Neuromorphic Semantic Communications with Wake-Up Radios

Neuromorphic communications deploys spiking neural networks (SNNs) to encode and decode semantic information, reducing the communication power by communicating asynchronously via sparse impulse radio (IR) waveforms. This way, the input signal sparsity translates directly into energy savings both in terms of computation and communication. However, with IR transmission, the main contributor to the overall energy consumption remains the power required to maintain the main radio on at the receiver. This work introduces a novel architecture that integrates a wake-up radio mechanism with neuromorphic communications. In this architecture, the main receiver remains idle until a signal of interest is detected, and a wake-up signal is received by the wake-up receiver. Experimental results confirms the advantages of the proposed architecture in terms of expected loss and energy consumption.