Peaches are a popular fruit appreciated by consumers due to their eating quality. Quality evaluation of peaches is important for their processing, inventory control, and marketing. Eleven quality indicators (shape index, volume, mass, density, firmness, color, impedance, phase angle, soluble solid concentration, titratable acidity, and sugar–acid ratio) of 200 peach fruits (Prunus persica (L.) Batsch “Spring Belle”) were measured within 48 h. Quality indicator data were normalized, outliers were excluded, and correlation analysis showed that the correlation coefficients between dielectric properties and firmness were the highest. A back propagation (BP) neural network was used to predict the firmness of fresh peaches based on their dielectric properties, with an overall fitting ratio of 86.9%. The results of principal component analysis indicated that the cumulative variance of the first five principal components was 85%. Based on k-means clustering analysis, normalized data from eleven quality indicators in 190 peaches were classified into five clusters. The proportion of red surface area was shown to be a poor basis for picking fresh peaches for the consumer market, as it bore little relationship with the comprehensive quality scores calculated using the new grading model.
This paper presents a review of recent advancements in metaheuristic algorithms, emphasizing their broad applicability across research domains and the performance improvements achieved through their derived variants. By mapping these algorithms to a proposed unified taxonomy, the review identifies the most generative and rapidly evolving category within the field. This paper also explores the emerging and fast-moving intersection between metaheuristics and Large Language Models (LLMs). This conceptual extension highlights a transformative convergence in which LLMs enable automated algorithm generation and optimization, while metaheuristic methods offer avenues to enhance the adaptability and efficiency of LLMs. Despite substantial progress and promising results, challenges remain regarding interpretability, reliability, computational demand, and ethical implementation. These findings underscore the need for continued, rigorous research into both metaheuristic methodologies and their evolving relationship with modern AI systems.
To date, many machine learning models have been used for peach maturity prediction using non-destructive data, but no performance comparison of the models on these datasets has been conducted. In this study, eight machine learning models were trained on a dataset containing data from 180 ‘Suncrest’ peaches. Before the models were trained, the dataset was subjected to dimensionality reduction using the least absolute shrinkage and selection operator (LASSO) regularization, and 8 input variables (out of 29) were chosen. At the same time, a subgroup consisting of the peach ground color measurements was singled out by dividing the set of variables into three subgroups and by using group LASSO regularization. This type of variable subgroup selection provided valuable information on the contribution of specific groups of peach traits to the maturity prediction. The area under the receiver operating characteristic curve (AUC) values of the selected models were compared, and the artificial neural network (ANN) model achieved the best performance, with an average AUC of 0.782. The second-best machine learning model was linear discriminant analysis with an AUC of 0.766, followed by logistic regression, gradient boosting machine, random forest, support vector machines, a classification and regression trees model, and k-nearest neighbors. Although the primary parameter used to determine the performance of the model was AUC, accuracy, F1 score, and kappa served as control parameters and ultimately confirmed the obtained results. By outperforming other models, ANN proved to be the most accurate model for peach maturity prediction on the given dataset.
This paper is an attempt of applying EDM methods on Moodle data in order to detect specific behaviours within student groups with the tendency to fail the course. The research is conducted on Moodle logs gathered in the blended course Programming 1. Extracting and using crucial information on time can be a turning point for students in at-risk stage, which is what we tried to achieve in this research.