1. Folder '01_Measurement_Raw_Data' contains the raw data of the experiment described in [2]. Using configurations given in the folder '03_SDR_Configuration_Data_Acquisation', you can make measurements that save the data in the same format. Using the Matlab code given in the folder '04_Signal_Processing_Feature_Extraction_and_Prediction_with_SVM_using_Matlab', you can process the raw data. 2. Folder '02_Feature_Table' contains two feature tables of all measurements provided in folder '01'. The first one has nine candidate features. The second one only includes the four features of the optimal set. These tables are made using the Matlab code in folder '04'. You can load a feature table directly in Matlab and use 'classificationLearner' to train and analyze classification models.

This research is part of the German research project SORTIE and is supported by the German Federal Ministry of Education and Research (BMBF) under grant number 13N15189. Related journal articles: [1] Shi, D.; Gidion, G.; Aftab, T.; Reindl, L.M.; Rupitsch, S.J. Frequency Comb-Based Ground-Penetrating Bioradar: System Implementation and Signal Processing. Sensors 2023, 23, 1335. https://doi.org/10.3390/s23031335. [2] Shi, D.; Gidion, G.; Reindl, L.M.; Rupitsch, S.J. Automatic life detection based on efficient features of ground-penetrating rescue radar signals. Submitted to Sensors.

{"references": ["Shi, D.; Gidion, G.; Aftab, T.; Reindl, L.M.; Rupitsch, S.J. Frequency Comb-Based Ground-Penetrating Bioradar: System Implementation and Signal Processing. Sensors 2023, 23, 1335. https://doi.org/10.3390/s23031335.", "Shi, D.; Gidion, G.; Reindl, L.M.; Rupitsch, S.J. Automatic life detection based on efficient features of ground-penetrating rescue radar signals. Submitted to Sensors"]}