The Internet of Things (IoT) presents great potential in various fields such as home automation, healthcare, and industry, among others, but its infrastructure, the use of open source code, and lack of software updates make it vulnerable to cyberattacks that can compromise access to data and services, thus making it an attractive target for hackers. The complexity of cyberattacks has increased, posing a greater threat to public and private organizations. This study evaluated the performance of deep learning models for classifying cybersecurity attacks in IoT networks, using the CICIoT2023 dataset. Three architectures based on DNN, LSTM, and CNN were compared, highlighting their differences in layers and activation functions. The results show that the CNN architecture outperformed the others in accuracy and computational efficiency, with an accuracy rate of 99.10% for multiclass classification and 99.40% for binary classification. The importance of data standardization and proper hyperparameter selection is emphasized. These results demonstrate that the CNN-based model emerges as a promising option for detecting cyber threats in IoT environments, supporting the relevance of deep learning in IoT network security.

This article introduces Peruvian coffee leaf datasets known as CATIMOR, CATURRA and BORBON of coffee plantations located at San Miguel de las Naranjas and La Palma Central, Jaén province, Cajamarca, Perú. The leaves with nutritional deficiencies were identified by agronomists, using a physical structure the controlled environment was designed and the images were captured with a digital camera. The dataset contains 1006 leaf images grouped according to their nutritional deficiencies (Boron, Iron, Potasium, Calcium, Magnesium, Manganese, Nitrogen and others). CoLeaf dataset contain images that facilitate training and validation during the utilization of deep learning algorithms for coffee plant leaf nutritional deficiencies recognition and classification. The dataset is publicly and freely available at http://dx.doi.org/10.17632/brfgw46wzb.1.

Mango production is fundamental to the agricultural economy, generating income and employment in various communities. Accurate estimation of its production optimizes the planning and logistics of harvesting; traditionally, manual methods are inefficient and prone to errors. Currently, machine learning, by handling large volumes of data, emerges as an innovative solution to enhance the precision of mango production estimation. This study presents an analysis of mango fruit detection using machine learning algorithms, specifically YOLO version 8 and Faster R-CNN. The present study employs a dataset consisting of 212 original images, annotated with a total of 9604 labels, which has been expanded to include 2449 additional images and 116,654 annotations. This significant increase in dataset size notably enhances the robustness and generalization capacity of the model. The YOLO-trained model achieves an accuracy of 96.72%, a recall of 77.4%, and an F1 Score of 86%, compared to the results of Faster R-CNN, which are 98.57%, 63.80%, and 77.46%, respectively. YOLO demonstrates greater efficiency, being faster in training, consuming less memory, and utilizing fewer CPU resources. Furthermore, this study has developed a web application with a user interface that facilitates the uploading of images from mango trees considered samples. The YOLO-trained model detects the fruits of each tree in the representative sample and uses extrapolation techniques to estimate the total number of fruits across the entire population of mango trees.

The field of hydrology is one of the sciences that focuses on the study, planning and quantification of water resources, generating a significant amount of data, which are indispensable in the branch of civil engineering. Currently these data are analyzed by a variety of techniques, among the predominant ones are artificial intelligence (IA) exclusively applied to the modeling of hydrological processes such as rain-runoff, floods, droughts, evapotranspiration, lake level and flow prediction. This document carried out a systematic review of the literature published between the years 2015 to 2021 in the various databases such as Scopus, Springer Link, EBSCOhost, SciELO and ScienceDirect. For this, a protocol process was established in which the selected database, definition of search terms and selection filters are entered. Indeed, after considering the protocol process, 50 indexed articles were obtained in addition to 4 articles and 1 book of web pages. As a consequence, it was found that artificial neural networks (ANNs) are the most widely used techniques for modeling hydrological processes where, with innovative programming languages, they can be encoded with much greater versatility. To date, the use of RNA is being implemented with other techniques to generate hybrid models that allow obtaining better estimates.

Artificial neural networks (ANN) have a relevant role nowadays; several areas apply this technique due to the advantages they have to solve complex problems with many constraints compared to traditional methods, which are becoming outdated. Very little is known about this technique and its application in different branches of Civil Engineering. For this reason, the present research aims to conduct a systematic review of the literature to identify the use of this technique and to determine the results of the application of ANN models in civil engineering. A total of 41 scientific articles were included, distributed as follows: 6 in Scopus, 1 in ScienceDirect, 23 in ProQuest, 7 in Google Scholar, 2 in DialNet, 2 in SciELO. It was found that ANNs are used to predict or forecast variables associated with the fields of study in civil engineering; 8 applications of ANN were found for concrete properties, 11 for soil properties, 5 for seismic analysis, 9 for hydraulics, 7 for real estate valuation and 1 for bridge design. Likewise, it was found that the multilayer Perceptron is the most used ANN model, achieving an average R2 of 0.99, which shows advantages to solve problems with precision, in shorter times, with missing data in the data sets, as well as the reduction of the error factor.