Spiking Neural Networks for Detecting Satellite-Based Internet-of-Things Signals

Abstract

<p>The obtained results demonstrate a significantly enhanced detection performance under heavy interference conditions when employing spiking-based and deep learning detection techniques, as opposed to traditional baseline matched-filter methods. Although spiking-based detection approaches exhibit error rates comparable to those of deep learning techniques, they consume considerably less power – several orders of magnitude lower, in fact. Owing to their power efficiency, spiking-based detection networks emerge as the optimal choice for signal detection in resource-limited systems, such as low-Earth orbit satellites.</p>