Task-oriented semantic communication, leveraging learning-based joint source-channel coding (JSCC), has emerged as a key paradigm for low-latency, high-precision edge-assisted Internet of Things systems. However, the direct mapping of source data to continuous channel symbols in JSCC poses a great challenge in compatibility with existing digital systems. To address this, we propose a digital semantic communication scheme, i.e., an AdaptiveSemanticCompression with jointResourceAllocation andModulation (Adaptive-SCRAM) optimization scheme for multi-user image classification. This scheme, with the semantics quantized by a compressed codebook, enables the discrete semantic transmission with adaptive modulation, while achieving high accuracy and low latency with transmission resources optimized in multi-user classification task. Specifically, we first design a vector quantized-variational autoencoder-based digital JSCC framework with regional quantization, by jointly maximizing the semantic entropy and minimizing the codebook training loss with various SNRs and modulation orders considered in Rayleigh fading. Then based on the well trained end-to-end architecture, we mathematically fit the classification accuracy with respect to the effects of both compressed codebook size and received SNR under different modulation orders, providing an effective premise for the task performance optimization. Finally, we consider to maximize the overall multi-user classification accuracy under the transmission delay constraint, by optimizing the compression, modulation, power and bandwidth allocation for each user. To address the highly non-convex issue, we develop a dual-layer optimization algorithm. The outer-layer problem, which optimizes the compressed codebook size and modulation order, is solved by a cross-entropy-based learning algorithm. While for the inner-layer problem, a successive convex approximation method is used to optimize the power and bandwidth allocation. Simulation results show that our JSCC framework significantly reduces the semantic codebook size without compromising the classification accuracy, which is applicable to practical digital transmission systems. More importantly, compared to most existing comparable optimization schemes for image classification, our Adaptive-SCRAM optimization scheme with adaptive compression, modulation, and resource allocation can achieve much higher classification accuracy for multi-user tasks, while guaranteeing the transmission efficiency.

Artificial noise (AN) has been recognized as an effective physical-layer security scheme impairing the eavesdropper (Eve). Recently, artificial noise elimination (ANE) has emerged as a promising strategy to mitigate the impact of AN at Eves. However, conventional ANE schemes rely on prior knowledge, such as legitimate channel state information (CSI) or classification information, which may limit their practical applicability. To address these practical challenges, we propose an ANE scheme beyond prior knowledge (BPK) by leveraging machine learning algorithms. Firstly, a coarse projection is applied to partially eliminate the impact of AN using maximum likelihood estimation on the equivalent AN matrix. Secondly, a density clustering algorithm is introduced to obtain classification information based on the coarsely-projected observed vectors. Thirdly, a generalized principal component analysis (PCA)-based ANE algorithm is developed to effectively mitigate the residual AN using the obtained classification information. Furthermore, the artificial-noise-to-signal ratio (ANSR) and computational complexity are analyzed for performance revaluation, and a redefinition of several AN design principles is provided for scenarios involving a powerful Eve equipped with the BPK-ANE scheme by deriving the validity boundary. Finally, numerical results reveal key insights into four principles of AN: 1) Allocating less power to AN; 2) Reducing the randomness of AN; 3) Increasing the number of transmit antennas; and 4) Increasing the modulation order.

Cognitive radio networks (CRNs) reduce interference and enhance the reliability and security of secondary users’ (SUs’) communications by sensing the spectrum occupancy of primary users (PUs). However, achieving accurate spectrum sensing remains challenging due to the wide frequency bands and the dynamic nature of the spectral environment. In this paper, we thus propose a cooperative spectrum sensing (CSS) approach to enhance the sensing accuracy. In particular, a fusion center is deployed to aggregate the local observations from multiple SUs, and then perform further spectrum sensing through combining the multi-agent proximal policy optimization (MAPPO) with a trust-aware weighted fusion (TWF) mechanism. To be specific, TWF dynamically adjusts the contribution of each SU’s local observations based on its reliability. At the same time, MAPPO uses centralized training to optimize the local decision-making based on local observations, enabling distributed cooperative sensing. Finally, numerical results demonstrate that the proposed algorithm, which integrates cooperative sensing with the TWF mechanism, outperforms independent learning and non-intelligent approaches, achieving a spectrum sensing accuracy of around 95%.

The increasing adoption of mobile edge computing (MEC) and non-orthogonal multiple access (NOMA) in vehicular networks is to reduce the execution delay of computation-intensive tasks and improve the spectrum efficiency. In this paper, we introduce a NOMA-assisted vehicular edge computing network, where vehicular users (VUs) form NOMA groups to share the radio resource with cellular users (CUs) for offloading their computing tasks to the MEC server in a highway scenario. Under the VU's execution delay constraints, we jointly optimize the computation resource allocation of the MEC server, the data transmission time, and the offloading decision to minimize the long-term energy consumption of the system. However, the long-term stochastic optimization problem is intricate due to the VU's mobility and the time-varying of the wireless channel. We thus propose a Lyapunov optimization based algorithm to transform the original problem into a single time slot optimization problem. Specifically, we decouple this problem into the computation resource allocation sub-problem solved at the MEC server and the offloading decision sub-problem solved at each VU. The optimal computation resource allocation is obtained by solving the knapsack problem, while the cross-entropy based algorithm is used to determine the optimal offloading decision for VUs. After that, our numerical simulations are conducted to demonstrate the effectiveness of the proposed algorithms.

Phase noise is one of the fundamental impairments in radar, communications, and even the integration of sensing and communications, which is necessary to be suppressed to guarantee the system performance for high-order modulations. In order to obtain precise phase estimation or effectively track phase noise, many estimation algorithms rooted in digital signal processing operate under the premise that the variance of the phase noise is known. However, in practical applications, the receiver side can hardly get the premise knowledge of the phase noise variance. Thus, accurate estimation of the phase noise variance is significantly important for not only carrier recovery, but also performance monitoring. This paper proposes a maximum likelihood (ML)-based Wiener phase noise variance estimation scheme, based on the amplitude and phase-form of the noisy received signal model for$M$-ary phase-shift keying ($M$PSK) modulated systems. Specifically, by making full use of the explicit statistics of the received phase after raising to the Mth power, the closed-form expressions for ML estimation of the incremental phase noise and the Wiener phase noise variance are derived. The estimated mean square error is both theoretically and numerically analyzed to validate the unbiased ML estimator. Numerical results are given to verify the estimation accuracy in terms of varing signal-to-noise ratio and memory length. The proposed ML estimator is demonstrated to have precise estimation performance with low computational complexity.

Cooperative spectrum sensing (CSS) plays a crucial role in this era of explosive Internet of Things with scarce spectrum resources, since it can effectively enhance the sensing accuracy with the cooperation of secondary users (SUs). However, most existing CSS algorithms primarily focus on increasing the cooperative detection accuracy, while neglecting the computational complexity or sensing latency. Therefore, we propose a deep learning (DL) driven CSS scheme with the consideration of dynamic multi-model selection and suitable resource allocation. Specifically, we first derive the closed-form expressions to fit and characterize the detection and false alarm probabilities of three popular DL models, including the convolutional neural network, the long short-term memory (LSTM) network and the hybrid convolutional LSTM network. Then, the problem of minimizing the cooperative sensing error is formulated under the constrains of limited computational resource and sensing latency. Finally, the cross-entropy algorithm is employed to dynamically select the most suitable cooperating SU set and their correspondingly matched models, to balance the sensing accuracy and computational complexity. Simulation results demonstrate that our CSS scheme are much more robust and computationally efficient compared to some well-known CSS algorithms, especially in achieving extremely high sensing accuracy at low transmit power or low received signal-to-noise ratio.

Due to the limited energy and computing resources of Internet of Things (IoT) devices, the collaboration of IoT devices and edge servers is considered to handle the complex deep neural network (DNN) inference tasks. However, the heterogeneity of IoT devices and the various accuracy requirements of inference tasks make it difficult to deploy all the DNN models in edge servers. Moreover, a large-scale data transmission is engaged in collaborative inference, resulting in an increased demand on spectrum resource and energy consumption. To address these issues, in this paper, we first design an accuracy-aware multi-branch DNN inference model and quantify the relationship between branch selection and inference accuracy. Then, based on the multi-branch DNN model, we aim to minimize the energy consumption of devices by jointly optimizing the selection of DNN branches and partition layers, as well as the computing and communication resources allocation. The proposed problem is a mixed-integer nonlinear programming problem. We propose a hierarchical approach to decompose the problem, and then solve it with a proportional integral derivative based searching algorithm. Experimental results demonstrate our proposed scheme has better inference performance and can reduce the total energy consumption up to 65.3$\%$, compared to other collaboration schemes.

Unmanned Aerial Vehicles (UAVs) are considered as promising data collection tools because of their maneuverability and line-of-sight conditions, especially for operations at sea. In this paper, we thus deploy a UAV-enabled offshore operating network, in which the UAV acts as an airborne base station and receives data from the sensing devices at sea. Considering the limited spectrum resources, the non-orthogonal multiple access technology is used for data transmission in parallel to improve the spectrum efficiency. In our scheme, we aim to minimize the total system latency by jointly optimizing the trajectory of the UAV and the number of hovering points, under the constraints of the maximum energy threshold of the UAV and the required data size to be collected. Since the proposed problem is non-convex, we use the deep deterministic policy gradient (DDPG) algorithm in the framework of bisection search to obtain the minimum total system latency. Specifically, we first get the optimal UAV trajectory by the DDPG algorithm for a given number of hovering points. Then, the optimal number of hovering points is derived using the bisection search algorithm, based on the requirement of the data amount to be collected. Lastly, the optimal latency is obtained by alternately iterating the DDPG and bisection search algorithms. Through numerical verification, we can effectively minimize the system latency using our proposed algorithm, with a minimum reduction of about 7.4% to a maximum reduction of about 17.7% in comparison with the existing algorithms A2C and DQN.

The performance of modern communication and radar systems can suffer severe performance degradation from oscillator phase noise. Existing receivers commonly assume that the carrier phase is a constant over a window of a few symbol intervals and average the received signals over these intervals to obtain an estimate of the carrier phase for data demodulation. For mmWave/THz wireless and optical communications with fast time-varying phase noise, this quasi-static carrier phase assumption will no longer be applicable to ensure optimum estimation and compensation for the unknown carrier phase. We present here an Mth-power receiver for$M$-ary phase-shift keying ($M\text{PSK}$) modulation and a Wiener process carrier phase model that is applicable in many situations, especially in optical communications. The receiver can eliminate the$M$-ary phase modulation by raising the received signal samples (one sample per symbol interval) with noise to the power of$M$. The resulting unmodulated phase samples then enable the receiver to perform joint maximum likelihood estimation and maximum a posteriori probability estimation of the unknown initial carrier phase and Wiener carrier phase noise process. The estimation performance improves with a relatively small data block length for any given signal-to-noise ratio and Wiener phase noise variance, and this leads to better error probability performance in data detection. Simulation results are obtained for the estimation mean square error of the noisy carrier phase and the error probability of the detected$M\text{PSK}$symbols.

Digital twin has been emerging as a promising paradigm that connects physical entities and digital space, and continuously evolves to optimize the physical systems. In this article, we focus on studying efficient communication and computation scheme when constructing the Marine Internet of Things (M-IoT)’s digital twin with secrecy provisioning. Specifically, the digital twin model is trained based on federated learning, in which all the unmanned surface vehicles deliver the trained models with nonorthogonal multiple access (NOMA) to the high-altitude platform (HAP) for global model aggregation. Considering the potential eavesdropping on the radio signals of HAP, we utilize the chaotic sequences to spread the model information before the global model broadcasting. In this framework, we aim to minimize the total energy consumption for constructing the digital twin of M-IoT by jointly optimizing the global accuracy, the local accuracy, the HAP’s transmission power and NOMA transmission duration, subject to the secrecy provisioning and latency constraint. An effective low-complexity algorithm is proposed to tackle this joint optimization problem with the use of a layered feature. Finally, numerical results are given to validate the performance gain of the proposed scheme, in comparison with the fixed accuracy scheme, the nonspread spectrum scheme and the time division multiple access transmission scheme.

Adaptive rate control for deep joint source and channel coding (JSCC) is considered as an effective approach to transmit sufficient information in scenarios with limited communication resources. We propose a deep JSCC scheme for wireless image transmission with entropy-aware adaptive rate control, using a single deep neural network to support multiple rates and automatically adjust the rate based on the feature maps of the input image and their entropy, as well as the channel conditions. In particular, we maximize the entropy of the feature maps to increase the average information carried by each transmitted symbol during the training. We further decide which feature maps should be activated based on their entropy, which improves the efficiency of the transmitted symbols. We also propose a pruning module to remove less important pixels in the activated feature maps in order to further improve transmission efficiency. The experimental results demonstrate that our proposed scheme learns an effective rate control strategy that reduces the required channel bandwidth while preserving the quality of the reconstructed images.

The integration of Maritime Internet of Things (M-IoT) technology and unmanned aerial/surface vehicles (UAVs/USVs) has been emerging as a promising navigational information technique in intelligent ocean systems. In this article, we consider the UAV-assisted M-IoT network where USVs offload computation-intensive maritime tasks via non-orthogonal multiple access (NOMA) to the UAV equipped with the mobile-edge computing (MEC) server subject to the UAV mobility. To improve the energy efficiency of offloading transmission and workload computation, we focus on minimizing the total energy consumption by jointly optimizing the USVs’ offloaded workload, transmit power, computation resource allocation, as well as the UAV trajectory subject to the USVs’ latency requirements. Despite the nature of mixed discrete and non-convex programming of the formulated problem, we exploit the vertical decomposition and propose a two-layered algorithm for solving it efficiently. Specifically, the top-layered algorithm is proposed to solve the problem of optimizing the UAV trajectory based on the idea of deep reinforcement learning (DRL), and the underlying algorithm is proposed to optimize the underlying multidomain resource allocation problem based on the idea of the Lagrangian multiplier method. Numerical results are provided to validate the effectiveness of our proposed algorithms as well as the performance advantage of NOMA-enabled computation offloading in terms of overall energy consumption.

This paper analyzes the error performance of M-ary amplitude phase-shift keying (M-APSK) signals with annular-sector (AS) detection over the channel where both additive white Gaussian noise and oscillator phase noise exist. This AS detector performs ring detection and phase detection separately, and leads to the circular decision boundaries in the middle of rings. We derive a unified, closed-form expression for the symbol error probability (SEP) of M-APSK with phase reference error (PRE) due to imperfect phase estimation, based on our previously proposed additive observation phase noise model. The SEP result is analytically tractable and consists of products of Gaussian Q-functions. An accurate, unified approximation to the error floor is directly obtained as a sum of Gaussian Q- functions. Within a wide range of PRE variances, our approximations agree very well with the Monte Carlo simulation for all signal-to-noise ratio (SNR) values of interest. We show that as the PRE variance or the SNR or both increase, the AS detector outperforms the conventional minimum Euclidean distance detector. Moreover, our results provide explicit insight into how the parameters affect the error performance, and facilitate the optimization of M-APSK constellations in phase noise. Examples of ring radii optimization have been given.