3 resultados
Resultados de la búsqueda
Mostrando 1 - 3 de 3
Ítem Una evaluación comparativa de la eficiencia de los algoritmos de ML supervisados en la clasificación de tráfico de NFV(Universidad Icesi, 2017-07-01) Vergara Reyes, Juliana Alejandra; Caicedo Rendón, Oscar Mauricio; Martínez Ordoñez, María CamilaThe implementation of NFV allows improving the flexibility, efficiency, and manageability of networks by leveraging virtualization and cloud computing technologies to deploy computer networks. The implementation of autonomic management and supervised algorithms from Machine Learning [ML] become a key strategy to manage this hidden traffic. In this work, we focus on analyzing the traffic features of NFV-based networks while performing a benchmarking of the behavior of supervised ML algorithms, namely J48, Naïve Bayes, and Bayes Net, in the IP traffic classification regarding their efficiency; considering that such an efficiency is related to the trade-off between time-response and precision. We used two test scenarios (an NFV-based SDN and an NFV-based LTE EPC). The benchmarking results reveal that the Naïve Bayes and Bayes Net algorithms achieve the best performance in traffic classification. In particular, their performance corroborates a good trade-off between precision and time-response, with precision values higher than 80 % and 96 %, respectively, in times less than 1,5 sec.Ítem Towards an automatic detection system of sports talents: an approach to Tae Kwon Do(Universidad Icesi, 2018-10-01) Estévez Salazar, Alexis DaríoTae Kwon Do is a Korean martial art included as an Olympic sport, where several tools have been deve - loped from the engineering point of view,mainly focused on improving the capacity of the athletes. Nevertheless, there is a breach in the selection process of high performance athletes. For this reason, this research was focused on developing a system based on the information of the classification for the athletes in the Tae Kwon Do Ecuadorian Federation by using the wrapper and embedded modes and the Decision Tree and Support Vector Machines machine learning algo - rithms. These algorithms and modes were used to assess the different factors considered in this classification. The main contribution of this work is to provide a support system for the selection of these athletes.Ítem Sistema de clasificación para afiliados en las Cámaras de Comercio(Universidad Icesi, 2020-01-01) Ibarra Escobar, Camilo José; Piedrahita Uribe, Esteban; Asesor TesisLas Cámaras de Comercio en Colombia tienen una alta dependencia de ingresos por concepto de registro mercantil, el cual es susceptible a cambios por factores externos. Entre las alternativas de ingreso de la organización se encuentran una serie de programas y servicios para empresas que se encuentran en la categoría B2B. El problema es que en las cámaras de comercio de Colombia y en particular la Cámara de Comercio de Cali, a pesar de tener información suficiente sobre los posibles clientes y los resultados de campañas anteriores, tienen un bajo nivel de captación o de venta de la membresía, que llega sólo al 5,6 porciento del total de empresas, con campañas comerciales que registran un porcentaje de éxito entre 20-30 por ciento.