Increasing demand for massive device connectivity in underserved regions drives the development of advanced low Earth orbit (LEO) satellite communication systems. Beam-hopping LEO systems without connection establishment provide a promising solution for achieving both demand-aware resource allocation and low access latency. However, integrating beam-hopping with grant-free random access presents unique challenges due to sporadic and unpredictable device activity, fundamentally differing from scheduled systems with deterministic resource allocation. This paper investigates beam-hopping pattern design for grant-free random access systems to dynamically allocate satellite resources according to traffic demands across serving cells. We formulate a binary optimization problem that maximizes the minimum successful transmission probability across cells, which captures performance in systems with unpredictable device activity. To solve this problem, we propose novel beam-hopping design algorithms that alternately enhance the collision avoidance rate to mitigate intra-cell collisions and the decoding success probability to manage inter-cell interference within an alternating optimization framework. Specifically, the algorithms employ a bisection method to optimize illumination allocation for each cell based on demand, while using the alternating direction method of multipliers (ADMM) to optimize beam-hopping patterns for maximizing decoding success probability. Furthermore, we enhance the ADMM by replacing the strict binary constraint with two equivalent continuous-valued constraints. Simulation results demonstrate the superiority of the proposed algorithms compared to other beam-hopping methods and verify robustness in managing traffic demand imbalance.

In this paper, we propose a novel hierarchical sensing framework for wideband integrated sensing and communications with uniform planar arrays (UPAs). Leveraging the beam-squint effect inherent in wideband orthogonal frequency-division multiplexing (OFDM) systems, the proposed framework enables efficient two-dimensional angle estimation through a structured multi-stage sensing process. Specifically, the sensing procedure first searches over the elevation angle domain, followed by a dedicated search over the azimuth angle domain given the estimated elevation angles. In each stage, true-time-delay lines and phase shifters of the UPA are jointly configured to cover multiple grid points simultaneously across OFDM subcarriers. To enable accurate and efficient target localization, we formulate the angle estimation problem as a sparse signal recovery problem and develop a modified matching pursuit algorithm tailored to the hierarchical sensing architecture. Additionally, we design power allocation strategies that minimize total transmit power while meeting performance requirements for both sensing and communication. Numerical results demonstrate that the proposed framework achieves superior performance over conventional sensing methods with reduced sensing power.

This paper presents a novel importance-aware quantization, subcarrier mapping, and power allocation (IA-QSMPA) framework for semantic communication in multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems, empowered by a pretrained Vision Transformer (ViT). The proposed framework exploits attention-based importance extracted from a pretrained ViT to jointly optimize quantization levels, subcarrier mapping, and power allocation. Specifically, IA-QSMPA maps semantically important features to high-quality subchannels and allocates resources in accordance with their contribution to task performance and communication latency. To efficiently solve the resulting nonconvex optimization problem, a block coordinate descent algorithm is employed. The framework is further extended to operate under finite blocklength transmission, where communication errors may occur. In this setting, a segment-wise linear approximation of the channel dispersion penalty is introduced to enable efficient joint optimization under practical constraints. Simulation results on multi-view image classification and single-object detection tasks demonstrate that IA-QSMPA significantly outperforms conventional methods in both ideal and finite blocklength transmission scenarios, achieving superior task performance and communication efficiency.

This paper proposes a novel end-to-end digital semantic communication framework based on multi-codebook vector quantization (VQ), referred to as ESC-MVQ. Unlike prior approaches that rely on end-to-end training with a specific power or modulation scheme, often under a particular channel condition, ESC-MVQ models a channel transfer function as parallel binary symmetric channels (BSCs) with trainable bit-flip probabilities. Building on this model, ESC-MVQ jointly trains multiple VQ codebooks and their associated bit-flip probabilities with a single encoder-decoder pair. To maximize inference performance when deploying ESC-MVQ in digital communication systems, we devise an optimal communication strategy that jointly optimizes codebook assignment, adaptive modulation, and power allocation. To this end, we develop an iterative algorithm that selects the most suitable VQ codebook for semantic features and flexibly allocates power and modulation schemes across the transmitted symbols. Simulation results demonstrate that ESC-MVQ, using a single encoder-decoder pair, outperforms existing digital semantic communication methods in both performance and memory efficiency, offering a scalable and adaptive solution for realizing digital semantic communication in diverse channel conditions.

In this paper, we propose a novel hierarchical sensing framework for integrated sensing and communication systems equipped with uniform planar arrays (UPAs) for wideband scenarios. Leveraging the beam-squint effect inherent in wideband orthogonal frequency-division multiplexing systems, the proposed framework enables efficient two-dimensional angle estimation through a structured multi-stage sensing process. Specifically, the sensing procedure first searches over the elevation angle domain, followed by a dedicated search over the azimuth angle domain given the estimated elevation angles. In each stage, true-time-delay lines and phase shifters of the UPA are jointly configured to simultaneously cover multiple grid points across subcarriers. To enable accurate and efficient target localization, we formulate the angle estimation problem as a sparse signal recovery problem and solve it using conventional compressed sensing algorithms tailored to the hierarchical sensing architecture. Numerical results demonstrate that the proposed framework achieves near-optimal sensing accuracy with significantly reducing sensing time.

Semantic communications based on deep joint source-channel coding (JSCC) aim to improve communication efficiency by transmitting only task-relevant information. How-ever, ensuring robustness to the stochasticity of communication channels remains a key challenge in learning-based JSCC. In this paper, we propose a novel regularization technique for learning-based JSCC to enhance robustness against channel noise. The proposed method utilizes the Kullback-Leibler (KL) divergence as a regularizer term in the training loss, measuring the discrepancy between two posterior distributions: one under noisy channel conditions (noisy posterior) and one for a noise-free system (noise-free posterior). We further show that the expectation of the KL divergence given the encoded representation can be analytically approximated using the Fisher information matrix and the covariance matrix of the channel noise. Notably, the proposed regularization is architecture-agnostic, making it broadly applicable to general semantic communication systems over noisy channels.

Multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems often suffer from channel estimation errors due to the limited number of reference signals and channel selectivity in both the time and frequency domains. To address these errors, this paper proposes a meta-learning-based channel denoising method for MIMO-OFDM systems. The proposed method employs a denoising convolutional neural network (DnCNN) to mitigate estimation errors in channel frequency responses (CFRs) across the time-frequency domain. For training the DnCNN, a model-agnostic meta-learning (MAML) approach is devised which enables fast adaptation of the DnCNN to new and unseen channel denoising tasks. In our MAML approach, training samples from past user equipments (UEs) are used to pre-train the DnCNN, following the MAML principle. After pre-training, a few training samples from new UEs are utilized to fine-tune the pre-trained DnCNN using only a few gradient steps. A practical data generation strategy is also presented, substituting true CFRs with high-quality CFR estimates determined via data-aided channel estimation. Simulation results show that the proposed channel denoising method effectively reduces the channel estimation errors of conventional techniques and adapts well to new and unseen channel environments.

This paper studies a data detection problem for multiple-input multiple-output (MIMO) communication systems with hardware impairments. To facilitate maximum likelihood (ML) data detection without knowledge of nonlinear and unknown hardware impairments, we develop a novel likelihood function estimation method based on data augmentation and boosting. In our method, we generate multiple augmented datasets by injecting noise with various distributions into seed data consisting of online received signals. We then estimate the likelihood function (LF) using each augmented dataset based on the expectationmaximization algorithm. We linearly combine the multiple LF estimates obtained from these datasets based on their reliability levels. Simulation results demonstrate that the ML detection combined with our LF estimation method outperforms existing methods, while also highlighting the effectiveness of our data augmentation approach.

Semantic communications provide significant performance gains over traditional communications by transmitting task-relevant semantic features through wireless channels. However, most existing studies rely on end-to-end (E2E) training of neural-type encoders and decoders to ensure effective transmission of these semantic features. To enable semantic communications without relying on E2E training, this paper presents a vision transformer (ViT)-based semantic communication system with importance-aware quantization (IAQ) for wireless image transmission. The core idea of the presented system is to leverage the attention scores of a pretrained ViT model to quantify the importance levels of image patches. Then, our IAQ framework assigns different quantization bits to image patches based on their importance levels. This is achieved by formulating a weighted quantization error minimization problem, where the weight is set to be an increasing function of the attention score. Then, an optimal incremental bit-allocation method and a low-complexity water-filling method are devised to solve the formulated problem. Simulations on multi-view image classification tasks show that our IAQ framework outperforms existing quantization methods.

In this paper, we present a novel approach for joint activity detection (AD), channel estimation (CE), and data detection (DD) in uplink grant-free non-orthogonal multiple access (NOMA) systems. Our approach employs an iterative and parallel interference removal strategy inspired by parallel interference cancellation (PIC), enhanced with deep learning to jointly tackle the AD, CE, and DD problems. Based on this approach, we develop three PIC frameworks, each of which is designed for either coherent or non-coherence schemes. The first framework performs joint AD and CE using received pilot signals in the coherent scheme. Building upon this framework, the second framework utilizes both the received pilot and data signals for CE, further enhancing the performances of AD, CE, and DD in the coherent scheme. The third framework is designed to accommodate the non-coherent scheme involving a small number of data bits, which simultaneously performs AD and DD. Through joint loss functions and interference cancellation modules, our approach supports end-to-end training, contributing to enhanced performances of AD, CE, and DD for both coherent and non-coherent schemes. Simulation results demonstrate the superiority of our approach over traditional techniques, exhibiting enhanced performances of AD, CE, and DD while maintaining lower computational complexity.

Semantic communications provide significant performance gains over traditional communications by transmitting task-relevant semantic features through wireless channels. However, most existing studies rely on end-to-end (E2E) training of neural-type encoders and decoders to ensure effective transmission of these semantic features. To enable semantic communications without relying on E2E training, this paper presents a vision transformer (ViT)-based semantic communication system with importance-aware quantization (IAQ) for wireless image transmission. The core idea of the presented system is to leverage the attention scores of a pretrained ViT model to quantify the importance levels of image patches. Based on this idea, our IAQ framework assigns different quantization bits to image patches based on their importance levels. This is achieved by formulating a weighted quantization error minimization problem, where the weight is set to be an increasing function of the attention score. Then, an optimal incremental allocation method and a low-complexity water-filling method are devised to solve the formulated problem. Our framework is further extended for realistic digital communication systems by modifying the bit allocation problem and the corresponding allocation methods based on an equivalent binary symmetric channel (BSC) model. Simulations on single-view image classification, multi-view image classification, and single-object detection tasks demonstrate that our IAQ framework outperforms conventional image compression methods under both error-free and realistic communication scenarios.

This paper addresses a data detection problem for multiple-input multiple-output (MIMO) communication systems with hardware impairments. To facilitate maximum likelihood (ML) data detection without knowledge of nonlinear and unknown hardware impairments, we develop novel likelihood function (LF) estimation methods based on data augmentation and boosting. The core idea of our methods is to generate multiple augmented datasets by injecting noise with various distributions into seed data consisting of online received signals. We then estimate the LF using each augmented dataset based on either the expectation maximization (EM) algorithm or the kernel density estimation (KDE) method. Inspired by boosting, we further refine the estimated LF by linearly combining the multiple LF estimates obtained from the augmented datasets. To determine the weights for this linear combination, we develop methods that take different approaches to measure the reliability of the estimated LFs. Simulation results demonstrate that both the EM- and KDE-based LF estimation methods offer significant performance gains over existing LF estimation methods. Our results also show that the effectiveness of the proposed methods improves as the size of the augmented data increases.

Semantic encoders and decoders for digital semantic communication (SC) often struggle to adapt to variations in unpredictable channel environments and diverse system designs. To address these challenges, this paper proposes a novel framework for training semantic encoders and decoders to enable channel-adaptive digital SC. The core idea is to use binary symmetric channel (BSC) as a universal representation of generic digital communications, eliminating the need to specify channel environments or system designs. Based on this idea, our framework employs parallel BSCs to equivalently model the relationship between the encoder’s output and the decoder’s input. The bit-flip probabilities of these BSCs are treated as trainable parameters during end-to-end training, with varying levels of regularization applied to address diverse requirements in practical systems. The advantage of our framework is justified by developing a training-aware communication strategy for the inference stage. This strategy makes communication bit errors align with the pre-trained bit-flip probabilities by adaptively selecting power and modulation levels based on practical requirements and channel conditions. Simulation results demonstrate that the proposed framework outperforms existing training approaches in terms of both task performance and power consumption.

To support higher throughput in next-generation Wi-Fi systems, efficient compression and feedback of channel state information (CSI) from a station (STA) to an access point (AP) is essential. This paper proposes a deep learning (DL)-based CSI feedback framework tailored for Wi-Fi systems. The framework employs encoder and decoder networks to compress and reconstruct CSI angle parameters, with a trainable vector quantization (VQ) module enabling efficient finite-bit representation through end-to-end training. To further enhance performance, we introduce an angle-difference feedback strategy that exploits the temporal correlation of the angle parameters by feeding back the difference between the current and previous values. This is complemented by preprocessing that handles the periodicity of angles and tailored VQ modules that compensate for residual quantization errors. Additionally, we present a DL-based CSI refinement module at the AP, which improves reconstruction by jointly using current and prior feedback. Simulation results show that the proposed framework outperforms both standard Wi-Fi feedback and existing DL-based feedback methods, with notable gains from both angle-difference feedback and CSI refinement.

This article proposes a novel communication-efficient split learning (SL) framework, named SplitFC, which reduces the communication overhead required for transmitting intermediate features and gradient vectors during the SL training process. The key idea of SplitFC is to leverage different dispersion degrees exhibited in the columns of the matrices. SplitFC incorporates two compression strategies: 1) adaptive feature-wise dropout and 2) adaptive feature-wise quantization. In the first strategy, the intermediate feature vectors are dropped with adaptive dropout probabilities determined based on the standard deviation of these vectors. Then, by the chain rule, the intermediate gradient vectors associated with the dropped feature vectors are also dropped. In the second strategy, the non-dropped intermediate feature and gradient vectors are quantized using adaptive quantization levels determined based on the ranges of the vectors. To minimize the quantization error, the optimal quantization levels of this strategy are derived in a closed-form expression. Simulation results on the MNIST, CIFAR-100, and CelebA datasets demonstrate that SplitFC outperforms state-of-the-art SL frameworks by significantly reducing communication overheads while maintaining high accuracy.

In this paper, we introduce a novel deep learning-assisted parallel interference cancellation (PIC) framework for joint activity detection (AD) and channel estimation (CE) in up-link grant-free non-orthogonal multiple access (NOMA) systems. Our framework employs an iterative and parallel interference removal strategy inspired by PIC, enhanced with deep learning to jointly tackle the AD and CE problems. The proposed framework consists of multiple uniform stages, each containing trainable CE modules and non-parameterized IC modules. Additionally, it integrates AD modules that estimate each device activity in a parallel manner by leveraging the received signals after interference removal processes. Through joint loss functions and IC modules, the proposed framework supports end-to-end training, contributing to enhanced performances of AD and CE. Simulation results demonstrate the superiority of the proposed framework over traditional techniques, exhibiting enhanced performances of AD and CE while maintaining lower computational complexity.

This paper proposes a novel joint source-channel coding (JSCC) approach for robust digital semantic communications. When employing a binary-output JSCC encoder with digital modulation, end-to-end training becomes challenging due to the unpredictable dynamics of channel conditions. To address this challenge, we first develop a new demodulation method which assesses the uncertainty of the demodulation output to improve the robustness of the digital semantic communication system. We then devise a robust training strategy which enhances the robustness and flexibility of the JSCC encoder and decoder against diverse channel conditions. To this end, we model the relationship between the encoder’s output and decoder’s input using binary symmetric erasure channels and then sample the parameters of these channels from diverse distributions. Using simulations, we demonstrate the superior performance of the proposed JSCC approach for image classification and reconstruction tasks compared to existing JSCC approaches.

This paper presents a robust beam alignment technique for millimeter-wave communications in low signal-to-noise ratio (SNR) regimes. The basic strategy of this technique involves the repeated transmission of beam candidates, aimed at minimizing the beam misalignment probability induced by noise. In this strategy, however, the beam training overhead becomes impractically significant when both the numbers of beam candidates and beam repetitions are large. To address this challenge, the presented technique aims at optimizing both the selection of beam candidates and the number of repetitions for each candidate based on channel prior information. In the presented technique, a deep neural network is employed to learn the prior probability of the optimal beam at each location. The beam misalignment probability is then analyzed based on the channel prior, and a practical algorithm is developed to find the optimal beam repetition strategy to minimize the beam misalignment probability. Simulation results using the DeepMIMO dataset demonstrate the superior performance of the presented technique in dynamic low-SNR communication environments compared to existing beam alignment techniques.

Federated learning (FL), as a type of distributed machine learning, is vulnerable to external attacks during parameter transmissions between learning agents and a model aggregator. In particular, malicious participant clients in FL can purposefully craft their uploaded model parameters to manipulate system outputs, which is know as a model poisoning (MP) attack. In this paper, we propose effective MP algorithms to attack the classical defensive aggregation Krum at the aggregator. The proposed algorithms are designed to evade detection, i.e., covert MP (CMP). Specifically, we first formulate the MP as an optimization problem by minimizing the Euclidean distance between the manipulated model and designated one, constrained by Krum. Then, we develop CMP algorithms against the Krum based on the solutions of this optimization problem. Furthermore, to reduce the optimization complexity, we propose low complexity CMP algorithms having only a slight performance degradation. Our experimental results demonstrate that the proposed CMP algorithms are effective and can substantially outperform existing attack mechanisms, such as Arjun's attack and the label flipping attack. More specifically, our original CMP can achieve a high rate of the attacker's accuracy ($\approx 90\%$). For example, in our experiments using the MNIST dataset, the proposed CMP attacking algorithm against Krum can successfully manipulate the aggregated model to incorrectly classify a given digit as a different one (e.g., 9 as 8). Meanwhile, our CMP algorithm with an approximated constraint can achieve a rate of 87% in terms of the attacker's accuracy (attacker-desired results), with a 73% complexity reduction compared to the original CMP.

This paper presents a novel split learning (SL) framework, referred to as SplitMAC, which reduces the latency of SL by leveraging simultaneous uplink transmission over multiple access channels. The key strategy is to divide devices into multiple groups and allow the devices within the same group to simultaneously transmit their smashed data and device-side models over the multiple access channels. The optimization problem of device grouping to minimize SL latency is formulated, and the benefit of device grouping in reducing the uplink latency of SL is theoretically derived. By examining a two-device grouping case, two asymptotically-optimal algorithms are devised for device grouping in low and high signal-to-noise ratio (SNR) scenarios, respectively. By merging these algorithms, a near-optimal device grouping algorithm is proposed to cover a wide range of SNR. Although our theoretical analysis holds only for the two-device case, our SL framework is also extended to consider practical fading channels and to support a general group size. Simulation results demonstrate that our SL framework with the proposed device grouping algorithm is superior to existing SL frameworks in reducing SL latency.

This paper considers a data detection problem in multiple-input multiple-output (MIMO) communication systems with hardware impairments. To address challenges posed by nonlinear and unknown distortion in received signals, two learning-based detection methods, referred to as model-driven and data-driven, are presented. The model-driven method employs a generalized Gaussian distortion model to approximate the conditional distribution of the distorted received signal. By using the outputs of coarse data detection as noisy training data, the model-driven method avoids the need for additional signaling overhead beyond traditional pilot overhead for channel estimation. An expectation-maximization algorithm is devised to accurately learn the parameters of the distortion model from noisy training data. To resolve a model mismatch problem in the model-driven method, the data-driven method employs a deep neural network (DNN) for approximating a-posteriori probabilities for each received signal. This method uses the outputs of the model-driven method as noisy labels and therefore does not require extra training overhead. To avoid the overfitting problem caused by noisy labels, a robust DNN training algorithm is devised, which involves a warm-up period, sample selection, and loss correction. Simulation results demonstrate that the two proposed methods outperform existing solutions with the same overhead under various hardware impairment scenarios.

In this paper, a new communication-efficient federated learning (FL) framework is proposed, inspired by vector quantized compressed sensing. The basic strategy of the proposed framework is to compress the local model update at each device by applying dimensionality reduction followed by vector quantization. Subsequently, the global model update is reconstructed at a parameter server by applying a sparse signal recovery algorithm to the aggregation of the compressed local model updates. By harnessing the benefits of both dimensionality reduction and vector quantization, the proposed framework effectively reduces the communication overhead of local update transmissions. Both the design of the vector quantizer and the key parameters for the compression are optimized so as to minimize the reconstruction error of the global model update under the constraint of wireless link capacity. By considering the reconstruction error, the convergence rate of the proposed framework is also analyzed for a non-convex loss function. Simulation results on the MNIST and FEMNIST datasets demonstrate that the proposed framework can improve classification accuracy by more than 2.4% compared to state-of-the-art FL frameworks when the communication overhead of the local model update transmission is 0.1 bit per local model entry.

Data-aided channel estimation is a promising solution to improve channel estimation accuracy by exploiting data symbols as pilot signals for updating an initial channel estimate. In this paper, we propose a semi-data-aided channel estimator for multiple-input multiple-output communication systems. Our strategy is to leverage reinforcement learning (RL) for selecting reliable detected symbols, then update the channel estimate by utilizing only the selected symbols as additional pilot signals. Towards this end, we first define a Markov decision process (MDP) which sequentially decides whether to use each detected symbol as an additional pilot signal. We then develop an RL algorithm to find an effective policy of the MDP based on a Monte Carlo tree search approach. In this algorithm, we exploit the a-posteriori probability for approximating both the optimal future actions and the corresponding state transitions of the MDP and derive a closed-form expression for the optimal policy under the approximations. A key advantage of the proposed channel estimator is that it requires less computational complexity than conventional iterative data-aided channel estimators. Simulation results demonstrate that the proposed channel estimator effectively mitigates both channel estimation error and detection performance loss caused by insufficient pilot signals.

In this paper, we present a communication-efficient federated learning framework inspired by quantized compressed sensing. The presented framework consists of gradient compression for wireless devices and gradient reconstruction for a parameter server (PS). Our strategy for gradient compression is to sequentially perform block sparsification, dimensional reduction, and quantization. By leveraging both dimension reduction and quantization, our strategy can achieve a higher compression ratio than one-bit gradient compression. For accurate aggregation of local gradients from the compressed signals, we put forth an approximate minimum mean square error (MMSE) approach for gradient reconstruction using the expectation-maximization generalized-approximate-message-passing (EM-GAMP) algorithm. Assuming Bernoulli Gaussian-mixture prior, this algorithm iteratively updates the posterior mean and variance of local gradients from the compressed signals. We also present a low-complexity approach for the gradient reconstruction. In this approach, we use the Bussgang theorem to aggregate local gradients from the compressed signals, then compute an approximate MMSE estimate of the aggregated gradient using the EM-GAMP algorithm. We also provide a convergence rate analysis of the presented framework. Using the MNIST dataset, we demonstrate that the presented framework achieves almost identical performance with the case that performs no compression, while significantly reducing communication overhead for federated learning.

In this paper, we propose a learning-based detection method for multiple-input multiple-output (MIMO) communications with hardware impairments. In the proposed method, we approximate the conditional distribution of a received signal distorted by the hardware impairments, by generalizing a conventional additive distortion model. We then present a low-overhead strategy for generating training data to learn the approximate conditional distribution. Our strategy only requires traditional pilot signals for channel estimation, but leads to noisy training data containing incorrect labels. To accurately learn the approximate distribution from noisy training data, we develop an expectation maximization algorithm that estimates not only the parameters of the distribution but also transition probabilities from noisy labels to true labels. The maximum likelihood detection is finally performed based on the learned distribution. Using simulations, we demonstrate that the proposed detection method outperforms existing detection methods under both additive and realistic distortion models.

This paper presents a joint modulation and coding technique called quantized sparse vector code (Q-SVC) for multiple-input multiple-output (MIMO) inter-symbol-interference (ISI) channel with low-resolution analog-to-digital converters (ADCs). The key idea of Q-SVC is to encode sparse information bits over the space-time domain by a superposition of selected dictionary vectors. To decode Q-SVC from coarsely-quantized measurements in a computationally efficient manner, we present a greedy sparse signal detection algorithm called Bayesian multipath matching pursuit (BMMP). The simulation results demonstrate that the proposed encoding and decoding pair can outperform the existing coded-modulation techniques in terms of both the frame error rate (FER) and the computational complexity.

Deep learning-based symbol detector gains increasing attention due to the simple algorithm design than the traditional model-based algorithms such as Viterbi and BCJR. The supervised learning framework is often employed to train a model, where true symbols are necessary. There are two major limitations in the supervised approaches: a) a model needs to be retrained from scratch when new train symbols come to adapt to a new channel status, and b) the length of the training symbols needs to be longer than a certain threshold to make the model generalize well on unseen symbols. To overcome these challenges, we propose a meta-learning-based self-supervised symbol detector named MetaSSD. Our contribution is two-fold: a) meta-learning helps the model adapt to a new channel environment based on experience with various meta-training environments, and b) self-supervised learning helps the model to use relatively less supervision than the previously suggested learning-based detectors. In experiments, MetaSSD outperforms OFDM-MMSE with noisy channel information and shows comparable results with BCJR. Further ablation studies show the necessity of each component in our framework.

Communication efficiency is of importance for wireless federated learning systems. In this paper, we propose a communication-efficient strategy for federated learning over multiple-input multiple-output (MIMO) multiple access channels (MACs). The proposed strategy comprises two components. When sending a locally computed gradient, each device compresses a high dimensional local gradient to multiple lower-dimensional gradient vectors using block sparsification. When receiving a superposition of the compressed local gradients via a MIMO-MAC, a parameter server (PS) performs a joint MIMO detection and the sparse local-gradient recovery. Inspired by the turbo decoding principle, our joint detection-and-recovery algorithm accurately recovers the high-dimensional local gradients by iteratively exchanging their beliefs for MIMO detection and sparse local gradient recovery outputs. We then analyze the reconstruction error of the proposed algorithm and its impact on the convergence rate of federated learning. From simulations, our gradient compression and joint detection-and-recovery methods diminish the communication cost significantly while achieving identical classification accuracy for the case without any compression.

As computing paradigms shift toward mobile and ubiquitous interaction, there is an increasing demand for wearable interfaces supporting multifaceted input in smart living environments. In this regard, we introduce a system that identifies contact fingers using vibration as a modality of communication. We investigate the vibration characteristics of the communication channels involved and simulate the transmission of vibration sequences. In the simulation, we test and refine modulation and demodulation methods to design vibratory communication protocols that are robust to environmental noises and can detect multiple simultaneous contact fingers. As a result, we encode an on-off keying sequence with a unique carrier frequency to each finger and demodulate the sequences by applying cross-correlation. We verify the communication protocols in two environments, laboratory and cafe, where the resulting highest accuracy was 93 % and 90.5 %, respectively. Our system achieves over 91 % accuracy in identifying seven contact states from three fingers while wearing only two actuator rings with the aid of a touch screen. Our findings shed light on diversifying touch interactions on rigid surfaces by means of vibratory communication.

Federated learning is a privacy-preserving approach to train a global model at a central server by collaborating with wireless devices, each with its own local training data set. In this paper, we present a compressive sensing approach for federated learning over massive multiple-input multiple-output communication systems in which the central server equipped with a massive antenna array communicates with the wireless devices. One major challenge in system design is to reconstruct local gradient vectors accurately at the central server, which are computed-and-sent from the wireless devices. To overcome this challenge, we first establish a transmission strategy to construct sparse transmitted signals from the local gradient vectors at the devices. We then propose a compressive sensing algorithm enabling the server to iteratively find the linear minimum-mean-square-error (LMMSE) estimate of the transmitted signal by exploiting its sparsity. We also derive an analytical threshold for the residual error at each iteration, to design the stopping criterion of the proposed algorithm. We show that for a sparse transmitted signal, the proposed algorithm requires less computationally complexity than LMMSE. Simulation results demonstrate that the presented approach outperforms conventional linear beamforming approaches and reduces the performance gap between federated learning and centralized learning with perfect reconstruction.

This paper presents a data-aided channel estimator that reduces the channel estimation error of the conventional linear minimum-mean-squared-error (LMMSE) method for multiple-input multiple-output communication systems. The basic idea is to selectively exploit detected symbol vectors obtained from data detection as additional pilot signals. To optimize the selection of the detected symbol vectors, a Markov decision process (MDP) is defined which finds the best selection to minimize the mean-squared-error (MSE) of the channel estimate. Then a reinforcement learning algorithm is developed to solve this MDP in a computationally efficient manner. Simulation results demonstrate that the presented channel estimator significantly reduces the MSE of the channel estimate and therefore improves the block error rate of the system, compared to the conventional LMMSE method.

The use of one-bit analog-to-digital converters (ADCs) at a receiver is a power-efficient solution for future wireless systems operating with a large signal bandwidth and/or a massive number of receive radio frequency chains. This solution, however, induces high channel estimation error and therefore makes it difficult to perform the optimal data detection that requires perfect knowledge of likelihood functions at the receiver. In this paper, we propose a likelihood function learning method for multiple-input multiple-output (MIMO) systems with one-bit ADCs using a reinforcement learning approach. The key idea is to exploit input-output samples obtained from data detection, to compensate for the mismatch in the likelihood function. The underlying difficulty of this idea is a label uncertainty in the samples caused by a data detection error. To resolve this problem, we define a Markov decision process (MDP) to maximize the accuracy of the likelihood function learned from the samples. We then develop a reinforcement learning algorithm that efficiently finds the optimal policy by approximating the transition function and the optimal state of the MDP. Simulation results demonstrate that the proposed method provides significant performance gains for data detection methods that suffer from the mismatch in the likelihood function.

The use of one-bit analog-to-digital converters (ADCs) at a receiver is a power-efficient solution for future wireless systems. This paper presents a likelihood function learning method that enables robust maximum-a-posteriori-probability (MAP) detection for time-varying multiple-input multiple-output systems with one-bit ADCs. The key idea is to track the temporal variations of likelihood functions by exploiting input-output samples obtained from data detection, each containing the likelihood function information at each time slot. To deal with the uncertainty of this information caused by a data detection error, a Markov decision process (MDP) is defined, which maximizes the accuracy of the likelihood function learned from the samples. Then a reinforcement learning algorithm is developed to solve this MDP in a computationally efficient manner. Simulation results demonstrate that the use of the proposed method significantly improves the robustness of MAP detection to both the channel estimation error and channel variations over time.

A novel channel estimation framework is presented for orthogonal frequency division multiplexing (OFDM) system that operates with low-precision analog-to-digital converters (ADCs). The framework is based on concatenated minimum mean square error (MMSE) estimation, which consists of an inner and an outer MMSE estimation blocks. The outer MMSE estimation finds the compound signal, i.e., the unknown channel multiplied by a pilot signal, from the nonlinear distortion of the received signal by the quantization and its mean square error (MSE). Using the estimated compound signal and its MSE, the inner MMSE estimation estimates the desired signal, i.e., the unknown channel value, assuming the resulting estimation error of the outer MMSE block follows the Gaussian distribution. One major finding is that the proposed framework is analytically tractable for quantifying the effective quantization error, unlike the widely-used Bussgang-based approach. From simulations, it is shown that the proposed channel estimation framework provides a significant gain over conventional Bussgang-based methods using the approximated covariance matrix of the quantization error.

In this paper, we analyze the information-theoretical limits of a multiple-input single-output (MISO) channel with one-bit transceiver. In particular, we present a capacity expression in a closed form when perfect channel state information (CSI) is available at both a transmitter and a receiver. One major finding is that the capacity-achieving transmission strategy is to uniformly use four multi-dimensional signal points. The four signal points are chosen as a function of the channel and the signal-to-noise ratio (SNR) from the channel input set constructed by a spatial lattice modulation (SLM) method. From our analysis and simulation results, we also demonstrate that the capacity loss caused by the use of one-bit DACs is sufficiently small throughout the entire SNR regime even with a few-bit CSIT feedback that suffices to achieve the capacity.

A one-bit wireless transceiver is a promising communication architecture that not only can facilitate the design of mmWave communication systems but also can extremely diminish power consumption. The non-linear distortion effects by one-bit quantization at the transceiver, however, change the fundamental limits of communication rates. In this paper, the capacity of a multiple-input single-output (MISO) fading channel with one-bit transceiver is characterized in a closed form when perfect channel state information (CSI) is available at both a transmitter and a receiver. One major finding is that the capacity-achieving transmission strategy is to uniformly use four multi-dimensional constellation points. The four multi-dimensional constellation points are optimally chosen as a function of the channel and the signal-to-noise ratio (SNR) among the channel input set constructed by the spatial lattice modulation method. As a byproduct, it is shown that a few-bit CSI feedback suffices to achieve the capacity. For the case when CSI is not perfectly known to the receiver, practical channel training and CSI feedback methods are presented, which effectively exploit the derived capacity-achieving transmission strategy.

In this paper, we propose computationally efficient yet near-optimal soft-output detection methods for coded millimeter-wave (mmWave) multiple-input-multiple-output (MIMO) systems with low-precision analog-to-digital converters (ADCs). The underlying idea of the proposed methods is to construct an extremely sparse inter-symbol-interference channel model by jointly exploiting the delay-domain sparsity in mmWave channels and a high quantization noise caused by low-precision ADCs. Then, we harness this sparse channel model to create a trellis diagram with a reduced number of states and a factor graph with very sparse edge connections, which are used for the computationally efficient soft-output detection methods. Using the reduced trellis diagram, we present a soft-output detection method that computes the log-likelihood ratios (LLRs) of coded bits by optimally combining the quantized received signals obtained from multiple receive antennas using a forward-and-backward algorithm. To reduce the computational complexity further, we also present a low-complexity detection method using the sparse factor graph to compute the LLRs in an iterative fashion based on a belief propagation algorithm. Simulations results demonstrate that the proposed soft-output detection methods provide significant frame-error-rates gains compared with the existing frequency-domain equalization techniques in a coded mmWave MIMO system using one- or two-bit ADCs.

This paper presents a low complexity maximum likelihood detection (MLD) algorithm called one-bit-sphere-decoding for an uplink massive multiple-input multiple-output (MIMO) system with one-bit analog-to-digital converters (ADCs). The idea of the proposed algorithm is to estimate the transmitted symbol vector sent by uplink users (a codeword vector) by searching over a sphere, which contains a collection of codeword vectors close to the received signal vector at the base station in terms of a weighted Hamming distance. To reduce the computational complexity for the construction of the sphere, the proposed algorithm divides the received signal vector into multiple sub-vectors each with reduced dimension. Then, it generates multiple spheres in parallel, where each sphere is centered at the sub-vector and contains a list of sub-codeword vectors. Simulation results demonstrate that the proposed algorithm achieves near-MLD performance, while reducing the computational complexity compared to the existing MLD method.

This paper considers a single-input multiple-output (SIMO) wide-band communication system that uses low-precision analog-to-digital converters (ADCs) for quantizing the received signal. The key contribution of this paper is to propose an optimal maximum likelihood sequence detector (MLSD), which is referred to as a quantized Viterbi algorithm, extending to the quantized output case of the conventional Viterbi algorithm. In addition, a variant of the quantized Viterbi algorithm is proposed, which is robust to the effect of channel estimation errors. One major observation is that it is possible to achieve low symbol- error-rates in the inter-symbol interference channel even with one-bit ADCs, provided that the number of receive antennas is sufficiently large. Simulations demonstrate that the proposed algorithm is more robust to the channel estimation error than the conventional Viterbi algorithm, which simply treats the channel estimation error as an additional noise.

This paper considers an uplink massive multiple-input multiple-output (MIMO) system with low-precision analog-to-digital converters (ADCs). In this system, a robust maximum-likelihood detection (MLD) method is proposed under imperfect channel state information at a receiver (CSIR). Inspired by reinforcement learning theory, the idea of the proposed method is to enhance the accuracy of a likelihood function estimated at the receiver, by exploiting associations between correctly detected data symbols and quantized received signals. The proposed method utilizes these associations as training examples to learn the true likelihood function of the system, which provides a more accurate estimate for the likelihood function that can overcome the effect of imperfect CSIR. Simulation results show that the proposed MLD considerably outperforms the conventional MLD in terms of the detection performance under imperfect CSIR.

This paper considers a K-cell multiple access channel with inter-symbol interference. The primary finding of this paper is that, without instantaneous channel state information at the transmitters, interference-free degrees-of-freedom (DoF) per cell is achievable, provided that the delay spread of the desired links is significantly longer than that of the interfering links when the number of user per cell is sufficiently large. This achievability is shown by a blind interference management method that exploits the relativity in delay spreads between desired and interfering links. In this method, all inter-cell-interference signals are aligned-and-cancelled by using discrete-Fourier-transform-based precoding and combining, both depend only on the lengths of channel-impulse-response. In addition to the DoF analysis, the achievable rate of the proposed method is characterized in a closed-form expression. Some illustrative examples are presented to show an additional sum-DoF gain obtained by exploiting propagation delay in the interfering links or the heterogeneity of the channel coherence time between the desired and interfering links.

This paper presents a low-complexity near-maximum-likelihood-detection (near-MLD) algorithm called one-bit sphere decoding for an uplink massive multiple-input multiple-output system with one-bit analog-to-digital converters. The idea of the proposed algorithm is to estimate the transmitted symbol vector sent by uplink users (a codeword vector) by searching over a sphere, which contains a collection of codeword vectors close to the received signal vector at the base station in terms of a weighted Hamming distance. To reduce the computational complexity for the construction of the sphere, the proposed algorithm divides the received signal vector into multiple subvectors each with a reduced dimension. Then, it generates multiple spheres in parallel, where each sphere is centered at the subvector and contains a list of subcodeword vectors. The detection performance of the proposed algorithm is also analyzed by characterizing the probability that the proposed algorithm performs worse than the MLD. The analysis shows how the dimension of each sphere and the size of the subcodeword list are related to the performance-complexity tradeoff achieved by the proposed algorithm. Simulation results demonstrate that the proposed algorithm achieves near-MLD performance, while reducing the computational complexity compared to the existing MLD method.

This paper considers a multiple-input multiple-output (MIMO) system with low-resolution analog-to-digital converters (ADCs). In this system, we present a new MIMO detection approach using coding theory. The principal idea of the proposed approach is to transform a non-linear MIMO channel to a linear MIMO channel by leveraging both a p-level quantizer and a lattice code where p ≥ 2. After transforming to the linear MIMO channel with the sets of finite input and output elements, efficient MIMO detection methods are proposed to attain both diversity and multiplexing gains by using algebraic coding theory. In particular, using the proposed methods, the analytical characterizations of achievable rates are derived for different MIMO configurations. One major observation is that the proposed approach is particularly useful for a large MIMO system with the ADCs that use a few bits.

This paper considers a multiple-input-multiple-output (MIMO) system with low-resolution analog-to-digital converters (ADCs). In this system, we propose a novel detection framework that performs data symbol detection without explicitly knowing channel state information at a receiver. The underlying idea of the proposed framework is to exploit supervised learning. Specifically, during channel training, the proposed approach sends a sequence of data symbols as pilots so that the receiver learns a nonlinear function that is determined by both a channel matrix and a quantization function of the ADCs. During data transmission, the receiver uses the learned nonlinear function to detect which data symbols were transmitted. In this context, we propose two blind detection methods to determine the nonlinear function from the training-data set. We also provide an analytical expression for the symbol-vector-error probability of the MIMO systems with one-bit ADCs when employing the proposed framework. Simulations demonstrate the performance improvement of the proposed framework compared to existing detection techniques.

This paper considers a K-cell multiple access channel with inter-symbol interference (ISI). The primary finding of this paper is that, without instantaneous channel state information at a transmitter, the interference-free sum degrees of freedom of K is asymptotically achievable when the number of users per cell is sufficiently large, and also when the number of channel-impulse-response taps of desired links is greater than that of interfering links. This achievability is shown by a blind interference management method that exploits the relativity in delay spreads between desired and interfering links.

We consider the block diagonalization (BD) and user selection based on limited feedback in multiple antenna broadcast channels. With limited feedback, due to the imperfect channel state information at the transmitter (CSIT), BD cannot completely eliminate multiuser interference, and the throughput is correspondingly lower than that achieved with perfect CSIT. Nevertheless, the achievable multiuser diversity gain can be the same, such that limited-feedback-based BD can achieve an optimal throughput growth as the number of users increases. To show this, we first propose a channel quality indicator (CQI) for user selection. The CQI is designed to accurately estimate an achievable rate of each user and is given by an expected rate, where the expectation is solely taken over precoding matrices which cannot be known at the feedback stage. With the proper CQI, user selection can benefit from a large number of users in the system. As a result, we show that the BD can achieve an asymptotically optimal growth in throughput with the proposed CQI, based solely on a finite-rate feedback of channel information.

Massive multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) is a promising technology for next-generation wireless communications. However, when channel state information (CSI) at the transmitter is obtained using channel feedback, the benefits of this system are severely limited by the tradeoff between downlink capacity and feedback overhead. To solve this problem, we propose a time-domain differential feedback scheme for massive multiple-input single-output (MISO) OFDM systems. The proposed scheme exploits channel correlations in time, frequency, and space domains simultaneously by considering differential channel impulse response (CIR). To simplify the codebook design, and to reduce codeword-search complexity, we partition and then quantize the differential CIR using a number of subcodebooks. Because the total feedback bits are shared by the subcodebooks, we further optimize the bit allocation for them to minimize the total quantization error. For this, we analyze the quantization error of the proposed scheme and then use the analysis results for the bit-allocation optimization. In simulations, the proposed scheme efficiently exploits all correlations and achieves significant spectral-efficiency gain compared to conventional feedback schemes.

To maintain a specific degree of multiplexing gain with limited feedback in multiple-input/multiple-output broadcast channels, the number of feedback bits has been increased linearly with the signal-to-noise ratio (SNR) measured in decibel, and conditions for the slope of this increase have been derived in previous studies. However, previous studies mostly focused on the chordal distance (ChD) for channel quantization, although it is not an optimally designed distance measure. Thus, the possibility exists that the same degree of multiplexing gain can be obtained by using fewer feedback bits than the existing method requires. In this paper, we propose an optimal distance measure that can maximize the multiplexing gain achieved by limited-feedback-based block diagonalization over broadcast channels. Then, we provide a sufficient condition for the number of feedback bits to achieve a specific degree of multiplexing gain with the proposed method. The sufficient number of feedback bits is given by a linear function of the SNR (decibel) as in previous studies, but the slope of the linear increase can be much less than that obtained in previous studies. As a consequence, the proposed method achieves higher multiplexing gain and corresponding throughput than the existing methods with the same number of feedback bits.

We consider limited-feedback-based block diagonalization (BD) and user selection for multiple antenna broadcast channels. With limited feedback, the conventional channel norm can not be a good estimate for channel quality of each user, because multiuser interference is not completely eliminated by using BD under limited channel direction information. Therefore, we need an appropriate channel quality indicator (CQI) to increase the diversity gain achieved by multiuser scheduling. To this end, we consider a determinant-based instantaneous channel capacity and propose a new CQI by taking an expectation over precoding matrices that can not be known at the feedback stage. Simulation results show that the sum rate with the proposed CQI is much higher than the sum rate with conventional CQIs.

This letter proposes a distributed beamforming scheme based on block diagonalization (BD) for multicell multiuser multiple-input multiple-output (MU-MIMO) downlink systems. Although conventional BD can be directly extended to these systems in a distributed manner, it suffers from sum-rate degradation due to strict zero-forcing (ZF) constraints. To overcome this problem, we introduce a sum-rate maximization problem for BD, to find the optimal selection of ZF constraints. Then we propose a search algorithm to solve the problem in a distributed and heuristic manner. Simulation results show that the proposed scheme effectively finds a near-optimal solution and significantly improves simple extended BD such that it can provide higher sum rate than the conventional schemes.