Latin American Journal of Computing
Not a member yet
191 research outputs found
Sort by
Sistema de Telemedicina para el Monitoreo de la Frecuencia Cardiaca Empleando Análisis de Componentes Independientes en Videos
Get PDFHeart is the organ responsible for providing blood, oxygen and nutrients through the human body, their initial monitoring was reflected in heart rate value, this measurement is a possible irregularity within the organism. Control of this vital sign in most cases involves help of medical staff or using sensors that need to maintain contact with the skin, these common monitoring methods generate discomfort and nonconformity in newborns, senior adults or patients suffering from skin sensitivity. According these disadvantages, project offers a non-invasive and non-contact system based on telemedicine principles, which provides a quick, reliable and economical remote heart rate monitor. Results are compared with a pulse oximeter with a resolution of 1 bpm and accuracy of ±2%, obtaining low and acceptable errors.
 
Optimising a Language Recognition System Through Phoneme-Based Vector Representation
Get PDFThis article analyzes vector representation of phonemes as an alternative to improve a language identification system (LID). CBOW (Continuous Bag-of-Words) and Skip-gram architectures proposed by Mikolov are studied. These models allow predicting words within a context by generating n-dimensional vectors. In this work we will analyze the application of these models in smaller phonetic units or n-grams.
 
Un Enfoque Evolutivo Multi-Objetivo al Problema de la Construcción de Grupos de Estudiantes Universitarios
Get PDFThe creation of working groups of students in education is a common process that is often developed by the teacher intuitively. However, such a process is actually a complex task since various students and criteria must be taken into account. In general, these criteria are often in conflict because they are a reflection of the educational interests of teachers and on the other hand, the individual preferences of students. In this sense, this paper has as general goal: to propose a mathematicalcomputational solution that efficiently automatizes, in terms of computational time and solution quality, the creation of working groups of college students. The results obtained from two real scenarios of the Universidad Tecnica Estatal de Quevedo indicate that the proposal is an effective alternative to the traditional model.
 
La Ciencia Acústica en los Ambientes Inteligentes
Get PDFIn this article is presented a revision of previous works related to acoustic science and intelligent environments, to establish a connection between these areas. The described works combine physics, psychoacoustics and neuroscience, including also sound objects and automatic acoustic management. The research’s goal is to show how these immersive environments are created with the sound as the main element to take into account, and other elements that are part of these systems. This description allows establishing the reference framework to create a reflective middleware for the acoustic self-management in intelligent environments, to make possible the inclusion of more audio elements in these spaces, in order to improve and extend the capabilities and benefits offered by the intelligent environments.
 
Deep Learning as a predictive model to classify handwritten digits
Get PDFIn this research work, the results of applying DeepLearning prediction models to identify the digit of an image,that contains a handwritten number of the MNIST database, arepresented. This set of dataset was acquired from the competitionof Kaggle: Digit Recognizer. The following process was applied:First, image preprocessing techniques were used, which focuson obtaining a pretty clear image and to reduce the size ofthe same, these objectives that are achieved with Otsu Method,transformed from Haar Wavelet and the Principal ComponentAnalysis (PCA), thus obtaining as a result, one set of new datasetto be evaluated. Second, the Deep Learning MxNET and H2omodels, which were executed in the statistical language R, wereapplied to these datasets obtained, this way, several predictionswere acquired. Finally, the best obtained predictions in theexperiment were sent to the Digit Recognizer competition, andthe results of this evaluation scored 99,129% of prediction.
 
Análisis de Datos Funcionales Aplicado al Riesgo Financiero: un Caso de Estudio en Cooperativas de Ahorro y Crédito Ecuatorianas
No full textThere is a wide variety of statistical tools developed for making decisions in the business context. The analysis of functional data is a area of study of growing importance in the last years. In the present paper some of its applied techniques are proposed to make analysis of financial risk. Specifically, results from exploratory functional analysis, identification of atypical data and the construction of supervised classification models based on the risk classification of credit unions, subject to the control of the Superintendency of Banks of Ecuador, taking as functional variables the NPL ratio and the net profit margin in the period July 2011 to December 2012.
 
First Order Methods for High Resolution Image Denoising
Get PDFIn this paper we are interested in comparing theperformance of some of the most relevant first order non-smoothoptimization methods applied to the Rudin, Osher and Fatemi(ROF) Image Denoising Model and a Primal-Dual Chambolle-Pock Image Denoising Model. Because of the properties of theresulting numerical schemes it is possible to handle these computationspixelwise, allowing implementations based on parallelparadigms which are helpful in the context of high resolutionimaging.
 
Design and Construction of a 3D Scanner and Integration to a 3D Printer (accessible low cost and open source reverse engineering)
Get PDFBuilt equipment has a 3D scanner with a principle in laser triangulation, integrated to a 3D printer based on fused deposition modeling. The same printer hardware has been used to integrate the peripherals of the scanner: lasers and rotating platform, the camera connects directly to a computer that has software developed to handle the functionalities of the scanner, which obtains a point cloud, and due to integration of postprocessing (surface reconstruction) and laminate tools (g-code), a file is automatically generated ready for interpretation in the 3D printer, closing the reproduction cycle of a model. Due to its low cost and open source, this prototype made accessible performing reverse engineer of an object by means of digital acquisition (3D scanner) and allows its total reproduction (3D printing).
 
Development of a Prototype for the Quality Control of Bovine Meat Determined by its Organoleptic Characteristics, based on an Automatic Inspection System for Artificial Vision
Get PDFThe world beef market is in full growth and with unsatisfied demands and prices up and these depend very much on their quality when arriving at the final consumer, while the national market, our country also has a future potential in the meat industry. In the present investigation is to evaluate the sensory characteristics of color and texture by means of the presence of a bovine meat sample in the system whose final result will be the acceptance or negation of its organoleptic quality. The system is constituted by a transport band in charge of taking the sample to a capsule where both the Lighting System (LS) and the Computer Vision System (CVS) are located, and when leaving there it will be automatically classified by an actuator, guaranteeing less manipulation and estimation of time by human intervention throughout the process while providing greater security to the final consumer about the meat that is entering their home.
 
Estimation of the Contaminant Risk Level of Petroleum Residues Applying FDA Techniques
Get PDFIn the process of oil extraction, specifically in therefinement and industrialization of hydrocarbons, as is known,multiple wastes are highly polluting for the soil, water and air.In this work, the risk level of these wastes in affected areasis estimated thanks to the application of statistical models inthe field of functional data analysis. These models have beenimplemented in a statistical software called RStudio that allowsan early measurement and evaluation of the level of risk by usingsemiquantitative and quantitative methods. This measurement iscarried out by the staff of PETROECUADOR close to the affectedplace. It was used the laser-induced fluorescence technique (LIF).The data obtained using this technique was used to adjust thefollowing models: Generalized Functional Linear Model (MLFG),which makes it possible to classify the spectrum generated intwo pollution levels: Low and High. Functional linear regressionmodel with scalar response and functional explanatory variablewith the aim of directly estimating the percentage of contaminationlevel. With these results it is verified that the shape ofthe laser fluorescence spectrum is highly related to the gasolinecontent in the sample.