Examinando por Materia "Modelamiento predictivo"

Mostrando 1 - 2 de 2
  • No hay miniatura disponible
    Ítem
    Modelamiento predictivo del número de visitantes en un centro comercial
    (Universidad EAFIT, 2022) Rua Jaramillo, Ramón David; Laniado Rodas, Henry; Almonacid Hurtado, Paula María
    The ability to make predictions about the number of customers or visitors in a shopping center is a very important input in the planning and efficient use of physical and human resources in this type of company. Also, it is important to understand what aspects influences their behavior. Based on historical data on the number of visitors, as well as external (environment) variables and online search trends, a forecasting model of the behavior of daily visits to the shopping center is suggested. The historical data correspond to the pedestrian and vehicular entries (cars and motorcycles) of the last 6 years in a shopping center located in the city of Medellín. This project begins with a literature review regarding forecasting models in different places such as museums, airports, natural parks, shopping centers and restaurants, among others, in order to explore methodologies in such cases and possible solution options. Through time series analysis and machine learning algorithms, the most representative variables and the best-fit model are selected to predict the number of visitors. This model is expected to be strengthened with estimation algorithms, improving performance over time and allowing it to be applied in other business or educational environments.
  • No hay miniatura disponible
    Ítem
    Predictive and prescriptive modeling for the clinical management of dengue: a case study in Colombia
    (Universidad EAFIT, 2023) Hoyos Morales, William Segundo; Aguilar Castro, José Lisandro; Toro Bermúdez, Mauricio
    In this research, we address the problem of clinical management of dengue, which is composed of diagnosis and treatment of the disease. Dengue is a vector-borne tropical disease that is widely distributed worldwide. The development of approaches to aid in decision-making for diseases of public health concern –such as dengue– are necessary to reduce morbidity and mortality rates. Despite the existence of clinical management guidelines, the diagnosis and treatment of dengue remains a challenge. To address this problem, our objective was to develop methodologies, models, and approaches to support decision-making regarding the clinical management of this infection. We developed several research articles to meet the proposed objectives of this thesis. The first article reviewed the latest trends in dengue modeling using machine learning (ML) techniques. The second article proposed a decision support system for the diagnosis of dengue using fuzzy cognitive maps (FCMs). The third article proposed an autonomous cycle of data analysis tasks to support both diagnosis and treatment of the disease. The fourth article presented a methodology based on FCMs and optimization algorithms to generate prescriptive models in clinical settings. The fifth article tested the previously mentioned methodology in other science domains such as, business and education. Finally, the last article proposed three federated learning approaches to guarantee the security and privacy of data related to the clinical management of dengue. In each article, we evaluated such strategies using diverse datasets with signs, symptoms, laboratory tests, and information related to the treatment of the disease. The results showed the ability of the developed methodologies and models to predict disease, classify patients according to severity, evaluate the behavior of severity-related variables, and recommend treatments based on World Health Organization (WHO) guidelines.