The use of Machine Learning for non-destructive classification of adulterated lemon juice has been successfully tested by researchers. The study utilized an electronic nose equipped with an array of metal oxide semiconductor sensors, which are commonly used in the beverage industry for quality control. The researchers prepared their own samples of lemon juice, both pure and adulterated with lemon pulp, water, citric acid, sugar, and wheat straw. The team then utilized chemometric methods such as principal component analysis (PCA), linear and quadratic analysis (LDA), support vector machines (SVMs), and artificial neural networks (ANNs) to analyze the volatile organic compound (VOC) profile of the samples.
In order to test the accuracy of the models, the authors separated their data into three groups: 60% for training, 20% for validation, and 20% for testing. The models were able to classify the adulterated lemon juice samples with an accuracy rate of 95% or higher. The Nu-SVM linear function method had the highest accuracy rate of all models. The researchers concluded that combining metal oxide semiconductor sensors with chemometric methods can be a powerful tool for rapid and non-destructive classification of pure lemon juice and its counterfeit products.
The study findings have significant implications for the food industry, as detecting the adulteration of food products, especially beverages, is an important step in ensuring food safety and quality. The use of machine learning methods can help to detect fraudulent practices, which can lead to increased trust in the authenticity of food products. Additionally, non-destructive testing methods can save time and resources by allowing testing to occur while preserving the quality of the product being tested.
Overall, the study presents a promising avenue for lemon juice authentication that can be applied to other food products as well. With the increasing availability of machine learning techniques and electronic sensing devices, it is likely that the development of these tools for the food industry will continue to grow. The success of this study highlights the potential for increased accuracy and efficiency in detecting food adulteration through the use of technology and advanced analytical methods.
