Pulse Repetition Interval Time Series Modeling for Radar Waves using Long Short-Term Memory Artificial Recurrent Neural Networks

Sammanfattning: This project is a performance study of Long Short-Term Memory artificial neural networks in the context of a specific time series prediction problem consisting of radar pulse trains. The network is tested both in terms of accuracy on a regular time series but also on an incomplete time series where values have been removed in order to test its robustness/resistance to small errors. The results indicate that the network can perform very well when no values are removed and can be trained relatively quickly using the parameters set in this project, although the robustness of the network seems to be quite low using this particular implementation.