Machine Learning Based Localization and Classification with Atomic Magnetometers - Orientation and Position

Datasets created with an atomic magnetometer performing magnetic induction imaging, and later analysed with machine learning.In this dataset, object's position is randomly varied in the (x,y) plane, four different orientation are used, with two samples, and two scan settings.Sample A: 50 mm x 25 mm x 3 mm Aluminium rectangleSample B: 40 mm x 20 mm x 3 mm Aluminium rectangle.Orientation 01: +90°Orientation 02: 0°Orientation 03: +45°Orientation 04: -45°Low-Res: 8 mm XY stage stepHigh-Res: 4 mm XY stage stepData are arranged per target/resolution/orientation; position is indicated in the file's name, in mm.Four classes of data are collected: Radius (R), Phase (P), in-phase (X), and out-of-phase (Y). Blind datasets: Information removed from filename.Details are reported in the file: Orientation_Position_blind_files.pdf and Orientation_Position_blind_files-High_Res.pdfFor further details, see the paper published in Physical Review Letters: https://doi.org/10.1103/PhysRevLett.120.033204.