Unbiasedness-constrained least squares state estimation for time-varying systems with missing measurements under round-robin protocol

Zhao, Ye; He, Xiao; Ma, Lifeng; Liu, Hongjian

doi:10.1080/00207721.2022.2031338

Cited by 44 publications

(14 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, in the future, our next study direction is to apply novel graph embedding ideas (based on the MAS model) to the realistic problem so as to look into the structures of society or rules of human activities [25], [27], [42], [52], [53]. It should be mentioned that the study for graph embedding on the dynamic graph can be a new challenge for MAS simulations on the graph evolution of the real network [5], [54].…”

Section: Discussionmentioning

confidence: 99%

Influence Maximization in Multiagent Systems by a Graph Embedding Method: Dealing With Probabilistically Unstable Links

Wang

Han

et al. 2023

IEEE Trans. Cybern.

View full text Add to dashboard Cite

This paper is concerned with the influence maximization problem under a network with probabilistically unstable links (PULs) via graph embedding for multi-agent systems (MASs). First, two diffusion models, the unstable-link independent cascade (UIC) model and the unstable-link linear threshold (ULT) model, are designed for the influence maximization problem under the network with PULs. Second, the MAS model for the influence maximization problem with PULs is established and a series of interaction rules among agents are built for the MAS model. Third, the similarity of the unstable structure of the nodes is defined and a novel graph embedding method, termed the unstable-similarity2vec (US2vec) approach, is proposed to tackle the influence maximization problem under the network with PULs. According to the embedding results of the US2vec approach, the seed set is figured out by the developed algorithm. Finally, extensive experiments are conducted to 1) verify the validity of the proposed model and the developed algorithms, and 2) illustrate the optimal solution for influence maximization under different scenarios with PULs.

show abstract

Section: Discussionmentioning

confidence: 99%

Influence Maximization in Multiagent Systems by a Graph Embedding Method: Dealing With Probabilistically Unstable Links

Wang

Han

et al. 2023

IEEE Trans. Cybern.

View full text Add to dashboard Cite

show abstract

“…Moreover, DCP-A can be extended into multi-task pruning. In the future, we will 1) consider more different guidance mechanisms with layer information [32,46,47,49,56,57,66], 2) introduce control strategies to enhance the model robustness [3,27,33,50,51,58], and 3) extend our approach to other complicated multi-task learning problems [1,23,34,59,65,67].…”

Section: Discussionmentioning

confidence: 99%

Differentiable channel pruning guided via attention mechanism: a novel neural network pruning approach

Cheng

Wang²,

Ma³

et al. 2023

Complex Intell. Syst.

Self Cite

View full text Add to dashboard Cite

Neural network pruning offers great prospects for facilitating the deployment of deep neural networks on computational resource limited devices. Neural architecture search (NAS) provides an efficient way to automatically seek appropriate neural architecture design for compressed model. It is observed that, for existing NAS-based pruning methods, there is usually a lack of layer information when searching the optimal neural architecture. In this paper, we propose a new NAS approach, namely, differentiable channel pruning method guided via attention mechanism (DCP-A), where the adopted attention mechanism is able to provide layer information to guide the optimization of the pruning policy. The training process is differentiable with Gumbel-softmax sampling, while parameters are optimized under a two-stage training procedure. The neural network block with the shortcut is dedicatedly designed, which is of help to prune the network not only on its width but also on its depth. Extensive experiments are performed to verify the applicability and superiority of the proposed method. Detailed analysis with visualization of the pruned model architecture shows that our proposed DCP-A learns explainable pruning policies.

show abstract

“…Nowadays, with the quick revolution of communication technologies, networked systems have been gaining increasing popularity because of the convenient cooperation/communication of the system components (e.g. sensors and filters) through shared networks [26], [28], [32], [37], [44], [49], [54]. Notice that the network bandwidth of a communication channel is inevitably limited, and this may cause various network-induced phenomena (NIP) such as data collision, network congestion, and packet dropout etc.…”

Section: Introductionmentioning

confidence: 99%

Variance-Constrained Filter Design With Sensor Resolution Under Round-Robin Communication Protocol: An Outlier-Resistant Mechanism

Geng

Wang

et al. 2023

IEEE Trans. Syst. Man Cybern, Syst.

View full text Add to dashboard Cite

In this paper, a new outlier-resistant mechanism is proposed to deal with the variance-constrained filtering problem for a class of networked systems subject to sensor resolution under the Round-Robin protocol (RRP). Sensor resolution, which serves as an important index in determining measurement accuracy, is taken into account in the addressed filtering problem, and the sensor-resolution-induced uncertainty is tackled by using an upper bounding technique. The RRP is employed to regulate the order of signal transmission in order to relieve communication overhead. In case of measurement outliers, a tailored saturation function is dedicatedly introduced to the filter structure for the purpose of suppressing the outlier-corrupted innovations, thereby maintaining satisfactory filtering performance. By solving a matrix difference equation, an upper bound is first acquired on the error covariance of the devised filter, and the associated filter parameters are subsequently determined through minimizing the acquired bound. The validity of the developed varianceconstrained filter design approach is thoroughly demonstrated via two simulation examples.

show abstract

Unbiasedness-constrained least squares state estimation for time-varying systems with missing measurements under round-robin protocol

Cited by 44 publications

References 54 publications

Influence Maximization in Multiagent Systems by a Graph Embedding Method: Dealing With Probabilistically Unstable Links

Influence Maximization in Multiagent Systems by a Graph Embedding Method: Dealing With Probabilistically Unstable Links

Differentiable channel pruning guided via attention mechanism: a novel neural network pruning approach

Variance-Constrained Filter Design With Sensor Resolution Under Round-Robin Communication Protocol: An Outlier-Resistant Mechanism

Contact Info

Product

Resources

About