Radar ML - Lite

<p dir="ltr">This is the "<b>RadarML Lite</b>". It is a sub-set of the complete "<b>RadarML</b>" dataset that has already been released.</p><p dir="ltr">The original <b>RadarML</b> dataset has <b>3 receiver channels: ADC0, ADC2 and ADC4</b>.</p><ul><li><b>648 configurations:</b> 1,000 pulses per channel.</li><li><b>12 configurations:</b> 8,000 pulses per channel.</li></ul><p dir="ltr">Which totals <b>744,000 pulse captures per channel</b>, or <b>2,232,000 channel-specific recordings</b> across all three channels, before SNR augmentation.</p><p dir="ltr">The compact "<b>RadarML Lite" </b>version retains <b>100 pulses per configuration from ADC0 only, </b>which totals <b>66,000 pulses</b>.</p><p dir="ltr">Here is a link to the projects GIT page:</p><p dir="ltr"><b>github.com/UCLRadarGroup/Radar_ML/tree/radar-ml-lite</b></p><p dir="ltr">See a further description of the full RadarML dataset below:</p><p dir="ltr">RadarML is a publicly available dataset of experimentally captured modulated radar pulses recorded over-the-air across multiple independent receive channels.</p><p dir="ltr">The dataset was captured on the UCL ARESTOR platform which is a Radio-Frequency-System-on-a-chip (RFSoC).

Each waveform was designed based on its central frequency, bandwidth, duration and modulation type. The overall dataset contains over 2 million waveforms across 7 different modulation types. The goal of this dataset is to enable comparative analysis of Radar Modulation Classification techniques on real data and stimulate research into multi-channel signal detection methods.</p><p dir="ltr">Baseline detection and classification results are presented in the linked publication, showing how the performance varies as a function of Signal to Noise ratio.</p>