SSwsrNet: A Semi-Supervised Few-Shot Learning Framework for Wireless Signal Recognition

Wireless signal recognition (WSR) is crucial in modern and future wireless communication networks since it aims to identify properties of the received signal. Although many deep learning-based WSR models have been developed, they still rely on a large amount of labeled training data. Thus, they cannot tackle the few-sample problem in the practically and dynamically changing wireless communication environment. To overcome this challenge, a novel SSwsrNet framework is proposed by using the deep residual shrinkage network (DRSN) and semi-supervised learning. The DRSN can learn discriminative features from noisy signals. Moreover, a modular semi-supervised learning method that combines labeled and unlabeled data using MixMatch is exploited to further improve the classification performance under few-sample conditions. Extensive simulation results on automatic modulation classification (AMC) and wireless technology classification (WTC) demonstrate that our proposed WSR scheme can achieve better performance than the benchmark schemes in terms of classification accuracy. This novel method enables more robust and adaptive signal recognition for next-generation wireless networks.

Deep CSI Compression for Dual-Polarized Massive MIMO Channels with Disentangled Representation Learning

Channel state information (CSI) feedback is critical for achieving the promised advantages of enhancing spectral and energy efficiencies in massive multiple-input multiple-output (MIMO) wireless communication systems. Deep learning (DL)-based methods have been proven effective in reducing the required signaling overhead for CSI feedback. In practical dual-polarized MIMO scenarios, channels in the vertical and horizontal polarization directions tend to exhibit high polarization correlation. To fully exploit the inherent propagation similarity within dual-polarized channels, we propose a disentangled representation neural network (NN) for CSI feedback, referred to as DiReNet. The proposed DiReNet disentangles dual-polarized CSI into three components: polarization-shared information, vertical polarization-specific information, and horizontal polarization-specific information. This disentanglement of dual-polarized CSI enables the minimization of information redundancy caused by the polarization correlation and improves the performance of CSI compression and recovery. Additionally, flexible quantization and network extension schemes are designed. Consequently, our method provides a pragmatic solution for CSI feedback to harness the physical MIMO polarization as a priori information. Our experimental results show that the performance of our proposed DiReNet surpasses that of existing DL-based networks, while also effectively reducing the number of network parameters by nearly one third.

Energy Efficient Design of Active STAR-RIS-Aided SWIPT Systems

In this paper, we consider the downlink transmission of a multi-antenna base station (BS) supported by an active simultaneously transmitting and reconfigurable intelligent surface (STAR-RIS) to serve single-antenna users via simultaneous wireless information and power transfer (SWIPT). In this context, we formulate an energy efficiency maximisation problem that jointly optimises the gain, element selection and phase shift matrices of the active STAR-RIS, the transmit beamforming of the BS and the power splitting ratio of the users. With respect to the highly coupled and non-convex form of this problem, an alternating optimisation solution approach is proposed, using tools from convex optimisation and reinforcement learning. Specifically, semi-definite relaxation (SDR), difference of concave functions (DC), and fractional programming techniques are employed to transform the non-convex optimisation problem into a convex form for optimising the BS beamforming vector and the power splitting ratio of the SWIPT. Then, by integrating meta-learning with the modified deep deterministic policy gradient (DDPG) and soft actor-critical (SAC) methods, a combinatorial reinforcement learning network is developed to optimise the element selection, gain and phase shift matrices of the active STAR-RIS. Our simulations show the effectiveness of the proposed resource allocation scheme. Furthermore, our proposed active STAR-RIS-based SWIPT system outperforms its passive counterpart by 57% on average.

Low Complexity Radio Frequency Interference Mitigation for Radio Astronomy Using Large Antenna Array

With the ongoing growth in radio communications, there is an increased contamination of radio astronomical source data, which hinders the study of celestial radio sources. In many cases, fast mitigation of strong radio frequency interference (RFI) is valuable for studying short lived radio transients so that the astronomers can perform detailed observations of celestial radio sources. The standard method to manually excise contaminated blocks in time and frequency makes the removed data useless for radio astronomy analyses. This motivates the need for better radio frequency interference (RFI) mitigation techniques for array of size M antennas. Although many solutions for mitigating strong RFI improves the quality of the final celestial source signal, many standard approaches require all the eigenvalues of the spatial covariance matrix ($\textbf{R} \in \mathbb{C}^{M \times M}$) of the received signal, which has $O(M^3)$ computation complexity for removing RFI of size $d$ where $\textit{d} \ll M$. In this work, we investigate two approaches for RFI mitigation, 1) the computationally efficient Lanczos method based on the Quadratic Mean to Arithmetic Mean (QMAM) approach using information from previously-collected data under similar radio-sky-conditions, and 2) an approach using a celestial source as a reference for RFI mitigation. QMAM uses the Lanczos method for finding the Rayleigh-Ritz values of the covariance matrix $\textbf{R}$, thus, reducing the computational complexity of the overall approach to $O(\textit{d}M^2)$. Our numerical results, using data from the radio observatory Long Wavelength Array (LWA-1), demonstrate the effectiveness of both proposed approaches to remove strong RFI, with the QMAM-based approach still being computationally efficient.

KGAMC: A Novel Knowledge Graph Driven Automatic Modulation Classification Scheme

Automatic modulation classification (AMC) is a promising technology to realize intelligent wireless communications in the sixth generation (6G) wireless communication networks. Recently, many data-and-knowledge dual-driven AMC schemes have achieved high accuracy. However, most of these schemes focus on generating additional prior knowledge or features of blind signals, which consumes longer computation time and ignores the interpretability of the model learning process. To solve these problems, we propose a novel knowledge graph (KG) driven AMC (KGAMC) scheme by training the networks under the guidance of domain knowledge. A modulation knowledge graph (MKG) with the knowledge of modulation technical characteristics and application scenarios is constructed and a relation-graph convolution network (RGCN) is designed to extract knowledge of the MKG. This knowledge is utilized to facilitate the signal features separation of the data-oriented model by implementing a specialized feature aggregation method. Simulation results demonstrate that KGAMC achieves superior classification performance compared to other benchmark schemes, especially in the low signal-to-noise ratio (SNR) range. Furthermore, the signal features of the high-order modulation are more discriminative, thus reducing the confusion between similar signals.

Movable-Antenna Array Enabled Multiuser Uplink: A Low-Complexity Gradient Descent for Total Transmit Power Minimization

We investigate multiuser uplink communication from multiple single-antenna users to a base station (BS), which is equipped with a movable-antenna (MA) array and adopts zero-forcing receivers to decode multiple signals. We aim to optimize the MAs' positions at the BS, to minimize the total transmit power of all users subject to the minimum rate requirement. After applying transformations, we show that the problem is equivalent to minimizing the sum of each eigenvalue's reciprocal of a matrix, which is a function of all MAs' positions. Subsequently, the projected gradient descent (PGD) method is utilized to find a locally optimal solution. In particular, different from the latest related work, we exploit the eigenvalue decomposition to successfully derive a closed-form gradient for the PGD, which facilitates the practical implementation greatly. We demonstrate by simulations that via careful optimization for all MAs' positions in our proposed design, the total transmit power of all users can be decreased significantly as compared to competitive benchmarks.

Movable-Antenna Array-Enabled Wireless Communication with CoMP Reception

We consider the movable antenna (MA) array-enabled wireless communication with coordinate multi-point (CoMP) reception, where multiple destinations adopt the maximal ratio combination technique to jointly decode the common message sent from the transmitter equipped with the MA array. Our goal is to maximize the effective received signal-to-noise ratio, by jointly optimizing the transmit beamforming and the positions of the MA array. Although the formulated problem is highly non-convex, we reveal that it is fundamental to maximize the principal eigenvalue of a hermite channel matrix which is a function of the positions of the MA array. The corresponding sub-problem is still non-convex, for which we develop a computationally efficient algorithm. Afterwards, the optimal transmit beamforming is determined with a closed-form solution. In addition, the theoretical performance upper bound is analyzed. Since the MA array brings an additional spatial degree of freedom by flexibly adjusting all antennas' positions, it achieves significant performance gain compared to competitive benchmarks.

Secure Wireless Communication via Movable-Antenna Array

Movable antenna (MA) array is a novel technology recently developed where positions of transmit/receive antennas can be flexibly adjusted in the specified region to reconfigure the wireless channel and achieve a higher capacity. In this letter, we, for the first time, investigate the MA array-assisted physical-layer security where the confidential information is transmitted from a MA array-enabled Alice to a single-antenna Bob, in the presence of multiple single-antenna and colluding eavesdroppers. We aim to maximize the achievable secrecy rate by jointly designing the transmit beamforming and positions of all antennas at Alice subject to the transmit power budget and specified regions for positions of all transmit antennas. The resulting problem is highly non-convex, for which the projected gradient ascent (PGA) and the alternating optimization methods are utilized to obtain a high-quality suboptimal solution. Simulation results demonstrate that since the additional spatial degree of freedom (DoF) can be fully exploited, the MA array significantly enhances the secrecy rate compared to the conventional fixed-position antenna (FPA) array.

Intelligent Reflecting Surface-Aided Wireless Communication with Movable Elements

Intelligent reflecting surface (IRS) has been recognized as a powerful technology for boosting communication performance. To reduce manufacturing and control costs, it is preferable to consider discrete phase shifts (DPSs) for IRS, which are set by default as uniformly distributed in the range of $[ - \pi,\pi )$ in the literature. Such setting, however, cannot achieve a desirable performance over the general Rician fading where the channel phase concentrates in a narrow range with a higher probability. Motivated by this drawback, we in this paper design optimal non-uniform DPSs for IRS to achieve a desirable performance level. The fundamental challenge is the \textit{possible offset in phase distribution across different cascaded source-element-destination channels}, if adopting conventional IRS where the position of each element is fixed. Such phenomenon leads to different patterns of optimal non-uniform DPSs for each IRS element and thus causes huge manufacturing costs especially when the number of IRS elements is large. Driven by the recently emerging fluid antenna system (or movable antenna technology), we demonstrate that if the position of each IRS element can be flexibly adjusted, the above phase distribution offset can be surprisingly eliminated, leading to the same pattern of DPSs for each IRS element. Armed with this, we then determine the form of unified non-uniform DPSs based on a low-complexity iterative algorithm. Simulations show that our proposed design significantly improves the system performance compared to competitive benchmarks.