DroneTFS-SemNet: semantic learning framework for multi task recognition of unmanned aerial vehicles

In this article, each CSV file in the DroneRF dataset is first divided into frames, and the low and high frequency signals are divided into multiple data segments with L points as a frame. Each sub sample is normalized by Min Max to eliminate the influence of dimensionality,Concatenate the normalized low-frequency and high-frequency subsamples in rows to form a single sample with dimensions of [2L, 1] within the same time period.   DroneRF is an open-source drone RF signal dataset created by Allahham et al. [1] in 2019. The dataset published in this article is based on DroneRF for data processing and is not original!!![1]Allahham, M.H.D.S., Al-Sa\u2019d, M.F., Al-Ali, A., et al.: DroneRF dataset: A dataset of drones for RF-based detection, classification and identification. Data Brief 26, 104313 (2019)