Application of hyperspectral imaging system to discriminate different diets of live Rainbow trout (Oncorhynchus mykiss)
- Published
- Accepted
- Subject Areas
- Aquaculture, Fisheries and Fish Science, Nutrition
- Keywords
- hyperspectral imaging, Rainbow trout, Plant-based diet, Commercial-based diet, fish skin, machine vision system, machine learning
- Copyright
- © 2018 Saberioon et al.
- Licence
- This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ Preprints) and either DOI or URL of the article must be cited.
- Cite this article
- 2018. Application of hyperspectral imaging system to discriminate different diets of live Rainbow trout (Oncorhynchus mykiss) PeerJ Preprints 6:e26562v1 https://doi.org/10.7287/peerj.preprints.26562v1
Abstract
The main aim of this study was to evaluate the feasibility of hyperspectral imagery for determining the influence of different diets on fish skin. Rainbow trout (Oncorhynchus mykiss) were fed either a commercial based diet (N= 80) or a 100 % plant-based diet (N = 80). Hyperspectral images were made using a push-broom hyperspectral imaging system in the spectral region of 394-1009 nm. All images were calibrated using dark and white reference and the average spectral data from the region of interest were extracted. Six spectral pre-treatment methods were used, including Savitzky-Golay (SG), First Derivative(FD), Second Derivative (SD), Standard Normal Variate (SNV) and Multiplicative Scatter Correction (MSC) then a support vector machine (SVM) with linear kernel was applied to establish the classification models. Additionally, the Genetic algorithm (GA) was used to select optimal wavelengths to reduce the high dimensionality from hyperspectral images in order to decrease the computational costs and simplify the classification models. Overall classification models established from full wavelengths and selected wavelengths showed the good performance (Correct Classification Rate (CCR) = 0.871, Kappa = 0.741) when coupled with SG. The overall results indicate that the integration of Vis/NIR hyperspectral imaging system and machine learning algorithms has promise for discriminating different diets based on the live fish skin.
Author Comment
This is a preprint submission to PeerJ Preprints. Also current version of the manuscript has submitted and under review in Scientific reports.