Pub Date : 2019-09-01DOI: 10.1109/CLEI47609.2019.235079
Santiago Gonzalez-Toral, Renán Freire, R. Gualán, Víctor Saquicela
Traditionally most of the steps involved in a Systematic Literature Review (SLR) process are manually executed, causing inconvenience of time and effort, given the massive amount of primary studies available online. This has motivated a lot of research focused on automating the process. Current state-of-the-art methods combine active learning methods and manual selection of primary studies from a smaller set so they can maximize the finding of relevant papers while at the same time minimizing the number of manually reviewed papers. In this work, we propose a novel strategy to further improve these methods whose early success heavily depends on an effective selection of initial papers to be read by researchers using a PCAbased method which combines different document representation and similarity metric approaches to cluster and rank the content within the corpus related to an enriched representation of research questions within the SLR protocol. Validation was carried out over four publicly available data sets corresponding to SLR studies from the Software Engineering domain. The proposed model proved to be more efficient than a BM25 baseline model as a mechanism to select the initial set of relevant primary studies within the top 100 rank, which makes it a promising method to bootstrap an active learning cycle.
{"title":"A ranking-based approach for supporting the initial selection of primary studies in a Systematic Literature Review","authors":"Santiago Gonzalez-Toral, Renán Freire, R. Gualán, Víctor Saquicela","doi":"10.1109/CLEI47609.2019.235079","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235079","url":null,"abstract":"Traditionally most of the steps involved in a Systematic Literature Review (SLR) process are manually executed, causing inconvenience of time and effort, given the massive amount of primary studies available online. This has motivated a lot of research focused on automating the process. Current state-of-the-art methods combine active learning methods and manual selection of primary studies from a smaller set so they can maximize the finding of relevant papers while at the same time minimizing the number of manually reviewed papers. In this work, we propose a novel strategy to further improve these methods whose early success heavily depends on an effective selection of initial papers to be read by researchers using a PCAbased method which combines different document representation and similarity metric approaches to cluster and rank the content within the corpus related to an enriched representation of research questions within the SLR protocol. Validation was carried out over four publicly available data sets corresponding to SLR studies from the Software Engineering domain. The proposed model proved to be more efficient than a BM25 baseline model as a mechanism to select the initial set of relevant primary studies within the top 100 rank, which makes it a promising method to bootstrap an active learning cycle.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130645351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/CLEI47609.2019.235112
Rogério Dias Moreira, P. S. Barreto
This article describes a framework proposal for the cold start problem in Function-as-a-service (FaaS). The proposed framework has the goal to reduce the execution time and is presented as a prototype implemented that was evaluated with two different experimental scenarios and compared with a commercial proposal, the FaaS AWS Lambda from Amazon. The results show that the proposed framework may be considered a solution for the cold start problem and may improve the performance for applications that require a low response time.
{"title":"A Framework for Improving Cold Start Time in Function-as-a-service (FaaS)","authors":"Rogério Dias Moreira, P. S. Barreto","doi":"10.1109/CLEI47609.2019.235112","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235112","url":null,"abstract":"This article describes a framework proposal for the cold start problem in Function-as-a-service (FaaS). The proposed framework has the goal to reduce the execution time and is presented as a prototype implemented that was evaluated with two different experimental scenarios and compared with a commercial proposal, the FaaS AWS Lambda from Amazon. The results show that the proposed framework may be considered a solution for the cold start problem and may improve the performance for applications that require a low response time.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125842193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/clei47609.2019.9073955
{"title":"CLEI 2019 Program Committee","authors":"","doi":"10.1109/clei47609.2019.9073955","DOIUrl":"https://doi.org/10.1109/clei47609.2019.9073955","url":null,"abstract":"","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"159 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127342567","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/CLEI47609.2019.235109
Gerardo Riveros, Pedro Pablo Cespedes Sanchez, D. Pinto, H. Legal-Ayala
Software defined networking (SDN) is an emerging technology based on the separation of the control plane and the data plane. This allows to obtain benefits, in comparison with traditional networks, in terms of network management, global monitoring-control, cost reduction, and in particular the energy saving by the strategic activation of devices. In this paper, we propose an approach that seeks to minimize the global energy consumption of the network by suspending inactive devices, such as chassis and line cards, as well as limiting the use of links in traffic sessions. For this purpose, we developed an Integer Linear Programming (ILP) model for the SDN routing problem in order to obtain the minimum energy consumption, subject to satisfy all traffic demands. The experimental results on two network topologies for a set of static traffic requests indicate that the proposed model is promising, saving up to 42% of the global energy consumption obtaining a better performance to the models proposed in the literature. On the other hand, the experimental results for incremental semi-dynamic traffic indicate that the performance of the optimization with re-routing improves the approach without re-routing when increasing the traffic in the network, but this improvement is not always perceptible. The approach without re-routing in terms of scalability is promising, by increasing the traffic load not generate interruptions to the traffic already attended and affect the quality of the service.
{"title":"ILP-based Energy Saving Routing for Software Defined Networking","authors":"Gerardo Riveros, Pedro Pablo Cespedes Sanchez, D. Pinto, H. Legal-Ayala","doi":"10.1109/CLEI47609.2019.235109","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235109","url":null,"abstract":"Software defined networking (SDN) is an emerging technology based on the separation of the control plane and the data plane. This allows to obtain benefits, in comparison with traditional networks, in terms of network management, global monitoring-control, cost reduction, and in particular the energy saving by the strategic activation of devices. In this paper, we propose an approach that seeks to minimize the global energy consumption of the network by suspending inactive devices, such as chassis and line cards, as well as limiting the use of links in traffic sessions. For this purpose, we developed an Integer Linear Programming (ILP) model for the SDN routing problem in order to obtain the minimum energy consumption, subject to satisfy all traffic demands. The experimental results on two network topologies for a set of static traffic requests indicate that the proposed model is promising, saving up to 42% of the global energy consumption obtaining a better performance to the models proposed in the literature. On the other hand, the experimental results for incremental semi-dynamic traffic indicate that the performance of the optimization with re-routing improves the approach without re-routing when increasing the traffic in the network, but this improvement is not always perceptible. The approach without re-routing in terms of scalability is promising, by increasing the traffic load not generate interruptions to the traffic already attended and affect the quality of the service.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130204282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/CLEI47609.2019.235097
Anié Bermudez Peña, G. F. Castro, D. M. L. Alvarez, I. M. Alcivar, Giselle Lorena Núñez Núñez, Danny Saavedra Cevallos, Jorge Luis Zambrano Santa
To support decision-making, organizations employ dissimilar tools during their projects execution control. However, they are still insufficient in environments with uncertain information and changing conditions in management styles. Deficiencies in systems for controlling the projects execution, affects the quality of their classification in aiding decision-making. An alternative solution is the introduction of soft computing techniques, which provide robustness, efficiency and adaptability at tools. This research proposes a method for project execution control based on soft computing and machine learning, which contributes to improve the project management. The proposed method allows the machine learning and adjusting of fuzzy inference systems to the project evaluation. The results are obtained from the execution of seven algorithms, which are based on space partitioning, neural networks, gradient descent and genetic algorithms. Validation of the proposed system, integrated to a project management tool, ratifies an improvement in the quality of project evaluation. The obtained result provides a contribution to the perfection of tools to support the decision-making in project management organization
{"title":"Method for Project Execution Control based on Soft Computing and Machine Learning","authors":"Anié Bermudez Peña, G. F. Castro, D. M. L. Alvarez, I. M. Alcivar, Giselle Lorena Núñez Núñez, Danny Saavedra Cevallos, Jorge Luis Zambrano Santa","doi":"10.1109/CLEI47609.2019.235097","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235097","url":null,"abstract":"To support decision-making, organizations employ dissimilar tools during their projects execution control. However, they are still insufficient in environments with uncertain information and changing conditions in management styles. Deficiencies in systems for controlling the projects execution, affects the quality of their classification in aiding decision-making. An alternative solution is the introduction of soft computing techniques, which provide robustness, efficiency and adaptability at tools. This research proposes a method for project execution control based on soft computing and machine learning, which contributes to improve the project management. The proposed method allows the machine learning and adjusting of fuzzy inference systems to the project evaluation. The results are obtained from the execution of seven algorithms, which are based on space partitioning, neural networks, gradient descent and genetic algorithms. Validation of the proposed system, integrated to a project management tool, ratifies an improvement in the quality of project evaluation. The obtained result provides a contribution to the perfection of tools to support the decision-making in project management organization","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129124409","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/CLEI47609.2019.9089044
V. Machado, Paulo Afonso Parreira Júnior, H. Costa
The software industry is continuously growing, and projects need to be planned to have a better chance of success. But, planning errors in a project can cause the project to fail. These errors, when there is damage/loss or gain, are called risks and need to be managed. Inadequate risk management can lead to project failure. Therefore, risk management in software design is crucial to its success. In this paper, through research in the literature, catalogs of risks that may occur during the development of software projects are presented. Besides, there are measures defined/identified in the literature to support decision making by project managers, using the GQM method.
{"title":"Risk Catalogs in Software Project Management","authors":"V. Machado, Paulo Afonso Parreira Júnior, H. Costa","doi":"10.1109/CLEI47609.2019.9089044","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.9089044","url":null,"abstract":"The software industry is continuously growing, and projects need to be planned to have a better chance of success. But, planning errors in a project can cause the project to fail. These errors, when there is damage/loss or gain, are called risks and need to be managed. Inadequate risk management can lead to project failure. Therefore, risk management in software design is crucial to its success. In this paper, through research in the literature, catalogs of risks that may occur during the development of software projects are presented. Besides, there are measures defined/identified in the literature to support decision making by project managers, using the GQM method.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116852859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/CLEI47609.2019.235076
L. Esnaola, Juan Pablo Tessore, Hugo Ramón, C. Russo
The language present in the context of social networks is usually more informal than the one used in traditional sources. The researches that take such content as input for machine learning based classifying algorithms, perform, as a first step, a cleaning and standardization process. The goal of the latter is to improve the accuracy of the classification. In this paper, several cleaning tasks are defined and executed over a dataset of comments extracted from the social network Facebook. The goal is to verify if the corrections, made by such tasks, produce a significant improvement in the accuracy reached by the classifying algorithms. The results obtained, indicate that, over this type of dataset, preprocessing tasks with a reasonably good performance in the correction of errors, do not necessarily produce a noteworthy improvement in the classification accuracy reached by the algorithms.
{"title":"Effectiveness of preprocessing techniques over social media texts for the improvement of machine learning based classifiers","authors":"L. Esnaola, Juan Pablo Tessore, Hugo Ramón, C. Russo","doi":"10.1109/CLEI47609.2019.235076","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235076","url":null,"abstract":"The language present in the context of social networks is usually more informal than the one used in traditional sources. The researches that take such content as input for machine learning based classifying algorithms, perform, as a first step, a cleaning and standardization process. The goal of the latter is to improve the accuracy of the classification. In this paper, several cleaning tasks are defined and executed over a dataset of comments extracted from the social network Facebook. The goal is to verify if the corrections, made by such tasks, produce a significant improvement in the accuracy reached by the classifying algorithms. The results obtained, indicate that, over this type of dataset, preprocessing tasks with a reasonably good performance in the correction of errors, do not necessarily produce a noteworthy improvement in the classification accuracy reached by the algorithms.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126925051","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/CLEI47609.2019.235070
Rosinei Cristiano Pereira, F. Lopes
Data are generated in several contexts, by various devices, and are collected by organizations whose aims to obtain as much information as possible to add value to their business. There are plenty of ethical and non-ethical purposes involved such as identifying consumers' needs and then recommend products and services, developing new business, conducting health-related research in order to reduce medical errors, assessing risk of people developing diseases, so on. The organizations’ concerns about risks associated to potential privacy leaks and their impacts have increased dramatically. Thus, apply data mining in process optimization without compromising sensitive data and provide a strong privacy standard are challenges imposed to data stewards, who use techniques and privacy models during data release process. This study aims to propose a classification decision tree application, developed under the Differential Privacy model definition, whose architecture was designed according to the interactive data release model that deploys a barrier to forbid users to have access data in their raw format. In addition, a self-tuning feature that controls the forest growth was put in place, resulting in a better classification performance if compared to the adoption of a fixed amount of trees in the forest. However, there was an increase in processing time. It also was observed in most of the datasets used in the experiment that beyond a threshold the classification performance is reduced by increasing the number of trees that compose the forest.
{"title":"An architectural proposal for the interactive publication of the data classification obtained through a Differentially Private Random Decision Forest","authors":"Rosinei Cristiano Pereira, F. Lopes","doi":"10.1109/CLEI47609.2019.235070","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235070","url":null,"abstract":"Data are generated in several contexts, by various devices, and are collected by organizations whose aims to obtain as much information as possible to add value to their business. There are plenty of ethical and non-ethical purposes involved such as identifying consumers' needs and then recommend products and services, developing new business, conducting health-related research in order to reduce medical errors, assessing risk of people developing diseases, so on. The organizations’ concerns about risks associated to potential privacy leaks and their impacts have increased dramatically. Thus, apply data mining in process optimization without compromising sensitive data and provide a strong privacy standard are challenges imposed to data stewards, who use techniques and privacy models during data release process. This study aims to propose a classification decision tree application, developed under the Differential Privacy model definition, whose architecture was designed according to the interactive data release model that deploys a barrier to forbid users to have access data in their raw format. In addition, a self-tuning feature that controls the forest growth was put in place, resulting in a better classification performance if compared to the adoption of a fixed amount of trees in the forest. However, there was an increase in processing time. It also was observed in most of the datasets used in the experiment that beyond a threshold the classification performance is reduced by increasing the number of trees that compose the forest.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"327 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123509118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：