MDTCNet: Multi-Task Classifications Network and TCNN for Direction of Arrival Estimation

The direction-of-arrival (DoA) estimation is one of the hot research areas in signal processing. To overcome the DoA estimation challenge without the prior information about signal sources number and multipath number in millimeter wave system, the multi-task deep residual shrinkage network (MT-DRSN) and transfer learning-based convolutional neural network (TCNN), namely MDTCNet, are proposed. The sampling covariance matrix based on the received signal is used as the input to the proposed network. A DRSN-based multi-task classifications model is first introduced to estimate signal sources number and multipath number simultaneously. Then, the DoAs with multi-signal and multipath are estimated by the regression model. The proposed CNN is applied for DoAs estimation with the predicted number of signal sources and paths. Furthermore, the model-based transfer learning is also introduced into the regression model. The TCNN inherits the partial network parameters of the already formed optimization model obtained by the CNN. A series of experimental results show that the MDTCNet-based DoAs estimation method can accurately predict the signal sources number and multipath number under a range of signal-to-noise ratios. Remarkably, the proposed method achieves the lower root mean square error compared with some existing deep learning-based and traditional methods.