Support dataset for: Radar Signal Classification with Quantum Machine Learning: A Study on the Ansatz Depth Impact

The datasets are the. parquet files, they can be accessed using Python 3.9.21, Pandas 2.2.3, and PyArrow 14.0.2 using the following syntax: import pandas as pd df_example = pd.read_parquet("file_name.parquet", engine="pyarrow") These datasets have been normalized and can be used directly on any machine learning model without any additional preprocessing. The training results are available as .log files. They can be opened with any text editor such as Notepad (for windows), TextEdit (for MacOS), or Gedit (for Linux). It contains four blocks of information per training run, they are: • A vector with the cost as function of epoch • Inference behaviour at the general dataset (testingDataset_general.parquet) represented by a matrix with the main performance metrics (precision, recall, F1-score, accuracy, macro averages, and weighted averages), and the confusion matrix. • Inference behaviour at the dataset with all signals of 0 dB of SNR (testingDataset_0dB.parquet) represented by a matrix with the main performance metrics (precision, recall, F1-score, accuracy, macro averages, and weighted averages), and the confusion matrix. • Inference behaviour at the dataset with all signals of 10 dB of SNR (testingDataset_0dB.parquet) represented by a matrix with the main performance metrics (precision, recall, F1-score, accuracy, macro averages, and weighted averages), and the confusion matrix. • Inference behaviour at the dataset with all signals of 20 dB of SNR (testingDataset_0dB.parquet) represented by a matrix with the main performance metrics (precision, recall, F1-score, accuracy, macro averages, and weighted averages), and the confusion matrix. These files can be processed with a parsing function or by taking the data directly by hand. For any additional information feel free to contact the corresponding authors.