Agriculture has always been an important economic and social sector for humans. Fruit production is especially essential, with a great demand from all households. Therefore, the use of innovative technologies is of vital importance for the agri-food sector. Currently artificial intelligence is one very important technological tool widely used in modern society. Particularly, Deep Learning (DL) has several applications due to its ability to learn robust representations from images. Convolutional Neural Networks (CNN) is the main DL architecture for image classification. Based on the great attention that CNNs have had in the last years, we present a review of the use of CNN applied to different automatic processing tasks of fruit images: classification, quality control, and detection. We observe that in the last two years (2019–2020), the use of CNN for fruit recognition has greatly increased obtaining excellent results, either by using new models or with pre-trained networks for transfer learning. It is worth noting that different types of images are used in datasets according to the task performed. Besides, this article presents the fundamentals, tools, and two examples of the use of CNNs for fruit sorting and quality control.

Machine learning (ML) has revolutionized resource management in agriculture by analyzing vast amounts of data and creating precise predictive models. Precision agriculture improves agricultural productivity and profitability while reducing costs and environmental impact. However, ML implementation faces challenges such as managing large volumes of data and adequate infrastructure. Despite significant advances in ML applications in sustainable agriculture, there is still a lack of deep and systematic understanding in several areas. Challenges include integrating data sources and adapting models to local conditions. This research aims to identify research trends and key players associated with ML use in sustainable agriculture. A systematic review was conducted using the PRISMA methodology by a bibliometric analysis to capture relevant studies from the Scopus and Web of Science databases. The study analyzed the ML literature in sustainable agriculture between 2007 and 2025, identifying 124 articles that meet the criteria for certainty assessment. The findings show a quadratic polynomial growth in the publication of articles on ML in sustainable agriculture, with a notable increase of up to 91% per year. The most productive years were 2024, 2022, and 2023, demonstrating a growing interest in the field. The study highlights the importance of integrating data from multiple sources for improved decision making, soil health monitoring, and understanding the interaction between climate, topography, and soil properties with agricultural land use and crop patterns. Furthermore, ML in sustainable agriculture has evolved from understanding weather data to integrating advanced technologies like the Internet of Things, remote sensing, and smart farming. Finally, the research agenda highlights the need for the deepening and expansion of predominant concepts, such as deep learning and smart farming, to develop more detailed and specialized studies and explore new applications to maximize the benefits of ML in agricultural sustainability.

Fingerprint classification is a stage of biometric identification systems that aims to group fingerprints and reduce search times and computational complexity in the databases of fingerprints. The most recent works on this problem propose methods based on deep convolutional neural networks (CNNs) by adopting fingerprint images as inputs. These networks have achieved high classification performances, but with a high computational cost in the network training process, even by using high-performance computing techniques. In this paper, we introduce a novel fingerprint classification approach based on feature extractor models, and basic and modified extreme learning machines (ELMs), being the first time that this approach is adopted. The weighted ELMs naturally address the problem of unbalanced data, such as fingerprint databases. Some of the best and most recent extractors (Capelli02, Hong08, and Liu10), which are based on the most relevant visual characteristics of the fingerprint image, are considered. Considering the unbalanced classes for fingerprint identification schemes, we optimize the ELMs (standard, original weighted, and decay weighted) in terms of the geometric mean by estimating their hyper-parameters (regularization parameter, number of hidden neurons, and decay parameter). At the same time, the classic accuracy and penetration-rate metrics are computed for comparison purposes with the superior CNN-based methods reported in the literature. The experimental results show that weighted ELM with the presence of the golden-ratio in the weighted matrix (W-ELM2) overall outperforms the rest of the ELMs. The combination of the Hong08 extractor and W-ELM2 competes with CNNs in terms of the fingerprint classification efficacy, but the ELMs-based methods have been demonstrated their extremely fast training speeds in any context.