Value-Added Carp Products: Multi-Class Evaluation of Crisp Grass Carp by Machine Learning-Based Analysis of Blood Indexes.

Yun Xia,Zhifei Li,Jun Xie,Kai Zhang,Wangbao Gong,Jingjing Tian,Bing Fu,Guangjun Wang,Gen Kaneko,Ermeng Yu

doi:10.3390/foods9111615

Yun Xia, Zhifei Li + Show 8 more

Open Access

https://doi.org/10.3390/foods9111615

Copy DOI

Abstract

Crisp grass carp products from China are becoming more prevalent in the worldwide fish market because muscle hardness is the primary desirable characteristic for consumer satisfaction of fish fillet products. Unfortunately, current instrumental methods to evaluate muscle hardness are expensive, time-consuming, and wasteful. This study sought to develop classification models for differentiating the muscle hardness of crisp grass carp on the basis of blood analysis. Out of the total 264 grass carp samples, 12 outliers from crisp grass carp group were removed based on muscle hardness (<9 N), and the remaining 252 samples were used for the analysis of seven blood indexes including hydrogen peroxide (H2O2), glucose 6-phosphate dehydrogenase (G6PD), malondialdehyde (MDA), glutathione (GSH/GSSH), red blood cells (RBC), platelet count (PLT), and lymphocytes (LY). Furthermore, six machine learning models were applied to predict the muscle hardness of grass carp based on the training (152) and testing (100) datasets obtained from the blood analysis: random forest (RF), naïve Bayes (NB), gradient boosting decision tree (GBDT), support vector machine (SVM), partial least squares regression (PLSR), and artificial neural network (ANN). The RF model exhibited the best prediction performance with a classification accuracy of 100%, specificity of 93.08%, and sensitivity of 100% for discriminating crisp grass carp muscle hardness, followed by the NB model (93.75% accuracy, 91.83% specificity, and 94% sensitivity), whereas the ANN model had the lowest prediction performance (85.42% accuracy, 81.05% specificity, and 85% sensitivity). These machine learning methods provided objective, cheap, fast, and reliable classification for in vivo crisp grass carp and also prove useful for muscle quality evaluation of other freshwater fish.

Highlights

Fish are a valuable source of high-quality animal protein throughout the world, with its annual consumption outpacing population growth between 1961 and 2016 [1]
As muscle hardness is the most obvious texture feature of crisp grass carp and increases with the faba bean feeding time [2], outliers were eliminated on the basis of muscle hardness
This study established six machine learning-based approaches for the classification of muscle hardness in different crisp grass carp samples based on seven blood indexes (H2 O2, glucose 6-phosphate dehydrogenase (G6PD), GSH/GSSH, MDA, red blood cells (RBC), platelet count (PLT), and LY)

Summary

Introduction

Fish are a valuable source of high-quality animal protein throughout the world, with its annual consumption outpacing population growth between 1961 and 2016 [1]. Grass carp (Ctenopharyngodon idella), the largest freshwater fish species, has a global production of about six million tons [1]. Crisp grass carp has been deemed a value-added product and is protected as a “China Geographical Indication. Hardness is the most prominent quality indicator of crisp grass carp and is directly related to the consumer’s acceptability [3,4]. Faba bean feeding for 90–120 days is used to improve textual characteristics of crisp grass carp. According to aquaculture experiences, approximately 5% of the treated fish still exhibit low muscle hardness similar to ordinary grass carp after 120 d of faba bean feeding, which financially affects producers, regulatory agencies, and consumers

Methods

Results

Conclusion