Drone swarms are increasingly important in IoT applications such as agriculture, disaster response, and industrial inspection. However, effective service discovery remains challenging due to drones’ limited resources and the swarm’s dynamic topology. Existing solutions often suffer from congestion, single points of failure, and poor adaptability. To overcome these limitations, we propose a decentralized and dynamic service discovery framework tailored for drone swarms. Our approach models services using fine-grained sensor-level decomposition and leverages spatiotemporal information from drones to enable timely coordination. The core of the framework is a two-phase affinity propagation mechanism: a fully distributed clustering phase based on spatiotemporal leadership to provide a decentralized service registry, followed by a local adaptation phase for dynamic registry updates. To enhance reliability, a spatiotemporal-driven priority chain is used for service replication and failover. Extensive simulations and a case study in a wildfire suppression scenario across various swarm sizes show that our framework significantly outperforms centralized and existing clustering-based methods in efficiency, robustness with limited resources. This makes it a promising solution for reliable service discovery and flexible, fine-grained collaboration in drone swarms.

Deep neural network(DNN) services are now widely used in industrial defect detection applications. With the increasing number of pre-trained model services on MaaS platforms like HuggingFace and inside smart enterprises, fine-tuning or directly applying DNN services has become a new solution for building intelligent applications. However, selecting appropriate services for tasks with various industrial requirements is also challenging work. Existing DNN model recommendation systems typically categorize models based on a limited set of task types or leverage the training data similarities. However, they fail to reflect the DNN service's native transferability and dynamic ability in the specific industrial scenario (i.e., pragmatics). In this paper, we introduce DSR, a novel pragmatic-information-model-based DNN service recommendation approach, designed to retrieve the most suitable services by incorporating information across the scene of industrial tasks and the ability of services. Through graph convolutional networks, DSR embeds the pragmatic information model of services into unified vectors and applies a regression model for usefulness-oriented recommendation towards specific industrial tasks. Additionally, we established a benchmark dataset with hundreds of customized tasks derived from public datasets with open-source services, on which we evaluate DSR compared to existing methodologies, including ImageDataset2Vec, AutoMRM, and TransferGraph. Our results demonstrate DSR's superior performance in terms of accuracy, efficiency, and generality. We also conduct a case study on an industrial surface defect detection scenario, which illustrates the feasibility of the system.

Unmanned aerial vehicle (UAV) swarms are useful for mobile and collaborative applications due to their flexibility, scalability, and reliability. However, managing their communication and collaboration in complex environments is challenging. Service mesh has demonstrated excellent performance in managing communication between microservices in cloudnative environments. However, its centralized and static network structure design hinders its adaptability to dynamic topologies, increases vulnerability to single points of failure, and exacerbates resource constraints when applied to UAV swarms. To address these challenges, we propose UAV-Mesh, a graph-based decentralized service mesh framework for UAV swarms. It models the swarm as a dynamic graph for enabling the data plane to adapt to changing topologies, mitigates the risk of single points of failure through a decentralized control plane, and addresses resource constraints by optimizing consensus mechanism and algorithm. UAV Mesh offers a decentralized perspective for the application of service mesh in UAV swarms. Through experiments and analysis involving varying numbers of UAVs in a complex scenario, we demonstrate the effectiveness and efficiency of UAV Mesh in managing and controlling UAV services.

In the domain of ship design and manufacturing, complex plates are widely used in ship structures, and the rapid retrieval of plate classifications is crucial for effective ship design management. This paper proposes a novel method for similar ship plate retrieval, which is based on semantic fuzzy classification. Commencing with the reconstruction of plate surface structures from point clouds, the method then proceeds to extract semantic features via multi-scale geometric feature extraction, feature line detection, and high-level semantic label extraction. To address the fuzzy boundaries between plate categories, the method constructs fuzzy category vectors to characterize the features of plates. Finally, by integrating fuzzy classification results with fine-grained geometric feature differences, the method achieves the retrieval of similar plates. Experimental results demonstrate that this approach significantly improves the efficiency and accuracy of similarity retrieval among complex ship plates, thereby providing robust support for efficient ship design, and holding important application value.

Tracking the process of remote task execution is critical to timely process analysis by collecting the evidence of correct execution or failure, which generates a process digital twin (DT) for remote supervision. Generally, it will encounter the challenge of constrained communication, high overhead, and high traceability demand, leading to the efficient remote process tracking issue. Existing approaches can address the issue by monitoring or simulating remote task execution. Nevertheless, they do not provide a cost-effective solution, especially when unexpected situation occurs. Thus, we proposed a new cloud-edge collaboration framework for process DT generation. It addresses the efficient remote process tracking issue with a real-virtual collaborative process tracking (RVCPT) approach. The approach contains three patterns of real-virtual collaboration for tracking the entire process of task execution with a coevolution pattern, identifying unexpected situations with a discrimination pattern, and generating a process DT with a real-virtual fusion pattern. This approach can minimize tracking overhead, and meanwhile maintains high traceability, which maximizes the overall cost-effectiveness. With prototype development, case study and experimental evaluation show the applicability and performance advantage of the new cloud-edge collaboration framework in remote supervision.

Since 2020, the COVID-19 pandemic severely disrupted regular off-line business activities. This unprecedented situation inspires the valuable research on facilitating off-line business under pandemics. In this article, we conceptualized the problem as travel management in pandemic (TMiP) and analyzed it from the technological perspective. Enabling travel in a pandemic not only needs a health certificate to prove that the traveler is safe but also entry/exit permissions from both the origin and the destination regions, determined by the local situation and measures. Thus, TMiP is related to technical, social, economic, and administrative factors. By conducting a review on the literature covering the health certificate technology, its adoption in practice, and the exchange system technology published during the COVID-19 pandemic, we learned about their usefulness and limitations in TMiP. Second, we analyzed the review outcomes to infer the six distinctive technical challenges of TMiP. Third, we analyzed the feasibility of referential solutions to these challenges and showed their applicability and limitations. Finally, we offered the perspectives on new TMiP solutions and concluded that they rely on adapting existing solutions, creating new ones, and integrating all of them. We also presented future research directions in a holistic view of TMiP technical solutions. Overall, the findings of the study will stimulate more research on a more coordinated, comprehensive, and intelligent TMiP solution. We also hope this article can help practitioners to restart economies in a pandemic.

One of the main goals of the Internet of Things(IoT) systems is to achieve intelligent interaction of IoT devices. Event prediction is one of the approaches to achieve intelligent interaction. Event logic graph can effectively represent the relationship between events and be used for event prediction. However, in IoT systems, the data generated by IoT devices are usually incomplete and there are complex relationships between events, which in turn affect the accuracy of event prediction in the event logic graph. To address the above problems, this paper proposes a scenario-aware event prediction approach based on event logic graph in IoT systems. First, a flexible paradigm is designed for recognizing events and scenarios in IoT devices. Then, a scenario collaboration-based event context extraction method is proposed for extracting event contexts with similar scenario attributes in the event logic graph. Finally, a scenario-based event prediction method is designed to predict the events that will occur subsequently. In this paper, we verify that our approach can improve the accuracy of event prediction through the case of driving, which shows that our approach in this paper can be effectively applied in IoT systems.

One of the primary goals of cyber-physical system is to deeply integrate cyberspace and the physical world to realize intelligent interaction of the system. Event prediction technique is a powerful means to fulfill this goal. Recently, a novel knowledge graph, the event graph, is widely studied in the field of event analysis due to its excellent ability in event relationship modeling. Therefore, this paper proposes constructing the event graph to model the sequential event evolution in the physical world for event prediction. To this end, the sequential event graph construction method and related event prediction mechanism for CPSs are proposed. First, a flexible and universal paradigm is designed to assist in extracting event instances from the data generated by physical devices. Then, an automatic event graph construction method based on frequent episode mining is proposed. Finally, the related prediction mechanism is designed, including the identification of contextual information a nd the prediction of subsequent events. A case study on car usage illustrates the feasibility of our approach. The flexibility and support for complexity are demonstrated by a comparative discussion.

With the development of mobile technology, mobile virtual worlds have attracted massive users. To improve scalability, a peer‐to‐peer virtual world provides the solution to accommodate more users without increasing hardware investment. In mobile settings, however, existing P2P solutions are not applicable due to the unreliability of mobile devices and the instability of mobile networks. To address the issue, a novel infrastructure model, called Virtual Net, is proposed to provide fault‐tolerance in managing user content and object state. In this paper, the key problem, namely, object state update, is resolved to maintain state consistency and high interaction responsiveness. This work is important in implementing a scalable mobile virtual world.