Pub Date : 2019-09-01DOI: 10.1109/CLEI47609.2019.235088
Christian Mendes, L. Almeida, Carlo Moro, Douglas Soares
This paper presents the implementation of the new Meteorological Alert Service of the State of Paraná, using an international protocol. The service is a mobile application integrated with government services, the Fire Department and Civil Defense of Paraná. The main objective of the implemented software is the dissemination of useful meteorological alerts for citizens, making it available on their mobile devices, regardless of the access location.
{"title":"Fire Department System of Paraná - Geolocation for Meteorological Alerts","authors":"Christian Mendes, L. Almeida, Carlo Moro, Douglas Soares","doi":"10.1109/CLEI47609.2019.235088","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235088","url":null,"abstract":"This paper presents the implementation of the new Meteorological Alert Service of the State of Paraná, using an international protocol. The service is a mobile application integrated with government services, the Fire Department and Civil Defense of Paraná. The main objective of the implemented software is the dissemination of useful meteorological alerts for citizens, making it available on their mobile devices, regardless of the access location.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"16 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":"130470501","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/CLEI47609.2019.235095
Daniel Reghin, F. Lopes
Value-at-Risk (VaR) as a risk quantification mechanism has more than one calculation method, one of which is the parametric method. In the bibliographic study, it was identified that the parametric method is not effective for all market moments, such as those of crisis or abrupt changes in behavior. This study, therefore, seeks to verify whether other methods of calculation are more efficient, such as the use of neural networks. This study compared the VaR calculation using the parametric method against the use of Feedforward neural networks and Long Short-Term Memory (LSTM) recurrent networks. It used the B3 São Paulo Stock Exchange, IBOVESPA, as the index of study. For the parametric method, volatility models such as standard deviation, Exponentially Weighted Moving Average (EWMA) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH) were tested. For neural networks, different layers and amounts of neurons, activation functions, use of different predictors and incorporation of macroeconomic data were explored. The result of the experiment showed that LSTM networks had a better performance when comparing the exception rate generated by the entire model. When analyzing periods of crisis or abrupt changes in behavior, LSTM and Feedforward networks were less efficient in predicting VaR compared to the parametric method.
{"title":"Value-at-Risk prediction for the Brazilian stock market: A comparative study between Parametric Method, Feedforward and LSTM Neural Network","authors":"Daniel Reghin, F. Lopes","doi":"10.1109/CLEI47609.2019.235095","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235095","url":null,"abstract":"Value-at-Risk (VaR) as a risk quantification mechanism has more than one calculation method, one of which is the parametric method. In the bibliographic study, it was identified that the parametric method is not effective for all market moments, such as those of crisis or abrupt changes in behavior. This study, therefore, seeks to verify whether other methods of calculation are more efficient, such as the use of neural networks. This study compared the VaR calculation using the parametric method against the use of Feedforward neural networks and Long Short-Term Memory (LSTM) recurrent networks. It used the B3 São Paulo Stock Exchange, IBOVESPA, as the index of study. For the parametric method, volatility models such as standard deviation, Exponentially Weighted Moving Average (EWMA) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH) were tested. For neural networks, different layers and amounts of neurons, activation functions, use of different predictors and incorporation of macroeconomic data were explored. The result of the experiment showed that LSTM networks had a better performance when comparing the exception rate generated by the entire model. When analyzing periods of crisis or abrupt changes in behavior, LSTM and Feedforward networks were less efficient in predicting VaR compared to the parametric method.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"31 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":"129856158","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/CLEI47609.2019.235117
Andrea Delgado, Daniel Calegari
Business Process Management System (BPMS) integrates several software modules to support the business process (BP) lifecycle. A process modeler, process engine, a web portal for interaction with users, and a REST/SOAP API which exposes operations from the engine are key ones. In previous works we have evaluated several BPMS identifying similarities in terms of the concepts they manage in their user portals and the APIs they expose, and how the user portals became highly coupled to the underlying process engine through the provided API. We proposed a generic user portal that makes invocations to a generic API decoupling the portal from the specific process engine it invokes, which can be exchanged through the generic API invocation to different process engines. In this paper we present an extension of this work by adding concepts to the generic API and data model, a comparative analysis between BPMS, as well as the implementation of adapters for three different engines to show its capabilities.
{"title":"A generic BPMS user portal for business processes execution interoperability","authors":"Andrea Delgado, Daniel Calegari","doi":"10.1109/CLEI47609.2019.235117","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235117","url":null,"abstract":"Business Process Management System (BPMS) integrates several software modules to support the business process (BP) lifecycle. A process modeler, process engine, a web portal for interaction with users, and a REST/SOAP API which exposes operations from the engine are key ones. In previous works we have evaluated several BPMS identifying similarities in terms of the concepts they manage in their user portals and the APIs they expose, and how the user portals became highly coupled to the underlying process engine through the provided API. We proposed a generic user portal that makes invocations to a generic API decoupling the portal from the specific process engine it invokes, which can be exchanged through the generic API invocation to different process engines. In this paper we present an extension of this work by adding concepts to the generic API and data model, a comparative analysis between BPMS, as well as the implementation of adapters for three different engines to show its capabilities.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"41 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":"133709242","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/CLEI47609.2019.235106
Javier Meden, Felipe Stuardo, B. Barán
This work presents the implementation of a Resource Optimizer System for a commercial datacenter in Paraguay, which offers cloud services and uses Citrix Hypervisor (XenServer) as virtualization platform. To solve the VMP problem in a real environment, an automatic data collection module was implemented to periodically obtain the status of the datacenter resources. An especially design multi-objective memetic algorithm was also implemented to recommend improvements on the virtual machine placement, when needed. Three objective functions were considered: (1) power consumption minimization, (2) network traffic minimization and (3) economical revenue maximization. Finally, recommendations were applied in the datacenter and measurements of the used resources were made, minimizing power consumption at 29%, minimizing network traffic up to 50% while maintaining to maximum the economical revenue.
{"title":"Multi-objective Optimization for a Commercial Datacenter in Paraguay","authors":"Javier Meden, Felipe Stuardo, B. Barán","doi":"10.1109/CLEI47609.2019.235106","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235106","url":null,"abstract":"This work presents the implementation of a Resource Optimizer System for a commercial datacenter in Paraguay, which offers cloud services and uses Citrix Hypervisor (XenServer) as virtualization platform. To solve the VMP problem in a real environment, an automatic data collection module was implemented to periodically obtain the status of the datacenter resources. An especially design multi-objective memetic algorithm was also implemented to recommend improvements on the virtual machine placement, when needed. Three objective functions were considered: (1) power consumption minimization, (2) network traffic minimization and (3) economical revenue maximization. Finally, recommendations were applied in the datacenter and measurements of the used resources were made, minimizing power consumption at 29%, minimizing network traffic up to 50% while maintaining to maximum the economical revenue.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"27 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":"130068520","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/CLEI47609.2019.235114
Leidy Carvajal-Ortiz, Beatriz Florian-Gaviria, J. F. Díaz
Many higher education institutions spend decades transforming their content-based to competency-based curricula. Furthermore, there is a clear tendency to improve summative to formative assessment, which demonstrates the learning process of students by measuring their learning outcomes. However, combining curriculum design, evaluation, and analysis of competencybased educational processes is a difficult task to implement in practice. For the design, it is necessary to understand a whole conceptual framework, also to comply with restrictions of the University, Faculty and Academic Unit, define clear models and methods for the curricular reform processes. Then, to implement them, technological support is required to make a more detailed evaluation and analysis. The lack of technological tools to support these processes makes it even more difficult. This work shows the work carried out so far in the framework of the curricular reform of the programs of the Faculty of Engineering of the Universidad del Valle and led by the Escuela de Ingeniería de Sistemas y Computación (EISC). In this review of conceptual references for the development of a curriculum management proposal that involves the definition of a curriculum design method supported by a software prototype to manage the processes of curriculum management in the medium term. This paper first shows a systematic review of software models and applications used to support the design, evaluation, and analysis of courses that may be useful in higher education. These models and applications are focused on the design, the formative evaluation by competences and the analysis of the learning outcomes of the students in the learning processes. Second, the elements of the review are identified for the construction of a curriculum design model, including the definition of a new evaluation system that facilitates the analysis of competency-based learning. A particular challenge of this model is to obtain a quantitative grade depending on the detailed evaluation of the student’s learning outcomes. For the EISC, it is also necessary to link the learning objectives of the new curriculum to those proposed by the Computer Science Curricula 2013 (CS2013). Finally, in the future work, the model should serve to produce learning analytics that allows measuring the level of the program and academic unit. Third, the proposed model for EISC curriculum management and advances in the software prototype is presented. Finally, validation is presented at the ESIC, where some proffesors designed their courses using the proposed model.
许多高等教育机构花了几十年的时间将基于内容的课程转变为基于能力的课程。此外，总结性评估有明显的向形成性评估转变的趋势，通过衡量学生的学习成果来展示学生的学习过程。然而，将基于能力的教育过程的课程设计、评估和分析结合起来，在实践中是一项困难的任务。对于设计，有必要了解整个概念框架，也要遵守大学，学院和学术单位的限制，为课程改革过程定义明确的模型和方法。然后，为了实现这些目标，需要技术支持，进行更详细的评估和分析。由于缺乏支持这些过程的技术工具，使其更加困难。这项工作显示了迄今为止在山谷大学工程学院课程改革框架内开展的工作，由Ingeniería de Sistemas y Computación (EISC)领导。本文回顾了课程管理建议的概念参考，包括定义一种由软件原型支持的课程设计方法，以管理中期的课程管理过程。本文首先展示了用于支持课程设计、评估和分析的软件模型和应用程序的系统回顾，这些课程可能在高等教育中有用。这些模型和应用侧重于设计、能力形成性评价和学生在学习过程中的学习成果分析。其次，为构建课程设计模型确定了审查的要素，包括定义一个新的评估系统，以促进对基于能力的学习的分析。这种模式的一个特殊挑战是根据对学生学习成果的详细评估来获得定量评分。对于EISC来说，还需要将新课程的学习目标与《计算机科学课程2013》(CS2013)提出的学习目标联系起来。最后，在未来的工作中，该模型应该用于产生学习分析，允许测量程序和学术单元的水平。第三，介绍了EISC课程管理模型及其软件原型的研究进展。最后，在ESIC上进行了验证，一些教授使用所提出的模型设计了他们的课程。
{"title":"Models, methods and software prototype to support the design, evaluation, and analysis in the curriculum management of competency-based for higher education","authors":"Leidy Carvajal-Ortiz, Beatriz Florian-Gaviria, J. F. Díaz","doi":"10.1109/CLEI47609.2019.235114","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235114","url":null,"abstract":"Many higher education institutions spend decades transforming their content-based to competency-based curricula. Furthermore, there is a clear tendency to improve summative to formative assessment, which demonstrates the learning process of students by measuring their learning outcomes. However, combining curriculum design, evaluation, and analysis of competencybased educational processes is a difficult task to implement in practice. For the design, it is necessary to understand a whole conceptual framework, also to comply with restrictions of the University, Faculty and Academic Unit, define clear models and methods for the curricular reform processes. Then, to implement them, technological support is required to make a more detailed evaluation and analysis. The lack of technological tools to support these processes makes it even more difficult. This work shows the work carried out so far in the framework of the curricular reform of the programs of the Faculty of Engineering of the Universidad del Valle and led by the Escuela de Ingeniería de Sistemas y Computación (EISC). In this review of conceptual references for the development of a curriculum management proposal that involves the definition of a curriculum design method supported by a software prototype to manage the processes of curriculum management in the medium term. This paper first shows a systematic review of software models and applications used to support the design, evaluation, and analysis of courses that may be useful in higher education. These models and applications are focused on the design, the formative evaluation by competences and the analysis of the learning outcomes of the students in the learning processes. Second, the elements of the review are identified for the construction of a curriculum design model, including the definition of a new evaluation system that facilitates the analysis of competency-based learning. A particular challenge of this model is to obtain a quantitative grade depending on the detailed evaluation of the student’s learning outcomes. For the EISC, it is also necessary to link the learning objectives of the new curriculum to those proposed by the Computer Science Curricula 2013 (CS2013). Finally, in the future work, the model should serve to produce learning analytics that allows measuring the level of the program and academic unit. Third, the proposed model for EISC curriculum management and advances in the software prototype is presented. Finally, validation is presented at the ESIC, where some proffesors designed their courses using the proposed model.","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":"122839607","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/CLEI47609.2019.235073
Fábio Reina, A. Luiz, Luciana Rech, Hylson Vescovi Netto, Frank Siqueira
The profusion of the Internet in the daily lives of people and organizations has triggered the production of a highly connected mass data, which encourages the use of non-traditional database technologies. In this context, graph databases have been gaining notoriety, for having facilities regarding the modeling of complex data, as well as for providing better performance on query processing. On the other hand, as it is a relatively new technology, implementations of graph database management systems still lack mechanisms to deal with maintaining data integrity. In this sense, this work introduces a solution for providing integrity (eg, verification and maintenance) of the data stored in a graph database.
{"title":"Providing Data Integrity in Graph Databases","authors":"Fábio Reina, A. Luiz, Luciana Rech, Hylson Vescovi Netto, Frank Siqueira","doi":"10.1109/CLEI47609.2019.235073","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235073","url":null,"abstract":"The profusion of the Internet in the daily lives of people and organizations has triggered the production of a highly connected mass data, which encourages the use of non-traditional database technologies. In this context, graph databases have been gaining notoriety, for having facilities regarding the modeling of complex data, as well as for providing better performance on query processing. On the other hand, as it is a relatively new technology, implementations of graph database management systems still lack mechanisms to deal with maintaining data integrity. In this sense, this work introduces a solution for providing integrity (eg, verification and maintenance) of the data stored in a graph database.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"40 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":"133194013","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/CLEI47609.2019.235090
Paulo Diogo Rodrigues Leão, S. Siqueira
Knowledge communities are composed of individuals who share the same interests and voluntarily work together to expand knowledge and understanding of a domain through learning and sharing. When a user asks a question in a knowledge community, he or she may usually add tags to categorize the question. These tags make it easy for experts to find the question and then answer it. One of the problems with this tagging system is that there is no hierarchy to aid in the search for broader themes. This study proposes a way of hierarchizing the folksonomy of an online knowledge community. In order to verify the applicability of the proposed approach, we used the Stack Exchange’s biology community. Through a crowdsourcing evaluation it was possible to show that the developed approach performed better than other heuristics and it was also possible to identify quality issues on the description of WordNet synsets.
{"title":"Structuring a Folksonomy in a Community of Questions and Answers","authors":"Paulo Diogo Rodrigues Leão, S. Siqueira","doi":"10.1109/CLEI47609.2019.235090","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235090","url":null,"abstract":"Knowledge communities are composed of individuals who share the same interests and voluntarily work together to expand knowledge and understanding of a domain through learning and sharing. When a user asks a question in a knowledge community, he or she may usually add tags to categorize the question. These tags make it easy for experts to find the question and then answer it. One of the problems with this tagging system is that there is no hierarchy to aid in the search for broader themes. This study proposes a way of hierarchizing the folksonomy of an online knowledge community. In order to verify the applicability of the proposed approach, we used the Stack Exchange’s biology community. Through a crowdsourcing evaluation it was possible to show that the developed approach performed better than other heuristics and it was also possible to identify quality issues on the description of WordNet synsets.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"269 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":"116182453","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/CLEI47609.2019.235111
Cristoffer Leite, J. Gondim, P. S. Barreto, Marcos F. Caetano, E. Alchieri
Internet of Things (IoT) is one of the key enabling technologies for an always-connected world and also a main enabler for generating information of interest in various application domains. A growing problem in recent years in this technology is security, as power-constrained devices that are typical of IoT applications may not always provide these implementations properly. These conditions can compromise entire environments and allow malicious agents to take control and perform malicious activities. In this article, we provide a summary of the principal vulnerabilities reported for IoT devices based on the OWASP Internet of Things Project, classified by test routine groups. Using models based on standard architectures to define and detail reproducible verification routines for each test, a selection of independent analyzes of each identified category was performed to ensure more comprehensive and accurate testing. Finally, the proposed routines are performed in a test environment to exemplify and ensure their operation, thus contributing to meeting the demand in the area for more accurate information and to assist in understanding the most common vulnerabilities.
{"title":"Pentest on Internet of Things Devices","authors":"Cristoffer Leite, J. Gondim, P. S. Barreto, Marcos F. Caetano, E. Alchieri","doi":"10.1109/CLEI47609.2019.235111","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235111","url":null,"abstract":"Internet of Things (IoT) is one of the key enabling technologies for an always-connected world and also a main enabler for generating information of interest in various application domains. A growing problem in recent years in this technology is security, as power-constrained devices that are typical of IoT applications may not always provide these implementations properly. These conditions can compromise entire environments and allow malicious agents to take control and perform malicious activities. In this article, we provide a summary of the principal vulnerabilities reported for IoT devices based on the OWASP Internet of Things Project, classified by test routine groups. Using models based on standard architectures to define and detail reproducible verification routines for each test, a selection of independent analyzes of each identified category was performed to ensure more comprehensive and accurate testing. Finally, the proposed routines are performed in a test environment to exemplify and ensure their operation, thus contributing to meeting the demand in the area for more accurate information and to assist in understanding the most common vulnerabilities.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"76 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":"115554086","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/CLEI47609.2019.235091
Daniel González, Libertad Tansini
Recommender Systems are valuable tools which suggest meaningful and useful items to users. In a previous research project, a real recommender system which offers personalized recommendations of items to health professionals and medical specialists in the context of Continuing Medical Education (CME) was designed and developed. Traceability helps recommender systems to generatejustifications about the criteria used for selecting the suggestions of items to the active user. This paper presents a novel approach for modelling traceability in recommender systems in the given context. The proposed approach shows how to use different levels of relationships between users to trace the origin of the recommendations. An important contribution of this research is to explain how to generalize the proposed model of traceability in recommender systems. In addition, an automated approach towards communicating the origin of the recommendations to the users is proposed.
{"title":"Modelling Traceability in Recommender Systems","authors":"Daniel González, Libertad Tansini","doi":"10.1109/CLEI47609.2019.235091","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235091","url":null,"abstract":"Recommender Systems are valuable tools which suggest meaningful and useful items to users. In a previous research project, a real recommender system which offers personalized recommendations of items to health professionals and medical specialists in the context of Continuing Medical Education (CME) was designed and developed. Traceability helps recommender systems to generatejustifications about the criteria used for selecting the suggestions of items to the active user. This paper presents a novel approach for modelling traceability in recommender systems in the given context. The proposed approach shows how to use different levels of relationships between users to trace the origin of the recommendations. An important contribution of this research is to explain how to generalize the proposed model of traceability in recommender systems. In addition, an automated approach towards communicating the origin of the recommendations to the users is proposed.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"10 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":"129336369","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/CLEI47609.2019.235098
M. Falcó, Gabriela Robiolo
Multi-Agent Systems became a powerful solution to model and solve problems in complex and dynamic environments. While research in this area grew exponentially before 2009, there is a need to understand the status quo of the field from 2009 to June 2017 in order to comprehend the general evolution. The results of a SLR related to Multi-Agent Systems, its applications and research gaps, following Kitchenham and Wholin guidelines are presented in this paper. From the analysis of279 papers (out of3522 candidates), our findings suggest that: a) there is a general decreasing trend of publications (but it is increasing for specific domains), b) only 15% of the papers portrayed a real case study, c) the top 20 were formed by 67 authors, d) the papers were mostly published in journals and conferences, e) there is no unified methodology or framework, f) the top 3 application domains were transport/traffic, healthcare/biology, and logistics/manufacturing, g) MAS interact with different disciplines like machine learning. Finally, the MAS community should work together to close the gaps and unify the field, bridging with other disciplines and industry.
{"title":"A Systematic Literature Review in Multi-Agent Systems: Patterns and Trends","authors":"M. Falcó, Gabriela Robiolo","doi":"10.1109/CLEI47609.2019.235098","DOIUrl":"https://doi.org/10.1109/CLEI47609.2019.235098","url":null,"abstract":"Multi-Agent Systems became a powerful solution to model and solve problems in complex and dynamic environments. While research in this area grew exponentially before 2009, there is a need to understand the status quo of the field from 2009 to June 2017 in order to comprehend the general evolution. The results of a SLR related to Multi-Agent Systems, its applications and research gaps, following Kitchenham and Wholin guidelines are presented in this paper. From the analysis of279 papers (out of3522 candidates), our findings suggest that: a) there is a general decreasing trend of publications (but it is increasing for specific domains), b) only 15% of the papers portrayed a real case study, c) the top 20 were formed by 67 authors, d) the papers were mostly published in journals and conferences, e) there is no unified methodology or framework, f) the top 3 application domains were transport/traffic, healthcare/biology, and logistics/manufacturing, g) MAS interact with different disciplines like machine learning. Finally, the MAS community should work together to close the gaps and unify the field, bridging with other disciplines and industry.","PeriodicalId":216193,"journal":{"name":"2019 XLV Latin American Computing Conference (CLEI)","volume":"76 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":"127497064","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：