LAUSR

With the recent advances in wireless technologies, high frequency radio has become the primary medium for long-distance communication. Among various types of modulation in signal transmission, morse code stands out due to its simplicity and efficiency in information transmission while costing small bandwidth. In practice, however, it is extremely laborious to locate morse signals in wideband communication. It’s a needle in a haystack, if morse code is sent in random carrier waves at random period. To avoid this, automatic morse signal detection has become a challenging task in wireless morse communications, and new solutions could be derived from the latest machine learning techniques. In this paper, we propose a deep learning framework, namely DeepMorse, to blindly detect morse signals in wideband spectrum data. In particular, we first develop a multi-signal sensing module to retrieve signal candidates from wideband spectrum without prior knowledge. Then, we construct a CNN-based module to extract informative features from the located candidates, in order to distinguish the morse signal from other types of modulation. To evaluate the proposed DeepMorse model, we set up a testbed utilizing commercialized long-distance wireless communication devices. The experimental results demonstrate that DeepMorse is able to effectively detect morse signals and outperform the state-of-the-art methods on four real-world datasets.