Xinbiao Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Xinbiao Lu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Hao Xing
School of Energy and Electrical Engineering, Hohai University, Nanjing, People’s Republic of China
4 shared publications - Chunlin Ye
School of Artificial Intelligence and Automation, Hohai University, Nanjing, China
3 shared publications - Xupeng Xie
School of Energy and Electrical Engineering, Hohai University, Nanjing, People’s Republic of China
3 shared publications - Zecheng Liu
School of Energy and Electrical Engineering, Hohai University, Nanjing, People’s Republic of China
3 shared publications - Changjiang Han
College of Artificial Intelligence and Automation, Hohai University, Changzhou 213200, P. R. China
2 shared publications - Gaofan Zhan
College of Artificial Intelligence and Automation, Hohai University, Changzhou 213200, P. R. China
2 shared publications
Latest Publications
- 24 October 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 38 (01)
An improved Vicsek model based on intermittent interaction approach
In the classical Vicsek model, the movement direction of each particle is calculated by the average direction of all its neighboring particles. However, due to the excessive number of interacting particles, the consensus velocity is slow, especially in the case of high particle density. Therefore, we propose a novel interaction mechanism to make all particle consensus velocity agree faster. The Euclidean distance between particles and their neighbors is divided into several points from far to near, and through the interaction frequency, we replace the classical Vicsek model with taking the average orientation of only some of these neighbors. In conclusion, the improved Vicsek model converges faster than the classical Vicsek model. According to the new rule, the appropriate communication frequency leads to the fastest convergence speed.
- 24 October 2025
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 38 (01)
An improved Vicsek model based on intermittent interaction approach
In the classical Vicsek model, the movement direction of each particle is calculated by the average direction of all its neighboring particles. However, due to the excessive number of interacting particles, the consensus velocity is slow, especially in the case of high particle density. Therefore, we propose a novel interaction mechanism to make all particle consensus velocity agree faster. The Euclidean distance between particles and their neighbors is divided into several points from far to near, and through the interaction frequency, we replace the classical Vicsek model with taking the average orientation of only some of these neighbors. In conclusion, the improved Vicsek model converges faster than the classical Vicsek model. According to the new rule, the appropriate communication frequency leads to the fastest convergence speed.
- 7 February 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41 (10) , 7447-7458
STIG-Net: a spatial–temporal interactive graph framework for recognizing violent behaviors in videos
- 7 February 2025
- Published by Springer Nature in The Visual Computer
- Vol. 41 (10) , 7447-7458
STIG-Net: a spatial–temporal interactive graph framework for recognizing violent behaviors in videos
- 30 November 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 36 (07)
Improved Vicsek model based on two exponential coupling functions
In order to speed up the consensus of the Vicsek model, existing studies assign different coupling strengths according to the inter-particle Euclidean distance, which effectively reduces the convergence step. In this paper, we propose two new coupling functions, resulting in two improved Vicsek models. Improved Model I introduces the exponential Relu coupling function into the original Vicsek model, and Improved Model II introduces the exponential Swish coupling function into the original Vicsek model. Simulations show that both improved Vicsek models have fewer convergence steps than the original improved Vicsek model based on the coupling function. With different system parameters, the number of convergence steps is smaller than the original improved Vicsek model based on the coupling function. In addition, the number of convergence steps further decreases when the exponent increases and then gradually remains constant. The improved Vicsek model II also achieves better results in resisting noise.
- 30 November 2024
- Published by World Scientific Pub Co Pte Ltd in International Journal of Modern Physics C
- Vol. 36 (07)
Improved Vicsek model based on two exponential coupling functions
In order to speed up the consensus of the Vicsek model, existing studies assign different coupling strengths according to the inter-particle Euclidean distance, which effectively reduces the convergence step. In this paper, we propose two new coupling functions, resulting in two improved Vicsek models. Improved Model I introduces the exponential Relu coupling function into the original Vicsek model, and Improved Model II introduces the exponential Swish coupling function into the original Vicsek model. Simulations show that both improved Vicsek models have fewer convergence steps than the original improved Vicsek model based on the coupling function. With different system parameters, the number of convergence steps is smaller than the original improved Vicsek model based on the coupling function. In addition, the number of convergence steps further decreases when the exponent increases and then gradually remains constant. The improved Vicsek model II also achieves better results in resisting noise.
- 9 November 2024
- Published by World Scientific Pub Co Pte Ltd in Advances in Complex Systems
- Vol. 27 (07n08)
A GRAPH CONVOLUTIONAL NETWORK APPROACH FOR PREDICTING NETWORK ROBUSTNESS
Network robustness, which includes controllability robustness and connectivity robustness, reflects the ability of a network system to withstand attacks. In this paper, a Graph Convolutional Network (GCN) approach is proposed for predicting network robustness. In contrast to the existing Convolutional Neural Network (CNN) approach, the network topology and the node characteristics are directly used as GCN input without being converted into a grayscale image. Due to the reduction in the number of feature maps, the model size of a GCN is greatly reduced to only 1% of a CNN. Extensive experimental studies on four representative networks and six real networks have proven that the proposed approach can achieve better predictive performance with less training and running time.
- 9 November 2024
- Published by World Scientific Pub Co Pte Ltd in Advances in Complex Systems
- Vol. 27 (07n08)
A GRAPH CONVOLUTIONAL NETWORK APPROACH FOR PREDICTING NETWORK ROBUSTNESS
Network robustness, which includes controllability robustness and connectivity robustness, reflects the ability of a network system to withstand attacks. In this paper, a Graph Convolutional Network (GCN) approach is proposed for predicting network robustness. In contrast to the existing Convolutional Neural Network (CNN) approach, the network topology and the node characteristics are directly used as GCN input without being converted into a grayscale image. Due to the reduction in the number of feature maps, the model size of a GCN is greatly reduced to only 1% of a CNN. Extensive experimental studies on four representative networks and six real networks have proven that the proposed approach can achieve better predictive performance with less training and running time.
- 23 August 2024
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 43 (12) , 7820-7842
A Hybrid Convolutional and Graph Neural Network for Human Action Detection in Static Images
- 23 August 2024
- Published by Springer Nature in Circuits, Systems, and Signal Processing
- Vol. 43 (12) , 7820-7842
A Hybrid Convolutional and Graph Neural Network for Human Action Detection in Static Images
- 22 November 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (2) , 1561-1575
A key-points-assisted network with transfer learning for precision human action recognition in still images
- 22 November 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (2) , 1561-1575
A key-points-assisted network with transfer learning for precision human action recognition in still images
- 1 September 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (1) , 233-241
Single-image super-resolution via a lightweight convolutional neural network with improved shuffle learning
- 1 September 2023
- Published by Springer Nature in Signal, Image and Video Processing
- Vol. 18 (1) , 233-241
Single-image super-resolution via a lightweight convolutional neural network with improved shuffle learning