Examinando por Autor "Uribe-Cadavid, D. C. (Diana Cecilia)"

Mostrando 1 - 3 de 3
  • Miniatura
    PublicaciónAcceso abierto
    Aplicación de CONWIP para mejorar los ciclos de retorno de canastillas para el manejo de frutas y verduras en almacenes de cadena
    (2014-05-13) Vasco-Mesa, J. A. (Johny Alejandro); Uribe-Cadavid, D. C. (Diana Cecilia); Diez-Montoya, J. F. (Juan Felipe)
    This paper presents an alternative to optimize the quality and freshness of the fruits and vegetables bought by final consumer, according to the evaluation and optimization of the return cycles of the plastic containers in the distribution centers (CEDI) in Medellín and in points of sale of a store chain studied for the zone of Medellín and the Atlantic Coast. In order to optimize the return cycles, people has believed that it is only necessary to study the direct logistics of products since they leave the CEDI until they arrive at the stores, consequently, only half of the problem is being studied. Retailers must guarantee to their supplier that the plastic containers return so that he can pack his products again, that is to say, to study inverse or reverse logistic, a new fundamental concept for all those companies that they have consciousness about environment and they worry about the recovery of products at the end of their life utility.
  • Miniatura
    PublicaciónAcceso abierto
    Atención oportuna a usuarios en salas de atención personalizada (estudio de caso)
    (2014-05-13) Uribe-Cadavid, D. C. (Diana Cecilia)
    According to the survey of satisfaction made by the company in study in November of 2004, they were like two dissatisfaction factors: time spent in queue and attention in charge of the personnel. Time spent in queue was the worst qualified. The causes of the long waiting times and large queues that the users were experiencing were analyzed. It was verified that the amount of customers who arrived at the system did not have any pattern of demand that allowed forecasting periods of greater affluence. The system was analyzed as a model of multi-channel lines with a single phase, where the number of customers arriving in a period has a Poisson distribution, but the service times did not have the exponential behavior required to solve mathematically the problem. The system was simulated using probabilistic distributions for each server and specifying the different services the customers needed. It was obvious that the system lost capacity during lunch time, increasing the time spent in queue of the customers. Several solutions were evaluated to improve the capacity.
  • Miniatura
    PublicaciónAcceso abierto
    Optimización de parámetros y de valores de inicio para el modelo de HOLT basado en señales de rastreo
    (2013-11-21) Castro, C. A. (Carlos Alberto); Uribe-Cadavid, D. C. (Diana Cecilia)
    Time series models are quantitative techniques commonly used to forecast the behavior of variables. These models include the exponential smoothing with trend or Holt model that requires the definition of the smoothing constants α and β and the initialization values, both required for the model upgrade. This paper proposes a different way to obtain the parameter values and initial conditions of the Holts model, optimizing the tracking signal range (TSR), in order to achieve a more robust model from the viewpoint of accuracy of the results and historical performance. Some comparisons between the proposed approach and the traditional methods based on the mean absolute deviation (MAD) and the mean square error (MSE) are provided. These are the measures traditionally used to determine the degree of accuracy of a model, and a better model performance is obtained.