In this paper we introduce an auto-encoder neural network that can be used to model a node-to-node radio frequency communication channel. With some simple assumptions the encoding layer of this neural network can be interpreted as a phase modulated signal which can be transmitted across a communication channel. When the auto-encoder is trained to minimize bit error rates within the transmitted messages, it effectively learns an optimal modulation scheme for that particular communication channel. To implement these signals in a physical link we developed GNURadio flowcharts along with custom signal processing blocks that transmit and receive the auto-encoder generated signals between a pair of Universal Serial Radio Peripherals. Finally, we show the methodology used for incorporating the GNURadio flowcharts with the auto-encoder training program so that the autoencoder can be trained on the physical communication channel itself.

Inspec keywords: minimisation; telecommunication computing; flowcharting; phase modulation; wireless channels; error statistics; radio networks; network coding; signal processing; learning (artificial intelligence); neural nets

Other keywords: autoencoder neural network; autoencoder signal generation; bit error rate minimisation; message transmission; optimal modulation scheme; physical communication channel; over-the-air packet communications; machine learning based modulation scheme; phase modulated signal; signal processing blocks; node-to-node radiofrequency communication channel; GNURadio flowcharts; universal serial radio peripherals; communication channel; autoencoder training program; encoding layer

Subjects: Signal processing and detection; Communications computing; Neural computing techniques; Optimisation techniques; Radio links and equipment; Other topics in statistics; Codes; Optimisation techniques; Knowledge engineering techniques; Digital signal processing; Other topics in statistics