Li Shen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Li Shen has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
Fangyuan Liu
UCSI University
1 shared publicationFenghua Liu
Huzhou University
1 shared publication- Lin Zhu
Zhejiang Yuexiu University
1 shared publication - Mengli Zhu
Zhejiang Yuexiu University
1 shared publication Xumin Zhao
Zhejiang Yuexiu University
1 shared publicationZhiqiang Zhang
Zhejiang University of Science and Technology
1 shared publication
Latest Publications
- Open Access
- 14 April 2025
- Published by Springer Nature in Research Square
Dynamic Community Detection in Mobile Communication Networks Using Deep Representation Learning and Gaussian Mixture Models
A mobile communication network is a complex system with millions of interconnected devices, each acting as a node and their communication forming edges. Securing such large-scale networks is a challenging and crucial area of research. While dynamic network structure detection is effective, existing methods often overlook the network topology and local disturbances. Therefore, effectively identifying community structures within the communication network and addressing multimedia security issues remains a significant challenge. This paper presents a dynamic community detection model (DCDAL) based on graph self-coding and a Gaussian mixture model integrated with representation learning to address these issues. The model's performance is evaluated using key network metrics such as NMI and modularization in complex communication networks. Results indicate that the DCDAL model outperforms the comparison model regarding NMI and other indicators, particularly in large-scale mobile communication datasets. The model demonstrates robust performance across multiple evaluation metrics.
- 14 April 2025
- Published by Springer Nature in Research Square
Open AccessDynamic Community Detection in Mobile Communication Networks Using Deep Representation Learning and Gaussian Mixture Models
A mobile communication network is a complex system with millions of interconnected devices, each acting as a node and their communication forming edges. Securing such large-scale networks is a challenging and crucial area of research. While dynamic network structure detection is effective, existing methods often overlook the network topology and local disturbances. Therefore, effectively identifying community structures within the communication network and addressing multimedia security issues remains a significant challenge. This paper presents a dynamic community detection model (DCDAL) based on graph self-coding and a Gaussian mixture model integrated with representation learning to address these issues. The model's performance is evaluated using key network metrics such as NMI and modularization in complex communication networks. Results indicate that the DCDAL model outperforms the comparison model regarding NMI and other indicators, particularly in large-scale mobile communication datasets. The model demonstrates robust performance across multiple evaluation metrics.