Pub Date : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9940056
Lautaro Estienne, Matías Vera, L. Vega
Sentiment Classification is a fundamental task in the field of Natural Language Processing, and has very important academic and commercial applications. It aims to automatically predict the degree of sentiment present in a text that contains opinions and subjectivity at some level, like product and movie reviews, or tweets. This can be really difficult to accomplish, in part, because different domains of text contains different words and expressions. In addition, this difficulty increases when text is written in a non-English language due to the lack of databases and resources. As a consequence, several cross-domain and cross-language techniques are often applied to this task in order to improve the results. In this work we perform a study on the ability of a classification system trained with a large database of product reviews to generalize to different Spanish domains. Reviews were collected from the MercadoLibre website from seven Latin American countries, allowing the creation of a large and balanced dataset. Results suggest that generalization across domains is feasible though very challenging when trained with these product reviews, and can be improved by pre-training and fine-tuning the classification model.
{"title":"Cross-domain Sentiment Classification in Spanish","authors":"Lautaro Estienne, Matías Vera, L. Vega","doi":"10.1109/ARGENCON55245.2022.9940056","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9940056","url":null,"abstract":"Sentiment Classification is a fundamental task in the field of Natural Language Processing, and has very important academic and commercial applications. It aims to automatically predict the degree of sentiment present in a text that contains opinions and subjectivity at some level, like product and movie reviews, or tweets. This can be really difficult to accomplish, in part, because different domains of text contains different words and expressions. In addition, this difficulty increases when text is written in a non-English language due to the lack of databases and resources. As a consequence, several cross-domain and cross-language techniques are often applied to this task in order to improve the results. In this work we perform a study on the ability of a classification system trained with a large database of product reviews to generalize to different Spanish domains. Reviews were collected from the MercadoLibre website from seven Latin American countries, allowing the creation of a large and balanced dataset. Results suggest that generalization across domains is feasible though very challenging when trained with these product reviews, and can be improved by pre-training and fine-tuning the classification model.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126196642","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 : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9940110
Nicolas Merchan, David Romero-Quete, Camilo A. Cortés
El presente documento describe una herramienta de software libre para el dimensionamiento de microrredes híbridas con generación fotovoltaica, baterías, turbinas eólicas, generación diesel e inversores híbridos. La herramienta hace uso de un modelo de Programación Lineal Entero Mixto (PLEM) que minimiza el Costo Presente Neto (CPN) y que integra restricciones técnicas de los inversores híbridos, límites de espacio físico, reemplazo de los equipos durante la vida útil del proyecto, minimización de emisiones contaminantes, penalización por energía no suministrada y perfiles de disponibilidad para la red principal y el generador diésel. En el documento se presentan los resultados del dimensionamiento de dos microrredes híbridas, una ubicada en la ciudad de Puerto Carreño y otra en la Isla de San Andrés, Colombia. Los resultados muestran que la herramienta logra obtener soluciones de microrred adaptadas a los recursos energéticos disponibles en cada uno de estos sitios, optimizando así la inversión.
{"title":"Herramienta para el dimensionamiento óptimo de microrredes híbridas PF/Baterías/Viento/Diésel con inversores híbridos","authors":"Nicolas Merchan, David Romero-Quete, Camilo A. Cortés","doi":"10.1109/ARGENCON55245.2022.9940110","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9940110","url":null,"abstract":"El presente documento describe una herramienta de software libre para el dimensionamiento de microrredes híbridas con generación fotovoltaica, baterías, turbinas eólicas, generación diesel e inversores híbridos. La herramienta hace uso de un modelo de Programación Lineal Entero Mixto (PLEM) que minimiza el Costo Presente Neto (CPN) y que integra restricciones técnicas de los inversores híbridos, límites de espacio físico, reemplazo de los equipos durante la vida útil del proyecto, minimización de emisiones contaminantes, penalización por energía no suministrada y perfiles de disponibilidad para la red principal y el generador diésel. En el documento se presentan los resultados del dimensionamiento de dos microrredes híbridas, una ubicada en la ciudad de Puerto Carreño y otra en la Isla de San Andrés, Colombia. Los resultados muestran que la herramienta logra obtener soluciones de microrred adaptadas a los recursos energéticos disponibles en cada uno de estos sitios, optimizando así la inversión.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124718422","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 : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939984
Mauro Grioni, Sergio A. Elaskar, P. Bruel, Anibal E. Mirasso
La precisión de los resultados, la estabilidad numérica y el tiempo de cálculo son factores importantes para cualquier tipo de problema dentro de la dinámica de fluidos computacional (CFD). Un aspecto importante a considerar que afecta estos factores es el acoplamiento de velocidad-presión cuando se trabaja con un flujo incompresible. Los algoritmos de solución más populares son SIMPLE, SIMPLEC, PISO y Coupled. Los tres primeros son métodos de solución segregados donde la ecuación de momento se resuelve primero seguida de la ecuación de continuidad, mientras que en el algoritmo Coupled las ecuaciones de momento y continuidad se resuelven simultáneamente. La performance numérica de cada algoritmo en las simulaciones numéricas varía de un problema a otro, por lo tanto, dependen del problema en estudio. Bajo este contexto, la presente contribución tiene como objetivo comparar los esquemas segregados SIMPLE, SIMPLEC y PISO en predecir el flujo turbulento no estacionario a través de un cilindro circular para un Re=10000 utilizando el modelo de turbulencia SST-SAS. Teniendo en cuenta la precisión de los resultados y la estabilidad numérica el esquema SIMPLEC presentó un mejor desempeño, mientras que al considerar el tiempo computacional el esquema SIMPLE logró destacarse sobre el resto.
{"title":"Comparación de algoritmos de acoplamiento velocidad-presión para problemás no estacionarios del flujo alrededor de un cilindro circular","authors":"Mauro Grioni, Sergio A. Elaskar, P. Bruel, Anibal E. Mirasso","doi":"10.1109/ARGENCON55245.2022.9939984","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939984","url":null,"abstract":"La precisión de los resultados, la estabilidad numérica y el tiempo de cálculo son factores importantes para cualquier tipo de problema dentro de la dinámica de fluidos computacional (CFD). Un aspecto importante a considerar que afecta estos factores es el acoplamiento de velocidad-presión cuando se trabaja con un flujo incompresible. Los algoritmos de solución más populares son SIMPLE, SIMPLEC, PISO y Coupled. Los tres primeros son métodos de solución segregados donde la ecuación de momento se resuelve primero seguida de la ecuación de continuidad, mientras que en el algoritmo Coupled las ecuaciones de momento y continuidad se resuelven simultáneamente. La performance numérica de cada algoritmo en las simulaciones numéricas varía de un problema a otro, por lo tanto, dependen del problema en estudio. Bajo este contexto, la presente contribución tiene como objetivo comparar los esquemas segregados SIMPLE, SIMPLEC y PISO en predecir el flujo turbulento no estacionario a través de un cilindro circular para un Re=10000 utilizando el modelo de turbulencia SST-SAS. Teniendo en cuenta la precisión de los resultados y la estabilidad numérica el esquema SIMPLEC presentó un mejor desempeño, mientras que al considerar el tiempo computacional el esquema SIMPLE logró destacarse sobre el resto.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128655928","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 : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9940124
Patricia Cristaldo, Daniela López de Luise, Lucas La Pietra
Este artículo se enfoca en el estudio de cómo evaluar el grado en que las metodologías de gestión de proyectos se adaptan a la naturaleza del proyecto en cuestión. A pesar de los esfuerzos técnicos la gestión continúa con valores significativos de fracasos. Muchos no finalizan o finalizan con cambios, principalmente debido a una carencia en aspectos formales. Por ello el foco de este trabajo son la detección sistemática de factores perjudiciales y el diseño de métricas que asistan a la cuantificación del proceso de formalización técnica de los mismos. En particular este trabajo se centra en el grado de planificación de la calidad y la gestión del equipo de proyecto. Como parte del curso de la investigación se desarrollaron herramientas con técnicas de procesamiento de lenguaje natural, para la extracción automática de toda información necesaria a partir de documentos del proyecto. Se introducen y aplican aquí métricas diseñadas para evaluar y comparar el desempeño de metodologías de gestión de proyectos. A partir de las métricas también se determinan indicadores de evaluación, proceso que culmina el análisis de los factores relevantes inicialmente identificados de manera automática desde la documentación relevada para el test. Los resultados permiten confirmar que la definición completa del alcance del proyecto, permite determinar la metodología a utilizar, extrayendo la información necesaria para la selección de las mismas. Asimismo, las herramientas serían beneficiosas para los líderes y administradores asistiéndoles en la determinación de la calidad de la gestión conforme se plasme en los documentos correspondientes.
{"title":"Métricas para Metodologías de Gestión de Proyectos: planificación de calidad y equipo de gestión","authors":"Patricia Cristaldo, Daniela López de Luise, Lucas La Pietra","doi":"10.1109/ARGENCON55245.2022.9940124","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9940124","url":null,"abstract":"Este artículo se enfoca en el estudio de cómo evaluar el grado en que las metodologías de gestión de proyectos se adaptan a la naturaleza del proyecto en cuestión. A pesar de los esfuerzos técnicos la gestión continúa con valores significativos de fracasos. Muchos no finalizan o finalizan con cambios, principalmente debido a una carencia en aspectos formales. Por ello el foco de este trabajo son la detección sistemática de factores perjudiciales y el diseño de métricas que asistan a la cuantificación del proceso de formalización técnica de los mismos. En particular este trabajo se centra en el grado de planificación de la calidad y la gestión del equipo de proyecto. Como parte del curso de la investigación se desarrollaron herramientas con técnicas de procesamiento de lenguaje natural, para la extracción automática de toda información necesaria a partir de documentos del proyecto. Se introducen y aplican aquí métricas diseñadas para evaluar y comparar el desempeño de metodologías de gestión de proyectos. A partir de las métricas también se determinan indicadores de evaluación, proceso que culmina el análisis de los factores relevantes inicialmente identificados de manera automática desde la documentación relevada para el test. Los resultados permiten confirmar que la definición completa del alcance del proyecto, permite determinar la metodología a utilizar, extrayendo la información necesaria para la selección de las mismas. Asimismo, las herramientas serían beneficiosas para los líderes y administradores asistiéndoles en la determinación de la calidad de la gestión conforme se plasme en los documentos correspondientes.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127080356","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 : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939805
Emanuel A. Dri, G. Peretti, E. Romero
This article proposes a fault diagnosis scheme for second-order switched-capacitor filters embedded in the Infineon PSoC1 reconfigurable microcontroller. The faults considered are single soft faults that diminish the capacitance of the capacitors. Specifically, the scheme focuses on incipient faults, which are the hardest to identify because they produce a small impact on the circuit’s performance. The scheme estimates the value of the degradation of the capacitors by employing a first nearest neighbor (1NN) classifier. Our proposal compares the output test patterns against a dictionary of selected fault patterns (one for each capacitor) using Dynamic Time Warping (DTW) distance measures. The easiness of construction of this dictionary and the conceptual simplicity of the method are the most relevant features of the proposal. The characterization of the scheme is made with MatLab simulations at a transfer-function level to limit the computational cost. The simulation results show that the diagnosis procedure can determine the capacitor that presents incipient faults.
{"title":"A Fast Soft-Fault Diagnosis Procedure Using a First Nearest Neighbor Classification","authors":"Emanuel A. Dri, G. Peretti, E. Romero","doi":"10.1109/ARGENCON55245.2022.9939805","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939805","url":null,"abstract":"This article proposes a fault diagnosis scheme for second-order switched-capacitor filters embedded in the Infineon PSoC1 reconfigurable microcontroller. The faults considered are single soft faults that diminish the capacitance of the capacitors. Specifically, the scheme focuses on incipient faults, which are the hardest to identify because they produce a small impact on the circuit’s performance. The scheme estimates the value of the degradation of the capacitors by employing a first nearest neighbor (1NN) classifier. Our proposal compares the output test patterns against a dictionary of selected fault patterns (one for each capacitor) using Dynamic Time Warping (DTW) distance measures. The easiness of construction of this dictionary and the conceptual simplicity of the method are the most relevant features of the proposal. The characterization of the scheme is made with MatLab simulations at a transfer-function level to limit the computational cost. The simulation results show that the diagnosis procedure can determine the capacitor that presents incipient faults.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127039919","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 : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939673
Ubaldo Yancachajlla Tito, Oliver Amadeo Vilca Huayta, Mario Gaston Borja Borja
For optimal use of the wind resource, an optimal aerodynamic design of the blade sections of a wind turbine is important. The article presents the design of the blades of a low power wind turbine for a region with low wind speed and lower than typical air density. The results of the design are presented, analyzed, and validated with the QBlade software, which uses the BEMT (Blade Element Momentum Theory) method. The pitch angle and the optimized chord in each section were determined, the power coefficient and power generated were also found. It was concluded that there is a similarity for the geometry found by the QBlade software and a traditional method for a wind turbine for a high Andean place.
{"title":"Diseño Aerodinámico de la Pala de una Mini Turbina de Eje Horizontal para Bajas Velocidades del Viento para la Zona Altoandina del Perú","authors":"Ubaldo Yancachajlla Tito, Oliver Amadeo Vilca Huayta, Mario Gaston Borja Borja","doi":"10.1109/ARGENCON55245.2022.9939673","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939673","url":null,"abstract":"For optimal use of the wind resource, an optimal aerodynamic design of the blade sections of a wind turbine is important. The article presents the design of the blades of a low power wind turbine for a region with low wind speed and lower than typical air density. The results of the design are presented, analyzed, and validated with the QBlade software, which uses the BEMT (Blade Element Momentum Theory) method. The pitch angle and the optimized chord in each section were determined, the power coefficient and power generated were also found. It was concluded that there is a similarity for the geometry found by the QBlade software and a traditional method for a wind turbine for a high Andean place.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"21 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128917223","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 : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9940034
Norma Furlan, R. Pringles, Andrés Flores Palma, Gabriela Escrivá, Valeria Lorenzo
This work describes the didactic experience made in the period 2020-2021 in Operations Research course in Industrial Engineering of the Faculty of Engineering of the National University of San Juan. Shifting to remote learning we made faster and deeper the methodological and technical changes in the teaching-learning process designed before pandemic. Both were based on the digital transformation of education and efforts to reform engineering education in Argentina: in order to meet the demands of this dynamic world, engineering programs are challenged to find innovative ways to teach classes so that graduates are prepared in soft skills as well as technical skills. The UNSJ Distance Education System made the Moodle platform immediately and massively available. This allowed us to make an abrupt transformation of the learning space. We use the flipped classroom method, design activities to promote transversal skills and modify the forms of evaluation. In response, the students have shown a strong commitment to the proposal, an important responsibility in group activities and a very good connection with virtual tools. In the post-pandemic we will opt a blend learning, to enhance the benefits of online and face-to-face teaching and tend to design a student-centered learning methodology.
{"title":"The challenge from remote to blended learning since the COVID-19 pandemic: the case of Operational Research in Industrial Engineering","authors":"Norma Furlan, R. Pringles, Andrés Flores Palma, Gabriela Escrivá, Valeria Lorenzo","doi":"10.1109/ARGENCON55245.2022.9940034","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9940034","url":null,"abstract":"This work describes the didactic experience made in the period 2020-2021 in Operations Research course in Industrial Engineering of the Faculty of Engineering of the National University of San Juan. Shifting to remote learning we made faster and deeper the methodological and technical changes in the teaching-learning process designed before pandemic. Both were based on the digital transformation of education and efforts to reform engineering education in Argentina: in order to meet the demands of this dynamic world, engineering programs are challenged to find innovative ways to teach classes so that graduates are prepared in soft skills as well as technical skills. The UNSJ Distance Education System made the Moodle platform immediately and massively available. This allowed us to make an abrupt transformation of the learning space. We use the flipped classroom method, design activities to promote transversal skills and modify the forms of evaluation. In response, the students have shown a strong commitment to the proposal, an important responsibility in group activities and a very good connection with virtual tools. In the post-pandemic we will opt a blend learning, to enhance the benefits of online and face-to-face teaching and tend to design a student-centered learning methodology.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132471870","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 : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939813
C. Ochoa-Malhaber, Diego Ochoa-Ochoa, Xavier Serrano-Guerrero, A. Barragán-Escandón
The use of microgrids is becoming increasingly widespread, as they can be implemented independently of location and according to the energy resource available in each area. They also provide a reliable, efficient and clean supply of electricity. In the Galapagos island region of Ecuador, there are several sources of energy resources, many of which are not used for the benefit of the communities. This study uses a load profile of a community of 50 families (300 people) that includes children, youth, adults and elderly. Three types of hybrid systems: Wind/PV, Biomass/PV, Biomass/Wind, are proposed to cover the electricity needs, which are modeled with HOMER Pro software. The results indicate that microgrid systems are feasible to implement, as they are shown to be capable of supplying electricity to entire communities. In addition, the microgrid system with the lowest net present cost (NPC) is Wind/PV with 75 k$, but the cost of energy (COE) is the highest at 1.41 $/kWh. In contrast, the Biomass/PV microgrid system has an NPC of 382.71 k$ and a COE of 0.49 $/kWh. Therefore, the system to be implemented will depend on the energy needs of the area.
{"title":"Technical-economic comparison of microgrids for rural communities in the island region of Galapagos, Ecuador: Isabela Island case","authors":"C. Ochoa-Malhaber, Diego Ochoa-Ochoa, Xavier Serrano-Guerrero, A. Barragán-Escandón","doi":"10.1109/ARGENCON55245.2022.9939813","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939813","url":null,"abstract":"The use of microgrids is becoming increasingly widespread, as they can be implemented independently of location and according to the energy resource available in each area. They also provide a reliable, efficient and clean supply of electricity. In the Galapagos island region of Ecuador, there are several sources of energy resources, many of which are not used for the benefit of the communities. This study uses a load profile of a community of 50 families (300 people) that includes children, youth, adults and elderly. Three types of hybrid systems: Wind/PV, Biomass/PV, Biomass/Wind, are proposed to cover the electricity needs, which are modeled with HOMER Pro software. The results indicate that microgrid systems are feasible to implement, as they are shown to be capable of supplying electricity to entire communities. In addition, the microgrid system with the lowest net present cost (NPC) is Wind/PV with 75 k$, but the cost of energy (COE) is the highest at 1.41 $/kWh. In contrast, the Biomass/PV microgrid system has an NPC of 382.71 k$ and a COE of 0.49 $/kWh. Therefore, the system to be implemented will depend on the energy needs of the area.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130449716","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 : 2022-09-07DOI: 10.1109/argencon55245.2022.9940075
Juan Medved, M. Real, Marcelo Cazabat, Alejandra Tonina
Este trabajo muestra los avances en la digitali- zación y automatización de las mediciones en el Laboratorio de Capacidad e Inductancia del INTI. El nuevo sistema de medición presentado permite extender el tipo de mediciones realizadas, como por ejemplo la determinación de coeficientes de temperatura o el estudio de la respuesta a distintas frecuencias de los patrones del laboratorio.
{"title":"Automatización en la medición de impedancias","authors":"Juan Medved, M. Real, Marcelo Cazabat, Alejandra Tonina","doi":"10.1109/argencon55245.2022.9940075","DOIUrl":"https://doi.org/10.1109/argencon55245.2022.9940075","url":null,"abstract":"Este trabajo muestra los avances en la digitali- zación y automatización de las mediciones en el Laboratorio de Capacidad e Inductancia del INTI. El nuevo sistema de medición presentado permite extender el tipo de mediciones realizadas, como por ejemplo la determinación de coeficientes de temperatura o el estudio de la respuesta a distintas frecuencias de los patrones del laboratorio.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127881319","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 : 2022-09-07DOI: 10.1109/ARGENCON55245.2022.9939868
Javier Esarte, Pablo Daniel Folino, Juan Carlos Gómez
Reinforcement learning is a field of artificial intelligence that is continuously evolving and has a wide variety of applications. In recent years major progress has been made in the application of deep reinforcement learning to high-dimensional problems with continuous state and action spaces. This paper presents a complete analysis of the application of the soft actor-critic algorithm to teach a four legged robot with three joints on each leg how to move towards the center of a virtually simulated environment. The general formulation of the reinforcement learning problem is first presented, followed by the description of the environment under analysis and the applied algorithm. Afterwards, the obtained results are compared against those of a manually programmed policy, closing with a discussion of some key design choices and common challenges.
{"title":"Moving in a Simulated Environment Through Deep Reinforcement Learning","authors":"Javier Esarte, Pablo Daniel Folino, Juan Carlos Gómez","doi":"10.1109/ARGENCON55245.2022.9939868","DOIUrl":"https://doi.org/10.1109/ARGENCON55245.2022.9939868","url":null,"abstract":"Reinforcement learning is a field of artificial intelligence that is continuously evolving and has a wide variety of applications. In recent years major progress has been made in the application of deep reinforcement learning to high-dimensional problems with continuous state and action spaces. This paper presents a complete analysis of the application of the soft actor-critic algorithm to teach a four legged robot with three joints on each leg how to move towards the center of a virtually simulated environment. The general formulation of the reinforcement learning problem is first presented, followed by the description of the environment under analysis and the applied algorithm. Afterwards, the obtained results are compared against those of a manually programmed policy, closing with a discussion of some key design choices and common challenges.","PeriodicalId":318846,"journal":{"name":"2022 IEEE Biennial Congress of Argentina (ARGENCON)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131235034","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：