- Conference Paper
Long-range communication systems require receivers that can detect and decode messages in spite of strong distorting effects. However, classical decoders often fail at coping with complex effects such as interference or multipath propagation. Deep learning has shown strong generalization and adaptation capabilities and is a promising approach for improving decoding systems. In this work, we study the specific case of aircraft communication and build a purely deep learning-based receiver. It detects incoming messages, finds the exact starting point and then decodes their message bits. We demonstrate the performance of our system and show that it can decode 45% more messages than a classical baseline decoder. Our approach is general and can be adapted to many communication protocols. Show more
Book title2020 28th European Signal Processing Conference (EUSIPCO)
Pages / Article No.
SubjectMessage detection; aircraft communication; deep learning
MoreShow all metadata