Multi-task Learning Dataset for Automatic Modulation Classification and DOA Estimation

A synthetic signal dataset of 12 different modulations (including PSK, QPSK, 8PSK, QFSK, 8FSK, 16APSK, 16QAM, 64QAM, 4PAM, LFM, DSB-SC, and SSBSC) with different DOAs (discrete angles ranging from -60° to 60° with the step size of 1°) is generated using MATLAB 2021a. Regarding the signal model configuration for the data generation, we specify a uniform linear antenna array of M = 5 elements to acquire incoming signals having N = 1024 envelope complex samples, thus conducting an I/Q data array of size 1024 × 2 × 5. To model real-world phenomena in wireless communication, various impairments are considered: the Gaussian noise in the range [-10, 20] dB (step size of 1 dB), the multi-path propagation with a random number of NLOS signals in the range of [1, 10], the propagation attenuation αp and delay τp randomly distributed in the range [-50, -1] dB and [1, 3000] ns, respectively. The dataset contains 450120 signals covering 121 DOA classes, 12 modulation classes at 31 SNR levels, where each signal has 1024 samples to form into an input data array with the size of 1024x2x5.Please refer and cite our paper as follows: V. -S. Doan, T. Huynh-The, V. -P. Hoang and D. -T. Nguyen, "MoDANet: Multi-task Deep Network for Joint Automatic Modulation Classification and Direction of Arrival Estimation," in IEEE Communications Letters, doi: 10.1109/LCOMM.2021.3132018.

本数据集为由12种不同调制方式（包括PSK、QPSK、8PSK、QFSK、8FSK、16APSK、16QAM、64QAM、4PAM、LFM、DSB-SC及SSBSC）组成的合成信号数据集，并针对不同的方向角（离散角度范围从-60°至60°，步进值为1°）进行生成。该数据集采用MATLAB 2021a软件构建，在信号模型配置方面，我们设定了由M=5个单元组成的均匀线性天线阵列以获取N=1024个包络复样本的入射信号，从而形成大小为1024×2×5的I/Q数据数组。为模拟无线通信中的实际现象，考虑了多种损耗：[-10, 20] dB范围内的高斯噪声（步进值为1 dB）、具有随机数量的NLOS信号的多径传播（信号数量在[1, 10]范围内）、随机分布在[-50, -1] dB范围内的传播衰减αp和[1, 3000] ns范围内的延迟τp。数据集包含450120个信号，覆盖121个方向角类别、12个调制类别及31个信噪比级别，每个信号包含1024个样本，以形成大小为1024x2x5的输入数据数组。请参照并引用以下论文：V. -S. Doan, T. Huynh-The, V. -P. Hoang和D. -T. Nguyen，'MoDANet: 多任务深度网络用于联合自动调制分类和方向角估计'，发表于IEEE Communications Letters，doi: 10.1109/LCOMM.2021.3132018。