Reconfigurable intelligent surface-assisted integrated sensing and communication (RIS-ISAC) presents a promising system architecture to leverage the wide bandwidth available at millimeter-wave (mmWave) frequencies, while mitigating severe signal propagation losses and reducing infrastructure costs. To enhance ISAC functionalities in the future air-ground integrated network applications, RIS deployment must be carefully designed and evaluated, which forms the core motivation of this paper. To ensure practical relevance, a multi-RIS-ISAC system is established, with its signal model at mmWave frequencies demonstrated using ray-launching that calibrated to real-world environments. On this basis, an energy-efficiencydriven optimization problem is formulated to minimize the multi-RIS size-to-coverage sum ratio, comprehensively considering real-world RIS deployment constraints, positions, orientations, as well as ISAC beamforming strategies at both the base station and the RISs. To solve the resulting non-convex mixed-integer problem, a reformulation based on equivalent gain scaling method is introduced. A two-step iterative algorithm is then proposed, in which the deployment varaibles are determined under fixed RIS positions in the first step, and the RIS position set is updated in the second step to progressively approach the optimum solution. Simulation results based on realistic parameter benchmarks present that the optimized RISs deployment significantly enhances communication coverage and sensing accuracy with the minimum RIS sizes, outperforming existing approaches.

This paper investigates the Integrated Sensing and Communication (ISAC) empowered predictive beamforming design for Uncrewed Aerial Vehicle (UAV) assisted networks, where the ground Base Station (BS) explores the echoes of communication signal for real-time UAV tracking. To ensure practicality and generalizability, we establish a random UAV mobility model incorporating position fluctuations and attitude variations during flight, which poses challenges to accurate UAV tracking. To address this, we propose Historical Echoes-based Convolutional Time Attention Network (HECTA-Net), a novel deep learning framework for end-to-end beamforming prediction. The proposed HECTA-Net integrates Convolutional Neural Network (CNN) and Temporal Convolutional Network (TCN) to jointly extract the spatio-temporal features from historical ISAC echoes across multiple time slots, where the attention mechanism is also embedded to dynamically identify and weight the critical time slots. Thus it enables accurate prediction on the transmit and receive beamforming matrices. Extensive simulations are conducted to validate the robustness and performance of proposed scheme. Results demonstrate that the proposed HECTA-Net outperforms the other state-of-art baselines, with its performance closely approaching the theoretical upper bound even in the high randomized UAV motion patterns.

Cooperative Multi-Agent Reinforcement Learning (MARL) has become a critical tool for addressing complex real-world problems. However, off-policy MARL methods, which rely on joint Q-functions, face significant scalability challenges due to the exponentially growing joint action space. In this work, we highlight a critical yet often overlooked issue: erroneous Q-target estimation, primarily caused by extrapolation error. Our analysis reveals that this error becomes increasingly severe as the number of agents grows, leading to unique challenges in MARL due to its expansive joint action space and the decentralized execution paradigm. To address these challenges, we propose a suite of techniques tailored for off-policy MARL, including annealed multi-step bootstrapping, averaged Q-targets, and restricted action representation. Experimental results demonstrate that these methods effectively mitigate erroneous estimations, yielding substantial performance improvements in challenging benchmarks such as SMAC, SMACv2, and Google Research Football.

This paper investigates a dual-hop mixed radio frequency (RF)-underwater wireless optical communication (UWOC) system, with an unmanned aerial vehicle (UAV) serving as the information source. Data from the UAV is assumed to be transmitted via an RF channel, modeled with generalized K distributed fading statistics and atmospheric path loss, to a relay mounted on a ship at sea. The relay decodes the received RF signal and re-transmits it to the destination using a decode-and-forward (DF) protocol through the UWOC link, which is mod-eled by generalized gamma distribution (GGD) turbulence fading and zero-boresight pointing errors in the presence of underwater path loss. Based on this, the average outage probability and its corresponding asymptotic expression for the considered hybrid dual-hop system under high signal-to-noise ratios are derived. Moreover, an analysis of the optimal UAV hovering altitude is carried out based on the derived asymptotic outage probability expressions. Numerical simulations are presented to support the performance analysis of the proposed RF-UWOC system and to demonstrate the feasibility of achieving the optimal UAV hovering height.

Immunohistochemistry (IHC) examination is essential to determine the tumour subtypes, provide key prognostic factors, and develop personalized treatment plans for breast cancer. However, compared to Hematoxylin and Eosin (H&E) staining, the preparation process of IHC staining is more complex and expensive, which limits its application in clinical practice. Therefore, H&E to IHC stain transfer may be an ideal solution to obtain IHC staining. To ensure high transferring quality, it would be much more desirable to exploit the supervised information between adjacent layer images of the same tissue, which are stained by H&E and IHC stainings, respectively. Nevertheless, adjacent layer tissue images are not accurately paired at the pixel level, which poses significant challenges to network training. To address this problem, we propose a generative adversarial network for breast IHC virtual staining, which contains an optimal transport-based supervised information mining (OT-SIM) mechanism and a pathological correlation-based supervised information mining (PC-SIM) mechanism. The OT-SIM guides the network in mining matching consistency between H&E images and the adjacent layer's real IHC images, providing as much instance-level supervision as possible. The PC-SIM further explores the consistency between the correlation among virtual IHC images and the correlation among real IHC images, providing batch-level supervision. Extensive experiments show the superiority of our method on two breast tissue benchmark datasets compared to the state-of-the-art methods both quantitatively and qualitatively. The code is available at https://github.com/xianchaoguan/SIM-GAN.

Effective Adaptive Bitrate (ABR) algorithm or policy is of paramount importance for Real-Time Video Communication (RTVC) amid this pandemic to pursue uncompromised quality of experience (QoE). Existing ABR methods mainly separate the network bandwidth estimation and video encoder control, and fine-tune video bitrate towards estimated bandwidth, assuming the maximization of bandwidth utilization yields the optimal QoE. However, the QoE of an RTVC system is jointly determined by the quality of the compressed video, fluency of video playback, and interaction delay. Solely maximizing the bandwidth utilization without comprehensively considering compound impacts incurred by both transport and video application layers, does not assure a satisfactory QoE. The decoupling of the transport and application layer further exacerbates the user experience due to codec-transport incoordination. This work, therefore, proposes the Palette, a reinforcement learning-based ABR scheme that unifies the processing of transport and video application layers to directly maximize the QoE formulated as the weighted function of video quality, stalling rate, and delay. To this aim, a cross-layer optimization is proposed to derive the fine-grained compression factor of the upcoming frame(s) using cross-layer observations like network conditions, video encoding parameters, and video content complexity. As a result, Palette manages to resolve the codec-transport incoordination and to best catch up with the network fluctuation. Compared with state-of-the-art schemes in real-world tests, Palette not only reduces 3.1%-46.3% of the stalling rate, 20.2%-50.8% of the delay but also improves 0.2%-7.2% of the video quality with comparable bandwidth consumption, under a variety of application scenarios.

In this article, joint communication and sensing (JCAS) is combined with reconfigurable intelligent surfaces (RISs), which validates a novel RIS-based JCAS (RIS-JCAS) system. The proposed system performs monostatic sensing to detect a potential user, after which communication with the user is established. The corresponding RIS-cascaded channel is formulated, based on which an algorithm is created, to handle radar target detection and communication channel estimation while multiple RISs operate simultaneously. A joint beam training process by utilizing the identical beamforming pattern on multiple RISs is created, which increases the time efficiency significantly. The detection accuracy is subsequently further improved through a novel fine-tuning method. To practically validate the aforementioned algorithm, a RIS-JCAS system is demonstrated using a mmWave testbed with a bandwidth of 1 GHz centralized at 26.2 GHz. Besides combining the widely adopted orthogonal frequency-division multiplexing (OFDM) scheme with high-directional RIS beams, the system also allows the use of variant RIS flat-top beam shaping combined with orthogonal chirp-division multiplexing radar (OCDM) waveforms. This idea keeps the sensitivity of the RIS-JCAS system while broader beams with wider coverage but lower gain are utilized. Overall, accurate 4-dimensional sensing results are derived, which strongly assists the communication channel estimation and realizes the core benefits of the proposed RIS-JCAS system.

Contemporary real-time video communication systems, such as WebRTC, use an adaptive bitrate (ABR) algorithm to assure high-quality and low-delay services, e.g., promptly adjusting video bitrate according to the instantaneous network bandwidth. However, target bitrate decisions in the network and bitrate control in the codec are typically incoordinated and simply ignoring the effect of inappropriate resolution and frame rate settings also leads to compromised results in bitrate control, thus devastatingly deteriorating the quality of experience (QoE). To tackle these challenges, Mamba, an end-to-end multi-dimensional ABR algorithm is proposed, which utilizes multi-agent reinforcement learning (MARL) to maximize the user's QoE by adaptively and collaboratively adjusting encoding factors including the quantization parameters (QP), resolution, and frame rate based on observed states such as network conditions and video complexity information in a video conferencing system. We also introduce curriculum learning to improve the training efficiency of MARL. Both the in-lab and real-world evaluation results demonstrate the remarkable efficacy of Mamba.

In the realm of short video streaming, popular adaptive bitrate (ABR) algorithms developed for classical long video applications suffer from catastrophic failures because they are tuned to solely adapt bitrates. Instead, short video adaptive bitrate (SABR) algorithms have to properly determine which video at which bitrate level together for content prefetching, without sacrificing the users' quality of experience (QoE) and yielding noticeable bandwidth wastage jointly. Unfortunately, existing SABR methods are inevitably entangled with slow convergence and poor generalization. Thus, in this paper, we propose Incendio, a novel SABR framework that applies Multi-Agent Reinforcement Learning (MARL) with Expert Guidance to separate the decision of video ID and video bitrate in respective buffer management and bitrate adaptation agents to maximize the system-level utilized score modeled as a compound function of QoE and bandwidth wastage metrics. To train Incendio, it is first initialized by imitating the hand-crafted expert rules and then fine-tuned through the use of MARL. Results from extensive experiments indicate that Incendio outperforms the current state-of-the-art SABR algorithm with a 53.2% improvement measured by the utility score while maintaining low training complexity and inference time.

Multi-agent policy gradient methods in centralized training with decentralized execution recently witnessed many progresses. During centralized training, multi-agent credit assignment is crucial, which can substantially promote learning performance. However, explicit multi-agent credit assignment in multi-agent policy gradient methods still receives less attention. In this paper, we investigate multi-agent credit assignment induced by reward shaping and provide a theoretical understanding in terms of its credit assignment and policy bias. Based on this, we propose an exponentially weighted advantage estimator, which is analogous to GAE, to enable multi-agent credit assignment while allowing the tradeoff with policy bias. Empirical results show that our approach can successfully perform effective multi-agent credit assignment, and thus substantially outperforms other advantage estimators.

Value decomposition recently injects vigorous vitality into multi-agent actor-critic methods. However, existing decomposed actor-critic methods cannot guarantee the convergence of global optimum. In this paper, we present a novel multi-agent actor-critic method, FOP, which can factorize the optimal joint policy induced by maximum-entropy multi-agent reinforcement learning (MARL) into individual policies. Theoretically, we prove that factorized individual policies of FOP converge to the global optimum. Empirically, in the well-known matrix game and differential game, we verify that FOP can converge to the global optimum for both discrete and continuous action spaces. We also evaluate FOP on a set of StarCraft II micromanagement tasks, and demonstrate that FOP substantially outperforms state-of-the-art decomposed value-based and actor-critic methods.

In this paper, the circle formation control problem is addressed for a group of cooperative underactuated fish-like robots involving unknown nonlinear dynamics and disturbances. Based on the reinforcement learning and cognitive consistency theory, we propose a decentralized controller without the knowledge of the dynamics of the fish-like robots. The proposed controller can be transferred from simulation to reality. It is only trained in our established simulation environment, and the trained controller can be deployed to real robots without any manual tuning. Simulation results confirm that the proposed model-free robust formation control method is scalable with respect to the group size of the robots and outperforms other representative RL algorithms. Several experiments in the real world verify the effectiveness of our RL-based approach for circle formation control.

In this paper, robust exponential synchronization of memristor-based neural networks (MNNs) with nonidentical characteristics is investigated. Coefficient mismatch, time-varying delay mismatch, and activation function mismatch are considered between the drive and the response MNNs. Pinning control strategy is developed to realize robust exponential synchronization and the stability criteria is established by using the Lyapunov function method and differential inclusion theory. Furthermore, the stable region of controller parameters is computed to guarantee that the synchronization errors enter a predetermined error bound within given settling time. Finally, the effectiveness of the proposed methods is verified by the numerical simulations. The methods presented in this paper offer novel schemes for robust exponential synchronization of nonidentical MNNs.

In this paper, the drive-response synchronization of the delayed memristive neural networks (MNNs) with unknown parameters is studied. With the realization of practical memristors, more and more researchers start to investigate MNNs, and their synchronization problem has became a hot topic. However, the majority of the existing works are based on the strict condition that the weights of MNNs are known and determined. When the parameters are unknown, the obtained results may be inapplicable. Thus, it is worthwhile to investigate the synchronization problem of the delayed MNNs with unknown parameters. Due to the parameter uncertainties of MNNs, a novel response system and an adaptive control method are proposed under different assumptions. The update laws for weights in the response system and the gains of adaptive controllers are developed to synchronize the proposed response system with the delayed MNNs. Furthermore, the proposed methods can be applied to various cases and the corresponding stability theories are established. Finally, the numerical simulations are conducted to verify the effectiveness of the developed methods.

Massive multiple-input multiple-output (MIMO) systems operating at millimeter-wave (mmWave) frequencies promise to satisfy the demand for higher data rates in mobile communication networks. A practical challenge that arises is the calibration in amplitude and phase of these massive MIMO systems, as the antenna elements are too densely packed to provide a separate calibration branch for measuring them independently. Over-the-air (OTA) calibration methods are viable solutions to this problem. In contrast to previous works, the here presented OTA calibration method is investigated and optimized for subarray-based hybrid beamforming (SBHB) systems. SBHB systems represent an efficient architectural solution to realize massive MIMO systems. Moreover, based on OTA scattering parameter measurements, the ambiguities of the phase shifters are exploited and two criteria to optimize the beam pattern are formulated. Finally, the optimization criteria are examined in measurements utilizing a novel SBHB receiver system operating at 27.8 GHz.

In this paper, the asymptotic synchronization for drive-response memristive neural networks(MNNs) with nonidentical parameters is investigated. Parameter inconformity is ubiquitous between drive and response systems due to environmental or internal influence. However, the majority of previous results were based on the well-matched MNNs. Thus, it is meaningful to study the synchronization problem of MNNs with nonidentical parameters. First, coefficient mismatches are dealt within the framework of set-valued maps and differential inclusions. Furthermore, in order to reduce the control cost, a pinning control strategy is adopted to drive two nonidentical MNNs to achieve asymptotic synchronization. And the sufficient stability conditions are given based on Lyapunov functional method. Finally, the effectiveness of proposed pinning controller is verified by a numerical example.

For guaranteeing quasi-error free delivery of realtime multicast services over wireless networks, an efficient greedy algorithm is proposed for optimizing the parameters of a HARQ scheme with rateless codes under strict delay and bandwidth constraints. We take systematic Raptor codes as an example for analyzing the optimum performance of the HARQ scheme. The results show that the optimum performance can be obtained by combining the optimum HARQ and FEC. Additionally, the simulation results show that the proposed optimization framework can be used for evaluating the tight lower bound performance of the HARQ, which indicates that it is suitable for designing optimum HARQ scheme with guaranteeing the target quasi-error free delivery requirements very well.

Convolutional codes are important channel codes to combat fading and noise in 3GPP 3.84/1.28 Mcps TDD systems. However, the design of the convolutional codes used in current specifications just obtain the best performance for BPSK modulation and the AWGN propagation channel. In 3GPP 3.84/1.28 Mcps TDD systems, QPSK modulation is adopted. Moreover, multipath fading channels are often encountered in practical communication environments. Therefore, convolutional codes used in the specifications cannot always achieve the best performance in practical 3GPP 3.84/1.28 Mcps TDD systems. We propose an improved convolutional encoder for the 3GPP 3.84/1.28 Mcps TDD downlink system by analyzing the integration effects of QPSK modulation and multipath fading channels on the code design. Performance analysis and simulation show that better system performance can be achieved by using the proposed encoder.

In this paper, the effect of out-of-synchronization on channel estimation and then joint detection in downlink TD-SCDMA has been analyzed from both theory and simulations when different midambles are assigned to different user equipments (UE). The analysis shows that the maximum likelihood (ML) channel estimation using the specially designed midambles implemented with fast Fourier transform (FFT) will result in a circular shift of the actual channel impulse response (CIR) when downlink channel is in out-of-synchronization, and based on this, the shift deviation of downlink synchronization point along different direction of level axis (left or right) during some periods will cause quite different impact on joint detection.

The Gauss-Seidel iterative algorithm for linear asynchronous decorrelation or minimum mean square error (MMSE) multiuser detector can be viewed as a kind of linear soft decision feedback multiuser detection. Based on this idea, a linear decorrelating or MMSE detector can be implemented by using a much simpler pipeline structure compared with the conventional scheme of computing the inverse of the corresponding correlation matrix. Through this pipeline structure, a lot of computations can be reduced.

Two bit estimators, the weighted average bit estimator and shrinkage bit estimator, used in DS-CDMA partial parallel interference cancellation (PPIC) proposed by Divsalar et al. (see IEEE Trans. on Comm., vol.46, no.2, 1998) , are compared. It is shown that the two bit estimators improve the performances by decreasing the power of the residual interferences, remaining in the decision statistic of each stage after interference cancellation, but in different capabilities. We also justify the assumption that the residual interference is Gaussian, under which the two bit estimators are derived by Divsalar et al. Furthermore, theoretical optimal weights of the above two estimators minimizing the BER are derived.

A reduced complexity multistage detector is introduced for DS-CDMA systems, which is derived from the soft sigmoid decision PIC (parallel interference cancellation) detector. From the derivation, we can see that this reduced complexity detector has a clear partial interference cancellation explanation about the soft sigmoid PIC detector. Derivation and computer simulations show that the proposed detector can reach the performance of the soft sigmoid PIC detector easily without the variance estimation of the residual noise at each stage or the sigmoid decision function which is not easily implemented in practice.