Maestría en Ciencias de la Información y las Comunicaciones
URI permanente para esta colecciónhttp://hdl.handle.net/11349/18
Examinar
Examinando Maestría en Ciencias de la Información y las Comunicaciones por Fecha de publicación
Mostrando 1 - 20 de 242
- Resultados por página
- Opciones de ordenación
Ítem Segmentación de Imágenes de Resonancia Magnética (IRM) para determinar regiones tumorales de cancer de próstataRodríguez Sánchez, Carlos Alberto; Cancino de Greiff, Héctor FernandoAim: The main purpose of this study is to present some results related with the use of code for the analysis of Magnetic Resonance Imaging (IMR) with the idea of analysing anatomical images with high contrast and resolution, based on the bi-exponential method of incoherent motion, initially implemented by Lebihan, commonly known as Intravoxel Incoherent Motion method (hereafter, IVIM). method: By analysing segmentation algorithms in IMR images acquired by IVIM’s method, we pretend to validate and compare novel techniques in the post-processing of the images obtained by perfusion, diffusion and apparent diffusion, often used in the characterization of angiogenesis in cancerous tissues. Results: This work validates the results reported by Roman, (2013) and Gomez (2010). While the images obtained by IVIM still exhibit high sensitivity, post-processing analysis supports the general idea that this technique can be useful for the detection of prostate cancer.Ítem Prueba Piloto para el levantamiento de información del RUD a través de plataforma móvil y visualización en visor geográficoAlvarado Vargas, Diana Carolina; Medina Daza, Rubén JavierThis project is aimed at carrying out a pilot test for the lifting of the "Unique Registry of Victims" (RUD), this being a tool whose purpose is to determine the effects caused throughout the Colombian territory, aware of the importance of identifying and characterizing the natural persons affected by unintentional natural or anthropogenic events, this tool is administered by the Disaster Management Subdirectorate of the "National Unit for Disaster Risk Management" (UNGRD), an entity attached to the Presidency of the Republic of Colombia , created in 2011 to direct and coordinate the national system for the prevention and attention of disasters.At this time, the Subdirectorate has problems with the management of the registry information, since its collection method is a web application which does not allows obtaining geographic coordinates of the victim and all the information is associated with Depa rtamento –Municipality, additionally there is no display of the registry and all related queries must be done under the SQL query command, causing this to generate a setback and not having the information available in real time. To solve this inconvenience, the present project explains the development to generate a pilot test for the collection of RUD information through a mobile platform which is dynamic, easy to access and manage so that after that the information is displayed in a viewer. geographical, which allows spatial analysis of the updated, quality and accurate information collected. For its development, the CROA methodology was used based on the creation of learning objects where the design of a form designed in Survey123 is carried out for the report of the record of the victim through the capture of data in a pilot test in the field in Colombia, where it provides consolidated information to prepare quantitative and qualitative analyses. This developed in ArcGIS Insights. For its visualization, a "Story Map" will be incorporated with the data collected in ArcGIS Online under an Enterprise license. To conclude, the developed project seeks to have real knowledge of the information from a geographic viewer, which allows knowing a georeferencing of points in the field with a mobile platform through a form where it will allow a better decision making for the Entity and It will serve as input to determine the level of affectation of the event that occurred.Ítem Modelo de un sistema de software basado en las técnicas de Learning Analytics como herramienta de apoyo en la toma de decisiones académico-administrativas en las instituciones públicas de educación superior.Nieto Acevedo, Yuri Vanessa; Montenegro Marin, Carlos EnriqueThe latest attention that Learning Analytics has received, in part is because it encounters hidden patterns in educational data that once is processed and integrated into a specific case of use, offers to stakeholders assistance to improve their task into educational context. Due to it highly application, Learning Analytics techniques are integrated into a Decision Support System proposed to help administrators to develop decision making process and collaterally enhance student performance. In this paper, is defined a Decision Support System and how it has been use in educational institutions; is presented the functionalities of Learning Analytics and presented a survey of how can be integrated to produce a Learning Decision Support System to help faculty or department administrators to improve their decision impact in the academic community.Ítem Diseño e implementación de un sistema de monitoreo remoto de ritmo cardiaco y generación de alertas preventivas para la supervisión de pacientes en riesgo potencialCañón Clavijo, Rubén Enrique; Marín, Carlos Enrique Montenegro; Ortiz-Guzman, Johan-Enrique; Marín, Carlos Enrique Montenegro [0000-0002-9460-7254]The technologies involved in the internet of things (“Internet of Things” IoT) allow objects, people or phenomena to be digitally represented through interesting data that is captured from them to be sent through the internet and interpreted by a computer. Interest in research on the Internet of Things has been growing in recent years (Jagtap, et al., 2021), impacting different sectors such as health, the environment, mobility, security, among others. Such is the interest in the health sector that the term Internet of Medical Things (MIoT) was born, which refers to the use of portable sensors and connected medical devices to provide innovative services to hospitals, patients and medical personnel (Bolhasani et al. ., 2021). Taking into account the possibilities offered by these technologies in the health sector, with the participation of the company Firefly energy, a heart rate monitoring project is proposed for remote patient supervision. This document shows the development of this project as an internship, detailing the stages of requirements management, design and verification of the monitoring system of the patient's health conditions and data analysis for the generation of preventive alarms.Ítem Metodología para la transformación de datos geográficos a recursos RDFFigueroa Ceferino, Diana Carolina; Perdomo Charry, Cesar Andrey; Perdomo Charry, Cesar Andrey [0000-0001-7310-4618]This project describes a methodology to transform geographic data sets into geographic linked data under the commonly used standards. For the methodology, the research considered different geographic data types and software tools available as part of the analysis of geographic data transformation into RDF. There were also considerations fordifferent alternatives for semantic queries as well as the for data inference and data management. This method aims not only to follow web publication standards but also to validate a component-based architecture for transforming and the series of tasks needed for transforming vector-data into RDF. By validating the designed method and the transformed data becomes a relevant contribution to the current state of research for the fields of geomatics and linked data.Ítem Creación de visor geográfico utilizando herramientas de software libre para la representación de fenómenos relacionados con el conflicto armadoCaballero Modera, Nicols Ernesto; Salcedo Parra, Octavio JoseThis document seeks to show the design process of an architecture for a WEB GIS system oriented towards the representation of phenomena related to the armed conflict, in order to develop and implement the base modules that allow administration, access, consultation and maintenance of geographic and cartographic information, the foregoing in order to simplify the access, administration, and publication of geographic and spatial data. Supporting this in free software elements that do not imply the generation of licensing costs for the construction of a customized solution (geographical viewer).Ítem Modelo de Entrenamiento de un Sistema Experto Basado en Reglas Mediante Aprendizaje por Refuerzo Aplicado a la Generación de TrayectoriasCalderon Coy, Milton Vicente; Camargo Casallas, EsperanzaIn mobile robotics, the task of generating trajectories to a destination point has been approached from various angles with different algorithms. These include heuristic search, graphs, neural networks, and swarm algorithms. Some of these require the generation of a set of nodes that can be organized in multiple ways throughout the environment through which the robot will move. Another type of approach focuses on the nature of the environment which may be fully or partially known, static or dynamic, which means that the route may be planned in advance or must be plotted and adjusted as it makes its way to the destination point. Artificial intelligence is a relatively new field that was born in the 1950s. Currently, one of its most interesting branches is reinforcement learning. This branch consists of a type of learning in which the artificial intelligence system interacts with an environment from which knowledge can be generated automatically and gradually. There are currently a large number of artificial intelligence systems that work by means of complex neural networks, in which it is not easy to determine whether the model behind their decisions presents some kind of bias when analyzing the data. For example, the classification of a person's credit risk based on variables such as race or gender, given the poor interpretability of such a model. On the other hand, there are other methodologies that have high model explainability, such as decision trees or rule-based expert systems. In stratospheric navigation, it is a challenge to guide a vehicle in the descent phase taking into account its fall speed, as well as the random behavior of the environmental variables it faces. Therefore, a rule-based expert system training system was developed, which is trained by reinforcement learning. With this in mind, it was necessary to generate a training context that implements the task to be solved by the expert system. This environment generates challenges to be learned by the expert system. The proposed system would present an advantage over other models: the possible human intervention in the resulting set of rules, and, therefore, in the model that controls the expert system that makes the decisions. However, the possibility of auditing the system and possible modification will result in a change in the system's ability to solve the task. As a result, a reinforcement training system was obtained through which a set of rules is obtained. These rules contain the knowledge required by the expert system to establish the trajectory from the starting point to the destination point, avoiding leaving the environment and avoiding obstacles in 76.2% of the validation episodes executed.Ítem Guía para el uso de cloud computing como mecanismo de recuperación ante desastres tecnológicos en PYMES ColombianasSerrano Molina, Yohel Rene; Perez Castillo, Jose NelsonThis work summarizes the design of a guide to use the tools offered by cloud computing as a mechanism to recover from technological disasters in Colombian SMEs. The objective of this work is a series of easy-to-use steps to implement information protection solutions and technological infrastructure, which allow organizations to continue operating when a technological disaster occurs for any circumstance. The development of the project began The analysis of the state of cloud computing, the monitoring of cloud computing and the vision in the model of cloud computing. and Windows azure), in relation to disaster recovery. Part of the above information is found in the guide that contains seven steps to implement disaster recovery projects in the cloud. Finally, in a company of type Pyme. The most important conclusion is that the guide implemented and subsequently tested allows entrepreneurs and staff in the technology areas to have a clear idea of the benefits of the cloud and how to use it in the disaster recovery plans.Ítem Implementación de una Plataforma Web para el IPAZUD con el objetivo de almacenar, clasificar y divulgar las publicaciones que produce la entidad (Libros, Revistas, Investigaciones y Proyectos), garantizando su integridad y disponiendo la información para su consulta a través del sitio webVargas Anzola, Manuel Antonio; Salcedo Parra, Octavio JoseThe Institute for Pedagogy, Peace and Urban Conflict - IPAZUD, which aims to preserve and disseminate editorial production around thematic axes such as peace, conflict, territory, citizenship, memories, Human Rights and gender studies in correspondence with the particular realities of the territories of Colombia; and that it has been developed or is the product of research by institutions, agencies and for-profit or non-profit organizations interested in specific issues. The project of the implementation of a repository seeks the storage, management and dissemination of the publications (books, magazines, research and projects) carried out by IPAZUD over time; information that can be accessed through a web browser. The attributes of each publication are subject to customization of its metadata with which the publications are stored. Also, management (uploading and editing posts) will only be available to users with specific roles. The publications will be available on the internet for searching, viewing and downloading where permitted. In addition, the content exposed by the website will have the ability to be indexed by web search engines such as Google, thereby contributing to its dissemination in the academic spheres surrounding the Institute and to all users who are interested in knowing the publications made by the Institute. IPAZUD.Ítem Modelo para la caracterización de procesos de toma de decisiones no programadas por medio de gamificaciónAlbadán Romero, Javier; Gaona García, Paulo AlonsoThis research is delimited in the decision-making non-programmed, which are carried out by a person in atypical scenarios, where the information is ambiguous and involves the implementation of unusual solution methods. In selection process for senior management roles, it require to measure the skills of a decision-making expert and, in this way, the tests applied mostly are in paper and pencil they, long application times and for a explicit transfer of information. The results of implementation, of the web application that was consolidated, show a decrease in the time of application of the psychological test and the implicit transfer of information to generate the profile of the candidate. Additionally, another potential area of implementation of gamification, in this case, in the selection process.Ítem Inteligencia artificial aplicada al posicionamiento de antenas en estaciones terrenas de seguimiento a picosatelites(Universidad Distrital Francisco José de Caldas) Mesa Lara, Jairo Alonso; Ferro Escobar, RobertoEl proyecto Cubesat UD tiene contemplada la construcción, entre otras, de una estación terrena en la ciudad de Tunja en conjunto con la Universidad Pedagógica y Tecnológica de Colombia, donde se hará seguimiento a picosatélites en órbitas bajas. Actualmente, cuenta con un software de predicción de órbita y a partir de los datos emitidos por este tipo de software, se propone diseñar un modelo que basado en Inteligencia Artificial, permita controlar de forma automática el posicionamiento de las antenas propias de la estación. Este trabajo muestra los elementos requeridos para la construcción del sistema de control de posicionamiento y corresponde a una aplicación puntual en la estación terrena ubicada en la Universidad Pedagógica y Tecnológica en la ciudad de Tunja, pero sirve como referente para ser aplicado en otras estaciones terrenas.Ítem Sistema de tutoría inteligente en redes de telecomunicaciones de sensores inalámbricos (WSN), basado en estándares abiertos e interoperablesZamora Navarro, Francisco Javier; Gaona García, Elvis EduardoThis master's thesis presents a rationale, a detailed summary of background investigation and practical development proposal and research framework in the field of intelillent tutoring systems (ITS) using an updated methodology to model, design and deploy an adaptive course with e-learning standards related to wireless sensors networks (WSN) for the Engineering Faculty at Universidad Distrital Francisco José de Caldas, using free tools, ontological modeling, adaptivity by case based reasoning (CBR), computerized Adaptive Testing (CAT) with item response theory (IRT), intelligent SCORM learning objects (OA) LMS MOODLE interoperable, and support for external assessment engine TAO. During this first intelligent, open, online course for the UDFJC Enineering Faculty, a results validation is proposed through statistical analysis by means of structural equation model (SEM) and recommended guidelines for future work which should integrate relevant technologies such as multiple agent systems, learning records store (LRS), IMS standards, digital portfolio (e-portfolios), massive open online courses (MOOC), learning analytics (LA), educational data mining (EDM) and brain computer interfaces (BCI).Ítem Análisis exploratorio espacio-temporal de la delincuencia en Colombia asociada al hurto de vehículos entre los años 2010-2019 mediante la integración de técnicas de minería de datos, Geoestadística y SIGGonzález Buitrago, Gabriel Hernán; Castillo Méndez, Luis EduardoIn this document, an exploratory spatiotemporal analysis of the criminal acts that occurred in Colombia associated with vehicle thefts between 2010 to 2019 is carried out through the integration of data mining techniques, Geostatistics and Geographic Information Systems with the aim of identifying relationships between variables associated with historical complaints, characterize the crime and determine the areas where the attention of the State should be prioritized. The research is based on the scientific method and is segmented into the observation phase, where an exploratory analysis of the data is carried out, followed by the experimentation phase comprised by the use of data mining techniques, Geostatistics and statistical modeling on the data. Tools such as the K-means algorithm, decision trees, the calculation of the Moran I statistic and a counting model allow us to understand the behavior of this crime at the municipal level.Ítem Clasificación de cobertura del suelo sobre área urbana a partir de imágenes satelitales de mediana resolución empleando regresión-kriging: una comparación con otros métodos no convencionalesRivera Guerrero, Bibiana Rocío; Melo Martínez, Carlos EduardoIn this paper the classification of land coverage on urban area from medium resolution satellite images using regression-kriging was proposed. In order to evaluate the performance of the regression-kriging method was made a classification of a satellite image, it was compared with other classifications obtained by the Support Vector Machines, Distance Mahalanobis, Decision Trees, Artificial Neural Networks methods and Random Forests. The classification of land coverage was made on a SPOT 5 satellite image. The study area corresponds to a central area of the city of Bogota, Colombia; the program selected to process the image was the software "R". Within the results of work is implementing a methodology for classifying satellite images using regression-kriging, the code developed in "R" to classify images by the six with the above methods, six classifications maps, the confusion matrices, the confidence intervals and other indexes to evaluate the accuracy of the classification. All methods showed a good performance in the classification task and thus it was found that in the case of the classification of land cover in urban areas is more effective the regresión-kriging method that considers not only the spectral characteristics of the image also the structure of spatial correlation existing between the data.Ítem Sistema de identificación y análisis de variables de riesgo para el cálculo de primas de reaseguro empleando modelos computacionalesVargas Carrillo, Luz Angela; Rodríguez Rodríguez, Jorge EnriqueThe purpose of this document is to build a model based on decision tress and learning algorithms, which will allow to predict, if a business opportunity that arrives to a reinsurance brokerage firm can be won or lost. In the same manner to obtain decision rules which can optimize the internal process of the company, in such a way as to reduce the percentage of loss of business and increase customer’s retention rate.Ítem Extracción del contexto geográfico a apartir de NLP para información de transito en redes socialesRobles Mondragón, Alexander; Perdomo Charry, César AndreyLittle has been said about the retrieval of spatial information from text, particularly because the term "spatial information" is associated with geometries in the form of vectors or raster-type information that express different variables or phenomena accompanied by coordinates, despite this the extraction of information in text is presented as one of the most promising advances thanks to natural language processing (NLP) and in this case it is outlined as a new field of action complementary to spatial analysis, trying to extract a specific event that happens in space and embodied in a text. The main source of text, for this research, are those shared in a collaboration network such as twitter. The extracted events are those that are found or refer to the road network and that arise in a recurring or random way, the latter, Chance, the most difficult to manage in any city that must monitor the traffic of road actors under a network of sensors that try to see the congestion of the roads and road incidents. Now, these texts were stored under a database scheme classified as road incidence that are passed over a writing pattern recognizer that extracts the location and subsequently feeds a georeferencer that returns a pair of coordinates (lat, lon), the The idea with these coordinates is to convert them into compiled data that, within a spatial analysis, show a grouping phenomenon under geostatistical techniques such as spatial autocorrelation, finding hot spots or cold spots of incident existence. The defined similar geographic results are compared with data from recent years collected by official transit entities and that are published for free access, the comparison of patterns between a previous year and those extracted with artificial intelligence show spatial behaviors and spatial self-connection preserves certain similarity revealing the usefulness of the geographical focus extraction that is proposed and possible to complement a data source for the management of road congestion and traffic incidents.Ítem Diseñode una oficina de dirección de proyectos, con enfoque en proyectos de investigación en la Red de Investigaciones de Tecnología Avanzada de la Universidad DistritalDiaz Carretero, Eduardo Alfonso; Roberto, Ferro EscobarThanks to the continuous technological growth in project innovation, this work seeks to create, design and implement a Project Management Office in the RITA Advanced Technology Research Network of the Francisco José de Caldas District University, where innovation is supported. in the execution of agile projects in a controlled manner, with a reliable risk index and with high quality standards.Ítem Diseño de un modelo de enrutamiento de tráfico vehicular basado en buenas practicas de otras ciudades con problemática similarFernandez Ibarra, Luz Myriam; Romero Villalobos, Oswaldo AlbertoThis preliminary research conducted on a model of vehicular traffic routing based on practices applied in other cities with similar problems, and raises the relevant variables that must be taken into account. The project is motivated considering the serious problem of mobility that exists in the city for several years, where even though the distances are not as extensive travel times if they are, this due to the congestion that occurs in different routes, in addition to the uncertainty of citizens before defining the route to be taken, it is considered that providing information to users regarding the state of the roads regarding different conditions could reduce this uncertainty and to collaborate citizens make better decisions in route to your destination, as well as avoid the jams become enlarged, improving mobility on our roadsÍtem Sistema de toma de decisiones en el entorno universitario, basado en el análisis de datos.Guzmán Castillo, Nanci Milena; Vera Parra, Nelsón EnriqueOver the years, Geographic Information Systems (GIS) have become an essential tool for the resolution of territorial, socioeconomic and including environmental, have also been used as a tool that adds value to the information, (Buzai & Baxendale, n.d.), since they allow transforming the data in order to perform analysis of spatial information using as much information as possible which will serve as support for business decision making and in turn the use and use of technological and geographic tools.Ítem Elaboración de un algoritmo aplicado a imágenes obtenidas por dron para la cuantificación de fitoplanctonCarrillo Duran, Iván Darío; Medina Daza, Ruben JavierThis thesis proposes a new strategy employing the use of UAV images (Unmanned Aerial Vehicle) for the study of Phytoplankton. The purpose is to build a mathematical model that allows obtaining Chlorophyll-a (Chl-a) from UAV images. With the chlorophyll-a estimate, the approximate amount of phytoplankton in mg m − 3 is estimated. The study area is the Tota lagoon, located in Boyacá (Colombia). The results indicate that chlorophyll-a towards the interior of the Tota lagoon has a very uniform behavior around 10-12 mgm − 3, in addition the image processing in these areas is difficult by the changes in brightness between the contiguous images in the water produced by the specular surface of the water. The contribution of this research is to provide a first approach in the study of Phytoplankton from images captured on board a UAV with the aim of finding a technique that is fast, economical and accurate that allows making decisions that contribute to the care, preservation and mitigation of the problems that deteriorate an aquatic ecosystem.