ABSTRACT Recently, crowd trajectory prediction has attracted increasing attention. In particular, the simulation of pedestrian movement in scenarios such as crowd evacuation has gained increasing focus. The social force model is a promising and effective method for predicting the stochastic movement of pedestrians. However, individual heterogeneity, group‐driven cooperation, and poor self‐adaptive environmental interactive capabilities have not been comprehensively considered. This often makes it difficult to reproduce real scenarios. Therefore, a group‐enabled social force model‐driven multi‐agent generative adversarial imitation learning framework, namely, SFMAGAIL, is proposed. Specifically, (1) a group‐enabled individual heterogeneity schema is utilized to obtain related expert trajectories, which are fully incorporated into the desire force and group‐enabled paradigms; (2) A joint policy is used to exploit the connection between the agents and the environment; and (3) To explore the intrinsic features of expert trajectories, an actor–critic‐based multi‐agent adversarial imitation learning framework is presented to generate effective trajectories. Finally, extensive experiments based on 2D and 3D virtual scenarios are conducted to validate our method. The results show that our proposed method is superior to the compared methods.

With the rapid development of Web3D, virtual reality, and digital twins, virtual trajectories and decision data considerably rely on the analysis and understanding of real video data, particularly in emergency evacuation scenarios. Correctly and effectively evacuating crowds in virtual emergency scenarios are becoming increasingly urgent. One good solution is to extract pedestrian trajectories from videos of emergency situations using a multi-target tracking algorithm and use them to define evacuation procedures. To implement this solution, a trajectory extraction and optimization framework based on multi-target tracking is developed in this study. First, a multi-target tracking algorithm is used to extract and preprocess the trajectory data of the crowd in a video. Then, the trajectory is optimized by combining the trajectory point extraction algorithm and Savitzky–Golay smoothing filtering method. Finally, related experiments are conducted, and the results show that the proposed approach can effectively and accurately extract the trajectories of multiple target objects in real time. In addition, the proposed approach retains the real characteristics of the trajectories as much as possible while improving the trajectory smoothing index, which can provide data support for the analysis of pedestrian trajectory data and formulation of personnel evacuation schemes in emergency scenarios. Further comparisons with methods used in related studies confirm the feasibility and superiority of the proposed framework.

With the increasing importance of data security, privacy protection has gradually risen to a strategic position, especially IoT data privacy protection. The concern for data security has become a national strategy. The discovery of potential risks of privacy data is of great significance, such as the risk of data privacy leakage, data security vulnerabilities, etc. In this article, starting from the privacy data protection mechanism in the Industrial Internet of Things (IIoT) scenario, we proposed a method based on generative adversarial imitation learning (GAIL) to discover the privacy data security risks in IIoT by training privacy protection agents using a large amount of expert data on privacy protection. Finally, our proposed method is validated by relevant simulation experiments, and the results show that our proposed method has wide generalizability and reliability to obtain the maximum payoff of the agents and thus, reduce the risk of data security leakage.

Abstract One of the most common solutions for the prevention of fire accidents is to conduct extensive fire evacuation drills in crowded places. However, there are multiple salient advantages to using virtual reality technology to simulate emergency solutions, for instance, saving costs and greatly decreasing uncertain risks or accidents. Therefore, in this article, a multiagent evacuation framework for complex virtual fire scenarios is proposed and effectively used to simulate a multiagent evacuation procedure to approximate the goal of fire drills in a less costly manner. Specifically, the concept of a multihierarchy agent group model is proposed; that is, the evacuation of multiple agents is separated into leader‐follower and freedom modes. Additionally, several complex actions of individual humans in actual fire drills are fully considered, and a multiaction agent schema is presented to characterize the associated real effects. In addition, generative adversarial imitation learning is adopted to obtain the evacuation path of the leader‐agent by training numerous learning epochs. Finally, extensive experiments are conducted to validate the feasibility of our proposed method. The results show that the proposed method is superior to other methods and that it realistically and reasonably shows the procedure of multiagent evacuation in complex fire emergency scenarios.

Functional connectivity (FC) networks derived from resting-state functional magnetic resonance imaging (rs-fMRI) have been widely used in automated identification of brain disorders, such as Alzheimer's disease (AD) and attention deficit hyperactivity disorder (ADHD). To generate compact representations of FC networks, various thresholding methods have been designed for FC network analysis. However, these studies usually use a pre-defined threshold or connection percentage to threshold whole FC networks, thus ignoring the diversity of temporal correlation (e.g., strong associations) between brain regions in subject groups. In this work, we propose a distribution-guided network thresholding learning (DNTL) method for FC network analysis in brain disorder identification with rs-fMRI. Specifically, for each connection of a pair of brain regions, we propose to determine its specific threshold based on the distribution of connection strength (i.e., temporal correlation) between subject groups (e.g., patients and normal controls). The proposed DNTL can adaptively yield an FC-specific threshold for each connection in an FC network, thus preserving diversity of temporal correlation among different brain regions. Experiment results on 365 subjects from two datasets (i.e., ADNI and ADHD-200) suggest that the DNT method outperforms state-of-the-art methods in brain disorder identification with rs-fMRI data.

In this article, we present a deep learning approach to sketch-based shape retrieval that incorporates a few novel techniques to improve the quality of the retrieval results. First, to address the problem of scarcity of training sketch data, we present a sketch augmentation method that more closely mimics human sketches compared to simple image transformation. Our method generates more sketches from the existing training data by (i) removing a stroke, (ii) adjusting a stroke, and (iii) rotating the sketch. As such, we generate a large number of sketch samples for training our neural network. Second, we obtain the 2D renderings of each 3D model in the shape database by determining the view positions that best depict the 3D shape: i.e., avoiding self-occlusion, showing the most salient features, and following how a human would normally sketch the model. We use a convolutional neural network (CNN) to learn the best viewing positions of each 3D model and generates their 2D images for the next step. Third, our method uses a cross-domain learning strategy based on two Siamese CNNs that pair up sketches and the 2D shape images. A joint Bayesian measure is used to measure the output similarity from these CNNs to maximize inter-class similarity and minimize intra-class similarity. Extensive experiments show that our proposed approach comprehensively outperforms many existing state-of-the-art methods.