Sistema Regional de Información
en línea para Revistas Científicas de América Latina,
el Caribe, España y Portugal

Pollution in dense populations such as the Metropolitan Area of Guadalajara grows exponentially, affecting the health of citizens and reducing their quality of life. One of the main research challenges pursued with the study of Smart Cities is environmental pollution to improve the well-being of citizens and to protect natural areas. Therefore, it is urgent the development of information technologies that allow to reduce this problem by the scientific analysis of data, to classify the zones with greater contamination. Currently, these data are captured by constant monitoring stations, generating a large volume of information representing a challenge for the classification process. This work proposes a model for the automatic execution of a classification algorithm using Support Vector Machine implementing libraries in python for parallel processing. As a result, we obtain two main subsystems: one of the Parameters of Configuration for the storage and cleaning of data and the design of the algorithm parallelized in the cloud importing modules mpi4py, numpy and sklearn.svm.

Agriculture is a fundamental pillar in the economy of many countries. To achieve this, investment in technology and the factors that make its development possible must be taken into account. Automated irrigation systems facilitate the work of farmers, improving the economy and lifestyle of people. The objective of this work is to determine the most important technologies and techniques to be used for the construction of automated irrigation systems, for this a systematic literature review is carried out using the SALSA method that describes the process in five steps, the bases were used of IEEE Xplore and Science Direct data, a quantitative analysis of the selected sample was made, identifying the techniques and technologies most used in these processes, in addition, the existing problems were determined from a qualitative analysis, identifying factors that should be taken into account in these implementations.

En la actualidad las organizaciones generan mucha información día a día, misma que puede ser de utilidad para adquirir conocimiento y para la toma de decisiones. El proyecto se enfoca en la construcción de un almacén de datos que contiene las variables correspondientes para poder aplicar estadísticas descriptivas y así visualizar patrones de comportamiento en la deserción académica de los alumnos de posgrado del Centro de Enseñanza LANIA; dichas variables se obtuvieron de un estudio del estado del arte. El trabajo brinda al lector un panorama de la construcción del almacén de datos, donde se destaca principalmente el proceso ETL, el cual se refiere a la extracción, transformación y carga de los datos. También se puede destacar la aplicación de la metodología CRISP-DM (Cross Industry Standard Process for Data Mining), donde se llevó a cabo cuatro fases de seis que contiene. Se pudo observar en los resultados que el 57.14% de los estudiantes que desertaron de la Maestría en Computación Aplicada (MCA) está en el rango de 23 a 25 años y el 40.47% de los estudiantes que desertaron de la Maestría en Redes y Sistemas Integrados (MRySI) está en el rango de 27 a 31 años.

(BACKGROUND) Requirement engineering is a fundamental process of the software development life cycle processes that allows defining the functionalities, quality and scope of a software. Requirement engineering is a human-intensive participation process and that have in ISO/IEC/IEEE 29148 a standard that defines a set of process (activities, tasks, information items, etc.) that provide support for its formalization. However, in the software industry there are many types of deficiencies have been reported. In this context, proposals for User-Centered Methodologies for Requirement Engineering have emerged and need to be studied to determine their alignment to the ISO 29148. (OBJETIVES) The objective of this study is to compare User-Centered Methodologies for Requirement Engineering taking process elements from ISO 29148 as criteria. (METHODS) For this research, a systematic mapping study and a comparative analysis of the UCMREs obtained were performed. (RESULTS) In the systematic mapping study, 4,463 studies were obtained from three relevant digital databases in the first stage, and after the selection process, five User-Centered Methodologies for Requirement Engineering were identified. These methodologies were characterized and analyzed from process elements perspective for comparison to ISO 29148. (CONCLUSIONS) The DoRCU methodology is the closest to ISO 29148, followed by Ammeth and Borja methodologies; and the XRE methodology is the most away to ISO 29148.

Tinnitus is a condition described as the perception of a sound, similar to that emitted by a bell, buzzing or whistling, in the absence of an acoustic source that generates it. The main methods used to evaluate this condition are questionnaires, visual analogue scales or pure tone audiometry tests; however, these are not completely reliable because the results depend on what is expressed by patients with this condition. The objective of this work is to review different sources of information in the search for works that report the identification of biomarkers, in other words an objective measurement based on electroencephalography (EEG) data in the study of tinnitus. Based on what was found, it was observed that there are a variety of works that report, through different methodologies, one or several features associated with the tinnitus; however, an aspect identified was that the pertinent evaluations have not been made to determine if a feature can be considered a biomarker, which can objectively, precisely and reproducibly describe the tinnitus condition, which is important to consider for the proposal and development of future works.

Humans can harbor parasites; hence, it is fundamental an early detection to prevent diseases. Parasites can be observed in microscopic images, and computer vision may be a helpful approach to detect and classify those parasites in digital images. Deep learning models have shown to have a high performance in image classification. Therefore, this article presents various multi-class deep learning classifiers to recognize 8 classes: 7 types of parasites and non-parasite class. The designed classifiers are based on transfer learning from an AlexNet modified architecture. By having a reduce amount of parasite images samples, a data augmentation was done, employing traditional methods and images generation with an adversarial neural network (GAN) designed for this purpose. The classifier with best performance presented a 99.94%, 98.97% and 98.18% accuracy in the for training, validation and testing sets, respectively.

This article explores the representations and experiences linked to male child labor in the city of Buenos Aires based on the analysis of the Mundo Infantil magazine, published between 1949 and 1955 by the Peronist government. Our hypothesis is that the prolonged participation of boys, girls and “muchachos” in formal and informal labor markets throughout the 20th century was not due solely to socioeconomic factors, but also to the vast and prolonged social circulation of positive representations of child labour, hence the interest in an approach to this object through massively consumed cultural products, such as children's magazines. In more specific terms, in this article we will prove that, during the 1940s and 1950s, Mundo Infantil presented the work of children from the popular sectors as a common, desirable and even commendable practice. Longstanding traditions, coupled with specific elements of Peronist imagery and discourse, came together to shape these representations.