OTA-ModSet: An Over-the-Air Modulation Recognition Dataset

This dataset contains over-the-air (OTA) recordings of 12 digital modulation schemes, collected in a controlled indoor environment. It is specifically designed for automatic modulation classification (AMC) research, providing a realistic benchmark for evaluating deep learning models under varying SNR conditions. The data generation and collection were performed by the Software Defined System Studio (SDS Studio), a platform independently developed by the Broad-band Communication and Network Group (BCNG) of the National University of Defense Technology, in conjunction with a Universal Software Radio Peripheral . All signals were transmitted and received in a controlled indoor environment, including real radio frequency impairments and channel impairments. The dataset is stored in a single HDF5 (.h5) or NumPy NPZ (.npz) file, with predefined training, validation, and test splits. Each sample consists of I/Q complex samples along with its modulation label and SNR value.