The application of Deep Learning models in fruit analysis has garnered significant attention due to its potential to revolutionize the agricultural sector and enhance crop monitoring. This paper presents a comprehensive review of recent research efforts in fruit analysis using Deep Learning techniques. The study delves into model selection, dataset characteristics, evaluation metrics, challenges, and future directions in this domain. Various model architectures, including classical Convolutional Neural Networks (CNNs) and advanced detection models like R-CNN and YOLO, have been explored for tasks ranging from fruit classification to detection. Evaluation metrics such as precision, recall, F1-score, and mean Average Precision (mAP) have been commonly used to assess model performance. Challenges, including data scarcity, labeling complexities, variations in fruit characteristics, and computational efficiency, have been identified and discussed. The paper also presents an overview of available datasets, encompassing both proprietary and publicly accessible sources. Future research directions involve exploring enhanced data augmentation, multi-modal integration, knowledge transfer across species, robustness in dynamic environments, improved computational efficiency, and practical integration of models into real-world agricultural systems. This review provides valuable insights for researchers and practitioners aiming to leverage Deep Learning for fruit analysis in the pursuit of sustainable agriculture and food production.

This paper presents a systematic literature review focusing on the application of machine learning techniques for deriving observational constraints in cosmology. The goal is to evaluate and synthesize existing research to identify effective methodologies, highlight gaps, and propose future research directions. Our review identifies several key findings: (1) Various machine learning techniques, including Bayesian neural networks, Gaussian processes, and deep learning models, have been applied to cosmological data analysis, improving parameter estimation and handling large datasets. However, models achieving significant computational speedups often exhibit worse confidence regions compared to traditional methods, emphasizing the need for future research to enhance both efficiency and measurement precision. (2) Traditional cosmological methods, such as those using Type Ia Supernovae, baryon acoustic oscillations, and cosmic microwave background data, remain fundamental, but most studies focus narrowly on specific datasets. We recommend broader dataset usage to fully validate alternative cosmological models. (3) The reviewed studies mainly address the $H_0$ tension, leaving other cosmological challenges—such as the cosmological constant problem, warm dark matter, phantom dark energy, and others—unexplored. (4) Hybrid methodologies combining machine learning with Markov chain Monte Carlo offer promising results, particularly when machine learning techniques are used to solve differential equations, such as Einstein Boltzmann solvers, prior to Markov chain Monte Carlo models, accelerating computations while maintaining precision. (5) There is a significant need for standardized evaluation criteria and methodologies, as variability in training processes and experimental setups complicates result comparability and reproducibility. (6) Our findings confirm that deep learning models outperform traditional machine learning methods for complex, high-dimensional datasets, underscoring the importance of clear guidelines to determine when the added complexity of learning models is warranted.

Background: Respect and inclusion are essential for gender equity in higher education, where subtle forms of gender-based violence, such as bias and stereotypes, often emerge and affect academic well-being. The systematic use of machine learning or deep learning models to automatically identify gender bias in higher education teaching evaluations remains underexplored, providing the main motivation for the present study. Purpose: This work evaluates the ability of machine learning (ML) and deep learning (DL) models to identify textual expressions of gender bias on digital platforms in higher education. Using student evaluations of teaching from the University of BÍo-BÍo (Chile), we characterize bias patterns linked to instructor gender. We address two questions: RQ1: To what extent do student comments in university teaching evaluations written in Spanish exhibit explicit gender biases and stereotypical patterns when stratified by the instructor’s gender? and RQ2: How accurately do ML and DL models (SVM, BETO, DistilBERT) detect explicit gender bias in this domain-specific corpus when evaluated using macro-average metrics? Method: We conducted a PRISMA-guided systematic review (2018–2024) to identify suitable detection techniques, followed by a determinant-variable analysis examining how gender-related attributes, stereotypes, and comment features influence bias in feedback. Student evaluations from 2017–2019 and 2023 were annotated with binary labels and used to train and evaluate models. The dataset contains 960 comments (691 for training, 77 for validation, and 192 for testing). We then developed predictive models, including SVMs and transformer-based (BETO and DistilBERT). Results: For RQ1, an analysis of determinant variables shows that comments on female instructors’ teaching performance tend to emphasize personal traits and relational behaviors, particularly dedication, accessibility, and willingness to answer questions. In contrast, comments about male instructors more often highlight academic competence, with frequent mentions of subject mastery and content expertise, as well as expressions of admiration for their intellectual performance. For RQ2, BETO+BiLSTM and DistiIBERT+BiLSTM were developed, which performed strongly, achieving average macro Fl score of 99% on the gender bias detection task, well above the BETO and SVM baselines of 95% and 88%, respectively. As part of the results, a dataset of 960 comments labeled as gender-based bias (GB) and non-gender-based bias (N-GB) was compiled and made available on the Zenodo repository at https://doi.org/10.5281/zenodo.17665445

This paper presents a systematic literature review focusing on the application of machine learning techniques for deriving observational constraints in cosmology. The goal is to evaluate and synthesize existing research to identify effective methodologies, highlight gaps, and propose future research directions. Our review identifies several key findings: (1) various machine learning techniques, including Bayesian neural networks, Gaussian processes, and deep learning models, have been applied to cosmological data analysis, improving parameter estimation and handling large datasets. However, models achieving significant computational speedups often exhibit worse confidence regions compared to traditional methods, emphasizing the need for future research to enhance both efficiency and measurement precision. (2) Traditional cosmological methods, such as those using Type Ia Supernovae, baryon acoustic oscillations, and cosmic microwave background data, remain fundamental, but most studies focus narrowly on specific datasets. We recommend broader dataset usage to fully validate alternative cosmological models. (3) The reviewed studies mainly address the $H_0$ tension, leaving other cosmological challenges-such as the cosmological constant problem, warm dark matter, phantom dark energy, and others-unexplored. (4) Hybrid methodologies combining machine learning with Markov chain Monte Carlo offer promising results, particularly when machine learning techniques are used to solve differential equations, such as Einstein Boltzmann solvers, as prior to Markov chain Monte Carlo models, accelerating computations while maintaining precision. (5) There is a significant need for standardized evaluation criteria and methodologies, as variability in training processes and experimental setups complicates result comparability and reproducibility (abridged).