http://sedici.unlp.edu.ar:80/handle/10915/103584 Sat, 14 Nov 2026 23:15:55 GMT 2026-11-14T23:15:55Z http://sedici.unlp.edu.ar:80/handle/10915/132374 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); Cloud Computing, Big Data & Emerging Topics. JCC-BD&ET 2020 Astronomical databases currently provide high-volume spectroscopic and photometric data. While spectroscopic data is better suited to the analysis of many astronomical objects, photometric data is relatively easier to obtain due to shorter telescope usage time. Therefore, there is a growing need to use photometric information to automatically identify objects for further detailed studies, specially H α emission line stars such as Be stars. Photometric color-color diagrams (CCDs) are commonly used to identify this kind of objects. However, their identification in CCDs is further complicated by the reddening effect caused by both the circumstellar and interstellar gas. This effect prevents the generalization of candidate identification systems. Therefore, in this work we evaluate the use of neural networks to identify Be star candidates from a set of OB-type stars. The networks are trained using a labeled subset of the VPHAS+ and 2MASS databases, with filters u, g, r, Hα, i, J, H , and K. In order to avoid the reddening effect, we propose and evaluate the use of reddening-free Q indices to enhance the generalization of the model to other databases and objects. To test the validity of the approach, we manually labeled a subset of the database, and use it to evaluate candidate identification models. We also labeled an independent dataset for cross dataset evaluation. We evaluate the recall of the models at a 99% precision level on both test sets. Our results show that the proposed features provide a significant improvement over the original filter magnitudes. Trabajo publicado en Rucci E., Naiouf M., Chichizola F., De Giusti L. (eds). <i>Cloud Computing, Big Data & Emerging Topics. JCC-BD&ET 2020</i>. Communications in Computer and Information Science, vol. 1291. Springer, Cham. Sat, 24 Oct 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/132374 2020-10-24T00:00:00Z Astronomical databases currently provide high-volume spectroscopic and photometric data. While spectroscopic data is better suited to the analysis of many astronomical objects, photometric data is relatively easier to obtain due to shorter telescope usage time. Therefore, there is a growing need to use photometric information to automatically identify objects for further detailed studies, specially H α emission line stars such as Be stars. Photometric color-color diagrams (CCDs) are commonly used to identify this kind of objects. However, their identification in CCDs is further complicated by the reddening effect caused by both the circumstellar and interstellar gas. This effect prevents the generalization of candidate identification systems. Therefore, in this work we evaluate the use of neural networks to identify Be star candidates from a set of OB-type stars. The networks are trained using a labeled subset of the VPHAS+ and 2MASS databases, with filters u, g, r, Hα, i, J, H , and K. In order to avoid the reddening effect, we propose and evaluate the use of reddening-free Q indices to enhance the generalization of the model to other databases and objects. To test the validity of the approach, we manually labeled a subset of the database, and use it to evaluate candidate identification models. We also labeled an independent dataset for cross dataset evaluation. We evaluate the recall of the models at a 99% precision level on both test sets. Our results show that the proposed features provide a significant improvement over the original filter magnitudes. http://sedici.unlp.edu.ar:80/handle/10915/104840 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) This article presents a possible approach for the integration of wireless sensor networks with applied IoT (Internet of Things) platforms related to Fog Computing concepts. Several ideas are presented related to: a) definition of the main characteristics to be considered in the deployment of sensor networks, b) evaluation of alternatives for combining wireless communication technologies and, c) experimentation with different IoT platforms for local data preprocessing that will then optimize the data flow of information to the cloud. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104840 2020-01-01T00:00:00Z This article presents a possible approach for the integration of wireless sensor networks with applied IoT (Internet of Things) platforms related to Fog Computing concepts. Several ideas are presented related to: a) definition of the main characteristics to be considered in the deployment of sensor networks, b) evaluation of alternatives for combining wireless communication technologies and, c) experimentation with different IoT platforms for local data preprocessing that will then optimize the data flow of information to the cloud. http://sedici.unlp.edu.ar:80/handle/10915/104838 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) The main goal of this work focuses on solving the problem of analyzing the data coming from Social Media and exploring the mechanisms for the extraction and representation of knowledge from all the different disciplines outside the world of information Technologies. Soft Computing and Big Data techniques are used to deal with the challenges mentioned. This paper shows a mechanism to detect hate speech in Social Media using Soft Computing and Sentiment Analysis, and it also stablishes the base of a doctoral thesis. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104838 2020-01-01T00:00:00Z The main goal of this work focuses on solving the problem of analyzing the data coming from Social Media and exploring the mechanisms for the extraction and representation of knowledge from all the different disciplines outside the world of information Technologies. Soft Computing and Big Data techniques are used to deal with the challenges mentioned. This paper shows a mechanism to detect hate speech in Social Media using Soft Computing and Sentiment Analysis, and it also stablishes the base of a doctoral thesis. http://sedici.unlp.edu.ar:80/handle/10915/104835 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) Numerical simulations used today by scientists in various disciplines, are frequently based on implementations created when the predominant compu­ting hardware was sequential by design. In this simulations, new features are added or updated, when new discoveries are made, but the computational implementation remains unchanged, not taking advantage of modern hardware architectures. This “legacy code” study cases, presents the opportunity to create a set of techniques and tools, oriented to perform optimizations from a computa­tional and software engineering points of view. As an example, in conjunction with an astrophysics research group, a real-world case numerical integrator optimization is presented, were these techniques were applied, showing the results obtained. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104835 2020-01-01T00:00:00Z Numerical simulations used today by scientists in various disciplines, are frequently based on implementations created when the predominant compu­ting hardware was sequential by design. In this simulations, new features are added or updated, when new discoveries are made, but the computational implementation remains unchanged, not taking advantage of modern hardware architectures. This “legacy code” study cases, presents the opportunity to create a set of techniques and tools, oriented to perform optimizations from a computa­tional and software engineering points of view. As an example, in conjunction with an astrophysics research group, a real-world case numerical integrator optimization is presented, were these techniques were applied, showing the results obtained. http://sedici.unlp.edu.ar:80/handle/10915/104778 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) Nowadays, organizations process large volumes of data. Being able to foster and maintain data quality is one of the biggest challenges that these organizations face. To do this, there are standards, such as ISO/IEC 25012 and ISO/IEC 25024, which are intended to measure data quality based on a set of inherent and system-dependent characteristics, along with a set of associated metrics. Using standards to carry out measurements can be complex and even expensive for those with little experience in the area. In this context, we propose in this work a prototype for a tool based on ISO/IEC 25012 and ISO/IEC 25024 that, by analyzing different patterns of common errors in data, allows an organization to understand data current status. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104778 2020-01-01T00:00:00Z Nowadays, organizations process large volumes of data. Being able to foster and maintain data quality is one of the biggest challenges that these organizations face. To do this, there are standards, such as ISO/IEC 25012 and ISO/IEC 25024, which are intended to measure data quality based on a set of inherent and system-dependent characteristics, along with a set of associated metrics. Using standards to carry out measurements can be complex and even expensive for those with little experience in the area. In this context, we propose in this work a prototype for a tool based on ISO/IEC 25012 and ISO/IEC 25024 that, by analyzing different patterns of common errors in data, allows an organization to understand data current status. http://sedici.unlp.edu.ar:80/handle/10915/104777 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) The concept of open government has promoted several initiatives in order to progress in their implementation in different governmental agencies. Generally, implantation is carried out, in the first place, based on transparency and the opening of data, giving citizens relevant information about their community. Within that information, data about the rational use of natural resources and care of the environment can be found. In this context, and taking into account the ongoing analysis, it was discovered that, apart from the positive measures taken for the progress of the implantation, the main existing flaw is the possibility to link and relate the existing data in different data sources. The linking of data will allow for a closer analysis that can generate a wider context for information. This paper is based on a PhD thesis in process whose aim is to generate a framework that allows the linking and relationship of information related to the environment published in different open government portals. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104777 2020-01-01T00:00:00Z The concept of open government has promoted several initiatives in order to progress in their implementation in different governmental agencies. Generally, implantation is carried out, in the first place, based on transparency and the opening of data, giving citizens relevant information about their community. Within that information, data about the rational use of natural resources and care of the environment can be found. In this context, and taking into account the ongoing analysis, it was discovered that, apart from the positive measures taken for the progress of the implantation, the main existing flaw is the possibility to link and relate the existing data in different data sources. The linking of data will allow for a closer analysis that can generate a wider context for information. This paper is based on a PhD thesis in process whose aim is to generate a framework that allows the linking and relationship of information related to the environment published in different open government portals. http://sedici.unlp.edu.ar:80/handle/10915/104775 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) Currently the publicly available datasets for Big Data Ana-lytics are of different qualities, and obtaining the expected behavior from the Machine Learning algorithms is crucial. Furthermore, since working with a huge amount of data is usually a time-demanding task, tohave high quality data is required. Smart Data refers to the process of transforming Big Data into clean and reliable data, and this can be accomplished by converting them, reducing unnecessary volume of data or applying some preprocessing techniques with the aim of improve their quality, and still to obtain trustworthy results. We present those properties that affect the quality of data. Also, the available proposals to analyze the quality of huge amount of data and to cope with low quality datasets in an scalable way, are commented. Furthermore, the need for a methodology towards Smart Data is highlighted. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104775 2020-01-01T00:00:00Z Currently the publicly available datasets for Big Data Ana-lytics are of different qualities, and obtaining the expected behavior from the Machine Learning algorithms is crucial. Furthermore, since working with a huge amount of data is usually a time-demanding task, tohave high quality data is required. Smart Data refers to the process of transforming Big Data into clean and reliable data, and this can be accomplished by converting them, reducing unnecessary volume of data or applying some preprocessing techniques with the aim of improve their quality, and still to obtain trustworthy results. We present those properties that affect the quality of data. Also, the available proposals to analyze the quality of huge amount of data and to cope with low quality datasets in an scalable way, are commented. Furthermore, the need for a methodology towards Smart Data is highlighted. http://sedici.unlp.edu.ar:80/handle/10915/104774 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) Based on previous experience in prediction systems with Fuzzy Deformable Prototypes, improvement in their functioning and deformation capacity is necessary, a new idea/concept for this is proposed. We propose a system with artificial intelligence that is capable of characterizing new situations, within the context of a PhD. thesis, capable of recognizing samples in a cognitive environment, in addition to testing its viability and performance in a non-cognitive environment a preliminary experiment is carried out, classifying handwritten digits from a reference database (MNIST) with a good success rate. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104774 2020-01-01T00:00:00Z Based on previous experience in prediction systems with Fuzzy Deformable Prototypes, improvement in their functioning and deformation capacity is necessary, a new idea/concept for this is proposed. We propose a system with artificial intelligence that is capable of characterizing new situations, within the context of a PhD. thesis, capable of recognizing samples in a cognitive environment, in addition to testing its viability and performance in a non-cognitive environment a preliminary experiment is carried out, classifying handwritten digits from a reference database (MNIST) with a good success rate. http://sedici.unlp.edu.ar:80/handle/10915/104772 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) The evaluation in terms of quality of the results obtained from the use of a heuristic method is necessary to, first, verify the obtained results since heuristic methods do not guarantee to reach the optimum because all the possibilities are not fully explored. Secondly, it becomes interesting to validate such method, thus granting a high-quality index. Through our proposal, starting on the analysis of the literature survey on many optimization test functions, we are proposing the evaluation of a heuristic method based on Montecarlo approaches in conjunction with K-means clustering. Besides this, we aim to evaluate the results obtained through the use of some complex optimization test functions. Also, we seek to add a defined quality index to the original heuristic method relying on the consequent improvement in the results. As a side-work, we would aim to validate the heuristic mentioned aboveand optimize the algorithm in terms of scalability and quality. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104772 2020-01-01T00:00:00Z The evaluation in terms of quality of the results obtained from the use of a heuristic method is necessary to, first, verify the obtained results since heuristic methods do not guarantee to reach the optimum because all the possibilities are not fully explored. Secondly, it becomes interesting to validate such method, thus granting a high-quality index. Through our proposal, starting on the analysis of the literature survey on many optimization test functions, we are proposing the evaluation of a heuristic method based on Montecarlo approaches in conjunction with K-means clustering. Besides this, we aim to evaluate the results obtained through the use of some complex optimization test functions. Also, we seek to add a defined quality index to the original heuristic method relying on the consequent improvement in the results. As a side-work, we would aim to validate the heuristic mentioned aboveand optimize the algorithm in terms of scalability and quality. http://sedici.unlp.edu.ar:80/handle/10915/104771 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) In this research we incorporate the contributions of the dynamic data driven systems development that is based on the possibility of incorporating data obtained in real time into an executing application, in particular a simulation. This paper reports on the first phase of our research in which we have used this idea to enhance the simulation quality of a river flow simulator by dynamic data inputs during the computational execution. We had presented an optimization methodology of this simulator model in previous works but in this opportunity, we could handle those time periods when a sudden level change takes place inthe river and we could improve the forecasting prediction. These results are the path towards the development of an automatic calibration framework fed with real-time data. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104771 2020-01-01T00:00:00Z In this research we incorporate the contributions of the dynamic data driven systems development that is based on the possibility of incorporating data obtained in real time into an executing application, in particular a simulation. This paper reports on the first phase of our research in which we have used this idea to enhance the simulation quality of a river flow simulator by dynamic data inputs during the computational execution. We had presented an optimization methodology of this simulator model in previous works but in this opportunity, we could handle those time periods when a sudden level change takes place inthe river and we could improve the forecasting prediction. These results are the path towards the development of an automatic calibration framework fed with real-time data. http://sedici.unlp.edu.ar:80/handle/10915/104769 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) Currently the techniques used to predict the future are statistical and machine learning techniques. The first continues the trend of historical data. The second learns from previous cases training. Both use historical information but do not take in mind key factors that can make the final result change. A knowledge-based framework is presented that allows predictions of some kind ofevents to be made using artificial intelligence techniques. This requires an expert to enter the key factors that can change the trend of historical data into the system.The current framework has been applied prior to happening to two use cases, obtaining good preliminary results, in the framework of the developing of a PhD Thesis. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104769 2020-01-01T00:00:00Z Currently the techniques used to predict the future are statistical and machine learning techniques. The first continues the trend of historical data. The second learns from previous cases training. Both use historical information but do not take in mind key factors that can make the final result change. A knowledge-based framework is presented that allows predictions of some kind ofevents to be made using artificial intelligence techniques. This requires an expert to enter the key factors that can change the trend of historical data into the system.The current framework has been applied prior to happening to two use cases, obtaining good preliminary results, in the framework of the developing of a PhD Thesis. http://sedici.unlp.edu.ar:80/handle/10915/104768 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) In massive biometric identification, response times highlydepend on the searching algorithms. Traditional systems operate with databases of up to 10,000 records. In large databases, with an increasing number of simultaneous queries, the system response time is a critical factor. This work proposes a GPU-based implementation for the matching process of finger-vein massive identification. Experimental resultss how that our approach solves up to 256 simultaneous queries on large databases achieving up to 136x. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104768 2020-01-01T00:00:00Z In massive biometric identification, response times highlydepend on the searching algorithms. Traditional systems operate with databases of up to 10,000 records. In large databases, with an increasing number of simultaneous queries, the system response time is a critical factor. This work proposes a GPU-based implementation for the matching process of finger-vein massive identification. Experimental resultss how that our approach solves up to 256 simultaneous queries on large databases achieving up to 136x. http://sedici.unlp.edu.ar:80/handle/10915/104766 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) Compute-heavy workloads are traditionally run on x86-based HPC platforms and Intel, AMD or Nvidia GPUs; these require a high initial capital expense and ongoing maintenance costs. ARM-based mobile devicesoffer a rad-ically different paradigm with substantially lower capital and maintenance costs and higher gains in performance and efficiency in recent years. When compared to their x-86 brethren, they have become ubiquitous in consumer markets and are making steady gains in the server market. Given this shifting computer paradigm, it is conceivable that a cost- and power-efficient solution for our world’s data processing would include those very same ARM-based mobile devices while they are idling. Given that context, we developed and deployed an auto-scalable, distributed and redundant platform on the basis of a cloud-based service managed via container orchestration and microservices that are in charge of recycling and optimizing these idle resources. We tested the platform performing distributed video compression. We concluded the system allows for improvements in terms of scalability, flexibility, stability, efficiency, and cost for compute-heavy work-loads. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104766 2020-01-01T00:00:00Z Compute-heavy workloads are traditionally run on x86-based HPC platforms and Intel, AMD or Nvidia GPUs; these require a high initial capital expense and ongoing maintenance costs. ARM-based mobile devicesoffer a rad-ically different paradigm with substantially lower capital and maintenance costs and higher gains in performance and efficiency in recent years. When compared to their x-86 brethren, they have become ubiquitous in consumer markets and are making steady gains in the server market. Given this shifting computer paradigm, it is conceivable that a cost- and power-efficient solution for our world’s data processing would include those very same ARM-based mobile devices while they are idling. Given that context, we developed and deployed an auto-scalable, distributed and redundant platform on the basis of a cloud-based service managed via container orchestration and microservices that are in charge of recycling and optimizing these idle resources. We tested the platform performing distributed video compression. We concluded the system allows for improvements in terms of scalability, flexibility, stability, efficiency, and cost for compute-heavy work-loads. http://sedici.unlp.edu.ar:80/handle/10915/104765 Objeto de conferencia VIII Conference on Cloud Computing, Big Data & Emerging Topics (Modalidad virtual, 8 al 10 de septiembre de 2020); https://sedici.unlp.edu.ar/handle/10915/103585; https://sedici.unlp.edu.ar/handle/10915/103585; Short Papers of the 8th Conference on Cloud Computing Conference, Big Data & Emerging Topics (JCC-BD&ET 2020) In today's university environment, most students are digital natives. Therefore, it is difficult to imagine their academic life without relating it to the various cloud tools for communication and collaborative work. In this context, university professors work in new scenarios of communication and collaborative work in the classroom. This represents a transformation in the teaching-learning process assisted by new ICTs s in the cloud. Working in the cloud offers the opportunity to transmit new knowledge when using pedagogical strategies supported by computer technologies. With the combination of ICTs and modern teaching-learning processes, the concept of Learning and Knowledge Technologies (TAC) is valuable. This work exposes the academic experience of researching and developing Cloud Computing using an OpenStack configuration so that students can empower themselves with the knowledge and use of cloud technologies. Thus, to be able to teach concepts and practices on IT Infrastructure including activities such as: design, configuration, implementation and administration of a private cloud for academic uses. Wed, 01 Jan 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/104765 2020-01-01T00:00:00Z In today's university environment, most students are digital natives. Therefore, it is difficult to imagine their academic life without relating it to the various cloud tools for communication and collaborative work. In this context, university professors work in new scenarios of communication and collaborative work in the classroom. This represents a transformation in the teaching-learning process assisted by new ICTs s in the cloud. Working in the cloud offers the opportunity to transmit new knowledge when using pedagogical strategies supported by computer technologies. With the combination of ICTs and modern teaching-learning processes, the concept of Learning and Knowledge Technologies (TAC) is valuable. This work exposes the academic experience of researching and developing Cloud Computing using an OpenStack configuration so that students can empower themselves with the knowledge and use of cloud technologies. Thus, to be able to teach concepts and practices on IT Infrastructure including activities such as: design, configuration, implementation and administration of a private cloud for academic uses. http://sedici.unlp.edu.ar:80/handle/10915/103585 Libro De Giusti, Armando Eduardo; Naiouf, Marcelo; Chichizola, Franco; Rucci, Enzo; De Giusti, Laura Cristina Compilación de los short papers presentados en las 8vas Jornadas de Cloud Computing, Big Data & Emerging Topics (JCC-BD&ET2020), llevadas a cabo en modalidad virtual durante septiembre de 2020 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) Tue, 01 Sep 2020 00:00:00 GMT http://sedici.unlp.edu.ar:80/handle/10915/103585 2020-09-01T00:00:00Z Compilación de los short papers presentados en las 8vas Jornadas de Cloud Computing, Big Data & Emerging Topics (JCC-BD&ET2020), llevadas a cabo en modalidad virtual durante septiembre de 2020 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.