Feng Pan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Feng Pan has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Hai-Bo Zhao
2 shared publicationsHua-Shan Liu
Donghua University
1 shared publication- Huashan Liu
School of Information and Intelligent Science, Donghua University, Shanghai, China
1 shared publication - Jun Zhou
College of Mathematics and Physics, Southwest Forestry University, Kunming 650224, China
1 shared publication - Ran-Ran Chen
Institute of Information Science and Technology, Donghua University, Shanghai 201620, China
1 shared publication - Shubo Zhou
College of Information Science and Technology, Donghua University, Shanghai, China
1 shared publication
Latest Publications
- Open Access
- 4 April 2023
- Published by MDPI AG in Electronics
- Vol. 12 (7) , 1711
2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition
As human actions can be characterized by the trajectories of skeleton joints, skeleton-based action recognition techniques have gained increasing attention in the field of intelligent recognition and behavior analysis. With the emergence of large datasets, graph convolutional network (GCN) approaches have been widely applied for skeleton-based action recognition and have achieved remarkable performances. In this paper, a novel GCN-based approach is proposed by introducing a convolutional block attention module (CBAM)-based graph attention block to compute the semantic correlations between any two vertices. By considering semantic correlations, our model can effectively identify the most discriminative vertex connections associated with specific actions, even when the two vertices are physically unconnected. Experimental results demonstrate that the proposed model is effective and outperforms existing methods.
- 4 April 2023
- Published by MDPI AG in Electronics
- Vol. 12 (7) , 1711
Open Access2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition
As human actions can be characterized by the trajectories of skeleton joints, skeleton-based action recognition techniques have gained increasing attention in the field of intelligent recognition and behavior analysis. With the emergence of large datasets, graph convolutional network (GCN) approaches have been widely applied for skeleton-based action recognition and have achieved remarkable performances. In this paper, a novel GCN-based approach is proposed by introducing a convolutional block attention module (CBAM)-based graph attention block to compute the semantic correlations between any two vertices. By considering semantic correlations, our model can effectively identify the most discriminative vertex connections associated with specific actions, even when the two vertices are physically unconnected. Experimental results demonstrate that the proposed model is effective and outperforms existing methods.
- 12 July 2017
- Published by Taylor & Francis in International Journal of Systems Science
- Vol. 48 (13) , 2742-2751
Synchronisation control for neutral-type multi-slave stochastic hybrid systems
In this paper, an exponential synchronisation problem for neutral-type multi-slave hybrid systems with stochastic perturbation is discussed, where the adaptive synchronisation model involves a master system and multiple slave systems. By the use of generalised It 's formula and M-matrix method, a sufficient condition is obtained to guarantee the stability of the error system, and the update law of the feedback controller is determined to deduce the synchronisation between the master system and the sum system of all slave systems. Finally, a numerical example is given to illustrate the effectiveness of the results obtained in this paper.- 12 July 2017
- Published by Taylor & Francis in International Journal of Systems Science
- Vol. 48 (13) , 2742-2751
Synchronisation control for neutral-type multi-slave stochastic hybrid systems
In this paper, an exponential synchronisation problem for neutral-type multi-slave hybrid systems with stochastic perturbation is discussed, where the adaptive synchronisation model involves a master system and multiple slave systems. By the use of generalised It 's formula and M-matrix method, a sufficient condition is obtained to guarantee the stability of the error system, and the update law of the feedback controller is determined to deduce the synchronisation between the master system and the sum system of all slave systems. Finally, a numerical example is given to illustrate the effectiveness of the results obtained in this paper.- 4 June 2013
- Published by Springer Nature in Journal of Shanghai Jiaotong University (Science)
- Vol. 18 (3) , 366-375
Online sequential extreme learning machine based multilayer perception with output self feedback for time series prediction
- 4 June 2013
- Published by Springer Nature in Journal of Shanghai Jiaotong University (Science)
- Vol. 18 (3) , 366-375
Online sequential extreme learning machine based multilayer perception with output self feedback for time series prediction
- 1 June 2013
- Published by Springer Nature in Journal of Shanghai Jiaotong University (Science)
- Vol. 18 (4) , 434-442
Time-series forecasting using autoregression enhanced k-nearest neighbors method
- 1 June 2013
- Published by Springer Nature in Journal of Shanghai Jiaotong University (Science)
- Vol. 18 (4) , 434-442
Time-series forecasting using autoregression enhanced k-nearest neighbors method