Dynamical Classification to Improve the Selection of the Driver-Cargo Transportation Duo for a Trucking Company

Abstract

The transfer of merchandise and products has played a fundamental role during this time of the pandemic, many countries have a high percentage of land transport routes by road and roads dedicated to the delivery of products. It is a great concern to establish the best conditions for human nature and cargo transportation to avoid accidents. The design of a system through a dynamic classifier has been developed to establish the best selection in the driver-cargo transportation duo, with an analytical approach based on Bayes’ Theorem that is supported by a software architecture through design patterns at runtime from the perspective of object-oriented, to optimize memory resources and improve the efficiency of the classification process. The conditions evaluated and the selected variables are the product of an exhaustive analysis between related works and archival data evidence from a local company.