Taking into account the execution context to optimize medical image databases indexation

Description

Grid are promising tools to tackle massively parallel medical applications such as medical image databases indexation but their complexity make the optimization of computation tasks and the design of computing models difficult. We tackle this complexity by a probabilistic approach. We have shown that a probabilistic model of the computing tasks execution time can be refined by taking into account the execution context which varies over the grid infrastructure. This modeling and the resulting optimization strategy enable the deployment of reliable and efficient large scale applications.

Additional details