The distributed networked control systems are considered in this paper. Several sub-systems which are connected with each other through a communication network make up the whole system. Each sub-system has its own qua...
详细信息
The distributed networked control systems are considered in this paper. Several sub-systems which are connected with each other through a communication network make up the whole system. Each sub-system has its own quantizer so that any information which needs be transmitted to other sub-systems will be quantized due to limited bandwidth. Meanwhile, the actuator faults, including outage, loss of effectiveness and stuck are also considered in our research. A mode-based state feedback controller is given in this paper to stable such NCSs and to meet the robust H-inf performance. A simulation example is proposed to illustrate the effectiveness of our method finally.
The generic object detection (GOD) task has been successfully tackled by recent deep neural networks, trained by an avalanche of annotated training samples from some common classes. However, it is still non-trivial to...
详细信息
This paper is concerned with developing a novel distributed Kalman filtering algorithm over wireless sensor networks based on randomized consensus strategy. Compared with centralized algorithm, distributed filtering t...
详细信息
In this paper, we first propose a specification ap-proach combining interface automata and Z language. This approach can be used to describe temporal properties and data properties of software components. A branching ...
详细信息
In this paper, we first propose a specification ap-proach combining interface automata and Z language. This approach can be used to describe temporal properties and data properties of software components. A branching time logic for ZIAs is presented. We then give an algorithm for model checking this logic on ZIAs with finite domain. Furthermore, we present a mu-calculus logic for ZIAs, and give a model checking algorithm for this logic.
Interactive medical image segmentation methods have become increasingly popular in recent years. These methods combine manual labeling and automatic segmentation, reducing the workload of annotation while maintaining ...
Interactive medical image segmentation methods have become increasingly popular in recent years. These methods combine manual labeling and automatic segmentation, reducing the workload of annotation while maintaining high accuracy. However, most current interactive segmentation frameworks are limited to 2D image data, and are not suitable for 3D image data due to the large size and high complexity of 3D data, as well as the challenges posed by information asymmetry and sparse annotation. In this paper, we propose SliceProp, an interactive segmentation framework that implements slice-wise Label Bidirectional Propagation (LBP) for 3D medical image segmentation. SliceProp extends the interactive 2D image segmentation algorithm to 3D image segmentation, and can handle 3D data with large size and high complexity. Moreover, equipped with a Backtracking Feedback Check (BFC) module, SliceProp effectively addresses the issues of information asymmetry and spatial sparse annotation in 3D medical image segmentation. Additionally, we adopt an uncertainty-based criterion to pri-oritize the slices to be refined interactively, which enhances the efficiency of the interaction process by enabling the model to focus on the regions with the most unreliable predictions. SliceProp is evaluated on two datasets and achieves promising results compared to state-of-the-art methods.
Robust estimation is a crucial and still challenging task, which involves estimating model parameters in noisy environments. Although conventional sampling consensus-based algorithms sample several times to achieve ro...
Robust estimation is a crucial and still challenging task, which involves estimating model parameters in noisy environments. Although conventional sampling consensus-based algorithms sample several times to achieve robustness, these algorithms cannot use data features and historical information effectively. In this paper, we propose RLSAC, a novel Reinforcement Learning enhanced SAmple Consensus framework for end-to-end robust estimation. RLSAC employs a graph neural network to utilize both data and memory features to guide exploring directions for sampling the next minimum set. The feedback of downstream tasks serves as the reward for unsupervised training. Therefore, RL-SAC can avoid differentiating to learn the features and the feedback of downstream tasks for end-to-end robust estimation. In addition, RLSAC integrates a state transition module that encodes both data and memory features. Our experimental results demonstrate that RLSAC can learn from features to gradually explore a better hypothesis. Through analysis, it is apparent that RLSAC can be easily transferred to other sampling consensus-based robust estimation tasks. To the best of our knowledge, RLSAC is also the first method that uses reinforcement learning to sample consensus for end-to-end robust estimation. We release our codes at https://***/IRMVLab/RLSAC.
Identifying influential nodes is a recognized challenge for the tremendous number of nodes in complex networks. Most of proposed methods detect the influential nodes based on their degree or topological location, whic...
详细信息
In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic...
详细信息
An efficient 3D point cloud learning architecture, named EfficientLO-Net, for LiDAR odometry is first proposed in this paper. In this architecture, the projection-aware representation of the 3D point cloud is proposed...
详细信息
Introducing virtualization enhances the flexibility of time-sensitive networking (TSN), wherein applications manifest as service function chains comprising a series of virtual network functions (VNFs). However, such v...
详细信息
ISBN:
(数字)9798350378412
ISBN:
(纸本)9798350378429
Introducing virtualization enhances the flexibility of time-sensitive networking (TSN), wherein applications manifest as service function chains comprising a series of virtual network functions (VNFs). However, such virtualized TSN realizes determinacy through global configuration, being too complicated to serve dynamic applications in time. To address this issue, we innovatively propose to achieve TSN scheduling by distributively executing admission control (AC), whereby the scheduling complexity is radically reduced. Specifically, we first build a two-way AC model that captures TSN multi-queue characteristics. Then, we define admissible regions of nodes and links, working as metrics for AC decision-making and enabling feasible TSN scheduling. Built upon this, we propose a joint AC and VNF embedding mechanism, Rapid Admission Control (RapidAC), which consists of two algorithms. The first algorithm responds to dynamic applications rapidly and derives node-mapping solutions by judging nodes’ admissible regions. Based on this, the second algorithm augments the detailed VNF embedding solution according to admissible regions of links. Simulation results show that RapidAC reduces runtime by 90% compared with existing TSN scheduling algorithms.
暂无评论