Interest continues to grow in utilizing federated learning (FL) for various signal processing and communications applications. Over-the-air (OTA) computation has been proposed to improve FL efficiency in bandwidth-limited environments by leveraging the superposition characteristic of a wireless multiple-access channel (MAC). However, OTA FL faces inherent challenges due to channel noise and fading in any wireless MAC scenario, which can degrade optimization and significantly reduce model accuracy. This paper aims to design a robust OTA FL system to counteract the effects of noise and fading over time-varying channels. We propose a novel approach employing a Kalman filter (KF)-based OTA FL algorithm under imperfect channel state information (CSI). We conduct a convergence analysis of our OTA FL scheme, which motivates our development of a complementary hierarchical optimization methodology to minimize the impact of bias and noise terms. Numerical results confirm that our methodology has superior performance to conventional OTA FL, and approaches the performance obtained by the upper limit of perfect CSI in low-SNR scenarios.

Integrated sensing and communications (ISAC) is a key enabler of new applications, such as precision agriculture, extended reality (XR), and digital twins, for 6G wireless systems. However, the implementation of ISAC technology is very challenging due to practical constraints such as high complexity. In this paper, we introduce a novel ISAC waveform design strategy, calledthe spatial-division ISAC (SD-ISAC) waveform, which simplifies the ISAC waveform design problem by decoupling it into separate communication and radar waveform design tasks. Specifically, the proposed strategy leverages the null-space of the communication channel to superimpose sensing signals onto communication signals without interference. This approach offers multiple benefits, including reduced complexity and the reuse of existing communication and radar waveforms. We then address the problem of optimizing the spatial and temporal properties of the proposed waveform. We develop a low-complexity beampattern matching algorithm, leveraging a majorization-minimization (MM) technique. Furthermore, we develop a range sidelobe suppression algorithm based on manifold optimization. We provide comprehensive discussions on the practical advantages and potential challenges of the proposed method, including null-space feedback. We evaluate the performance of the proposed waveform design algorithm through extensive simulations. Simulation results show that the proposed method can provide similar or even superior performance to existing ISAC algorithms while reducing computation time significantly.

Channel prediction addresses outdated channel state information by forecasting future channels based on past channel estimates. We propose a machine learning (ML)-based approach using neural networks to learn complex temporal statistics. Unlike conventional offline-trained predictors that suffer from unfamiliar environments, our online re-training framework adapts to varying channel conditions by re-training the networks from scratch. To minimize the re-training time for practical implementation, we introduce an aggregated learning (AL) approach for massive multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems. AL splits and aggregates training data in array or frequency domains of MIMO-OFDM channels, significantly reducing data collection time. Numerical results show that AL not only decreases training time overhead but also improves prediction performance across various scenarios.

In this paper, we consider people counting and localization systems exploiting channel state information (CSI) measured from commodity WiFi network interface cards (NICs). CSI has useful information of amplitude and phase to describe signal propagation affected by the number of people or their locations in a designated space. However, due to hardware impairments of transceivers, CSI measurement suffers from offsets such as packet boundary detection uncertainty, sampling time difference, and carrier frequency difference. Moreover, an uncontrollable external environment where other WiFi devices communicate each other induces interfering signals, resulting in erroneous CSI captured at a receiver. In this paper, preprocessing of CSI is first proposed for offset removal, and it guarantees low-latency operation without any filtering process. The number of samples collected for each specific scenario is kept after packet-preserving preprocessing, which can be fully utilized to learn neural network models. Afterwards, we design people counting and localization models based on pre-training. To be adaptive to different measurement environments, meta-learning-based people counting and localization models are also proposed. We provide computational and space complexity analyses, confirming that the proposed meta-learning-based people counting and localization models require comparable resources to conventional adaptive models. Numerical results show that, compared with other learning-based benchmarks, the proposed scheme can achieve high sensing accuracy.

This paper proposes a beamforming method under a per-antenna power constraint (PAPC). Although many beamformer designs with the PAPC need to solve complex optimization problems, the proposed complete power reallocation (CPR) method can generate beamformers with excellent performance only with linear operations. CPR is designed to have a simple structure, making it highly flexible and practical. In this paper, three CPR variations considering algorithm convergence speed, sum-rate maximization, and robustness to the channel uncertainty are developed. Simulation results verify that CPR and its variations satisfy their design criteria, and, hence, CPR can be readily utilized for various purposes.

Accurate channel knowledge is critical in massive multiple-input multiple-output (MIMO), which motivates the use of channel prediction. Machine learning techniques for channel prediction hold much promise, but current schemes are limited in their ability to adapt to changes in the environment because they require large training overheads. To accurately predict wireless channels for new environments with reduced training overhead, we propose a fast adaptive channel prediction technique based on a meta-learning algorithm for massive MIMO communications. We exploit the model-agnostic meta-learning (MAML) algorithm to achieve quick adaptation with a small amount of labeled data. Also, to improve the prediction accuracy, we adopt the denoising process for the training data by using deep image prior (DIP). Numerical results show that the proposed MAML-based channel predictor can improve the prediction accuracy with only a few fine-tuning samples in various scenarios. The DIP-based denoising process gives an additional gain in channel prediction, especially in low signal-to-noise ratio regimes.

Time division duplexing (TDD) is adopted to exploit the uplink and downlink channel reciprocity in most of studies on massive multiple-input multiple-output (MIMO) systems. However, even in TDD, a base station (BS) still requires to transmit downlink training signals, which are named in the 3GPP standard as channel state information reference signals (CSI-RSs), to fully support spatial multiplexing in practice. This is because user equipments (UEs) may deploy less number of transmit antennas than receive antennas due to practical issues. Since uplink sounding reference signals (SRSs) are transmitted from only the transmit antennas of the UE, the BS is not able to obtain full downlink MIMO CSI by using channel reciprocity for spatial multiplexing. Hence, after reception of the downlink CSI-RSs, the UE still needs to feed back quantized CSI using a codebook to support spatial multiplexing. Taking practical antenna structures into account for reducing downlink CSI-RS overhead, this paper proposes possible approaches for downlink MIMO CSI reconstruction at the BS using the SRS with quantized downlink CSI to support spatial multiplexing. Numerical results show that the proposed techniques outperform the conventional one, i.e., solely based on the quantized CSI, in terms of the spectral efficiencies of spatial multiplexing.

This paper focuses on channel prediction techniques for massive multiple-input multiple-output (MIMO) systems. Previous channel predictors are based on theoretical channel models, which would be deviated from realistic channels. In this paper, we develop and compare a vector Kalman filter (VKF)-based channel predictor and a machine learning (ML)-based channel predictor using the realistic channels from the spatial channel model (SCM), which has been adopted in the 3GPP standard for years. First, we propose a low-complexity mobility estimator based on the spatial average using a large number of antennas in massive MIMO. The mobility estimate can be used to determine the complexity order of developed predictors. The VKF-based channel predictor developed in this paper exploits the autoregressive (AR) parameters estimated from the SCM channels based on the Yule-Walker equations. Then, the ML-based channel predictor using the linear minimum mean square error (LMMSE)-based noise pre-processed data is developed. Numerical results reveal that both channel predictors have substantial gain over the outdated channel in terms of the channel prediction accuracy and data rate. The ML-based predictor has larger overall computational complexity than the VKF-based predictor, but once trained, the operational complexity of ML-based predictor becomes smaller than that of VKF-based predictor.

To get channel state information (CSI) at a base station (BS), most of researches on massive multiple-input multiple-output (MIMO) systems consider time division duplexing (TDD) to get benefit from the uplink and downlink channel reciprocity. Even in TDD, however, the BS still needs to transmit downlink training signals, which are referred to as channel state information reference signals (CSI-RSs) in the 3GPP standard, to support spatial multiplexing in practice. This is because there are many cases that the number of transmit antennas is less than the number of receive antennas at a user equipment (UE) due to power consumption and circuit complexity issues. Because of this mismatch, uplink sounding reference signals (SRSs) from the UE are not enough for the BS to obtain full downlink MIMO CSI. Therefore, after receiving the downlink CSI-RSs, the UE needs to feedback quantized CSI to the BS using a pre-defined codebook to support spatial multiplexing. In this paper, possible approaches to reconstruct full downlink MIMO CSI at the BS are proposed by exploiting both the SRS and quantized downlink CSI considering practical antenna structures with reduced downlink CSI-RS overhead. Numerical results show that the spectral efficiencies by spatial multiplexing based on the proposed downlink MIMO CSI reconstruction techniques outperform the conventional methods solely based on the quantized CSI.

Massive multiple-input multiple-output (MIMO) can improve the overall system performance significantly. Massive MIMO systems, however, may require a large number of radio frequency (RF) chains that could cause high cost and power consumption issues. One of promising approaches to resolve these issues is using low-resolution analog-to-digital converters (ADCs) at base stations. Channel estimation becomes a difficult task by using low-resolution ADCs though. This paper addresses the channel estimation problem for massive MIMO systems using one-bit ADCs when the channels are spatially and temporally correlated. Based on the Bussgang decomposition, which reformulates a non-linear one-bit quantization to a statistically equivalent linear operator, the Kalman filter is used to estimate the spatially and temporally correlated channel by assuming the quantized noise follows a Gaussian distribution. Numerical results show that the proposed technique can improve the channel estimation quality significantly by properly exploiting the spatial and temporal correlations of channels.