Efficiency of Identification of Blackcurrant Powders Using Classifier Ensembles

Abstract

In the modern times of technological development, it is important to select adequate methods to support various food and industrial problems, including innovative techniques with the help of artificial intelligence (AI). Effective analysis and the speed of algorithm implementation are key points in assessing the quality of food products. Non-invasive solutions are being sought to achieve high accuracy in the classification and evaluation of various food products. This paper presents various machine learning algorithm architectures to evaluate the efficiency of identifying blackcurrant powders (i.e., blackcurrant concentrate with a density of 67 °Brix and a color coefficient of 2.352 (E520/E420) in combination with the selected carrier) based on information encoded in microscopic images acquired via scanning electron microscopy (SEM). Recognition of blackcurrant powders was performed using texture feature extraction from images aided by the gray-level co-occurrence matrix (GLCM). It was evaluated for quality using individual single classifiers and a metaclassifier based on metrics such as accuracy, precision, recall, and F1-score. The research showed that the metaclassifier, as well as a single random forest (RF) classifier most effectively identified blackcurrant powders based on image texture features. This indicates that ensembles of classifiers in machine learning is an alternative approach to demonstrate better performance than the existing traditional solutions with single neural models. In the future, such solutions could be an important tool to support the assessment of the quality of food products in real time. Moreover, ensembles of classifiers can be used for faster analysis to determine the selection of an adequate machine learning algorithm for a given problem.

Explainable AI: Machine Learning Interpretation in Blackcurrant Powders

“…Each type of powder specifies a blackcurrant fruit solution with 30% carrier (Figure 1a-e): milk whey protein (w), maltodextrin (md), inulin (in), gum arabic (ga), microcrystalline cellulose (c), and fiber (f). More details on how the currant powders were obtained are described in Przybył et al 2023 [38] and 2024 [41]. The digital images were taken using Scanning Electron Microscopy (SEM), which was made available in the research data repository.…”

“…This step required transforming the secondary images to acquire a numerical dataset. In a previous study [41], microscopic images of blackcurrant powders were used in determining the performance of the results of different machine learning models. The models were evaluated for classifier performance due to each image texture descriptor of currant powders with 6 different data sets [41].…”

“…In a previous study [41], microscopic images of blackcurrant powders were used in determining the performance of the results of different machine learning models. The models were evaluated for classifier performance due to each image texture descriptor of currant powders with 6 different data sets [41]. In this research, the process of transforming microscopic images into numerical data was carried out, integrating all textural features of the images into a single data set.…”

“…In this research, the process of transforming microscopic images into numerical data was carried out, integrating all textural features of the images into a single data set. In the previous study, it was observed that fruit powders are effectively recognized using image texture descriptor, i.e., entropy [41]. In other cases, the current application intended to automate the machine learning process to a certain extent to obtain significantly higher machine learning results [41].…”

“…In the previous study, it was observed that fruit powders are effectively recognized using image texture descriptor, i.e., entropy [41]. In other cases, the current application intended to automate the machine learning process to a certain extent to obtain significantly higher machine learning results [41].…”