http://sedici.unlp.edu.ar:80/handle/10915/155278 2026-11-15T16:31:04Z 2026-11-15T16:31:04Z Marrero, Luciano Olsowy, Verena Thomas, Pablo Javier http://sedici.unlp.edu.ar:80/handle/10915/155446 2023-07-11T20:01:29Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics NoSQL databases have emerged as a response to scalability problems presented by relational databases when used in Big Data contexts. These databases do not have a standard process for designing data schemas, but have emerged as solutions directly at the physical level. As NoSQL databases have gained popularity, different NoSQL design processes and/or methodologies have been proposed, which are necessary to understand the semantics of the stored data. This paper presents a comparative study of NoSQL database design processes.

2023-01-01T00:00:00Z NoSQL databases have emerged as a response to scalability problems presented by relational databases when used in Big Data contexts. These databases do not have a standard process for designing data schemas, but have emerged as solutions directly at the physical level. As NoSQL databases have gained popularity, different NoSQL design processes and/or methodologies have been proposed, which are necessary to understand the semantics of the stored data. This paper presents a comparative study of NoSQL database design processes. Nuñez, Gustavo Buckle, Carlos Ezequiel Zárate, Marcos Daniel http://sedici.unlp.edu.ar:80/handle/10915/155442 2023-07-11T20:01:30Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics As the deployment of ocean sensors continues to grow, there is a growing need for standardized ways to represent and integrate sensor data from different sources. One approach to achieving this is through the use of Semantic Sensor Network (SSN/SOSA) ontology, which provides a common vocabulary and framework for describing sensors, observations, and their properties. In this paper, we present a method for converting ocean sensor data in CSV format to Resource Description Framework (RDF) using RDFLib library for Phyton and SSN/SOSA ontology. The resulting RDF triples can be stored in a triplestore for querying and analysis, providing a standardized representation of ocean sensor data that can be easily integrated with other data sources.

2023-01-01T00:00:00Z As the deployment of ocean sensors continues to grow, there is a growing need for standardized ways to represent and integrate sensor data from different sources. One approach to achieving this is through the use of Semantic Sensor Network (SSN/SOSA) ontology, which provides a common vocabulary and framework for describing sensors, observations, and their properties. In this paper, we present a method for converting ocean sensor data in CSV format to Resource Description Framework (RDF) using RDFLib library for Phyton and SSN/SOSA ontology. The resulting RDF triples can be stored in a triplestore for querying and analysis, providing a standardized representation of ocean sensor data that can be easily integrated with other data sources. Rubio León, José Miguel Rubio Cienfuegos, José Manuel http://sedici.unlp.edu.ar:80/handle/10915/155439 2023-07-11T20:01:31Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics Electric power is one of the main engines of humanity since the late eighteenth century, therefore, understanding the behavior of the demand of this corresponds to a very important study. Within this field, electricity demand prediction has been one of the most developed activities in several researches, where the use of fuzzy time series models has had good results. This paper presents the use of scalable fuzzy time series methods, which were developed by Petronio Silva [1] to predict the Spanish electricity demand collected by the Spanish TSO, whose computational implementation uses a Mamdani fuzzy inference system, which directly processes a time series containing the demand data and its register. It should be noted that the database also includes forecasts made by the same Spanish TSO, so comparisons are made with these forecasts.

2023-01-01T00:00:00Z Electric power is one of the main engines of humanity since the late eighteenth century, therefore, understanding the behavior of the demand of this corresponds to a very important study. Within this field, electricity demand prediction has been one of the most developed activities in several researches, where the use of fuzzy time series models has had good results. This paper presents the use of scalable fuzzy time series methods, which were developed by Petronio Silva [1] to predict the Spanish electricity demand collected by the Spanish TSO, whose computational implementation uses a Mamdani fuzzy inference system, which directly processes a time series containing the demand data and its register. It should be noted that the database also includes forecasts made by the same Spanish TSO, so comparisons are made with these forecasts. Rios, Cristian Emmanuel Estrebou, César Armando Frati, Fernando Emmanuel http://sedici.unlp.edu.ar:80/handle/10915/155434 2023-07-11T20:01:33Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics This paper proposes to apply pre-trained Convolutional Neural Networks (CNN) for the early detection of two common grapevine diseases: peronospora and o´ıdio. These diseases present similar symptoms and are of great viticultural importance. Our objective is to train a CNN using transfer learning techniques to accurately detect the presence of early symptoms of the diseases under study. To achieve that, we’ll design a pipeline that starts with data acquisition in the field and finalizes with the early disease identification, including class definition, labeling, image preprocessing and training process of the CNN, employing edge computing-based service computing paradigm to overcome some inherent problems of traditional mobile cloud computing paradigm.

2023-01-01T00:00:00Z This paper proposes to apply pre-trained Convolutional Neural Networks (CNN) for the early detection of two common grapevine diseases: peronospora and o´ıdio. These diseases present similar symptoms and are of great viticultural importance. Our objective is to train a CNN using transfer learning techniques to accurately detect the presence of early symptoms of the diseases under study. To achieve that, we’ll design a pipeline that starts with data acquisition in the field and finalizes with the early disease identification, including class definition, labeling, image preprocessing and training process of the CNN, employing edge computing-based service computing paradigm to overcome some inherent problems of traditional mobile cloud computing paradigm. Borrelli, Franco Martín Challiol, Cecilia http://sedici.unlp.edu.ar:80/handle/10915/155432 2023-07-11T20:01:34Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics Sentiment analysis is a process of identifying and extracting personal information from textual data. It has become essential for businesses and organizations to understand customers' opinions, emotions, and attitudes toward their products, services, or brands. While creating a custom sentiment analysis model can provide tailored results for specific datasets, it can also be time-consuming, resource-intensive, and require a high level of expertise in machine learning. Some tools offer a faster and more accessible alternative to users without a background in machine learning to create a custom model. However, researchers and practitioners usually do not know how to choose the best tool for each domain. This paper compares and evaluates some sentiment analysis tools' differences, considering how they were built and how suitable they are for analyzing sentiments on some specific topics. In particular, this paper focuses on four popular sentiment analysis tools for Python: TextBlob, Vader, Flair, and HuggingFace Transformers.

2023-01-01T00:00:00Z Sentiment analysis is a process of identifying and extracting personal information from textual data. It has become essential for businesses and organizations to understand customers' opinions, emotions, and attitudes toward their products, services, or brands. While creating a custom sentiment analysis model can provide tailored results for specific datasets, it can also be time-consuming, resource-intensive, and require a high level of expertise in machine learning. Some tools offer a faster and more accessible alternative to users without a background in machine learning to create a custom model. However, researchers and practitioners usually do not know how to choose the best tool for each domain. This paper compares and evaluates some sentiment analysis tools' differences, considering how they were built and how suitable they are for analyzing sentiments on some specific topics. In particular, this paper focuses on four popular sentiment analysis tools for Python: TextBlob, Vader, Flair, and HuggingFace Transformers. Caiafa, Marcelo Dante Aurelio, Ariel Bevilacqua, Alejandro http://sedici.unlp.edu.ar:80/handle/10915/155429 2023-07-11T20:01:36Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics The data has become a main source of knowledge for organizations. Its adequate treatment allows to obtain valuable information. The professional link between university and industry is the goal of our academic work. It is intended to register an articulation project based on data analysis. It is an initiative based on a collaboration between a company and the academy. The aim is using the knowledge and skills of the students to improve the efficiency of the company by automating a process and at the same time bring computer engineering students closer to the productive environment. The work is based on Python and its libraries for data processing of a telecommunication services. The project is based on an exploratory, correlation and segmentation study of data processing for telecommunication services. The goal is to build a customer profile with high dropout potential. The work´s intention is to add value to decision makers in a data-based organization and verify the contribution that new tools can offer to students and teachers in the ICT sector (information and communication technologies).

2023-01-01T00:00:00Z The data has become a main source of knowledge for organizations. Its adequate treatment allows to obtain valuable information. The professional link between university and industry is the goal of our academic work. It is intended to register an articulation project based on data analysis. It is an initiative based on a collaboration between a company and the academy. The aim is using the knowledge and skills of the students to improve the efficiency of the company by automating a process and at the same time bring computer engineering students closer to the productive environment. The work is based on Python and its libraries for data processing of a telecommunication services. The project is based on an exploratory, correlation and segmentation study of data processing for telecommunication services. The goal is to build a customer profile with high dropout potential. The work´s intention is to add value to decision makers in a data-based organization and verify the contribution that new tools can offer to students and teachers in the ICT sector (information and communication technologies). Marianetti, Osvaldo Godoy, Pablo D. Chediak, Ernesto Fontana, Daniel García Gariono, Carlos http://sedici.unlp.edu.ar:80/handle/10915/155425 2023-07-11T20:01:37Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics This paper discusses the use of Radar Sensor Network at Great Mendoza area in order to register and to store vehicular traffic information. Both the network features and the software used in order to analyze and post process the captured information are provided. The main issues of vehicular traffic flow at Great Mendoza area are described from a qualitative point of view. Preliminary results registered with a Radar Sensor Networks placed at Godoy Guaymallén department are discussed as well. Based on the obtained results it can be expected that this kind of tools be very useful in order to alleviate vehicular traffic bottlenecks and related problems.

2023-01-01T00:00:00Z This paper discusses the use of Radar Sensor Network at Great Mendoza area in order to register and to store vehicular traffic information. Both the network features and the software used in order to analyze and post process the captured information are provided. The main issues of vehicular traffic flow at Great Mendoza area are described from a qualitative point of view. Preliminary results registered with a Radar Sensor Networks placed at Godoy Guaymallén department are discussed as well. Based on the obtained results it can be expected that this kind of tools be very useful in order to alleviate vehicular traffic bottlenecks and related problems. Gelvez-Almeida, Elkin Barrientos, Ricardo J. Vilches-Ponce, Karina Mora, Marco http://sedici.unlp.edu.ar:80/handle/10915/155423 2023-07-11T20:01:39Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics Nowadays, the sizes of databases in real-world applications are around TeraByte or PetaByte. Therefore, training neural networks in reasonable times is challenging and requires high-cost computational architectures. OS-ELM is a variant of ELM, proposed for real-world applications. This algorithm allows training with new data using the previous results without reusing the previous dataset. In this work, we present a parallel model of OS-ELM for classification problems using large-scale databases. The model consists of training several OS-ELM using multithreaded programming. The training dataset is distributed according to the number of working threads. Then, the test dataset is classified by all pre-trained OS-ELMs. Finally, the test dataset is classified using a frequency criterion. Preliminary results show that increasing the number of threads decreases the training time without significantly affecting the test accuracy of each OS-ELM.

2023-01-01T00:00:00Z Nowadays, the sizes of databases in real-world applications are around TeraByte or PetaByte. Therefore, training neural networks in reasonable times is challenging and requires high-cost computational architectures. OS-ELM is a variant of ELM, proposed for real-world applications. This algorithm allows training with new data using the previous results without reusing the previous dataset. In this work, we present a parallel model of OS-ELM for classification problems using large-scale databases. The model consists of training several OS-ELM using multithreaded programming. The training dataset is distributed according to the number of working threads. Then, the test dataset is classified by all pre-trained OS-ELMs. Finally, the test dataset is classified using a frequency criterion. Preliminary results show that increasing the number of threads decreases the training time without significantly affecting the test accuracy of each OS-ELM. Costanzo, Manuel Rucci, Enzo García-Sánchez, Carlos Naiouf, Marcelo http://sedici.unlp.edu.ar:80/handle/10915/155420 2023-07-11T20:01:41Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics The heterogeneous computing paradigm has led to the need for portable and efficient programming solutions that can leverage the capabilities of various hardware devices, such as NVIDIA, Intel, and AMD GPUs. This study evaluates the performance and portability of the SYCL and CUDA languages for a matrix multiplication (MM) application across different GPU architectures. The experimental work showed that, while the CUDA implementation outperforms the SYCL implementation on NVIDIA devices due to optimizations provided by the nvcc compiler, the latter implementation demonstrated remarkable code portability to other GPU architectures, such as AMD and Intel. Furthermore, the architectural efficiency percentages obtained on AMD and Intel GPUs showed consistency with the results observed on NVIDIA devices.

2023-01-01T00:00:00Z The heterogeneous computing paradigm has led to the need for portable and efficient programming solutions that can leverage the capabilities of various hardware devices, such as NVIDIA, Intel, and AMD GPUs. This study evaluates the performance and portability of the SYCL and CUDA languages for a matrix multiplication (MM) application across different GPU architectures. The experimental work showed that, while the CUDA implementation outperforms the SYCL implementation on NVIDIA devices due to optimizations provided by the nvcc compiler, the latter implementation demonstrated remarkable code portability to other GPU architectures, such as AMD and Intel. Furthermore, the architectural efficiency percentages obtained on AMD and Intel GPUs showed consistency with the results observed on NVIDIA devices. Alvarez, Candelaria Ibeas, José Balladini, Javier Suppi, Remo http://sedici.unlp.edu.ar:80/handle/10915/155419 2023-07-11T20:01:42Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics Chronic kidney disease (CKD) is a major health problem worldwide. In Spain, the incidence of CKD has increased nearly 17% in ten years, from 2010 to 2020; and in 2020 it had a prevalence of 20% in adults over 60 years. This disease has some characteristics that make it complex; for instance, CKD has a late diagnosis, because the symptoms appear when it is already advanced, and they are not directly related to kidney problems. Furthermore, the causes of the disease are multiple; the most common are arterial hypertension and diabetes. In this context, we believe that simulation and agent-based modelling can provide new tools for assisting professionals in the decision-making process. Therefore, we are proposing the design of a model for CKD progression in order to predict the appearance of renal failure and its evolution in patients through the different states of the disease. Our work is divided into four main stages; and in this article, we present the tasks that have been carried out so far in the first stage which are related to data analysis to define the complexity of the problem.

2023-01-01T00:00:00Z Chronic kidney disease (CKD) is a major health problem worldwide. In Spain, the incidence of CKD has increased nearly 17% in ten years, from 2010 to 2020; and in 2020 it had a prevalence of 20% in adults over 60 years. This disease has some characteristics that make it complex; for instance, CKD has a late diagnosis, because the symptoms appear when it is already advanced, and they are not directly related to kidney problems. Furthermore, the causes of the disease are multiple; the most common are arterial hypertension and diabetes. In this context, we believe that simulation and agent-based modelling can provide new tools for assisting professionals in the decision-making process. Therefore, we are proposing the design of a model for CKD progression in order to predict the appearance of renal failure and its evolution in patients through the different states of the disease. Our work is divided into four main stages; and in this article, we present the tasks that have been carried out so far in the first stage which are related to data analysis to define the complexity of the problem. Pardo, Xoán C. González, Patricia Banga, Julio R. Doallo, Ramón http://sedici.unlp.edu.ar:80/handle/10915/155416 2023-07-11T20:01:44Z 2023-01-01T00:00:00Z

Objeto de conferencia XI Jornadas de Cloud Computing, Big Data & Emerging Topics (La Plata, 27 al 29 de junio de 2023); https://sedici.unlp.edu.ar/handle/10915/155281; XI Jornadas de Cloud Computing, Big Data & Emerging Topics Particle Swarm Optimization (PSO) is a popular population-based search algorithm that has been applied to all kinds of complex optimization problems. Although the performance of the algorithm strongly depends on the social topology that determines the interaction between the particles during the search, current Metaheuristic Optimization Frameworks (MOFs) provide limited support for topologies. In this paper, we present an approach to support generic topologies in distributed PSO algorithms within a framework for the development and execution of populationbased metaheuristics in Spark, which is currently under development.

2023-01-01T00:00:00Z Particle Swarm Optimization (PSO) is a popular population-based search algorithm that has been applied to all kinds of complex optimization problems. Although the performance of the algorithm strongly depends on the social topology that determines the interaction between the particles during the search, current Metaheuristic Optimization Frameworks (MOFs) provide limited support for topologies. In this paper, we present an approach to support generic topologies in distributed PSO algorithms within a framework for the development and execution of populationbased metaheuristics in Spark, which is currently under development. De Giusti, Armando Eduardo Naiouf, Marcelo Chichizola, Franco Rucci, Enzo De Giusti, Laura Cristina http://sedici.unlp.edu.ar:80/handle/10915/155281 2023-07-07T20:01:23Z 2023-07-07T00:00:00Z

Libro De Giusti, Armando Eduardo; Naiouf, Marcelo; Chichizola, Franco; Rucci, Enzo; De Giusti, Laura Cristina Compilación de los short papers presentados en las 11vas Jornadas de Cloud Computing, Big Data & Emerging Topics (JCC-BD&ET2023), llevadas a cabo en modalidad híbrida durante junio de 2023 y organizadas por el Instituto de Investigación en Informática LIDI (III-LIDI) y la Secretaría de Posgrado de la Facultad de Informática de la UNLP en colaboración con universidades de Argentina y del exterior. Facultad de Informática (UNLP)

2023-07-07T00:00:00Z Compilación de los short papers presentados en las 11vas Jornadas de Cloud Computing, Big Data & Emerging Topics (JCC-BD&ET2023), llevadas a cabo en modalidad híbrida durante junio de 2023 y organizadas por el Instituto de Investigación en Informática LIDI (III-LIDI) y la Secretaría de Posgrado de la Facultad de Informática de la UNLP en colaboración con universidades de Argentina y del exterior.