Abstract
Abstract Chemometric modeling concerns both accuracy and computational expense for the prediction of quality-indicating attributes of food materials. Modeling approaches were explored with the hyperspectral images with pH and Brix values of greengages. A two-phase architecture was applied for modeling. Firstly, waveband selection was performed using two approaches, i.e., succession projection algorithm (SPA) and its combination with genetic algorithm (SPA+GA). Secondly, multispectral models based on the two feature sets of wavebands were built via a total of six different modeling methods, i.e., partial least squares regression (PLSR) and extreme learning machine (ELM) in their respective stand-alone versions, their applications combined with genetic algorithm (GA), and their ensemble enhancements with modified Adaboost.RT (MAdaboost.RT). Analysis of accuracy and computational expense showed that supervised feature selection with SPA+GA was superior to unsupervised SPA for better modeling accuracy. MAdaboost.RT-ELM showed high accuracy at low computational expense. ELM models were the better base models than the PLSR ones, for being more randomized and diverse. It indicates that MAdaboost.RT-ELM on SPA is the best choice for a quick test on a newly available dataset, while switching the dimensionality reduction from SPA to SPA+GA may yield more accurate models with added, but well worthy, computational expense.
Highlights
Greengage, which currently grows mainly in the coastal areas of Southeast China, is nutritional and categorized as one of the strong alkaline forming foods
The additional time required for the second stage of the genetic algorithm (GA) selection of wavelengths always yielded an improvement in accuracy of the Brix and pH values in every type of multispectral modelling. This is because, after the initial stage of redundancy removal in succession projection algorithm (SPA), the evolutional process guides the selection of wavelengths toward the target attribute and yields tailored final sets of feature wavelengths with a moderate time overhead; (2) MAdaboost.RT-extreme learning machine (ELM) is the preferred type of multispectral modelling
In this study, exemplified by two target physiochemical attributes—Brix and pH values—multispectral modeling procedures were repeatedly performed on sets of feature wavelengths selected with supervised or unsupervised algorithms, and the following conclusions were drawn: (1) Supervised feature wavelength selection is preferred over unsupervised selection for better accuracy
Summary
Greengage, which currently grows mainly in the coastal areas of Southeast China, is nutritional and categorized as one of the strong alkaline forming foods. It is useful in neutralizing the acidity of blood and keeping the body fluids alkalescent. Greengage fruit has a long history of being used in traditional Chinese foods as pulp served dried or salted, or as an ingredient in fruit wine, as well as for traditional Chinese medicine. These simple-processed products have low added values. There is an urgency to upgrade the greengage processing industry with new products of more added values
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
