Dynamic brain networks provide a powerful representation for capturing temporal variations in functional brain connectivity and have gained increasing attention in brain disease diagnosis. However, most existing methods extract features from isolated time windows, making it difficult to capture the high-order dynamic evolution of brain activity. Moreover, these methods often neglect the functional heterogeneity among brain regions, thereby limiting diagnostic performance. To address these limitations, we propose HyperDiag, a novel temporal-regional Hypergraph learning via topology-enhanced state propagation for brain disease Diagnosis. Specifically, we first design a dual-level hypergraph learning strategy: a temporally-evolving hypergraph message passing strategy to capture dynamic high-order dependencies within and across time windows, and meanwhile, a region-wise functional hypergraph learning strategy to capture regional dependencies. Subsequently, we construct a topology-enhanced selective state-space propagation network to integrate complementary information from both the temporally-evolving and region-wise features. Extensive experiments on four brain disorder datasets (ABIDE-I, ADNI, REST-meta-MDD, and Epilepsy) demonstrate that HyperDiag not only outperforms state-of-the-art methods but also identifies biologically meaningful abnormal connections, offering potential biomarkers for clinical interpretation.

In the human-centric Industry 5.0 environment, factors such as personalized customer demands and the fuzzy characteristics of task times in human-machine collaborative operations will be further considered, resulting in a type of human-machine-Iogistics collaborative scheduling problem for flexible job shops. This problem involves random arrival times of workpieces, fuzzy processing times, and stringent order deadlines. Such a multi-disturbance manufacturing scenario places higher demands on resource collaboration and scheduling within the workshop. To address this problem, this paper introduces swarm theory and constructs a human-machine-logistics resource task consensus model. A real-time task slackness model is developed based on personalized order characteristics, and a real-time scheduling method considering human-machine-logistics resource consensus is proposed, enabling adaptive real-time collaboration of swarm resources in smart workshops for randomly arriving orders. Finally, the effectiveness of the proposed method is evaluated through simulation case studies.

Large-scale pre-trained models hold significant potential for learning universal EEG representations. However, most existing methods, particularly autoregressive (AR) frameworks, primarily rely on straightforward temporal sequencing of multi-channel EEG data, which fails to capture the rich physiological characteristics inherent to EEG signals. Moreover, their time-centered modeling approach also limits the effective representation of the dynamic spatial topology of brain activity. To address these challenges and fully exploit the potential of large-scale EEG models, we propose a novel Topology Hierarchical Derived Brain Autoregressive Modeling (THD-BAR) for EEG generic representations. The core innovation of THD-BAR lies in the introduction of the Brain Topology Hierarchy (BTH), which establishes a multi-scale spatial order for EEG channels. This hierarchical structure enables a redefinition of autoregressive learning as a "next-scale-time prediction" problem, effectively capturing both spatial and temporal dynamics. Based on BTH, we design a Topology-Hierarchical Vector Quantized-Variational Autoencoder (THVQ-VAE) for multi-scale tokenization and develop an enhanced Brain Autoregressive (BAR) module with specialized masking strategies for prediction. Through extensive large-scale pre-training on 17 datasets, followed by rigorous validation on 10 downstream datasets spanning 5 distinct tasks, THD-BAR consistently outperforms existing methods. These results highlight the superior generalization and modeling capabilities of our proposed approach.

Accurate localization in challenging garage environments—marked by poor lighting, sparse textures, repetitive structures, dynamic scenes, and the absence of GPS—is crucial for automated valet parking (AVP) tasks. Addressing these challenges, our research introduces AVM-SLAM, a cutting-edge semantic visual SLAM architecture with multi-sensor fusion in a bird’s eye view (BEV). This novel framework synergizes the capabilities of four fisheye cameras, wheel encoders, and an inertial measurement unit (IMU) to construct a robust SLAM system. Unique to our approach is the implementation of a flare removal technique within the BEV imagery, significantly enhancing road marking detection and semantic feature extraction by convolutional neural networks for superior mapping and localization. Our work also pioneers a semantic prequalification (SPQ) module, designed to adeptly handle the challenges posed by environments with repetitive textures, thereby enhancing loop detection and system robustness. To demonstrate the effectiveness and resilience of AVM-SLAM, we have released a specialized multi-sensor and high-resolution dataset of an underground garage, accessible at https://yale-cv.github.io/avm-slamdataset, encouraging further exploration and validation of our approach within similar settings.

In the context of new retail and personalized, small-batch, distributed collaborative production, orders arrive in real time, and each workshop needs to organize production lines based on suborders in real time under the constraints of smart contracts. However, the existing cloud centralized scheduling method has very high calculation and communication costs when inserting orders in real time, and the fully reactive edge scheduling method is difficult to meet the various order-level requirements of customers. Therefore, this article proposes a real-time edge scheduling model that considers real-time trial insertion of orders based on order-level requirements. Further, a real-time edge adjustment method to eliminate fluctuations is proposed. The proposed strategies were implemented using the lightest methods, avoiding cascading effects, to apply to the edge. Experimental results show that proposed strategies have significant advantages in order-level indicators such as customer satisfaction and have slightly better performance in workshop-level indicators such as resource utilization, energy consumption, and makespan.

The Internet of things (IoT) is embedded into the industrial scene and combined with various devices, facilities and materials to form Smart Objects (SOs). The SOs could be thought of as a heterogeneous swarm in a smart factory under Industrial IOT environment. The process of production is the coordinated operation of various production resources, but dynamic events often interfere with production activities. To solve this problem, an swarm collaboration architecture is proposed. Specifically, it considers the influence of human factors with Human-in-the-Loop on workshop intelligent equipment interaction, and the multi-level dynamic scheduling method of swarm collaboration under the framework is discussed.