A Machine Learning Approach for Lamb Meat Quality Assessment Using FTIR Spectra

Abstract

The food industry requires automatic methods to establish authenticity of food products. In this work, we address the problem of the certification of suckling lamb meat with respect to the rearing system. We evaluate the performance of neural network classifiers as well as different dimensionality reduction techniques, with the aim of categorizing lamb fat by means of spectroscopy and analyzing the features with more discrimination power. Assessing the stability of feature ranking algorithms also becomes particularly important. We assess six feature selection techniques (χ 2 , Information Gain, Gain Ratio, Relief and two embedded techniques based on the decision rule 1R and SVM (Support Vector Machine). Additionally, we compare them with common approaches in the chemometrics field like the Partial Least Square (PLS) model and Principal Component Analysis (PCA) regression. Experimental results with a fat sample dataset collected from carcasses of suckling lambs show that performing feature selection contributes to classification performance increasing accuracy from 89.70% with the full feature set to 91.80% and 93.89% with the SVM approach and PCA, respectively. Moreover, the neural classifiers yield a significant increase in the accuracy with respect to the PLS model (85.60% accuracy). It is noteworthy that unlike PCA or PLS, the feature selection techniques that select relevant wavelengths allow the user to identify the regions in the spectrum with the most discriminant power, which makes the understanding of this process easier for veterinary experts. The robustness of the feature selection methods is assessed via a visual approach. INDEX TERMS Meat quality assessment, feature selection, machine learning, neural networks, feature selection robustness.

Usage of Then Neural Network to Predict Meat Tenderness Approach

“…The development of fast and efficient tools to be implemented in the industry of food attracted great interest in the last decade ( [11]). Modern techniques, including electronic noses, computer vision, spectroscopy and spectral imaging, and so on, have been widely used to detect meat attributes.…”

Applying Machine Learning Algorithms for the Classification of Mink Infected with Aleutian Disease Using Different Data Sources

“…They are also widely used methods in agriculture [ 17 , 18 , 19 ], such as for high throughput phenotyping [ 20 ] or predicting plant diseases [ 21 ]. In animals, the ML algorithms have been used for monitoring the health status [ 22 , 23 ], product quality [ 24 , 25 ], and prediction of diseases [ 26 , 27 , 28 , 29 , 30 ]. Selection of the ML algorithms for studies on farm animals depends on the traits and data, and their performance also varies among the studies [ 17 , 28 , 31 ].…”

Application of Artificial Intelligence in Food Industry—a Guideline

“…On the other hand, GA has been utilized for finding the optimum parameters in food whereas NN has been occupied to predict the final fouling rate in food processing [ 84 ]. ML has shown to be advantageous in predicting the food insecurity in the UK [ 85 ]. Apart from that, ML has also proven to have predicted the trend of sales in the food industry [ 86 ] In addition to that, ML was also able to predict the food waste generated and give an insight to the production system [ 87 ].…”