Scielo RSS <![CDATA[Computación y Sistemas]]> vol. 25 num. 4 lang. en <![CDATA[SciELO Logo]]> <![CDATA[Introduction to the Thematic Issue on Artificial Intelligence for Industry 4.0]]> <![CDATA[Actions Selection during a Mobile Robot Navigation for the Autonomous Recharging Problem]]> Abstract: The use of mobile robots has increased for its application in various areas such as supply chains, factories, cleaning, disinfection, medical assistance, search, and exploration. It is a fact that most of these robots, if not all, use batteries to power themselves. During a mobile robot task execution, the battery's electric charge tends to deplete as a function of the energy load demands, which would cause the robot to shut down if the discharge is critical, leaving its task inconclusive. Therefore, it is of utmost importance that the robot learns when to charge its batteries, avoiding turning off. This work shows a reactive navigation scheme for a mobile robot that integrates a module for battery-level monitoring. A robot moves from a starting point to a destination according to the battery level. During the navigation, the robot decides when to change the course toward a battery charging station. This paper presents a rules-based reinforcement learning architecture with three entries; these entries correspond to the robot's battery level, the distance to the destination, and the distance to the battery charging station. According to the simulations, the robot learns to select an appropriate action to accomplish its task. <![CDATA[IoT Architecture for Monitoring Variables of Interest in Indoor Plants]]> Abstract: Based on the need to integrate variables of interest related to the growth of indoor plants and obtain value-added information from them, in this paper we propose as a contribution the design and implementation of an IoT-based software architecture for monitoring, analysis, and visualization of the main variables of interest in indoor plants. The proposed architecture is presented in three views and four layers, taking into account the structure of the lambda architecture. Based on the defined architecture, a prototype system was developed for monitoring and analyzing the variables of interest in indoor plants such as temperature, humidity and luminance, which was evaluated in a particular case study with the Chinese Evergreen plant. The architecture and prototype developed are intended to serve as a reference to be replicated in similar application contexts such as: precision agriculture and environmental variable monitoring scenarios. <![CDATA[Symbolic Learning using Brain Programming for the Recognition of Leukemia Images]]> Abstract: in this work, We propose an approach of symbolic learning for the recognition of leukemia images. Image recognition for cancer detection is often a subjective problem due to different interpretations by experts of the medical area. Feature extraction is a critical step in image recognition, and current automatic approaches are unintelligible since they need to be adapted to different image domains. We propose the paradigm of brain programming as a symbolic learning approach to address aspects involved in the derivation of knowledge that allows us to recognize subtypes of leukemia in color images. Experimental results provide evidence that the multi-class recognition task is achieved through the solutions discovered from multiples runs of the bioinspired model. <![CDATA[New Explainability Method based on the Classification of Useful Regions in an Image]]> Abstract: Machine learning is a necessary and widely used tool nowadays in industry. Talking about the evaluation of its reliability, already known metrics are broadly used, but they are focused on how precise, accurate or sensitive the model is. Nevertheless, these metrics do not offer an overview of the consistency or stability of the predictions, that is, how much reliable the model is, which could be deduced if the reasons behind the predictions are understood. In the present work, we propose a novel method that can be applied to image classifiers and allows the understanding, in a non-subjective visual manner, of the background of a prediction. <![CDATA[Post-Quantum Digital Signature for the Mexican Digital Invoices by Internet]]> Abstract: This paper presents an analysis of the Post-Quantum Cryptography (PQC) digital signature algorithms accepted for the third-round of NIST Post-Quantum Cryptography Competition. The digital signature primitive is the core of the Mexican Digital Invoices by Internet (CFDI), and it is based on the RSA algorithm but with the future arrival of Quantum Computers, it is vulnerable to cryptographic attacks. This paper points out the advantages and disadvantages of the NIST candidates for their potential adoption as the new core of CFDI. <![CDATA[High-Resolution Reconstructions of Aerial Images Based on Deep Learning]]> Abstract: We present a methodology for high-resolution orthomosaic reconstruction using aerial images. Our proposal consists a neural network with two main stages, one to obtain the correspondences necessary to perform a LR-orthomosaic and another one that uses these results to generate an HR- orthomosaic, and a feedback connection. The CNN are based on well known models and are trained to perform image stitching and obtain a high-resolution orthomosaic. The results obtained in this work show that our methodology provides similar results to those obtained by an expert in orthophotography, but in high-resolution. <![CDATA[On the Algebrization of the Multi-valued Logics CG′<sub>3</sub> and G′<sub>3</sub>]]> Abstract: Multi-valued logics form a family of formal languages with several applications in computer sciences, particularly in the field of Artificial intelligence. Paraconsistent multi-valued logics have been successful applied in logic programming, fuzzy reasoning, and even in the construction of paraconsistent neural networks. G ′ 3 is a 3-valued logic with a single represented truth value by 1. C G ′ 3 is a paraconsistent, 3-valued logic that extends G ′ 3 with two truth values represented by 1 and 2. The state of the art of C G ′ 3 comprises a Kripke semantics and a Hilbert axiomatization inspired by the Lindenbaum-Łos technique. In this work, we show that G ′ 3 and C G ′ 3 are algebrizable in the sense of Blok and Pigozzi. These results may apply to the development of paraconsistent reasoning systems. <![CDATA[Artificial Intelligence for Industry 4.0 in Iberoamerica]]> Abstract: Artificial intelligence applied to industry 4.0 will help the Iberoamerican industries to experiment and adopt a digital transformation. In this paper, we present a literature review of the work conducted by Iberoamerican countries regarding artificial intelligence for Industry 4.0. The works analyzed are aligned with the eight technological pillars that support industry 4.0, including robotics, Internet of things, big data, additive manufacturing and simulation, cloud computing, cybersecurity, virtual and augmented reality, and horizontal and vertical integration. As a result of our perusal, we propose many strategies that Iberoamerican countries could follow to successfully implement artificial intelligence to daily life. <![CDATA[Negations of Probability Distributions: A Survey]]> Abstract: In recent years many papers have been devoted to the analysis and applications of negations of finite probability distributions (PD), first considered by Ronald Yager. This paper gives a brief overview of some formal results on the definition and properties of negations of PD. Negations of PD are generated by negators of probability values transforming element-by-element PD into a negation of PD. Negators are non-increasing functions of probability values. There are two types of negators: PD-independent and PD-dependent negators. Yager's negator is fundamental in the characterization of linear PD-independent negators as a convex combination of Yager's negator and uniform negator. Involutivity of negations is important in logic, and such involutive negator is considered in the paper. We propose a new simple definition of the class of linear negators generalizing Yager's negator. Different examples illustrate properties of negations of PD. Finally, we consider some open problems in the analysis of negations of probability distributions. <![CDATA[Covid-19 Fake News Detection: A Survey]]> Abstract: The increase of fake news in social media, especially about Covid-19, poses a real threat to the mental and physical health of people. It is an important task to detect such news and to stop it spreading. In this article, we describe the main approaches for fake news about Covid-19 detection, including Classical Machine Learning models, models based on Neural Networks and models, which were created based on the other approaches and preprocessing steps. We analyze the results of the challenge “Constraint@AAAI2021 -COVID19 Fake News Detection”, the main goal of which was the binary classification of news collected from social media for fake and real news. We analyze the best approaches, which were proposed by researchers during the challenge. In addition, we describe datasets of fake news related to Covid-19, which could be useful for the detection and classification of such news. <![CDATA[A Novel Hybrid Grey Wolf Optimization Algorithm Using Two-Phase Crossover Approach for Feature Selection and Classification]]> Abstract: Data mining process can be hampered by high dimensional large datasets, so feature selection become a mandatory task in prior for dimensionality reduction of datasets. Main motive of feature selection process is to choose most informative features and use them to maximize the classification accuracy. This work introduces a novel two phase crossover operator with grey wolf algorithm to solve the problem of feature selection. Two phase crossover improves the exploitation part. First phase crossover is used for feature selection and second phase used for adding some more important information and improve the classification accuracy. The KNN classifier improved the classification accuracy which is most famous classifier based on wrapper method. Ten-fold crossover validation is used to defeat the over-fitting problem which is always a milestone in the way of accuracy. Experiments are applied using various datasets and results prove that proposed algorithm outperform and provide better results. <![CDATA[Part-of-Speech Tagging for Mizo Language Using Conditional Random Field]]> Abstract: Part of speech (POS) tagging assigns a class or tag to each token in a sentence. The tag allocated to a word is mainly its part of speech or any other class of interest. Several applications of Natural Language Processing (NLP) require it as a prerequisite. The development of part-of-speech tagging for the under-resourced Mizo language is presented in this study, which makes use of a stochastic model known as Conditional Random Field (CRF). The CRF is a discriminative probabilistic classifier that considers both the context of a given word and the tag transition probabilities in the training dataset. A corpus of approximately 30,000 words was collected and manually annotated with the proposed tagset for system evaluation. On various sizes of training and test sets, the tagger achieved 89.46 % accuracy, 89.3 % F1-score, 89.42 % precision, and 89.48 % recall. <![CDATA[Estimating Volume of the Tomato Fruit by 3D Reconstruction Technique]]> Resumen: Debido a su valor nutricional y económico, el tomate es considerado una de las principales hortalizas en términos de producción y consumo en el mundo. Por esta razón, un estudio importante es el volumen del fruto relacionado con la pérdida de masa. Este proceso se desarrolla en el fruto principalmente después de la cosecha. Como este parámetro afecta el valor económico del cultivo, la comunidad científica ha ido abordando progresivamente el problema; sin embargo, no hay ningún método sin contacto que permita la estimación del volumen. En este trabajo se desarrolla un método cuantitativo que permite estimar el volumen del fruto del tomate mediante una técnica de reconstrucción 3D. El método se basa en una cámara que adquiere diferentes vistas de la silueta de la fruta y mediante el procesamiento de imágenes se genera una nube de puntos 3D y posteriormente una técnica de triangulación de Delaunay, que permite la estimación del volumen 3D de la fruta. Esta estimación de volumen permite el diseño de estrategias precisas enfocadas en la predicción del tomate postcosecha por parte de productores, distribuidores y consumidores.<hr/>Abstract: Due to its nutritional and economic value, the tomato is considered one of the main vegetables in terms of production and consumption in the world. For this reason, an important study is the volume of the fruit related to the loss of mass. This process develops in the fruit mainly after the harvest. This parameter affects the economic value of the crop, the scientific community has been progressively addressing the problem. However, there is no non-contact method that allows volume estimation. In this work a quantitative method is developed that allows to estimate the volume of the tomato fruit by means of a 3D reconstruction technique. The method is based on a camera that acquires different views of the silhouette of the fruit and by means of image processing a 3D point cloud is generated and later a Delaunay triangulation technique, which allows the estimation of the 3D volume of the tomato fruit. This volume estimation allows the design of precise strategies focused on the prediction of tomato post-harvest by producers, distributors and consumers. <![CDATA[Design Aids for Beams of Rectangular Cross Section with Parabolic Haunches: Part 2]]> Resumen: En este trabajo se presentan las ayudas de diseño más utilizadas para vigas de sección rectangular con cartelas parabólicas. La viga se encuentra sujeta a una carga concentrada localizada en cualquier parte de la viga, y toma en cuenta las deformaciones por flexión y cortante para obtener los factores de momentos de empotramiento, que es la principal aportación de este trabajo de investigación. La primera parte de este trabajo presenta las ayudas de diseño para el mismo tipo de vigas para obtener los factores de transporte o arrastre, los factores de rigidez, y los factores de momentos de empotramiento se obtienen para una carga uniformemente distribuida. Las variables y las simplificaciones son las mismas que en la parte 1. Además, se muestra un ejemplo numérico utilizando las ayudas de diseño, y se compara con las ecuaciones previamente descritas por los autores en un artículo anterior a este documento, y los resultados son iguales con una aproximación de tres dígitos. Por lo tanto, las ayudas de diseño proporcionan una gran herramienta de ayuda para los ingenieros estructurales por el gran ahorro de tiempo.<hr/>Abstract: In this paper, the most used design aids for beams of rectangular section with parabolic haunches are presented. The beam is found subjected to concentrated load localized anywhere on the beam, and takes into account the bending and shear deformations to obtain the fixed-end moments factors, which is the main contribution of this research work. The first part of this work presents the design aids for the same type of beams to obtain the carry-over factors, the stiffness factors, and the fixed-end moments factors are obtained for a uniformly distributed load. The variables and the simplifications are the same as in the part 1. Also, a numerical example is shown using the design aids, and it is compared with the equations previously presented by the authors in a paper prior to this document, and the results are equal to a three-digit approximation. Therefore, design aids provide a great tool of help for structural engineers by the greatly time-savings. <![CDATA[Design of a Soft Gripper Using Genetic Algorithms]]> Abstract: In this paper, we present an artificial intelligence-assisted design of a soft robotic gripper. First, we formulate the design of the soft gripper as an optimization problem. Then, we design and configure a genetic algorithm (GA) method to solve the problem under design constraints. Lastly, we implement the whole system in co-simulation between the GA and a computer-aided design software that evaluates the candidate solutions using finite element analysis. A network-attached storage server connecting multiple nodes runs the GA method in parallel, to accelerate the process. After experimentation, we present simulation results to validate our approach. <![CDATA[Impact of Aggregation and Compression on Cluster-Based Wireless Sensor Networks]]> Abstract: In Wireless Sensor Networks (WSNs), a clustered architecture is generally used to reduce energy consumption irrespectively of the application of the system. We prove in this work that, a clustered network only reduces energy consumption if aggregation or compression functions are enabled. Furthermore, a clustered network would consume much more energy if clustering techniques without the use of aggregation/compression (or a low aggregation coefficient) due to the extra consumption in the cluster formation phase. As an additional feature, a general energy consumption model based on the notion of energy units is developed that can be easily extrapolated to either theoretical or experimental values. Hence, the proposed analytical framework is valid for any commercial node or energy consumption model. <![CDATA[Gate-based Rules for Extracting Attribute Values]]> Abstract: Automated ontology population is intended to enrich ontologies. The main entities of an ontological model are classes, subclasses, attributes (datatype properties), relationships (object properties), and instances. Class instances are important to the scientific community, since some work is devoted to automatically populating ontologies by using statistical methods, information extraction, and natural language processing, among others. The problem is focused on identifying and extracting attribute values of instances. Commonly, such values have a predefined type like numeric, string, boolean, etc. The difficulty arises when you want to know which instance belongs to such values. In this paper we propose an approach based on Natural Language Processing (NLP) and Information Extraction (IE) technologies for extracting attribute values. We use syntactic patterns implemented on the GATE (General Architecture for Text Engineering) tool. The results are independent of the application domain and they exhibit promising values of recall, precision, and F-measure. <![CDATA[Utilization of Multi-Criteria Decision-Making for Emergency Management]]> Abstract: When emergencies or disasters strike, decision-making is a critical component in emergency management. One area of emergency management is ensuring that vulnerable communities are identified and can get the aid they need before, during, and after emergency events. Artificial Intelligence (AI) can be leveraged to improve decision-making in dynamic and complex situations. We propose that Multi-Criteria Decision-Making (MCDM), specifically a hybrid methodology of AHP-TOPSIS, is an approach that can be utilized in AI that can help evaluate, prioritize, and select the most favorable alternative based on computation of the criteria. A study was conducted considering the positive COVID-19 cases in randomly selected counties in three states – Texas, California, and Oklahoma – that have historically experienced the most declared emergencies. The empirical results from the three cases (one case for each state) demonstrate the superiority of the AHP-TOPSIS approach.