In this paper, an underdetermined three-dimensional (3-D) near-field source localization method is proposed, based on a two-dimensional (2-D) symmetric nonuniform cross array. Firstly, the fourth-order cumulant of the near-field observations with multiple delay lags is exploited to construct virtual far-field pseudo-observations, leading to increased degrees of freedom (DOF); then, 2-D angles of the nearfield sources are jointly estimated by employing the recently proposed sparse and parametric approach (SPA) and Vandermonde decomposition technique, eliminating the need for parameter discretization. To estimate the range term, the one-dimensional (1-D) MUSIC algorithm is applied by resorting to the conjugate symmetry property of the signal's autocorrelation function. Numerical results are provided to demonstrate the superiority of our method.

Federated learning (FL) can achieve privacy-safe and reliable collaborative training without collecting users’ private data. Its excellent privacy security potential promotes a wide range of federated learning (FL) applications in Internet of Things (IoT), wireless networks, mobile devices, autonomous vehicles, and cloud medical treatment. However, the FL method suffers from poor model performance on non-independent and identically distributed (non-i.i.d.) data and excessive traffic volume. To this end, we propose a personalized FL algorithm using a hierarchical proximal mapping based on the moreau envelop, named sparse federated learning with hierarchical personalized models (sFedHP), which significantly improves the acrlong GM performance facing diverse data. A continuously differentiable approximated$\ell _{1}$-norm is also used as the sparse constraint to reduce the communication cost. Convergence analysis shows that sFedHP’s convergence rate is state-of-the-art with linear speedup and the sparse constraint only reduces the convergence rate to a small extent while significantly reducing the communication cost. Experimentally, we demonstrate the benefits of sFedHP compared with the federated averaging (FedAvg), hierarchical fedavg (HierFAVG), and personalized FL methods based on local customization, including FedAMP, FedProx, per- FedAvg, pFedMe, and pFedGP.

In this article, we propose a novel power control scheme for secure transmission and smart jamming game to solve the problem of the decline of anti-jamming performance due to the unknown behavior of the opponent. By exploring recursive reasoning principles and reinforcement learning approaches, we design a high-performance framework for predicting the opponent’s power strategies in dynamic wireless environments. The proposed framework consists of two parts: 1) we develop a game model considering the opponent’s dynamic to characterize the jamming/anti-jamming confrontation and 2) we propose a jamming and anti-jamming policy recursive reasoning (JPR2) algorithm for power control based on reinforcement learning, where the opponent’s dynamic prediction model is learned through variational inference from the transmitter and jammer’s observation history. In addition, we optimize the policy considering the opponent’s dynamic prediction to maximize both parties’ utility functions and achieve their optimal power control strategies. More elaborately, we theoretically guarantee the algorithm’s convergence to the Nash equilibrium of the game. Our experiments show that the proposed algorithm significantly improves the performance of both parties.

Intelligent electromagnetic signature recognition is one of the key technologies in Internet of Things (IoT) device connection, which can improve system security and speed up the authentication process. In practical scenarios, as the number of IoT devices increases, electromagnetic features, such as fingerprint and modulation signals also increase substantially. However, since intelligent recognition technology, such as automatic modulation classification (AMC), requires a large amount of labeled data to train the neural network classifier, it is challenging to collect so much labeled data. To address the performance degradation challenges with small training data, we propose an efficient semisupervised electromagnetic recognition framework to break the performance gap with the fully supervised learning scheme. This framework can fully use the unlabeled electromagnetic data collected during the authentication process for self-training to improve the classifier’s performance. According to the idea of consistency regularization, we design a signal augmentation method and propose an ensemble pseudolabel design algorithm to improve confidence. Moreover, we perform a convex combination of electromagnetic features to smooth the model decision boundary while generalizing to unknown data distribution regions. Experimental results on the modulated data demonstrate the performance superiority of the proposed algorithm, i.e., use less than 5% of data with no more than 10% performance drop.

Federated learning (FL) is a collaborative machine learning technique to train a global model (GM) without obtaining clients' private data. The main challenges in FL are statistical diversity among clients, limited computing capability among clients' equipment, and the excessive communication overhead between the server and clients. To address these challenges, we propose a novel sparse personalized FL scheme via maximizing correlation (FedMac). By incorporating an approximated $\ell _{1}$ -norm and the correlation between client models and GM into standard FL loss function, the performance on statistical diversity data is improved and the communicational and computational loads required in the network are reduced compared with nonsparse FL. Convergence analysis shows that the sparse constraints in FedMac do not affect the convergence rate of the GM, and theoretical results show that FedMac can achieve good sparse personalization, which is better than the personalized methods based on the $\ell _{2}$ -norm. Experimentally, we demonstrate the benefits of this sparse personalization architecture compared with the state-of-the-art personalization methods (e.g., FedMac, respectively, achieves 98.95%, 99.37%, 90.90%, 89.06%, and 73.52% accuracy on the MNIST, FMNIST, CIFAR-100, Synthetic, and CINIC-10 datasets under non-independent and identically distributed (i.i.d.) variants).

Direction-of-arrival (DOA) estimation using sub-Nyquist tensor signals benefits from enhanced performance by extracting structural angular information with multi-dimensional sparse arrays. Although convolutional neural network (CNN) has been employed to achieve efficient DOA estimation in challenging conditions, conventional methods demand excessive memory storage and computation power to process sub-Nyquist tensor statistics. In this letter, we propose a decomposed CNN for sub-Nyquist tensor-based 2-D DOA estimation, where an augmented coarray tensor is derived and used as the network input. To compress convolution kernels for efficient coarray tensor propagation, we develop a convolution kernel decomposition approach. This enables the acquisition of canonical polyadic (CP) factors containing compressed parameters. Performing decomposable convolution between the coarray tensor and the CP factors leads to resource-efficient DOA estimation. Our simulation results indicate that the proposed method conserves system resources while maintaining competitive performance.

In this paper, a gridless super-resolution direction-of-arrival (DOA) estimation method with unknown mutual coupling is proposed. A new clean steering vector is obtained based on the banded symmetric Toeplitz structure of the mutual coupling matrix (MCM). Further, atomic norms associated with the array structure are generated, which can provide a breakthrough in solving super-resolution estimation problem by directly working on the continuous parameter domain. Finally, a semidefinite programming (SDP) method is derived to solve this atomic norm minimization problem. Simulations are provided to verify the effectiveness of the propose method.

We consider the problem of multi-agent reinforcement learning (MARL) in video game AI, where the agents are located in a spatial grid-world environment and the number of agents varies both within and across episodes. The challenge is to flexibly control an arbitrary number of agents while achieving effective collaboration. Existing MARL methods usually suffer from the trade-off between these two considerations. To address the issue, we propose a novel architecture that learns a spatial joint representation of all the agents and outputs grid-wise actions. Each agent will be controlled independently by taking the action from the grid it occupies. By viewing the state information as a grid feature map, we employ a convolutional encoder-decoder as the policy network. This architecture naturally promotes agent communication because of the large receptive field provided by the stacked convolutional layers. Moreover, the spatially shared convolutional parameters enable fast parallel exploration that the experiences discovered by one agent can be immediately transferred to others. The proposed method can be conveniently integrated with general reinforcement learning algorithms, e.g., PPO and Q-learning. We demonstrate the effectiveness of the proposed method in extensive challenging multi-agent tasks in StarCraft II.

In deep reinforcement learning, policy optimization methods need to deal with issues such as function approximation and the reuse of off-policy data. Standard policy gradient methods do not handle off-policy data well, leading to premature convergence and instability. This paper introduces a method to stabilize policy optimization when off-policy data are reused. The idea is to include a Bregman divergence between the behavior policy that generates the data and the current policy to ensure small and safe policy updates with off-policy data. The Bregman divergence is calculated between the state distributions of two policies, instead of only on the action probabilities, leading to a divergence augmentation formulation. Empirical experiments on Atari games show that in the data-scarce scenario where the reuse of off-policy data becomes necessary, our method can achieve better performance than other state-of-the-art deep reinforcement learning algorithms.

Due to the low cost, easy deployment and high flexibility, unmanned aerial vehicles (UAVs) have attracted much attention for civil and military applications. In this paper, we investigate the problem of channel selection for multiple UAV clusters where UAVs work cooperatively to accomplish tasks in a large area. Firstly, the problem is formulated as a game model to minimize the aggregate interference and decrease channel switching cost. Secondly, we prove the game is an exact potential game which ensures the existence of Nash equilibrium (NE). Thirdly, we solve the game using a distributed way and propose two learning methods with different update rules. Finally, we verify the optimality of proposed algorithms. Comparing with the traditional baseline scheme, we demonstrate the effectiveness of proposed algorithms.

In a smart home environment, assisted living has been a topic of great research over the past decade. Human motion analysis is considered as a key technology for living states recognition in an assisted living system. Recent research has proved that rich information can be obtained from human movements, such as the motion category, moving patterns, and human identity. In this paper, a nonintrusive human movement sensing system is established with a mono-static ultrawide bandwidth radar. Then, we propose a well-designed joint motion classification (MCL) and person identification (PID) convolutional neural network (named as “JMI-CNN”). To recognize human motions and identities simultaneously, the network employs a multitask learning scheme as well as the attention mechanism and the hierarchical feature reuse strategies. We report the experimental result on the data from 15 individuals, each performing six motions. It shows that the model achieves a promising performance of 80.57% on the joint task, while the accuracy for MCL and PID are 98.50% and 80.92%, respectively. Moreover, we carry out ablation studies to evaluate the design principles of the proposed method. Discussions on the impact of signal noise ratio and slow-time window length are also conducted.

Micro-Doppler-based human motion classification has become a topical area of research recently. However, the current research is limited by the lack of labeled training data. Domain adaptation, namely, the ability to take advantage of knowledge from an available source data set and apply it to an unlabeled target data set, is useful in this situation. A typical strategy for this transfer learning technique is to extract domain-invariant feature representations. In this letter, an unsupervised domain adaptation method for micro-Doppler classification is proposed. Given no available measurement training samples, we creatively utilize the motion capture database as an auxiliary and adapt its interior knowledge to the measurement data set. To achieve domain-invariant features, three types of features are extracted and fused including low-level deep features from the convolutional neural network, empirical features, and statistical features. After feature fusion, a k-nearest neighbor classifier is applied to the measurement data to classify seven human activities. Experimental results show that our approach outperforms several state-of-the-art unsupervised domain adaptation methods. The impact of the output from different convolution layers is further investigated, and ablation studies of the efficacy of each feature are also carried out in this letter.

We consider deep policy learning with only batched historical trajectories. The main challenge of this problem is that the learner no longer has a simulator or ``environment oracle'' as in most reinforcement learning settings. To solve this problem, we propose a monotonic advantage reweighted imitation learning strategy that is applicable to problems with complex nonlinear function approximation and works well with hybrid (discrete and continuous) action space. The method does not rely on the knowledge of the behavior policy, thus can be used to learn from data generated by an unknown policy. Under mild conditions, our algorithm, though surprisingly simple, has a policy improvement bound and outperforms most competing methods empirically. Thorough numerical results are also provided to demonstrate the efficacy of the proposed methodology.

Analog to digital converters (ADC) and cascade integrator-comb (CIC) filters are the basic modules in a digital intermediate frequency (IF) spectrum analyzer. The optimal output signal-to-noise ratio (SNR) of the digital IF spectrum analyzer with the Gaussian input signal is considered in this letter. The idea is to strike a trade-off between the saturation error and granular error when quantizing the Gaussian input signal. This letter firstly derives a relationship among the maximum allowed input signal amplitude, input signal power, ADC quantization bits and optimal quantization SNR. Besides, an optimal clipping strategy for the CIC decimation filter with variable decimation rates is proposed. Both numerical and simulation results are presented to demonstrate that the proposed clipping method is able to achieve significant SNR gain compared with the traditional rounding or truncation method.

The advance of the Internet in the past decade has radically changed the way people communicate and collaborate with each other. Physical distance is no more a barrier in online social networks, but cultural differences (at the individual, community, as well as societal levels) still govern human-human interactions and must be considered and leveraged in the online world. The rapid deployment of high-speed Internet allows humans to interact using a rich set of multimedia data such as texts, pictures, and videos. This position paper proposes to define a new research area called ‘connected multimedia’, which is the study of a collection of research issues of the super-area social media that receive little attention in the literature. By connected multimedia, we mean the study of the social and technical interactions among users, multimedia data, and devices across cultures and explicitly exploiting the cultural differences. We justify why it is necessary to bring attention to this new research area and what benefits of this new research area may bring to the broader scientific research community and the humanity.