Maestría en Ciencias de la Información y las Comunicaciones
URI permanente para esta colecciónhttp://hdl.handle.net/11349/18
Examinar
Envíos recientes
Ítem Identificación y simulación de patrones de siembra de cultivos ilícitos de coca mediante minería de datos y autómatas celularesVelandia Casallas, Maria IsabelAlternatively in the identification of coca cultivation in Colombia, it is proposed in this research a methodology based on remote sensing techniques, data mining, fuzzy logic and cellular automata to model the phenomenon of coca planting in the municipality of Miraflores in Guaviare. The proposed methodology can identify the underlying rules that determine the probability of existence of illicit coca crops using the strengths of the techniques of spatial data mining and fuzzy logic. These rules are the input to program the cellular automata so that the phenomenon can be modeled based on the fact that each pixel in the image is a cell controller. The methodology includes four phases i) Analysis and processing of information collected ii) Identification of variables used iii) construction of fuzzy logic model and finally, iv) construction of cellular automata model capable of simulating the planting of coca cultivation Final results after validation give a reliability above 75%, measured by comparing pixel to pixel "image result" with the conventional interpretation of coca crops in the study areaÍtem Sistema ludificado de realidad virtual para el desarrollo de procesos de enseñanza relacionados con la programación de computadoresTamayo Hernández, Donna Johanna; Coronado Sánchez, Paulo Cesar; Coronado Sánchez, Paulo Cesar [0000-0003-2980-2376]This in-depth master's project describes the design, implementation and evaluation of "APOLO", an educational technology system that supports training experiences in computer programming for the development of computational thinking skills and promotion of self-regulation of learning. APOLO is an integrated technosystem that combines the domains of curricular planning, didactic design, open educational resources, learning management systems, software engineering, computer tools and educational analytics. It stands out for its connection to project-based learning (PBL), the inclusion of playful elements (gamification) and the use of immersive virtual reality technologies. These elements interact in APOLO to enhance student motivation, reinforce their self-efficacy, and encourage both self-regulation and the implementation of effective learning strategies.Ítem Desarrollo de un prototipo de sistema para el apoyo en la movilidad autónoma de personas invidentes en exteriores(Universidad Francisco Jose de Caldas) Arévalo Silva, José Agustín; Montenegro Marín, Carlos EnriqueFor individuals with visual impairments, navigating requires a deep understanding of their everyday environment. However, in unfamiliar settings, it becomes a significant challenge, involving their safety, physical well-being, and emotional comfort, as the sense of sight, a primary element for spatial orientation, is absent. Various solutions have been developed to ensure safer navigation and better adaptability to changes in unfamiliar environments, aiming to reduce the risk of accidents or misplacements. In this context, a proposal for a support system for autonomous mobility (SAMA) is introduced for individuals with visual impairments. This system, utilizing low-cost wireless technologies, aims to significantly enhance their adaptability while navigating outdoor spaces.Ítem Modelo para clasificación de precipitaciones estratiformes y convectivas en zona ecuatorial usando datos de radares meteorológicosRomero Ortega, Raúl; Perdomo Charry , Cesar Andrey; Perdomo Charry, César Andrey [0000-0001-7310-4618]This paper shows the proposal of a classification model of stratiform and convective precipitation using data obtained by meteorological radars in equatorial areas, especially in the Colombian geography. The data generated by the meteorological radars will be decoded, this because the data are obtained in the format of the radar manufacturer brand; the above in order to carry out a statistical analysis of them. Having the information statistically analyzed will allow the selection of the variables that will be used in the project from the information obtained in the preliminary analysis. Then, a conceptual model will be designed to define the constraints and relationships between the components of the system, in order to determine the appropriate tools to be used in the classification algorithm. Finally, the design and development of a test protocol will be carried out to validate the classification model of stratiform and convective rainfall.Ítem Modelo de sistema de alerta temprana para desbordamientos de arroyos en Barranquilla basado en la comunidad(Universidad Distrital Francisco José de Caldas) Serna Galeano, Ivan Andres; Goméz Vargas, Ernesto; Gomez Vargas, Ernesto [0000-0003-4957-7313]The present work seeks to design and create a community-based early warning model as an alternative to as an alternative for mitigating the disaster caused by overflowing streams in Barranquilla (Colombia). in Barranquilla (Colombia). This model is based on the contributions in social networks, which are consulted by means of the api of each social network and filtered according to their according to their location, The information collected is cleaned and debugged, and then with debugging, and then with natural language processing techniques to tokenize the texts, seeking to operate vectorize the texts, seeking to operate mathematically to find the vector similarity between processed texts, generating from between processed texts, generating in this way a classification between texts associated with stream associated with stream overflow and texts not associated with overflow. Additionally, the texts classified as stream overflow are processed again in order to obtain a location or assign a default one, in order to georeference these data on a map that georeferencing this data on a map that allows to associate the risk zone and visualize it in a web application, monitoring and decreasing and visualize it in a web application, monitoring and reducing the possible damage to the population. generated to the population. In order to choose the best classifier, 3 classification algorithms were selected (random forest, randomly generated and randomly generated). classification algorithms (random forest, extra tree and k-neigbor) were selected, which showed the best and R2 in reference to the data processed in the regressions performed. regressions. Finally, the three aforementioned algorithms were trained, found that the k-neighbor algorithm obtained 88 failures out of a test set of 400 tweets, being the one with the least number of failures. tweets, being this the one that obtained the least number of failures and selected for the proposed system.Ítem Network Slicing en redes 5G para tráfico Streaming aplicando Deep Learning(Universidad Distrital Francisco José de Caldas) Bojacá Cabra, John Neiver; Salcedo Parra, Octavio José; Salcedo Parra, Octavio José [0000-0002-0767-8522]Network Slicing has been positioned as a technology that is a fundamental pillar for 5G networks, intended to support new technologies with improved requirements in terms of performance and flexibility when dividing the physical network into numerous virtual networks. In this work, an efficient Network Slicing design is proposed using a Deep Neural Network that allows selecting the ideal network Slice so that the packets of each vertical are transported. A training method for the Deep Neural Network is proposed with a metaheuristic algorithm called Glowworm Swarm Optimization (GSO) that presented an efficiency of 99.8% in the accuracy of the data obtained. The virtual network infrastructure is mounted on Openstack – Tacker, which has a complete implementation of what the ETSI suggests for implementations with Virtual Networks and Network Slicing. Free5GC and EURanSim are used to simulate a 5G network environment in the Core of the network and TorchServe is used to deploy the Deep Leaning model in a high-efficiency, low-latency productive environment. The tests focused on comparing the high-resolution Video Streaming vertical, but together with them, Massive IoT traffic and internet browsing were generated to corroborate the correct separation of Slices and the correct flow of traffic in the Slice corresponding to the vertical. An improvement was found in the tests that were done separating the Network Slices and with the Neural Network training method the possibility opens up to new methods that can increasingly provide better accuracy and efficiency when training models even more complex and can help improve the way in which the challenges of implementing networks that support the great diversity of emerging services that are currently being presented are being met. For the Slice deployed for Video Streaming, an improvement in the average transmission speed of 10.71 Mbps is evident.Ítem Modelo de una infraestructura de posicionamiento como soporte a la construcción de una sociedad espacialmente habilitada en Bogotá(Universidad Distrital Francisco José de Caldás) Pulido Arias, Robert Andres; Rocha Salamanca, Luz Ángela; Rocha Salamanca, Luz Ángela [0009-0008-2070-7632]This thesis presents a geomatics model for the positioning infrastructure in Bogotá, essential for the creation of a Spatially Enabled Society (SEH) that supports national geographic information policies and promotes smart and sustainable cities. It analyzes the interoperability, use, and sustainability of geospatial information, substantiating its importance in decision making and urban management. The research diagnoses critical components, designs and validates a geomatics model with technological tools such as R and ArcGIS, and conducts surveys to assess citizen perception of geographic applications. The results highlight the need to improve positioning infrastructure and increase community participation, proposing strategies to integrate emerging technologies and foster the development of SEH in Bogota and other cities.Ítem Construcción de geometrías 3D utilizando imágenes UAV como alternativa de solución para la oclusión fotogramétricaRomero Beltrán, Jeisson Andrés; Barragán Zaque, William BenignoPhotogrammetric occlusion occurs in urban areas, making difficult to reconstruct a 3D geometry of an object, as certain areas are not properly identified in an aerial photograph. Correctly studying this phenomenon allows to generate true orthoimages, avoiding the double mapping phenomenon, also called ghost image, mainly caused by the perspective projection. This research work aims to show the results got from the construction and deployment of a geometrical methodology for detection of photogrammetric occlusions and reconstruction of true orthoimages, by using datasets associated to the digital surface model and conventional orthoimages generated through high-resolution imagery processing related to a photogrammetric model. Behavior of the proposed methodology was initially validated on simulated datasets belonging to a controlled scenario and, subsequently, on a controlled scenario that sought to recreate the existence of three-dimensional geometries. Finally, its behavior was verified in a real scenario, through the use of high-resolution imagery obtained for a flyover carried out over the Headquarter “Aduanilla de Paiba”, one which belongs to the Universidad Distrital Francisco José de Caldas, located in Bogotá D.C., Colombia. In all cases, from visual verification carried out for areas detected as occluded, it was possible to obtain coherent results in the reconstruction of the true orthoimage.Ítem Desarrollo de un sistema de IoT con machine learning para la detección temprana de crisis epilépticas(Universidad Distrital Francisco José de Caldas) Peña Arismendi, Santiago Andrés; Salcedo Parra , Octavio José; Guio Mahecha, Laura Victoria; Salcedo Parra , Octavio José []0000-0002-0767-8522This research addresses the development of a system based on the Internet of Things (IoT) and optimized through machine learning techniques for the early detection of epileptic seizures. An algorithm was developed to capture biological signals through wearable sensors and process them within an IoT architecture. Data obtained from the Hospital de la Misericordia in Bogotá were used to validate various models, with a decision tree and a multilayer perceptron neural network standing out, achieving accuracies of 92.47% and 93.56%, respectively. In real clinical settings, these models achieved an accuracy of 65%. The proposed architecture allows for real-time preventive alerts, offering a potentially effective tool to improve the quality of life for people with epilepsy.Ítem Predicción de indicadores económicos a través de noticias usando rss, minería de texto e inteligencia computacionalIzquierdo Ortiz, Cristhian Johnatan; Alvarado Nieto, Luz DeicyThis study introduces an innovative approach to analyzing economic phenomena by integrating news and social media data as external sources to forecast the values of commodities such as LBMA GOLD and Brent oil, as well as the USD/COP exchange rate. Over twelve months, data from 166 news sources were collected through RSS and Twitter. Techniques including linear regression and ensemble machine learning, such as XGBoost and Random Forest, were employed to predict daily changes. Furthermore, a multi-agent system inspired by the socio-economic framework was developed, capable of evolving using external information and identifying characteristic patterns of complex systems.Ítem Diseño de un sistema de supervisión y monitoreo en tiempo real para agentes contaminantes en el aire, aplicado a la vereda Mochuelo Alto aledaña al Relleno Sanitario Doña Juana (RSDJ) de Bogotá - ColombiaRojas Pulido, Stiven Orlando; Espinel Ortega, Álvaro; Espinel Ortega, Álvaro [0000-0002-7747-7718]This document is a research around the gas emissions problem of Hydrogen Sulfide- H2S, Methane - CH4 carbon dioxide - CO2 and ammonia NH3 (polluting compounds), generated by the works of the Doña Juana landfill that affects the around communities; for instance, La Vereda el Mochuelo Alto(little town) is one of them because over the last ten years they have showing their disagreement with significative amount of protest, generating the interest for the implementation of technologies of the information and communication in this problem.Ítem Modelo para predicción del rendimiento de cultivos de maíz en Colombia empleando aprendizaje profundo(Universidad Distrital Francisco José de Caldas) Sierra Forero, Brayan Leonardo; Barón Velandia, Julio; Vanegas Ayala, Sebastián Camilo; Vanegas Ayala, Sebastián Camilo [0000-0002-8610-9765]This document presents the results obtained in the construction of a predictive model for the yield of corn crops in Colombia to accurately estimate the yield that will be obtained at the end of the harvest, based on a set of climatic variables. Using the CRISP-DM methodology as a framework, a systematic review of literature related to the case study is carried out, in order to identify the essential elements for the research. A climate data set consisting of a historical record of seemingly unrelated data is compiled, and from this, the variables with the greatest influence on performance estimation are determined through statistical analysis, correlation calculations, and relevance assessment. Then, a predictive model is developed with three variants implemented using computational tools and various deep learning (DL) algorithms, with the purpose of identifying the one that offers the best performance through its training and validation. The final model uses sunshine, precipitation, vapor pressure, and maximum and minimum temperatures as input variables, and is based on the DNN algorithm to estimate crop yield. This model provides highly precise results that, compared to those obtained by models found in related research works, stand out for their relevance and accuracy.Ítem Modelo de perfil de índice para fibra óptica de pocos modosRomero Peña, Manuel; Puerto Leguizamón, Gustavo Adolfo; Gustavo Adolfo Puerto Leguizamón [0000-0002-6420-9693]This paper presents the development of a model that allows the calculation and design of multimode optical fibers of few modes, from the mechanical parameters that describe the geometry of the parabolic index profile and the electromagnetic behavior in this guided transmission medium. For this purpose, a system of equations have been developed based on the performance evaluation metrics of an optical fiber and an independent variable that is adjusted through an optimization algorithm to evaluate the best values of bandwidth, dispersion and propagated modes in multimode optical fiber propagation windows.Ítem Estimación de áreas afectadas por incendios en la Reserva Forestal Protectora Bosque Oriental De Bogotá. Usando imágenes satelitales Sentinel- 2, basado en objetos geográficos (GEOBIA).Suárez Albarracín, Nadia Luz; Medina Daza, Rubén JavierFire plays an essential role in the dynamics of ecosystems, as a controlling factor in the selection and adaptation of species. In Colombia, 95% of fires are causedby anthropogenic factors, as a consequence of controlled burns for agricultural or tourism activities. The Cerros Orientales de Bogotá Forest Reserve, located in the department of Cundinamarca, with an area of 13,142.11 hectares, is affected by the colonization of invasive species, the most prominent of which is the thorny broom Ulex europaeus, a woody, thorny, perennial and pyrogenic shrub of European origin. This species increases the risk of forest fires due to the accumulation of standing necro-mass (highly flammable) and its flattened architecture, which facilitates the conduction of warm wind currents in its interior. For this reason, a very precise monitoring of spatial information is required to provide data on the accuracy and speed of land cover changes in these affected areas. The present research, is based on the calculation of the areas affected by the forest fires occurred on December 30, 2018, in the forest reserve, through an object-oriented approach, a methodology that allows the analysis of satellite images beyond the pixel paradigm, evaluating and validating the information obtained through the processing of Sentinel 2 satellite images, with the calculation of spectral indices and a supervised classification.Ítem Modelo de gestión de calidad de datos forestales en el marco de los Objetivos de Desarrollo Sostenible (ODS)(Universidad Distrital Francisco José de Caldas) González González, Diana Sofia; Cárdenas Quintero, Beitmantt Geovanni; Cárdenas Quintero, Beitmantt Geovanni [0000-0003-0293-0036]This document applies the four phases of the Total Data Quality Management methodology (TDQM): Definition, Analysis, Measurement, and Improvement, to the development of an open data quality management model for the surface data of natural forest and protected areas in Colombia, which constitute the basis for measurement, monitoring and decision making of the Sustainable Development Goal (SDG) 15: Life of terrestrial ecosystems, Target 15.1. Conserve and restore terrestrial ecosystems, Indicators: Thousands of hectares of protected areas, Percentage of the surface covered by natural forest, Annualized loss of natural forest.Ítem Aplicación de autómatas celulares y algoritmos genéticos en la creación de una técnica esteganográficaGuerrero Calderón, Árnol; Aparicio Pico, Lilia Edith; 0000-0003-1841-4423This document describes the creation of a steganographic technique focused on image analysis, supported by Artificial Intelligence (AI) methods and mathematical optimization models. Initially, a two-dimensional Cellular Automaton (CA) (d=2) with Moore neighborhood (N(1)=8) is used, the evolution is semi-totalist in order to select the fittest pixels (cells), from those defined in Eden, by applying a set of transition rules, defined in terms of the game of life, through several generations. Then, through genetic algorithms, the rules of the CA will be improved, to finally obtain a position vector, which will be given by the implementation of a one-dimensional CA, whose operation is executed through Wolfram rules 30 or 150 as the case may be. This method has been called modular steganography.Ítem Detección de Fraudes en Empresas de Servicios Públicos Domiciliarios utilizando ciencia de datos y análisis geoespacialesPachón Rodríguez, Willian Antonio; Melo Martinez, Carlos Eduardo; 0000-0002-6570-8144; 0000-0002-5598-1913One of the great challenges of any utilities around the world is the control of losses, which have different causes that are usually classified as technical (accuracy of equipment, leaks and breaks, construction and maintenance procedures) and NON-technical (thefts and frauds), affecting issues such: as investments for the expansion and maintenance of the networks, the profitability of the shareholders and even the continuity of the service. This research proposes a methodology for the detection of NON-technical losses common to any utility company, based on data analytics on business information enriched with data from third parties through geospatial analysis from its geographic location and market segmentation, which allows finding patterns on anomalous situations through supervised (on historical information) and unsupervised (if no information is available) machine learning models. The results of different classification algorithms used in data analytics were analyzed and the one with the highest accuracy and lowest type two error rates (false negatives) was selected to perform field verification work. The methodology was implemented in a natural gas distribution company and was contrasted with methodologies proposed by other authors for electric energy distribution companies, who consider that the problem should be addressed based on an analysis of historical consumption and its deviations. The results obtained with the proposed methodology improve the accuracy and sensitivity of the models by more than 20% and decrease false negatives by the same percentage, facilitating the verification and normalization of customers in anomalous situations and/or fraudulent conditions.Ítem Generación e implementación de una metodología para el análisis espacial de restricciones y condicionantes a derechos de uso y propiedad de la tierra sobre predios objeto de regularización, formalización, acceso y restitución de tierras en Colombia(Universidad Distrital Francisco José de Caldas) Castillo Castellanos, Oscar Javier; Castillo Méndez, Luis EduardoThe purpose of this article is to address the difficulty encountered in the framework of projects related to social planning of rural property, as well as land restitution, in understanding the restrictions related to environmental, mining-energy, and infrastructure rights and regulations. These restrictions act as limitations on the use and enjoyment of the land. This process causes delays and errors in generating technical-legal analyses for properties subject to individual and collective restitution requests or properties to be awarded or titled as part of property planning by professionals from the agencies responsible for these matters in the country. The goal was to generate and implement a spatial analysis model that addressed the stated problem through a methodology in which a series of geoprocesses were created and a web application was implemented. This web application allows for the consistent and timely consultation of spatial analyses, reducing time and avoiding human errors in the process.Ítem Diseño de un prototipo para clasificación automática de imágenes satelitales mediante algoritmos de machine learningPatiño Rivera, Héctor Ricardo; Ortiz Dávila, Álvaro EnriqueIn this document, a prototype is designed and implemented that, using machine algorithms learning allows automatic land cover classification for classes predefined; Additionally, the training set is presented, this will allow, In the future, said prototype can be versioned so that new training data, new preprocessing steps, different algorithms or different combinations of hyperparameters can be taken into account at the time of training and thus avoid The performance of the model decreases over time. To achieve this result, a selection of areas is made in Colombian territory and in different times (years 2021 and 2022) so that a set of data can be obtained multitemporal and spatially distributed, these areas are chosen taking into account that have little presence of clouds (although areas that have them are chosen, so that the model learn to characterize them correctly, as well as the shadows generated). Later,14 For each image, a series of unsupervised models were trained which identify different clusters present in each image. Following this, a reclassification of the previously mentioned clusters to predefined classes. Then, for each image and with the In order to slightly reduce the amount of data due to issues associated with hardware, a stratified random sample to ensure that all classes of all images are present in the final training set. Then a model is built and trained proposed, the hyperparameters of the model are found using group validation, where each image is a group. The validation of the hyperparameterized model is carried out on images from 2023 which were not taken into account in the modeling process. Finally, the hyperparameters of the model that maximize the effectiveness of the model have been obtained. The prototype is developed, which is deployed in an open repository for free consumption.Ítem Diseño de la plataforma de datos de autoservicio para soportar la implantación de un enfoque de Malla de Datos en la oficina asesora de tecnologías de la informaciónOrjuela Velásquez, Sergio David; Daza Corredor, Alejandro Paolo; Daza Corredor,Alejandro Paolo [0000-0002-3089-1233]Context: Data mesh is a decentralized method for managing and governing analytical data proposed by Zhamak Dehghani. The Information Technology Advisory Office of the District University leads an initiative to adopt, validate and implement the data mesh approach within the context of the academic entity. This project focused on designing and presenting an AWS architecture that illustrates the components (tools and services) and their interaction to support the self-service data platform, this platform is one of the four fundamental principles in the data mesh approach. Method: The architecture was designed based on four axes: Identify and prioritize the needs established by the three principles of the data mesh that must be supported on the platform, consider the roles that use the platform, use the notion of a plane to logically divide the platform and design the platform around the services offered by AWS. Results: The functionalities matrix by role and plane, the AWS component diagram, the technical manual and a functional manual were prepared. Conclusions: Starting a data mesh implementation process is within everyone’s reach. The approach is new but flexible, the platform is only the first step but the functionalities and alternatives are available to take the step to the culture of and domains in data analytics.