In this paper, online deep learning (DL)-based channel estimation algorithm for doubly selective fading channels is proposed by employing the deep neural network (DNN). With properly selected inputs, the DNN can not only exploit the features of channel variation from previous channel estimates but also extract additional features from pilots and received signals. Moreover, the DNN can take the advantages of the least squares estimation to further improve the performance of channel estimation. The DNN is first trained with simulated data in an off-line manner and then it could track the dynamic channel in an online manner. To reduce the performance degradation from random initialization, a pre-training approach is designed to refine the initial parameters of the DNN with several epochs of training. The proposed algorithm benefits from the excellent learning and generalization capability of DL and requires no prior knowledge about the channel statistics. Hence, it is more suitable for communication systems with modeling errors or non-stationary channels, such as high-mobility vehicular systems, underwater acoustic systems, and molecular communication systems. The numerical results show that the proposed DL-based algorithm outperforms the existing estimator in terms of both efficiency and robustness, especially when the channel statistics are time-varying.
INDEX TERMSDeep learning, neural networks, channel estimation, doubly selective channel, LS oriented input, pre-training.
Artificial intelligence (AI) based downlink channel state information (CSI) prediction for frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems has attracted growing attention recently. However, existing works focus on the downlink CSI prediction for the users under a given environment and is hard to adapt to users in new environment especially when labeled data is limited. To address this issue, we formulate the downlink channel prediction as a deep transfer learning (DTL) problem, where each learning task aims to predict the downlink CSI from the uplink CSI for one single environment. Specifically, we develop the directtransfer algorithm based on the fully-connected neural network architecture, where the network is trained on the data from all previous environments in the manner of classical deep learning and is then fine-tuned for new environments. To further improve the transfer efficiency, we propose the meta-learning algorithm that trains the network by alternating inner-task and acrosstask updates and then adapts to a new environment with a small number of labeled data. Simulation results show that the direct-transfer algorithm achieves better performance than the deep learning algorithm, which implies that the transfer learning benefits the downlink channel prediction in new environments. Moreover, the meta-learning algorithm significantly outperforms the direct-transfer algorithm in terms of both prediction accuracy and stability, which validates its effectiveness and superiority.
Source number detection is a critical problem in array signal processing. Conventional model-driven methods e.g., Akaikes information criterion (AIC) and minimum description length (MDL), suffer from severe performance degradation when the number of snapshots is small or the signal-to-noise ratio (SNR) is low. In this paper, we exploit the model-aided based deep neural network (DNN) to estimate the source number. Specifically, we first propose the eigenvalue based regression network (ERNet) and classification network (ECNet) to estimate the number of non-coherent sources, where the eigenvalues of the received signal covariance matrix and the source number are used as the input and the supervise label of the networks, respectively. Then, we extend the ERNet and ECNet for estimating the number of coherent sources, where the forward-backward spatial smoothing (FBSS) scheme is adopted to improve the performance of ERNet and ECNet. Numerical results demonstrate the outstanding performance of ERNet and ECNet over the conventional AIC and MDL methods as well as their excellent generalization capability, which also shows their great potentials for practical applications.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.