Gengrun Wang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Gengrun Wang has a total of 12 co-authors. Here are the top co-authors by number of shared publications:
Aijun Liu
College of Communication Engineering, PLA University of Science and Technology, Nanjing, Jiangsu 210007, China
2 shared publicationsBangning Zhang
College of Communication Engineering, PLA University of Science and Technology, Nanjing, Jiangsu 210007, China
2 shared publicationsDaoxing Guo
College of Communication Engineering, PLA University of Science and Technology, Nanjing, Jiangsu 210007, China
2 shared publications- Fei Pan
National Digital Switching System Engineering and Technological R&D Center, Zhengzhou 450001, China
1 shared publication Kai Wang
Institute of Information Technology PLA Information Engineering University Zhengzhou China
1 shared publicationKegang Pan
College of Communication Engineering, PLA University of Science and Technology, Nanjing, Jiangsu 210007, China
1 shared publication
Latest Publications
- Open Access
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Communications
- Vol. 20 (1) , e70210
STTAT: A Spatiotemporal Trajectory Attention Model for Cross‐Network User Identity Linkage Using Check‐In Data
User identity linkage is the core task of cross‐network user behaviour analysis. Conventional methods build user matching links by utilising explicit auxiliary information such as user registration metadata. In this paper, we propose a spatiotemporal trajectory attention (STTAT) model for user identity linkage based on user check‐in records in cyberspace. STTAT exploits the powerful feature extraction ability of graph attention to capture fine‐grained similarities between trajectory segments and matches segments belonging to the identical user via latent characteristics, including dwell point distribution and sequential mobility patterns. Experimental results show STTAT achieves an ACC@1 of 88% and a weighted‐ F 1 of 0.859 on Geolife, and an ACC@1 of 62% and a weighted‐ F 1 of 0.623 on Gowalla. Comprehensive comparisons verify that STTAT outperforms existing models with consistent gains in both accuracy and recall.
- 1 January 2026
- Published by Institution of Engineering and Technology (IET) in IET Communications
- Vol. 20 (1) , e70210
Open AccessSTTAT: A Spatiotemporal Trajectory Attention Model for Cross‐Network User Identity Linkage Using Check‐In Data
User identity linkage is the core task of cross‐network user behaviour analysis. Conventional methods build user matching links by utilising explicit auxiliary information such as user registration metadata. In this paper, we propose a spatiotemporal trajectory attention (STTAT) model for user identity linkage based on user check‐in records in cyberspace. STTAT exploits the powerful feature extraction ability of graph attention to capture fine‐grained similarities between trajectory segments and matches segments belonging to the identical user via latent characteristics, including dwell point distribution and sequential mobility patterns. Experimental results show STTAT achieves an ACC@1 of 88% and a weighted‐ F 1 of 0.859 on Geolife, and an ACC@1 of 62% and a weighted‐ F 1 of 0.623 on Gowalla. Comprehensive comparisons verify that STTAT outperforms existing models with consistent gains in both accuracy and recall.
- Open Access
- 3 April 2023
- Published by MDPI AG in Electronics
- Vol. 12 (7) , 1686
Transformer-Based User Alignment Model across Social Networks
Cross-social network user identification refers to finding users with the same identity in multiple social networks, which is widely used in the cross-network recommendation, link prediction, personality recommendation, and data mining. At present, the traditional method is to obtain network structure information from neighboring nodes through graph convolution, and embed social networks into the low-dimensional vector space. However, as the network depth increases, the effect of the model will decrease. Therefore, in order to better obtain the network embedding representation, a Transformer-based user alignment model (TUAM) across social networks is proposed. This model converts the node information and network structure information from the graph data form into sequence data through a specific encoding method. Then, it inputs the data to the proposed model to learn the low-dimensional vector representation of the user. Finally, it maps the two social networks to the same feature space for alignment. Experiments on real datasets show that compared with GAT, TUAM improved ACC@10 indicators by 11.61% and 16.53% on Facebook–Twitter and Weibo–Douban datasets, respectively. This illustrates that the proposed model has a better performance compared to other user alignment models.
- 3 April 2023
- Published by MDPI AG in Electronics
- Vol. 12 (7) , 1686
Open AccessTransformer-Based User Alignment Model across Social Networks
Cross-social network user identification refers to finding users with the same identity in multiple social networks, which is widely used in the cross-network recommendation, link prediction, personality recommendation, and data mining. At present, the traditional method is to obtain network structure information from neighboring nodes through graph convolution, and embed social networks into the low-dimensional vector space. However, as the network depth increases, the effect of the model will decrease. Therefore, in order to better obtain the network embedding representation, a Transformer-based user alignment model (TUAM) across social networks is proposed. This model converts the node information and network structure information from the graph data form into sequence data through a specific encoding method. Then, it inputs the data to the proposed model to learn the low-dimensional vector representation of the user. Finally, it maps the two social networks to the same feature space for alignment. Experiments on real datasets show that compared with GAT, TUAM improved ACC@10 indicators by 11.61% and 16.53% on Facebook–Twitter and Weibo–Douban datasets, respectively. This illustrates that the proposed model has a better performance compared to other user alignment models.
- Open Access
- 12 February 2015
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2015, 1-8
A Cooperative Mobile Satellite Communication System with the Dynamic Space-Time Coding
Channels of mobile satellite communications are affected by multipath fading and shadowing attenuation. At the same time, diversity gains are believed to improve the transmission reliability in fading channels. Considering that the traditional Space-Time Coding (STC) is not suitable for the cooperative mobile satellite communication, in this paper, a new cooperative mobile satellite communication system is proposed based on the Dynamic Space-Time Coding (D-STC). The transmitting energy of the proposed scheme is saved by avoiding forwarding erroneous signals in cooperative users. Meanwhile, this system benefits from diversity gains and the transmission is robust. Additionally, a closed-form expression of the outage probability for the proposed scheme is derived, and then it is demonstrated that this scheme is much better than the existing noncooperative scheme and schemes with traditional STCs in the outage performance. Finally, the analytical result is supported and validated by numerical simulations.
- 12 February 2015
- Published by Wiley in Mathematical Problems in Engineering
- Vol. 2015, 1-8
Open AccessA Cooperative Mobile Satellite Communication System with the Dynamic Space-Time Coding
Channels of mobile satellite communications are affected by multipath fading and shadowing attenuation. At the same time, diversity gains are believed to improve the transmission reliability in fading channels. Considering that the traditional Space-Time Coding (STC) is not suitable for the cooperative mobile satellite communication, in this paper, a new cooperative mobile satellite communication system is proposed based on the Dynamic Space-Time Coding (D-STC). The transmitting energy of the proposed scheme is saved by avoiding forwarding erroneous signals in cooperative users. Meanwhile, this system benefits from diversity gains and the transmission is robust. Additionally, a closed-form expression of the outage probability for the proposed scheme is derived, and then it is demonstrated that this scheme is much better than the existing noncooperative scheme and schemes with traditional STCs in the outage performance. Finally, the analytical result is supported and validated by numerical simulations.
- 10 June 2014
- Published by Wiley in IEEJ Transactions on Electrical and Electronic Engineering
- Vol. 9 (5) , 514-522
High‐throughput selective cooperation with complex field network coding in multiuser networks
In this paper, a cooperation system suitable for networks with multiple users is proposed. In the first phase of the cooperation, the user who has correctly decoded the source signal and has the best channel condition is selected as the relay. Given that the best relay selected by one source–destination (s‐d) pair may also be selected by other pairs, complex field network coding (CFNC) is adopted by the relay in the second phase, to provide diversity gains for the s‐d pairs simultaneously. The number of channels used is reduced, thus increasing the network throughput. Additionally, this system makes up for the performance loss of the traditional CFNC cooperation in large‐scale networks by achieving more diversity gains. Especially, a closed‐form expression of the average signal error probability (SEP) is derived for small‐scale networks, while an upper‐bound estimation is given for larger networks. It is demonstrated that the system achieves full diversity and is robust. To improve the SEP performance of the system, the receiver is modified, and the results demonstrate desirable average SEP performance. Finally, the analytical results are validated by numerical simulations. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.
- 10 June 2014
- Published by Wiley in IEEJ Transactions on Electrical and Electronic Engineering
- Vol. 9 (5) , 514-522
High‐throughput selective cooperation with complex field network coding in multiuser networks
In this paper, a cooperation system suitable for networks with multiple users is proposed. In the first phase of the cooperation, the user who has correctly decoded the source signal and has the best channel condition is selected as the relay. Given that the best relay selected by one source–destination (s‐d) pair may also be selected by other pairs, complex field network coding (CFNC) is adopted by the relay in the second phase, to provide diversity gains for the s‐d pairs simultaneously. The number of channels used is reduced, thus increasing the network throughput. Additionally, this system makes up for the performance loss of the traditional CFNC cooperation in large‐scale networks by achieving more diversity gains. Especially, a closed‐form expression of the average signal error probability (SEP) is derived for small‐scale networks, while an upper‐bound estimation is given for larger networks. It is demonstrated that the system achieves full diversity and is robust. To improve the SEP performance of the system, the receiver is modified, and the results demonstrate desirable average SEP performance. Finally, the analytical results are validated by numerical simulations. © 2014 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.