Many approaches have been developed so far to give an estimation of the upper bound of the end-to-end delay or the response-time for real time applications. There are two main approaches developed to perform this analysis. The first one is Liu and Layland theory, and gives which is called the worst-case response time for a given set of periodic sources. The second approach made by R. Cruz gives an upper bound on delay for a set of streams defined by their burstiness constraints. The outcome of this paper is to compare bounds of both approaches for periodic and pseudo periodic arrival processes with Fixed Priority and FIFO policies. For this purpose, a relationship is given between jitter and the maximum burst size for a reliable transposition between the two approaches. We propose a hybrid method to optimize upper bound given by Network Calculus approach. A comparison study shows the advantage of our method and how presented results are useful in admission control context for getting better utilization of network resources.