http://sedici.unlp.edu.ar:80/handle/10915/87791 Tue, 10 Nov 2026 10:10:34 GMT 2026-11-10T10:10:34Z http://sedici.unlp.edu.ar:80/handle/10915/87823 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) Identifying gender discrimination in the allocations of public grants is a matter of key importance. The objective of this article is to explore the presence of gender bias in the allocation of public funds to support scientific activity by studying the Fund for Scientific and Technological Research (FONCYT) in Argentina. In order to identifying gender discrimination in the allocations of grants, we test the presence of Matthew and Matilda effects. The former is related to the positive feedbacks between previous access to public funds and present possibilities of accessing. The latter, in turn, refers to lower level of probabilities of accessing and remaining for women. Research questions are about the existence and verification of Matthew and Matilda effects. The database consist of all the researchers that applied to FONCYT between 2003 and 2015, whether they were granted or not. Available information includes participation into the program together with their scientific production, academic achievements, and demographic information -such as date of birth, gender, place of residence, academic affiliation, years of experience, and other relevant data is considered. The period under analysis coincides with a period of significant expansion of the fund given by an increase in the level of financial resources. Additionally, the information related to academic productivity was validated with bibliometric information retrieved from SCOPUS database. Results provide evidence that confirms multiple forms of the Matilda effect, and verifies the Matthew one in the scientific research subsidy program. This seems to verify that female researchers suffer a strong disadvantage in the allocation of public funds to finance their research projects. http://sedici.unlp.edu.ar:80/handle/10915/87823 Identifying gender discrimination in the allocations of public grants is a matter of key importance. The objective of this article is to explore the presence of gender bias in the allocation of public funds to support scientific activity by studying the Fund for Scientific and Technological Research (FONCYT) in Argentina. In order to identifying gender discrimination in the allocations of grants, we test the presence of Matthew and Matilda effects. The former is related to the positive feedbacks between previous access to public funds and present possibilities of accessing. The latter, in turn, refers to lower level of probabilities of accessing and remaining for women. Research questions are about the existence and verification of Matthew and Matilda effects. The database consist of all the researchers that applied to FONCYT between 2003 and 2015, whether they were granted or not. Available information includes participation into the program together with their scientific production, academic achievements, and demographic information -such as date of birth, gender, place of residence, academic affiliation, years of experience, and other relevant data is considered. The period under analysis coincides with a period of significant expansion of the fund given by an increase in the level of financial resources. Additionally, the information related to academic productivity was validated with bibliometric information retrieved from SCOPUS database. Results provide evidence that confirms multiple forms of the Matilda effect, and verifies the Matthew one in the scientific research subsidy program. This seems to verify that female researchers suffer a strong disadvantage in the allocation of public funds to finance their research projects. http://sedici.unlp.edu.ar:80/handle/10915/87821 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) The motivation of the IPC Online, was to act and make accountable a policy that misinformed economic agents. It allows for cross checking to highly important variable such as prices with different geographical scopes. It has been shown how webscraping- data-based urban indices were estimated and contrasted to traditional-based indices granting highly efficient measurements at one thousandth of cost. Combined with many other variables that can be captured or downloaded from the Internet [2] paints a future of combined indicators for tracking the socioeconomic life, even remotely. http://sedici.unlp.edu.ar:80/handle/10915/87821 The motivation of the IPC Online, was to act and make accountable a policy that misinformed economic agents. It allows for cross checking to highly important variable such as prices with different geographical scopes. It has been shown how webscraping- data-based urban indices were estimated and contrasted to traditional-based indices granting highly efficient measurements at one thousandth of cost. Combined with many other variables that can be captured or downloaded from the Internet [2] paints a future of combined indicators for tracking the socioeconomic life, even remotely. http://sedici.unlp.edu.ar:80/handle/10915/87818 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) En el presente trabajo se pretende detectar patrones que ayuden a identificar los tipos de delitos ejecutados sobre adultos mayores, de modo que este análisis colabore con la prevención a partir de medidas de concientización y demás acciones, estudiando para ello las características y modalidades relevantes de éstos actos, a través de la aplicación de técnicas descriptivas de minería de datos. Para este estudio se tomaron en cuenta los datos obtenidos de los hechos delictivos ocurridos en la provincia de Jujuy durante el primer trimestre del año 2019. La aplicación de técnicas descriptivas de minería de datos son un apoyo confiable para los organismos de seguridad en la toma de decisiones, ya que muestran de forma clara, características importantes sobre la información existente, en este caso, correspondiente a delitos acontecidos en la provincia de Jujuy. En la primera etapa de este proyecto se busca incorporar técnicas descriptivas para el análisis inteligente de los hechos delictivos registrados, considerando, en sucesivas etapas la aplicación de técnicas predictivas. El trabajo se encara como parte de las actividades del grupo de investigación denominado “Implementación de técnicas específicas de Minería de datos en aplicaciones web con motores de Base de Datos Relacionales” de la Facultad de Ingeniería de la UNJu. http://sedici.unlp.edu.ar:80/handle/10915/87818 En el presente trabajo se pretende detectar patrones que ayuden a identificar los tipos de delitos ejecutados sobre adultos mayores, de modo que este análisis colabore con la prevención a partir de medidas de concientización y demás acciones, estudiando para ello las características y modalidades relevantes de éstos actos, a través de la aplicación de técnicas descriptivas de minería de datos. Para este estudio se tomaron en cuenta los datos obtenidos de los hechos delictivos ocurridos en la provincia de Jujuy durante el primer trimestre del año 2019. La aplicación de técnicas descriptivas de minería de datos son un apoyo confiable para los organismos de seguridad en la toma de decisiones, ya que muestran de forma clara, características importantes sobre la información existente, en este caso, correspondiente a delitos acontecidos en la provincia de Jujuy. En la primera etapa de este proyecto se busca incorporar técnicas descriptivas para el análisis inteligente de los hechos delictivos registrados, considerando, en sucesivas etapas la aplicación de técnicas predictivas. El trabajo se encara como parte de las actividades del grupo de investigación denominado “Implementación de técnicas específicas de Minería de datos en aplicaciones web con motores de Base de Datos Relacionales” de la Facultad de Ingeniería de la UNJu. http://sedici.unlp.edu.ar:80/handle/10915/87816 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) El presente trabajo describe el desarrollo de un sistema que provee una solución al manejo de grandes volúmenes de datos primarios generados por dispositivos adquisidores de datos (dataloggers) y posibilita su búsqueda en un Repositorio Institucional por medio de georreferencias. En particular para esta implementación se utilizaron datos de pingüinos y cormoranes donde se registran sus datos georreferenciados y archivos multimedia asociados. La solución propuesta permite la catalogación de los registros, incorporación de metadatos, almacenamiento, control de acceso y consultas. El sistema integra DSpace, PostGIS y Leaflet. http://sedici.unlp.edu.ar:80/handle/10915/87816 El presente trabajo describe el desarrollo de un sistema que provee una solución al manejo de grandes volúmenes de datos primarios generados por dispositivos adquisidores de datos (dataloggers) y posibilita su búsqueda en un Repositorio Institucional por medio de georreferencias. En particular para esta implementación se utilizaron datos de pingüinos y cormoranes donde se registran sus datos georreferenciados y archivos multimedia asociados. La solución propuesta permite la catalogación de los registros, incorporación de metadatos, almacenamiento, control de acceso y consultas. El sistema integra DSpace, PostGIS y Leaflet. http://sedici.unlp.edu.ar:80/handle/10915/87811 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) We are tackling the problem of trading real-world private information using only cryptographic protocols and a public blockchain to guarantee honest transactions. In this project, we consider three types of agents —buyers, sellers and notaries— interacting in a decentralized privacy-preserving data marketplace (dPDM) such as theWibson data marketplace. This framework offers infrastructure and financial incentives for individuals to securely sell personal information while preserving personal privacy. Here we provide an efficient cryptographic primitive for the secure exchange of data in a dPDM, which occurs as an atomic operation wherein the data buyer gets access to the data and the data seller gets paid simultaneously. http://sedici.unlp.edu.ar:80/handle/10915/87811 We are tackling the problem of trading real-world private information using only cryptographic protocols and a public blockchain to guarantee honest transactions. In this project, we consider three types of agents —buyers, sellers and notaries— interacting in a decentralized privacy-preserving data marketplace (dPDM) such as theWibson data marketplace. This framework offers infrastructure and financial incentives for individuals to securely sell personal information while preserving personal privacy. Here we provide an efficient cryptographic primitive for the secure exchange of data in a dPDM, which occurs as an atomic operation wherein the data buyer gets access to the data and the data seller gets paid simultaneously. http://sedici.unlp.edu.ar:80/handle/10915/87809 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) Large amounts of ancient documents have become available in the last years, regarding Argentinian history. This fact turns possible to find interesting and useful aggregated information. This work proposes the application of Natural Language Processing, Text Mining and Visualization tools over Argentinian ancient document repositories. Conceptual maps and entity networks make up the first target of this preliminary paper. The first step is the normalization of OCR acquired books of General G¨uemes. Exploratory analyses reveal the presence of manifold spelling errors, due to the OCR acquisition process of the volumes. We propose smart automatic ways for overcoming this issue in the process of normalization. Besides, a first topic landscape of a subset of volumes is obtained and analysed, via Topic Modelling tools. http://sedici.unlp.edu.ar:80/handle/10915/87809 Large amounts of ancient documents have become available in the last years, regarding Argentinian history. This fact turns possible to find interesting and useful aggregated information. This work proposes the application of Natural Language Processing, Text Mining and Visualization tools over Argentinian ancient document repositories. Conceptual maps and entity networks make up the first target of this preliminary paper. The first step is the normalization of OCR acquired books of General G¨uemes. Exploratory analyses reveal the presence of manifold spelling errors, due to the OCR acquisition process of the volumes. We propose smart automatic ways for overcoming this issue in the process of normalization. Besides, a first topic landscape of a subset of volumes is obtained and analysed, via Topic Modelling tools. http://sedici.unlp.edu.ar:80/handle/10915/87808 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) En este trabajo desarrollamos una metodología para cuanti car la controversia en una red social exclusivamente a través de su jerga, es decir por el lenguaje que utilizan sus usarios. Presentamos resultados preliminares de nuestros experimentos en los que logramos una accuracy equiparable a los métodos del estado del arte basados en la estructura. http://sedici.unlp.edu.ar:80/handle/10915/87808 En este trabajo desarrollamos una metodología para cuanti car la controversia en una red social exclusivamente a través de su jerga, es decir por el lenguaje que utilizan sus usarios. Presentamos resultados preliminares de nuestros experimentos en los que logramos una accuracy equiparable a los métodos del estado del arte basados en la estructura. http://sedici.unlp.edu.ar:80/handle/10915/87805 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) We present a tool to calculate distances and travel times between a set of origins and a set of destinations, using different modes of transport in Argentina. The input data for the tool is a set of destinations (a geo-referenced list of points of city amenities or “opportunities”, such as firms, schools, hospitals, parks, banks or retail, etc.) and a set of origins characterized by their geographic coordinates that could be interpreted as households or other. The tool determines, from each origin, which is the closest destination, depending on the distance or travel time and the mode of transport (on foot, by bicycle, by car, and by public transport). The sets of origins and destinations are large sets, which can contain up to several thousand points. We applied and developed algorithms to improve the scalability of the different parts of the procedure. For the public transportation network, we pre-processed the reachable lines from each point and used quad-trees to determine the distance between said points and the bus line’s path. A second objective of this project was to rely only on open data, such as Open Street Map (OSM) data, together with making this tool open source. Therefore, the successful development and implementation of this tool is potentially beneficial to both public sector agencies as well as NGOs and other civil society organizations that focus their work on the design and implementation of public policies, aimed at improving accessibility in cities as a way to reduce spatial inequalities and social exclusion. http://sedici.unlp.edu.ar:80/handle/10915/87805 We present a tool to calculate distances and travel times between a set of origins and a set of destinations, using different modes of transport in Argentina. The input data for the tool is a set of destinations (a geo-referenced list of points of city amenities or “opportunities”, such as firms, schools, hospitals, parks, banks or retail, etc.) and a set of origins characterized by their geographic coordinates that could be interpreted as households or other. The tool determines, from each origin, which is the closest destination, depending on the distance or travel time and the mode of transport (on foot, by bicycle, by car, and by public transport). The sets of origins and destinations are large sets, which can contain up to several thousand points. We applied and developed algorithms to improve the scalability of the different parts of the procedure. For the public transportation network, we pre-processed the reachable lines from each point and used quad-trees to determine the distance between said points and the bus line’s path. A second objective of this project was to rely only on open data, such as Open Street Map (OSM) data, together with making this tool open source. Therefore, the successful development and implementation of this tool is potentially beneficial to both public sector agencies as well as NGOs and other civil society organizations that focus their work on the design and implementation of public policies, aimed at improving accessibility in cities as a way to reduce spatial inequalities and social exclusion. http://sedici.unlp.edu.ar:80/handle/10915/87802 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) En este trabajo proponemos utilizar una función de costo con términos de regularización dependientes de la estructura del grafo combinándola con el modelo de árboles optimizados por el gradiente (XGB+SSL). De esta forma, logramos adaptar el modelo de XGB a escenarios semi-supervisados. Además, mostramos que nuestra implementación supera http://sedici.unlp.edu.ar:80/handle/10915/87802 En este trabajo proponemos utilizar una función de costo con términos de regularización dependientes de la estructura del grafo combinándola con el modelo de árboles optimizados por el gradiente (XGB+SSL). De esta forma, logramos adaptar el modelo de XGB a escenarios semi-supervisados. Además, mostramos que nuestra implementación supera http://sedici.unlp.edu.ar:80/handle/10915/87801 Objeto de conferencia V Simposio Argentino de Ciencia de Datos y GRANdes DAtos (AGRANDA 2019) - JAIIO 48 (Salta) In this work, we present two new variants to the deepSOM model: the deep elastic SOM (deSOM) and the deep ensemble elastic SOM (deeSOM), which overcome the mentioned issues. In deSOM the number of deep levels not only grows automatically, but also the size of each layer is expanded adaptively according to the data at each level, thus pre-miRNA neurons can be re-organized in a larger space. Extended abstract from Deep neural architectures for highly imbalanced data in bioinformatics, L. A. Bugnon, C. Yones, D. H. Milone, G. Stegmayer, (to appear in) IEEE Transactions on Neural Networks and Learning Systems (2019), doi 10.1109/TNNLS.2019.2914471 http://sedici.unlp.edu.ar:80/handle/10915/87801 In this work, we present two new variants to the deepSOM model: the deep elastic SOM (deSOM) and the deep ensemble elastic SOM (deeSOM), which overcome the mentioned issues. In deSOM the number of deep levels not only grows automatically, but also the size of each layer is expanded adaptively according to the data at each level, thus pre-miRNA neurons can be re-organized in a larger space.