing 9 commercial insect species were collected. Machine learning methods were applied to build the calibration models to predict fatty acid content from Fourier-transform infrared spectroscopy spectra. For all fatty acids, partial least square regression, regression trees and neural network based methods were among the best machine learning methods. For the best performing model, a coefficient of determination of 0.98, a root mean square error of prediction of 3.19%, and a ratio of performance of 3.91 were achieved using regression tree to predict linoleic acid. The high model performance indicates the potential of applying FTIR and such machine learning methods for fast and nondestructive prediction of fatty acid of insect oil products. Keywords Mealworm · Fatty acid · FTIR · Machine learning · Prediction
Introduction Insects have been studied intensively for their use in food and feed industry, due to their sustainable rearing process and nutritional facts such as high protein content and high unsaturated fatty acid content [1–3]. Fatty acid profiles, such as the percentage of unsaturated fatty acid, ratios of unsaturated fatty acid to saturated fatty acid and n-6 to n-3, determine the quality of insect and insect derived oil
products. Multiple studies have focused on upstream rearing process, such as studying the effect of diet formulation on fatty acid composition of different insect species [2, 4–6]. For commercial insect product quality assessment and labelling, determination of fatty acid composition is necessary. The conventional fatty acid measurement uses methanolysis and gas chromatographic analysis, which requires the use of organic solvent and is time-consuming. Therefore, a
* Zhongdong Liu [email protected]
5
Department of Pharmaceutics, University of Florida, Orlando 32827, USA
* Mengxing Li [email protected]
6
College of Food Engineering, Henan University of Animal Husbandry and Economy, Zhengzhou 450046, China
7
Hunan Fisheries Science Research Institute, Changsha 410153, China
8
Department of Statistics, University of Ne
Data Loading...
