<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/">
<title>Volumen 17 | Número 01</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59975" rel="alternate"/>
<subtitle/>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59975</id>
<updated>2026-11-19T05:31:10Z</updated>
<dc:date>2026-11-19T05:31:10Z</dc:date>
<entry>
<title>Modeling and Simulation for Healthcare Operations Management using High Performance Computing and Agent-Based Model</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59994" rel="alternate"/>
<author>
<name>Liu, Zhengchun</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59994</id>
<updated>2019-06-24T04:03:34Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Revision
Journal of Computer Science &amp; Technology; vol. 17, no. 1
Hospital based Emergency Departments (EDs) serve as the primary gateway to the acute healthcare system, are struggling to provide timely care to a steadily increasing number of unscheduled visits. It is a highly integrated service units that primarily handles the needs of the patients arriving without prior appointment, and with uncertain conditions. In this context, analysis and management of patient flows play a key role in developing policies and decision tools for overall performance improvement of the system. However, patient flows in EDs are considered to be very complex because of the different pathways patients may take and the inherent uncertainty and variability of healthcare processes. Due to the complexity and crucial role of an ED in the healthcare system, the ability to accurately represent, simulate and predict performance of ED is invaluable for decision makers to solve operations management problems. One way to realize this requirement is by modeling and simulation.&#13;
In this thesis, we build high fidelity simulation tools to identify system bottleneck, quantitatively predict the benefit and cost of a policy, and discovery knowledge for a better understanding of the complex ED system. The agentbased model and simulation technique provides a flexible way to study ED operations as it predicts the systemlevel behavior from micro-level interactions, so as to see the forest through the trees. In this way, policies such as staffing could be changed and the effect on parameters such as waiting times and throughput could be quantified.&#13;
Here, we use agent-based model and simulation techniques to model the interaction of ED components (i.e, patient, nurse, doctor, equipment etc.). We then applied high performance computing techniques to execute the model and analyze simulation results. In summary, armed with the ability to execute a compute-intensive model and analyze huge datasets, the overall goal of this study is to develop tools to better understand the complexity (explain), evaluate policy (predict) and improve efficiencies (optimize) of ED units.
Es revisión de: http://www.tesisenred.net/handle/10803/392743; Resumen de la tesis doctoral del autor defendida en la Universidad Autónoma de Barcelona el 22 de julio de 2016.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>Hospital based Emergency Departments (EDs) serve as the primary gateway to the acute healthcare system, are struggling to provide timely care to a steadily increasing number of unscheduled visits. It is a highly integrated service units that primarily handles the needs of the patients arriving without prior appointment, and with uncertain conditions. In this context, analysis and management of patient flows play a key role in developing policies and decision tools for overall performance improvement of the system. However, patient flows in EDs are considered to be very complex because of the different pathways patients may take and the inherent uncertainty and variability of healthcare processes. Due to the complexity and crucial role of an ED in the healthcare system, the ability to accurately represent, simulate and predict performance of ED is invaluable for decision makers to solve operations management problems. One way to realize this requirement is by modeling and simulation.&#13;
In this thesis, we build high fidelity simulation tools to identify system bottleneck, quantitatively predict the benefit and cost of a policy, and discovery knowledge for a better understanding of the complex ED system. The agentbased model and simulation technique provides a flexible way to study ED operations as it predicts the systemlevel behavior from micro-level interactions, so as to see the forest through the trees. In this way, policies such as staffing could be changed and the effect on parameters such as waiting times and throughput could be quantified.&#13;
Here, we use agent-based model and simulation techniques to model the interaction of ED components (i.e, patient, nurse, doctor, equipment etc.). We then applied high performance computing techniques to execute the model and analyze simulation results. In summary, armed with the ability to execute a compute-intensive model and analyze huge datasets, the overall goal of this study is to develop tools to better understand the complexity (explain), evaluate policy (predict) and improve efficiencies (optimize) of ED units.</dc:description>
</entry>
<entry>
<title>Write management mechanisms for systems with non-volatile memory technologies</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59993" rel="alternate"/>
<author>
<name>Rodríguez Rodríguez, Roberto Alonso</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59993</id>
<updated>2019-06-24T04:03:33Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Revision
Journal of Computer Science &amp; Technology; vol. 17, no. 1
Since the beginning of computer systems, the memory subsystem has always been one of their essential components. However, the different pace of change between microprocessor and memory has become one of the greatest challenges that current designers have to address in order to develop more powerful computer systems.&#13;
This problem, called memory gap, is further compounded by the limited scalability and the high energy consumption of conventional memory technologies (DRAM and SRAM), which has leaded to consider new nonvolatile memory (NVM) technologies as potential candidates to replace them. Among NVMs, PCM and STTRAM are currently postulated as the best alternatives.&#13;
Although PCM and STT-RAM have significant advantages over DRAM and SRAM, they also suffer from some drawbacks that need to be mitigated before they can both be employed as memory technologies for the next computers generation. Notably, the slow and energy-hungry write operations on both technologies, and the limited endurance of PCM cells, which become unchangeable after performing a relatively reduced amount of writes on them, are the main constraints of PCM and STT-RAM technologies. This thesis presents two proposals aimed to efficiently manage the write operations on this kind of memories.
Es revisión de: http://repositorio.conicit.go.cr:8080/xmlui/handle/123456789/207; Resumen de la tesis presentada por el autor para obtener el título de Doctor en Ingeniería Informática (Universidad Complutense de Madrid, España).
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>Since the beginning of computer systems, the memory subsystem has always been one of their essential components. However, the different pace of change between microprocessor and memory has become one of the greatest challenges that current designers have to address in order to develop more powerful computer systems.&#13;
This problem, called memory gap, is further compounded by the limited scalability and the high energy consumption of conventional memory technologies (DRAM and SRAM), which has leaded to consider new nonvolatile memory (NVM) technologies as potential candidates to replace them. Among NVMs, PCM and STTRAM are currently postulated as the best alternatives.&#13;
Although PCM and STT-RAM have significant advantages over DRAM and SRAM, they also suffer from some drawbacks that need to be mitigated before they can both be employed as memory technologies for the next computers generation. Notably, the slow and energy-hungry write operations on both technologies, and the limited endurance of PCM cells, which become unchangeable after performing a relatively reduced amount of writes on them, are the main constraints of PCM and STT-RAM technologies. This thesis presents two proposals aimed to efficiently manage the write operations on this kind of memories.</dc:description>
</entry>
<entry>
<title>Wild Cetacea Identification using Image Metadata</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59992" rel="alternate"/>
<author>
<name>Pollicelli, Débora</name>
</author>
<author>
<name>Coscarella, Mariano</name>
</author>
<author>
<name>Delrieux, Claudio</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59992</id>
<updated>2019-06-24T04:03:31Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
Identification of individuals in marine species, especially in Cetacea, is a critical task in several biological and ecological endeavours. Most of the times this is performed through human-assisted matching within a set of pictures taken in different campaigns during several years and spread around wide geographical regions. This requires that the scientists perform laborious tasks in searching through archives of images, demanding a significant cognitive burden which may be prone to intra- and interobserver operational errors. On the other hand, additional available information, in particular the metadata associated to every image, is not fully taken advantage of. The present work presents the result of applying machine learning techniques over the metadata of archives of images as an aid in the process of manual identification.&#13;
The method was tested on a database containing several pictures of 223 different Commerson’s dolphins (Cephalorhynchus commersoni) taken over a span of seven years. A supervised classifier trained with identifications made by the researchers was able to identify correctly above 90% of the individuals on the test set using only the metadata present in the image files. This reduces significantly the number of images to be manually compared, and therefore the time and errors associated with the assisted identification process.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>Identification of individuals in marine species, especially in Cetacea, is a critical task in several biological and ecological endeavours. Most of the times this is performed through human-assisted matching within a set of pictures taken in different campaigns during several years and spread around wide geographical regions. This requires that the scientists perform laborious tasks in searching through archives of images, demanding a significant cognitive burden which may be prone to intra- and interobserver operational errors. On the other hand, additional available information, in particular the metadata associated to every image, is not fully taken advantage of. The present work presents the result of applying machine learning techniques over the metadata of archives of images as an aid in the process of manual identification.&#13;
The method was tested on a database containing several pictures of 223 different Commerson’s dolphins (Cephalorhynchus commersoni) taken over a span of seven years. A supervised classifier trained with identifications made by the researchers was able to identify correctly above 90% of the individuals on the test set using only the metadata present in the image files. This reduces significantly the number of images to be manually compared, and therefore the time and errors associated with the assisted identification process.</dc:description>
</entry>
<entry>
<title>Fuzzy Control of a Germination Chamber</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59991" rel="alternate"/>
<author>
<name>Marinelli, Marcelo</name>
</author>
<author>
<name>Acosta, Nelson</name>
</author>
<author>
<name>Toloza, Juan Manuel</name>
</author>
<author>
<name>Kornuta, Carlos</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59991</id>
<updated>2019-06-24T04:03:27Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
The design of a fuzzy control system for a germination chamber for hydroponic crops is presented. The system measures humidity and temperature inside the chamber and, by means of a Sugeno type fuzzy controller embedded in an Arduino board, it generates control signals that are sent to a forced ventilation system and to the artificial lighting control system. Experiences were carried out with a germination chamber using this fuzzy control system. Lettuce seeds were sowed in the fuzzy control chamber and on a conventional culture tray, with the former yielding better growth results.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>The design of a fuzzy control system for a germination chamber for hydroponic crops is presented. The system measures humidity and temperature inside the chamber and, by means of a Sugeno type fuzzy controller embedded in an Arduino board, it generates control signals that are sent to a forced ventilation system and to the artificial lighting control system. Experiences were carried out with a germination chamber using this fuzzy control system. Lettuce seeds were sowed in the fuzzy control chamber and on a conventional culture tray, with the former yielding better growth results.</dc:description>
</entry>
<entry>
<title>Analysis of a GPU implementation of Viola-Jones’ Algorithm for Features Selection</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59990" rel="alternate"/>
<author>
<name>Lescano, Germán Ezequiel</name>
</author>
<author>
<name>Santana Mansilla, Pablo</name>
</author>
<author>
<name>Costaguta, Rosanna</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59990</id>
<updated>2019-06-24T04:03:25Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
Faces and facial expressions recognition is an interesting topic for researchers in machine vision.&#13;
Viola-Jones algorithm is the most spread algorithm for this task. Building a classification model for face recognition can take many years if the implementation of its training phase is not optimized.&#13;
In this study, we analyze different implementations for the training phase. The aim was to reduce the time needed during training phase when using one computer with a cheap graphical processing unit (GPU). The execution times were analyzed and compared with previous studies. Results showed that combining C language, CUDA, etc., it is possible to reach acceptable times for training phase. Further research may involve the measurement of the performance of our approach computers with better GPU capacity and exploring a multi-GPU approach.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>Faces and facial expressions recognition is an interesting topic for researchers in machine vision.&#13;
Viola-Jones algorithm is the most spread algorithm for this task. Building a classification model for face recognition can take many years if the implementation of its training phase is not optimized.&#13;
In this study, we analyze different implementations for the training phase. The aim was to reduce the time needed during training phase when using one computer with a cheap graphical processing unit (GPU). The execution times were analyzed and compared with previous studies. Results showed that combining C language, CUDA, etc., it is possible to reach acceptable times for training phase. Further research may involve the measurement of the performance of our approach computers with better GPU capacity and exploring a multi-GPU approach.</dc:description>
</entry>
<entry>
<title>Robotics Based Strategies to Support Computational Thinking: The Case of the Pascual Bravo Industrial Technical Institute</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59989" rel="alternate"/>
<author>
<name>García, Maritza A.</name>
</author>
<author>
<name>Deco, Claudia</name>
</author>
<author>
<name>Collazos, César A.</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59989</id>
<updated>2019-06-24T04:03:23Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
At present there are different public and private companies that support the Colombian government in the initiative of taking the technological processes and of research and innovation to the classrooms in order to generate a knowledge that propitiates great changes in the society and that at the same time helps to mitigate some national problematic. This generates great changes inside the school and the student, achieving significant learning in various areas of knowledge such as environmental, physical, electronic, mathematics, programming, and mechanics, among others. This article presents some strategies, such as robotics clubs, and how their problem-based teaching methodology collaborates in the development of competences of various types and the achievement of computational thinking in students. In addition, mention is made of the results of the project developed at the Pascual Bravo Industrial Technical Institute in Medellin-Colombia, which was presented at the XXII CACIC Congress in Argentina.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>At present there are different public and private companies that support the Colombian government in the initiative of taking the technological processes and of research and innovation to the classrooms in order to generate a knowledge that propitiates great changes in the society and that at the same time helps to mitigate some national problematic. This generates great changes inside the school and the student, achieving significant learning in various areas of knowledge such as environmental, physical, electronic, mathematics, programming, and mechanics, among others. This article presents some strategies, such as robotics clubs, and how their problem-based teaching methodology collaborates in the development of competences of various types and the achievement of computational thinking in students. In addition, mention is made of the results of the project developed at the Pascual Bravo Industrial Technical Institute in Medellin-Colombia, which was presented at the XXII CACIC Congress in Argentina.</dc:description>
</entry>
<entry>
<title>Web Information Retrieval System for Technological Forecasting</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59988" rel="alternate"/>
<author>
<name>Montiel, Raúl</name>
</author>
<author>
<name>Lezcano Airaldi, Luis</name>
</author>
<author>
<name>Favret, Fabián</name>
</author>
<author>
<name>Eckert, Karina</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59988</id>
<updated>2019-06-24T04:03:21Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
Technological Forecasting and Competitive Intelligence are two different disciplines that, used together, provide the organizations with an invaluable analytic tool for the environment and the competing companies’ behavior. This kind of technology can be used for extracting useful information to make strategic decisions. This paper describes a Web mining system which gathers the users’ information requirements through a series of guided questions, constructs various search keys with the answers and uses them to perform a continuous search and analysis process by means of several web search engines and different information retrieval algorithms to score the relevance of the documents obtained. These documents are later presented to the user as an aid in the decision making process. After the description, the system was tested in several scenarios and the obtained results are shown and discussed.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>Technological Forecasting and Competitive Intelligence are two different disciplines that, used together, provide the organizations with an invaluable analytic tool for the environment and the competing companies’ behavior. This kind of technology can be used for extracting useful information to make strategic decisions. This paper describes a Web mining system which gathers the users’ information requirements through a series of guided questions, constructs various search keys with the answers and uses them to perform a continuous search and analysis process by means of several web search engines and different information retrieval algorithms to score the relevance of the documents obtained. These documents are later presented to the user as an aid in the decision making process. After the description, the system was tested in several scenarios and the obtained results are shown and discussed.</dc:description>
</entry>
<entry>
<title>Black-Box Testing Technique for Information Visualization. Sequencing Constraints with Low-Level Interactions</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59980" rel="alternate"/>
<author>
<name>Larrea, Martín Leonardo</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59980</id>
<updated>2019-06-24T04:03:19Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
The software development process has matured significantly over the past decade. We are currently in a state where the need for the verification and validation of the product under development is unquestionable. Visualizations, as software products, must go through such verification and validation control. At the implementation level, a visualization software is no different from any other software, its source code can be verified and validated by using any available white-box technique. The usability studies and controlled experiments are helpful to understand how the user perceives and uses the visualization. However, at an interaction level, a visualization software is not like any other software. Most interactions on a traditional software, are based on buttons and text fields while on a visualization, the interactions are mostly based on zooming, selecting and filtering visual elements. The black-box techniques found in the literature, also known as functional tests, are not suitable for this context. This paper describes a black-box technique tailored for information visualization implementations. The technique is built on constraints imposed over the sequences of low-level interactions available in the visualization and the User Action Notation.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>The software development process has matured significantly over the past decade. We are currently in a state where the need for the verification and validation of the product under development is unquestionable. Visualizations, as software products, must go through such verification and validation control. At the implementation level, a visualization software is no different from any other software, its source code can be verified and validated by using any available white-box technique. The usability studies and controlled experiments are helpful to understand how the user perceives and uses the visualization. However, at an interaction level, a visualization software is not like any other software. Most interactions on a traditional software, are based on buttons and text fields while on a visualization, the interactions are mostly based on zooming, selecting and filtering visual elements. The black-box techniques found in the literature, also known as functional tests, are not suitable for this context. This paper describes a black-box technique tailored for information visualization implementations. The technique is built on constraints imposed over the sequences of low-level interactions available in the visualization and the User Action Notation.</dc:description>
</entry>
<entry>
<title>Towards Information Quality Assurance in Spanish: Wikipedia</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59979" rel="alternate"/>
<author>
<name>Ferretti, Edgardo</name>
</author>
<author>
<name>Soria, Matías</name>
</author>
<author>
<name>Pérez Casseignau, Sebastián</name>
</author>
<author>
<name>Pohn, Lian</name>
</author>
<author>
<name>Urquiza, Guido</name>
</author>
<author>
<name>Gómez, Sergio Alejandro</name>
</author>
<author>
<name>Errecalde, Marcelo Luis</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59979</id>
<updated>2019-06-24T04:03:15Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
Featured Articles (FA) are considered to be the best articles that Wikipedia has to offer and in the last years, researchers have found interesting to analyze whether and how they can be distinguished from “ordinary” articles. Likewise, identifying what issues have to be enhanced or fixed in ordinary articles in order to improve their quality is a recent key research trend. Most of the approaches developed to face these information quality problems have been proposed for the English Wikipedia. However, few efforts have been accomplished in Spanish Wikipedia, despite being Spanish, one of the most spoken languages in the world by native speakers. In this respect, we present a breakdown of Spanish Wikipedia’s quality flaw structure. Besides, we carry out studies with three different corpora to automatically assess information quality in Spanish Wikipedia, where FA identification is evaluated as a binary classification task. Our evaluation on a unified setting allows to compare with the English version, the performance achieved by our approach on the Spanish version. The best results obtained show that FA identification in Spanish, can be performed with an F1 score of 0.88 using a document model consisting of only twenty six features and Support Vector Machine as classification algorithm.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>Featured Articles (FA) are considered to be the best articles that Wikipedia has to offer and in the last years, researchers have found interesting to analyze whether and how they can be distinguished from “ordinary” articles. Likewise, identifying what issues have to be enhanced or fixed in ordinary articles in order to improve their quality is a recent key research trend. Most of the approaches developed to face these information quality problems have been proposed for the English Wikipedia. However, few efforts have been accomplished in Spanish Wikipedia, despite being Spanish, one of the most spoken languages in the world by native speakers. In this respect, we present a breakdown of Spanish Wikipedia’s quality flaw structure. Besides, we carry out studies with three different corpora to automatically assess information quality in Spanish Wikipedia, where FA identification is evaluated as a binary classification task. Our evaluation on a unified setting allows to compare with the English version, the performance achieved by our approach on the Spanish version. The best results obtained show that FA identification in Spanish, can be performed with an F1 score of 0.88 using a document model consisting of only twenty six features and Support Vector Machine as classification algorithm.</dc:description>
</entry>
<entry>
<title>Analysis of Methods for Generating Classification Rules Applicable to Credit Risk</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59978" rel="alternate"/>
<author>
<name>Jimbo Santana, Patricia</name>
</author>
<author>
<name>Villa Monte, Augusto</name>
</author>
<author>
<name>Rucci, Enzo</name>
</author>
<author>
<name>Lanzarini, Laura Cristina</name>
</author>
<author>
<name>Fernández Bariviera, Aurelio</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59978</id>
<updated>2019-06-24T04:03:12Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
Credit risk is defined as the probability of loss due to non-compliance by the borrower with the required payments in relation to any type of debt. When financial institutions select their customers correctly, they can reduce their credit risk.&#13;
To achieve this, they use various classification methodologies to sort customers based on their risk, analyzing a set of variables such as reputation, leverage, income and so forth. The extensive analysis and processing of these variables is quite time-consuming, partly because the data to be analyzed are not homogeneous. In this paper, we present an alternative method that operates on nominal and numeric attributes, which allows obtaining a predictive model that uses a reduced set of classification rules aimed at reducing credit risk.&#13;
When the number of rules used decreases, credit analysts need less time to make their decisions, which will also result in better customer service.&#13;
The methodology proposed here was applied to two databases of the UCI repository and two real databases of Ecuadorian banks that grant various types of credit. The results obtained have been satisfactory. Finally, our conclusions are discussed and future research lines are suggested.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>Credit risk is defined as the probability of loss due to non-compliance by the borrower with the required payments in relation to any type of debt. When financial institutions select their customers correctly, they can reduce their credit risk.&#13;
To achieve this, they use various classification methodologies to sort customers based on their risk, analyzing a set of variables such as reputation, leverage, income and so forth. The extensive analysis and processing of these variables is quite time-consuming, partly because the data to be analyzed are not homogeneous. In this paper, we present an alternative method that operates on nominal and numeric attributes, which allows obtaining a predictive model that uses a reduced set of classification rules aimed at reducing credit risk.&#13;
When the number of rules used decreases, credit analysts need less time to make their decisions, which will also result in better customer service.&#13;
The methodology proposed here was applied to two databases of the UCI repository and two real databases of Ecuadorian banks that grant various types of credit. The results obtained have been satisfactory. Finally, our conclusions are discussed and future research lines are suggested.</dc:description>
</entry>
<entry>
<title>Hybrid-Parallel Uncertainty Reduction Method Applied to Forest Fire Spread Prediction</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59977" rel="alternate"/>
<author>
<name>Méndez Garabetti, Miguel</name>
</author>
<author>
<name>BIanchini, Germán</name>
</author>
<author>
<name>Tardivo, María Laura</name>
</author>
<author>
<name>Caymes Scutari, Paola</name>
</author>
<author>
<name>Gil Costa, Graciela Verónica</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59977</id>
<updated>2019-06-24T04:03:08Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
Fire behavior prediction can be a fundamental tool to reduce losses and damages in emergency situations. However, this process is often complex and affected by the existence of uncertainty. For this reason, from different areas of science, several methods and systems are developed and refined to reduce the effects of uncertainty In this paper we present the Hybrid Evolutionary-Statistical System with Island Model (HESS-IM). It is a hybrid uncertainty reduction method applied to forest fire spread prediction that combines the advantages of two evolutionary population metaheuristics: Evolutionary Algorithms and Differential Evolution. We evaluate the HESS-IM with three controlled fires scenarios, and we obtained favorable results compared to the previous methods in the literature.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>Fire behavior prediction can be a fundamental tool to reduce losses and damages in emergency situations. However, this process is often complex and affected by the existence of uncertainty. For this reason, from different areas of science, several methods and systems are developed and refined to reduce the effects of uncertainty In this paper we present the Hybrid Evolutionary-Statistical System with Island Model (HESS-IM). It is a hybrid uncertainty reduction method applied to forest fire spread prediction that combines the advantages of two evolutionary population metaheuristics: Evolutionary Algorithms and Differential Evolution. We evaluate the HESS-IM with three controlled fires scenarios, and we obtained favorable results compared to the previous methods in the literature.</dc:description>
</entry>
<entry>
<title>WSNs Data and Configuration Management in Sensor Clouds with Cloud File Synchronization Services</title>
<link href="http://sedici.unlp.edu.ar:80/handle/10915/59976" rel="alternate"/>
<author>
<name>Iacono, Lucas</name>
</author>
<author>
<name>García Garino, Carlos</name>
</author>
<author>
<name>Marianetti, Osvaldo</name>
</author>
<author>
<name>Párraga, Cristina</name>
</author>
<id>http://sedici.unlp.edu.ar:80/handle/10915/59976</id>
<updated>2019-06-24T04:03:05Z</updated>
<published>2017-04-01T00:00:00Z</published>
<summary type="text">Articulo
Journal of Computer Science &amp; Technology; vol. 17, no. 1
Sensor Clouds have opened new possibilities for researchers of disciplines such as environmental monitoring, precision agriculture and flood prevention.&#13;
This technology uses Wireless Sensor Networks (WSNs) to collect real world data and Cloud Computing to store and process them. The remote management of WSNs setup and data in Sensor Clouds implies: real time access to collected data, sensor setup reconfiguration and sensor battery status monitoring. Currently there are different platforms for WSNs data and setup management in Sensor Clouds. Generally, these platforms require that scientists of the mentioned disciplines must have knowledge of WSNs and web services programming in order to reconfigure the sensors setup. Hence, these sensing resources can not be provided in a transparent way to end-users. In this paper, we propose the use of standard Cloud File Synchronization Services (CFSS) for carrying out the full management of WSNs in Sensor Clouds. In order to validate our proposal, we conduct experiments using a Sensor Cloud platform based on CFSS called Sensor Cirrus.
</summary>
<dc:date>2017-04-01T00:00:00Z</dc:date>
<dc:description>Sensor Clouds have opened new possibilities for researchers of disciplines such as environmental monitoring, precision agriculture and flood prevention.&#13;
This technology uses Wireless Sensor Networks (WSNs) to collect real world data and Cloud Computing to store and process them. The remote management of WSNs setup and data in Sensor Clouds implies: real time access to collected data, sensor setup reconfiguration and sensor battery status monitoring. Currently there are different platforms for WSNs data and setup management in Sensor Clouds. Generally, these platforms require that scientists of the mentioned disciplines must have knowledge of WSNs and web services programming in order to reconfigure the sensors setup. Hence, these sensing resources can not be provided in a transparent way to end-users. In this paper, we propose the use of standard Cloud File Synchronization Services (CFSS) for carrying out the full management of WSNs in Sensor Clouds. In order to validate our proposal, we conduct experiments using a Sensor Cloud platform based on CFSS called Sensor Cirrus.</dc:description>
</entry>
</feed>
