Examinando por Materia "Inteligencia artificial - Bogotá (Colombia)"
Mostrando 1 - 3 de 3
- Resultados por página
- Opciones de ordenación
Ítem Determinación de características constructivas de un predio mediante el análisis de fachada por medio de una red neuronal artificial para una UPZ de BogotáVanegas Avila, Daniel Felipe; Pérez Carvajal, Edwin RobertThe development of artificial intelligence and the tools it proposes has meant a breakthrough in the advancement of new methodologies and technologies that have been applied in different fields and aspects of society that have led to a revolution in itself and thus in the cities and environments in which it is applied. Artificial neural networks are born in the area of artificial intelligence, evoking the biological structure of neural networks present in the brain, seeking that, through a previous learning, the system can adapt to the characteristics that the environment determines and can perform the proper analysis and processing of information to provide solutions to a problem. For this reason, the present study proposes to develop a methodology for property qualification and description, based on artificial neural networks using as a basis the variables and attributes that exist in the property card, which is used in the cadastral processes by a property recognizer, in order to optimize the recognition process by improving time, accuracy and reducing the existing subjectivity in the procedure.Ítem Implementación de una arquitectura de red convolucional aplicada a la predicción de masas de crimen en la Ciudad de Bogotá.Fajardo Fajardo, Luis Andrey; Piraján Ovalle, Freddy Humberto; Melgarejo Rey, Miguel AlbertoThe current work presents the design and adaptation of a deep neural network architecture for urban crime forecasting in Bogota city. The architecture skeleton is based on convolutional and deconvolutional layers trained with multidimensional data from criminal subreports. A subset of convolutional layers is used to capture spatial patterns from crime events. Additionally, transposed convolutional layers are used on top of the deepest convolutional layer to recover the spatial dimensions of the input data. Therefore, the information generated by the architecture is compared with the expected output over two-dimensional crime masses maps. Moreover, this work expands upon a previous study of urban crime in Bogota city by generating synthetic data from the cellular automaton known as Conway's Game of Life. This synthetic data exhibits similar properties to the Spatio-temporal crime dynamics in Bogota city. In addition, the experimentation over the convolutional-deconvolutional architecture is performed with two subsets of input volumes. The first subset of input arrays was built based upon information gathered from criminal subreports in Bogota city. The second subset of inputs consists of synthetic data. Hence, the experiments with real, synthetic, and the union of real and synthetic data were summarized in five use cases. Each use case was set up with a specific scheme of deep learning techniques and a variation of parameters to evaluate performance for each case independently.Ítem Prototipo de un asistente virtual web para optimizar el acceso a la información administrativa del estudiante - Facultad de Ingeniería de la Universidad Distrital Francisco José de CaldasMorales Aguilar, David; Bolaños Castro, Sandro JavierThis work shows the development process for a chatbot prototype in order to provide administrative and academic information to the student of the engineering faculty of the Francisco José de Caldas District University. This chatbot or virtual assistant used the development framework called Dialogflow, a technology owned by the Google company. It relied on a custom layout to create intents, training phrases, and entities. Finally the prototype was implemented in Google actions and tested in Google Assistant.