Congratulations! Javier for getting your paper accepted @ IEEE SMC 2021.
Javier Perez Tobia
Is Timing Critical to Trace Reconstruction ?
Abstract Dynamic analysis of real-world software systems is challenging due to imperfections, noise and data loss. Moreover, these systems evolve with time and their requirements are usually either not clearly specified or not known, which makes it hard to analyze them. Therefore, it is important to create models that can learn to behave similar to these systems to allow us to predict their actions, impute missing data, or detect potential failures ahead of time.
Several models have been proposed to model sequential data but the vast majority of them have only a qualitative notion of time or no notion of it at all. In this paper we extend the work on Time-LSTM to other recurrent neural architectures. We show that our model learns the behaviour of the complex software systems to a very high degree of accuracy. We use Blackberry’s QNX real-time operating system as a case study. We predict upcoming sequences of events 20 time steps ahead with more than 90 % accuracy. This allows for significant improvement in trace reconstruction. Our approach is scalable and has shown state-of-the-art performance on industry strength softwares.