Formation control is a key technology for multi-agent collaboration to complete certain tasks. Reliability is the core of multi-agent formation control technology. The formation topology of most existing formation control algorithms is random, and these algorithms have specific restrictions on obstacle boundary. To address these issues, a novel anonymous dynamic formation control algorithm with obstacle avoidance is proposed. In this algorithm, we assume that the agent cannot distinguish between other agents and obstacles within its sensing radius. Then, we divide the virtual leaders into the target virtual leader, formation virtual leaders, and bypass virtual leaders. The target virtual leader forms the broadcast sequence of the formation by dynamically planning its geometric shape, and sends the sequence to the agents. The agent selects a formation virtual leader and follows it to achieve desired formation. The agent switches to follow a bypass virtual leader to navigate around the obstacles when it perceives obstacles preventing it from following the formation virtual leaders. After navigating around the obstacles, the agent follows the formation virtual leader to restructure the formation. Simulation results indicate that the proposed algorithm can achieve dynamic formation, relax obstacle boundary constraints, and has high reliability in formation construction and obstacle avoidance.

As public awareness of privacy protection increases and data become more valuable, the applications of federated learning (FL) in the emerging field of Artificial Internet of Things (AIoT) has received widespread attention. Meanwhile, differential privacy (DP), providing strict privacy guarantees, has been introduced to meet users’ stringent privacy protection needs and increasingly sound laws and regulations. However, the implementations of DP in multiple iterations and rounds of FL training, as well as adding noise to all parameters without differentiation, will cause noise accumulation, resulting in the FL system to decline in performance or even fail to converge. To address the issue, FL with denoising DP and sparsification (DDPS-FL) is proposed in this article. First, a local denoising mechanism (LDM) suitable for DP with arbitrary noise adding mechanism is proposed. By removing the previously added noise from global models, LDM achieves direct noise reduction for clients. Second, sparsification based on parameter variation (SPV) is proposed to reduce noise indirectly by deleting nonsignificant parameters without compromising the level of privacy protection. Besides, SPV is able to multiple beneficial effects, such as saving privacy budget, stimulating the dynamism of FL training, amplifying privacy protection effect, and improving communication efficiency. Third, theoretical analysis is performed to prove that DDPS-FL can guarantee user privacy and has ideal convergence, and to analyze the impact of parameters, such as the number of training rounds and iterations on the system performance. Evaluation experiments based on four real-world datasets are elaborated to show that DDPS-FL outperforms state-of-the-art schemes in terms of training stability, model accuracy, and communication efficiency, and its performance becomes relatively better when more noise is added.

The collaborative control algorithms of multiagents system have been applied to many Internet of Things (IoT) devices. The anonymous flocking algorithm of multiagents is a core technology in the collaborative control research of multiagents system. It does not need agents to distinguish other agents and obstacles, but most existing researches have specific constraints on the obstacle shape, which limits its practical applications. The obstacle boundary points contain the shape characteristics of the obstacle. To relax the obstacle shape constraint, we assume that all agents can only perceive the position of obstacle boundary points within their sensing radius, and propose an anonymous flocking algorithm with obstacle avoidance via the position of obstacle boundary point. In this algorithm, the consensus term is divided into velocity consensus term and velocity unit direction consensus term. The velocity consensus term is designed to tow agents that perceive the obstacle boundary points preventing them from following to bypass obstacles, and the velocity unit direction consensus term is designed to achieve the matching of velocity unit direction. Additionally, the gradient-based term is designed to realize the separation and aggregation between agents and obstacle boundary points, and the navigational feedback term is designed to lead all agents to realize the group objective following. Furthermore, it is verified through simulations that the proposed algorithm can relax obstacle shape constraint and has better environmental adaptability.

With the development of Metaverse technology, the avatar in Metaverse has faced serious security and privacy concerns. Analyzing facial features to distinguish between genuine and manipulated facial videos holds significant research importance for ensuring the authenticity of characters in the virtual world and for mitigating discrimination as well as preventing malicious use of facial data. To address this issue, the Facial Feature Points and Class-head-Transformer (FFP-ChT) deepfake video detection model is designed based on the clues of different FFPs distribution in real and fake videos and different displacement distances of real and fake FFPs between frames. The face video input is first detected by the BlazeFace model, and the face detection results are fed into the FaceMesh model to extract 468 FFPs. Then, the Lucas–Kanade (LK) optical flow method is used to track the points of the face, the face calibration algorithm is introduced to re-calibrate the FFPs, and the jitter displacement is calculated by tracking the FFPs between frames. Finally, the Ch is designed in the transformer, and the FFPs and FFP displacement are jointly classified through the ChT model. In this way, the designed ChT classifier is able to accurately and effectively identify deepfake videos. Experiments on open datasets clearly demonstrate the effectiveness and generalization capabilities of our approach.

Abstract Deep learning models have been widely used in hyperspectral images classification. However, the classification results are not satisfactory when the number of training samples is small. Focused on above-mentioned problem, a novel Two-stage Multi-dimensional Convolutional Stacked Autoencoder (TMC-SAE) model is proposed for hyperspectral images classification. The proposed model is composed of two sub-models SAE-1 and SAE-2. The SAE-1 is a 1D autoencoder with asymmetric structre based on full connection layers and 1D convolution layers to reduce spectral dimensionality. The SAE-2 is a hybrid autoencoder composed of 2D and 3D convolution operations to extract spectral-spatial features from the reduced dimensionality data by SAE-1. The SAE-1 is trained with raw data by unsupervised learning and the encoder of SAE-1 is employed to reduce spectral dimensionality of raw data. The data after dimension reduction is used to train the SAE-2 by unsupervised learning. The fine-tuning of SAE-2 encoder and the training of classifier are implemented simultaneously with small number of samples by supervised learning. Comparative experiments are performed on three widely used hyperspectral remote sensing data. The extensive comparative experiments demonstrate that the proposed architecture can effectively extract deep features and maintain high classification accuracy with small number of training samples.

Obstacle avoidance is a key technology of multiagents flocking control. However, most existing research studies assume that the agent can obtain global information about obstacles and have specific constraints on the shape and boundary of obstacles, which easily limit their practical applications. To relax these constraints, we assume that the agent can only perceive the position of obstacle boundary points within its sensing radius and propose an obstacle boundary point and an expected velocity‐based flocking algorithm of multiagents with obstacle avoidance. In this algorithm, the attraction/repulsion potential is designed to avoid collisions between agents and between the agent and obstacle boundary points, the expected velocity is designed to tow the agent to move along the boundary of obstacles, and the virtual leader is designed to lead all agents to realize the group objective. Finally, the sufficient conditions that the agent does not collide are demonstrated, and the performance of the proposed algorithm is further verified through simulations.

The multi-view subspace clustering attracts much attention in recent years. Most methods follow the framework of fusing the affinity graph learned in each view. In this framework, both the fusion strategy and built graph of each view are very important. In this paper, we propose novel methods for multi-view subspace clustering to address these two aspects. On the one hand, we adopt the autoencoders with Laplacian regularization to construct the affinity graph in each view. Compared with previous work employing the autoencoders, the Laplacian term in our method can guide the learned latent representation favoring affinity extraction. Besides, we also discuss the reasons for adding Laplacian regularization. On the other hand, we propose a novel fusion strategy distinguished from the related literature. If the affinity graph of some view is not extracted well, the performance of previous fusion strategies will be seriously affected. Since our strategy can choose the best part from each affinity graph, it can overcome this limitation to some extent. Extensive experimental results on multiple benchmark data sets confirm the effectiveness of our method.

Summary The search for an effective nature‐inspired optimization technique has certainly continued for decades. This work proposes a novel robust multi‐user detection algorithm based on Grey wolf optimization and differential evolution algorithm to overcome the problem of high bit error rate (BER) in multi‐user detection under an impulse noise environment. The simulation results show that the iteration times of the multi‐user detector based on the proposed algorithm is less than those of genetic algorithm, differential evolution algorithm, Grey wolf optimization algorithm, salp swarm algorithm, grasshopper optimisation algorithm, and whale optimization algorithm with the lowerst BER value.

In an open-domain dialogue system, recognition and expression of emotions are the key factors for success. Most of the existing research related to Chinese dialogue systems aims at improving the quality of content but ignores the expression of human emotions. In this article, we propose a Chinese emotional dialogue response generation algorithm based on reinforcement learning that can generate responses not only according to content but also according to emotion. In the proposed method, a multi-emotion classification model is first used to add emotion labels to the corpus of post-response pairs. Then, with the help of reinforcement learning, the reward function is constructed based on two aspects, namely, emotion and content. Among the generated candidates, the system selects the one with long-term success as the best reply. At the same time, to avoid safe responses and diversify dialogue, a diversity beam search algorithm is applied in the decoding process. The comparative experiments demonstrate that the proposed model achieves satisfactory results according to both automatic and human evaluations.

Analyzing structures of crowd mobility at city level is a challenging task due to the complex crowd mobility and dynamic changes generated by the social activities over time. These structures, defined as high-dimensional mobility structures (HMSs), contain spatiotemporal information and are simultaneously influenced by the geographical distributions and daily activities of citywide crowd. However, few work has been dedicated to depict and analyze these structures, mainly due to the lack of effective models. In this paper, we propose to model the crowd mobility as a dynamical system and characterize the irregular mobility data with a novel local coherence of sparse field (LCSF) algorithm. The proposed algorithm makes it possible to measure the separation behavior of trajectories in an irregular and sparse topology network. Detected HMS, referred as local separation measure of LCSF, divides the geographical urban areas into distinct functional regions over time. We design and implement a visual analytics system to facilitate situation-aware analysis of a huge amount of crowd mobility and their socialized behaviors. Case studies based on a real-world data set demonstrate the effectiveness of the proposed approach.