Wellshald6807

To explicitly measure the specificity of features, jMFSR decomposes features of vertices into common and specific parts, thereby enhancing the quality of features. Then, jMFSR jointly learns feature extraction, common-specific feature factorization, and clustering of multilayer networks. The experiments on 11 datasets indicate that jMFSR significantly outperforms state-of-the-art baselines in terms of various measurements.This article addresses the problem of lateral control problem for networked-based autonomous vehicle systems. A novel solution is presented for nonlinear autonomous vehicles to smoothly follow the planned path under external disturbances and network-induced issues, such as cyber-attacks, time delays, and limited bandwidths. First, a fuzzy-model-based system is established to represent the nonlinear networked vehicle systems subject to hybrid cyber-attacks. To reduce the network burden and effects of cyber-attacks, an asynchronous resilient event-triggered scheme (ETS) is proposed. A dynamic output-feedback control method is developed to address the underlying problem. Conditions are derived to obtain the output-feedback controller and resilient asynchronous ETS such that the closed-loop switched fuzzy system is globally exponentially stable. Examples are provided to demonstrate the effectiveness and merits of the proposed new control design techniques.In the actual production, the insertion of new job and machine preventive maintenance (PM) are very common phenomena. Under these situations, a flexible job-shop rescheduling problem (FJRP) with both new job insertion and machine PM is investigated. ONO-AE3-208 First, an imperfect PM (IPM) model is established to determine the optimal maintenance plan for each machine, and the optimality is proven. Second, in order to jointly optimize the production scheduling and maintenance planning, a multiobjective optimization model is developed. Third, to deal with this model, an improved nondominated sorting genetic algorithm III with adaptive reference vector (NSGA-III/ARV) is proposed, in which a hybrid initialization method is designed to obtain a high-quality initial population and a critical-path-based local search (LS) mechanism is constructed to accelerate the convergence speed of the algorithm. In the numerical simulation, the effect of parameter setting on the NSGA-III/ARV is investigated by the Taguchi experimental design. After that, the superiority of the improved operators and the overall performance of the proposed algorithm are demonstrated. Next, the comparison of two IPM models is carried out, which verifies the effectiveness of the designed IPM model. Last but not least, we have analyzed the impact of different maintenance effects on both the optimal maintenance decisions and integrated maintenance-production scheduling schemes.Fully supervised semantic segmentation has performed well in many computer vision tasks. However, it is time-consuming because training a model requires a large number of pixel-level annotated samples. Few-shot segmentation has recently become a popular approach to addressing this problem, as it requires only a handful of annotated samples to generalize to new categories. However, the full utilization of limited samples remains an open problem. Thus, in this article, a mutually supervised few-shot segmentation network is proposed. First, the feature maps from intermediate convolution layers are fused to enrich the capacity of feature representation. Second, the support image and query image are combined into a bipartite graph, and the graph attention network is adopted to avoid losing spatial information and increase the number of pixels in the support image to guide the query image segmentation. Third, the attention map of the query image is used as prior information to enhance the support image segmentation, which forms a mutually supervised regime. Finally, the attention maps of the intermediate layers are fused and sent into the graph reasoning layer to infer the pixel categories. Experiments are conducted on the PASCAL VOC- 5i dataset and FSS-1000 dataset, and the results demonstrate the effectiveness and superior performance of our method compared with other baseline methods.The accurate estimation of Q-function and the enhancement of agent's exploration ability have always been challenges of off-policy actor-critic algorithms. To address the two concerns, a novel robust actor-critic (RAC) is developed in this article. We first derive a robust policy improvement mechanism (RPIM) by using the local optimal policy about the current estimated Q-function to guide policy improvement. By constraining the relative entropy between the new policy and the previous one in policy improvement, the proposed RPIM can enhance the stability of the policy update process. The theoretical analysis shows that the incentive to increase the policy entropy is endowed when the policy is updated, which is conducive to enhancing the exploration ability of agents. Then, RAC is developed by applying the proposed RPIM to regulate the actor improvement process. The developed RAC is proven to be convergent. Finally, the proposed RAC is evaluated on some continuous-action control tasks in the MuJoCo platform and the experimental results show that RAC outperforms several state-of-the-art reinforcement learning algorithms.Although convolutional neural networks (CNNs) have shown good performance on grid data, they are limited in the semantic segmentation of irregular point clouds. This article proposes a novel and effective graph CNN framework, referred to as the local-global graph convolutional method (LGGCM), which can achieve short- and long-range dependencies on point clouds. The key to this framework is the design of local spatial attention convolution (LSA-Conv). The design includes two parts generating a weighted adjacency matrix of the local graph composed of neighborhood points, and updating and aggregating the features of nodes to obtain the spatial geometric features of the local point cloud. In addition, a smooth module for central points is incorporated into the process of LSA-Conv to enhance the robustness of the convolution against noise interference by adjusting the position coordinates of the points adaptively. The learned robust LSA-Conv features are then fed into a global spatial attention module with the gated unit to extract long-range contextual information and dynamically adjust the weights of features from different stages. The proposed framework, consisting of both encoding and decoding branches, is an end-to-end trainable network for semantic segmentation of 3-D point clouds. The theoretical analysis of the approximation capabilities of LSA-Conv is discussed to determine whether the features of the point cloud can be accurately represented. Experimental results on challenging benchmarks of the 3-D point cloud demonstrate that the proposed framework achieves excellent performance.Optimization algorithms are of great importance to efficiently and effectively train a deep neural network. However, the existing optimization algorithms show unsatisfactory convergence behavior, either slowly converging or not seeking to avoid bad local optima. Learning rate dropout (LRD) is a new gradient descent technique to motivate faster convergence and better generalization. LRD aids the optimizer to actively explore in the parameter space by randomly dropping some learning rates (to 0); at each iteration, only parameters whose learning rate is not 0 are updated. Since LRD reduces the number of parameters to be updated for each iteration, the convergence becomes easier. For parameters that are not updated, their gradients are accumulated (e.g., momentum) by the optimizer for the next update. Accumulating multiple gradients at fixed parameter positions gives the optimizer more energy to escape from the saddle point and bad local optima. Experiments show that LRD is surprisingly effective in accelerating training while preventing overfitting.Graph neural networks (GNNs) have received increasing interest in the medical imaging field given their powerful graph embedding ability to characterize the non-Euclidean structure of brain networks based on magnetic resonance imaging (MRI) data. However, previous studies are largely node-centralized and ignore edge features for graph classification tasks, resulting in moderate performance of graph classification accuracy. Moreover, the generalizability of GNN model is still far from satisfactory in brain disorder [e.g., autism spectrum disorder (ASD)] identification due to considerable individual differences in symptoms among patients as well as data heterogeneity among different sites. In order to address the above limitations, this study proposes a novel adversarial learning-based node-edge graph attention network (AL-NEGAT) for ASD identification based on multimodal MRI data. First, both node and edge features are modeled based on structural and functional MRI data to leverage complementary brain information and preserved in the constructed weighted adjacent matrix for individuals through the attention mechanism in the proposed NEGAT. Second, two AL methods are employed to improve the generalizability of NEGAT. Finally, a gradient-based saliency map strategy is utilized for model interpretation to identify important brain regions and connections contributing to the classification. Experimental results based on the public Autism Brain Imaging Data Exchange I (ABIDE I) data demonstrate that the proposed framework achieves a classification accuracy of 74.7% between ASD and typical developing (TD) groups based on 1007 subjects across 17 different sites and outperforms the state-of-the-art methods, indicating satisfying classification ability and generalizability of the proposed AL-NEGAT model. Our work provides a powerful tool for brain disorder identification.Detection of formalin to prevent food adulteration, especially in tropical countries, is of primary concern for public health issues. Life-threatening diseases such as leukaemia and lymphoma occur due to the regular consumption of formalin with food. Traditionally, spectrophotometry and chromatography-based sensors have been employed to detect formalin, which have limitations related to their ability to achieve high sensitivity, selectivity, and fast response. In this paper, a surface plasmon resonance (SPR) sensor for improved sensing of formalin is proposed. The Kretschmann configured SPR sensor probe is designed using silver (Ag), platinum (Pt), antimonene, and chitosan, which increases the sensitivity and selectivity. The maximum sensitivity achieved for the proposed SPR sensor is 206.86 o/RIU. The distribution of the electric field (Ey) component of the electric field is also evaluated to analyze the field enhancement at different layer interfaces and to calculate the penetration depth (176.75 nm).Tissue-level mechanics (e.g., stress and strain) are important factors governing tissue remodeling and development of knee osteoarthritis (KOA), and hence, the success of physical rehabilitation. To date, no clinically feasible analysis toolbox has been introduced and used to inform clinical decision making with subject-specific in-depth joint mechanics of different activities. Herein, we utilized a rapid state-of-the-art electromyography-assisted musculoskeletal finite element analysis toolbox with fibril-reinforced poro(visco)elastic cartilages and menisci to investigate knee mechanics in different activities. Tissue mechanical responses, believed to govern collagen damage, cell death, and fixed charge density loss of proteoglycans, were characterized within 15 patients with KOA while various daily activities and rehabilitation exercises were performed. Results showed more inter-participant variation in joint mechanics during rehabilitation exercises compared to daily activities. Accordingly, the devised workflow may be used for designing subject-specific rehabilitation protocols.