Impact of the Pre-Processing in AI-Based Classification at Mm-Waves

Based on various applications involving millimeter-wave (mm-wave) imaging, we highlight the importance of processing the measurements prior to their classification with Artificial Intelligence (AI) algorithms. The key point for enabling a good classification accuracy is to obtain the same structure for the training and the test datasets. Throughout the paper, we discuss a set of pre-processing methods, ranging from 2-Dimensional Fast Fourier Transform (2D-FFT) with or without segmentation to 3-Dimensional Fast Fourier Transform (3D-FFT), and their influence on the final classification results.