Direction-of-arrival (DOA) estimation is a vital research topic in array signal processing, with extensive applications in many fields. In recent years, deep learning has been applied to DOA estimation to improve the performance. However, most existing deep learning-based DOA estimation methods extract DOA information from the covariance matrix (CM) input. In this paper, we introduce a novel deep learning-based DOA estimation scheme that utilizes the raw in-phase (I) and quadrature (Q) components of the signal as the input. We formulate the problem as single-label classification and multi-label classification based on the number of signal sources. We design a convolutional neural network to solve the problems and to adapt to different number of snapshots. We also propose a deep learning regression-based method to overcome the limitations of classify-based methods in dealing with off-grid angles. We conduct extensive experiments with simulations and over-the-air collected signals to analyze the performance of the proposed method in various scenarios including different SNRs, additive generalized Gaussian noise (AGGN) and extreme multi-source DOA estimation. Results demonstrate that our proposed method outperforms the existing deep learning-based DOA estimation methods.

Frequency Modulation (FM) broadcast signals, regarded as opportunistic signals, hold significant potential for indoor and outdoor positioning applications. The existing FM-based positioning methods primarily rely on Received Signal Strength (RSS) for positioning, the accuracy of which needs improvement. In this paper, we introduce FM-Pnet, an end-to-end FM-based positioning method that leverages deep learning. This method utilizes the time-frequency representation of FM signals as network input, enabling automatically learning of deep features for positioning. We also propose two strategies, noise injection and enriching training samples, to enhance the model’s generalization performance over long time spans. We construct datasets for both indoor and outdoor scenarios and conduct extensive experiments to validate the performance of our proposed method. Experimental results demonstrate that FM-Pnet significantly outperforms traditional RSS-based positioning methods in terms of both positioning accuracy and stability.

Semantic communication is a novel communication paradigm which refers to the extraction and encoding of semantic information from the source, and the restoration of information from a semantic perspective at the receiver. In this paper, we propose an end-to-end speech semantic communication system based on Transformer, called DeepSC-TS. It focuses on reconstructing and integrating multi-level information from the transmitted semantic signal at the receiver, effectively eliminating semantic signal noise while preserving the original semantic information. Moreover, it does not increase the data load of the original signal during transmission. Simulation results demonstrate that our proposed DeepSC-TS exhibits outstanding performance in different channel environments and it performs better than an existing speech semantic communication system.

The signal-to-noise ratio (SNR) is an important metric for measuring signal quality and its estimation has received widespread attention in various application scenarios. In this paper, we propose an SNR estimation framework based on deep learning classification. Power spectrum input is proposed to reduce the computational complexity. We also propose an SNR estimation method based on deep learning regression to overcome the inevitable estimation error problem of classification-based methods in dealing with signals with SNR not within the training label set. We conduct a large number of simulation experiments considering various scenarios. Results show that the proposed methods have better estimation accuracy than two existing deep learning-based SNR estimation methods in different noises and multipath channels. Furthermore, the proposed methods only need to be trained under one modulation signals to adapt to SNR estimation of other modulation signals, with superior transfer performance. Finally, the method using the average periodogram as input has stronger adaptability in few-shot scenario and requires lower computational complexity compared to the method with in-phase and quadrature (IQ) input.

In this paper we study multiple-input multiple-output (MIMO) systems with a large number of antennas at a base station serving a number of users in a cell. The antennas at the base station are assembled into multiple antenna arrays (MAA), which are well separated to keep independence between the arrays, but in each array antennas are densely installed. The MAA can be viewed as a flexible configuration of multiple antennas to reduce the space for installing the antennas and benefit from beamforming. In order to determine how dense the MAA can be designed, we define an antenna area efficiency, that is the ratio of the achievable rate and the 2D space required by installing the antennas. Then, we analyze the achievable rate of the massive MIMO system with $K$ uplink users and $NM$ antenna elements at the base station placed in $N$ square arrays and each array having $\sqrt{M}\times\sqrt{M}$ antennas densely deployed. Specifically, the analytical uplink sum-rate is first derived. Then, the sum-rate in the low-SNR and high-SNR regimes are respectively studied. A case study is provided to show how dense MAA can be designed in a massive MIMO system. Our analytical and simulations results show that, for $10$ users in low SNR, a single dense antenna array with $11\times 11$ antennas in a square requires only $1/200$ of the area of conventional $100$ independent antennas to achieve the same rate. For $10$ users in high SNR, we find that two $8\times 8$ square arrays can achieve the highest antenna area efficiency in comparison with one $16\times 16$ antenna arrays, four $5\times 5$ antenna arrays and $100$ independent antennas.

The frequency-hopping communication system has been widely used in anti-jamming communication due to its anti-interception and anti-jamming performance. With the increasingly complex electromagnetic environment, the frequency-hopping communication system needs more flexible frequency-hopping patterns to deal with interferences, which brings great challenges to the communication receiver. In this paper, an intelligent receiving scheme of frequency-hopping sequences is proposed, which combines time–frequency analysis with deep learning to realize an intelligent estimation of frequency-hopping sequences. A hybrid network module is designed by combining a convolutional neural network (CNN) with a gated recurrent unit (GRU). In the proposed network module, the combination of a residual network (ResNet) and squeeze and extraction (SE) improves the feature extraction and expression capabilities of the CNN network. The GRU network is proposed to solve the problem of dealing with signals with variant input lengths. A transfer learning scheme is further proposed to deal with communications systems with different frequency-hopping sets. Simulation results show that the proposed method has strong generalization ability and robustness, and the bit error rate (BER) performance of intelligent receiving is close to the receiving performance under ideal conditions.