Zu-Guo Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zu-Guo Yu has a total of 142 co-authors. Here are the top co-authors by number of shared publications:
Jin-Long Liu
18 shared publicationsVo Anh
Faculty of Science, Engineering and Technology, Swinburne University of Technology, PO Box 218, Hawthorn, Victoria 3122, Australia
13 shared publications- Yu-Chu Tian
Queensland University of Technology
9 shared publications - Guosheng Han
School of Mathematics and Computational Science, Xiangtan University, Xiangtan, China
8 shared publications - Vo Van Anh
Faculty of Science, Engineering and Technology, Swinburne University of Technology, Hawthorn, Australia
7 shared publications Bao-Gen Li
Hunan Key Laboratory for Computation and Simulation in Science and Engineering and Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education, Xiangtan University, Xiangtan, Hunan 411105, P. R. China
6 shared publications
Latest Publications
- 30 October 2026
- Published by World Scientific Pub Co Pte Ltd in Fractals
RELATIONSHIP BETWEEN THE FRACTAL DIMENSION AND THE SUM OF EDGE LIN–LU–YAU RICCI CURVATURES ON TWO TYPES OF FRACTAL MODEL NETWORKS
In this paper, we aim to study the relationship between the fractal dimension and the Lin–Lu–Yau Ricci curvature in complex networks in this paper. We analyzed two types of networks with fractal properties, and compared the total edge Lin–Lu–Yau Ricci curvature with the fractal dimension of the complex networks from a global point of view. Except for a special case of one type of fractal network (i.e. a tree graph), we observed a quantitative relationship with the diameter of the network, thereby linking two important properties of complex networks. We found that the sum of the Lin–Lu–Yau Ricci curvatures of tree graphs is constantly 2. These properties provide a new perspective for analyzing complex networks and help us better understand their characteristics.
- 30 October 2026
- Published by World Scientific Pub Co Pte Ltd in Fractals
RELATIONSHIP BETWEEN THE FRACTAL DIMENSION AND THE SUM OF EDGE LIN–LU–YAU RICCI CURVATURES ON TWO TYPES OF FRACTAL MODEL NETWORKS
In this paper, we aim to study the relationship between the fractal dimension and the Lin–Lu–Yau Ricci curvature in complex networks in this paper. We analyzed two types of networks with fractal properties, and compared the total edge Lin–Lu–Yau Ricci curvature with the fractal dimension of the complex networks from a global point of view. Except for a special case of one type of fractal network (i.e. a tree graph), we observed a quantitative relationship with the diameter of the network, thereby linking two important properties of complex networks. We found that the sum of the Lin–Lu–Yau Ricci curvatures of tree graphs is constantly 2. These properties provide a new perspective for analyzing complex networks and help us better understand their characteristics.
- Open Access
- 11 September 2026
- Published by MDPI AG in Fractal and Fractional
- Vol. 10 (9) , 636
Asymptotic Behavior of Angstmann–Henry–McGann Fractional SIS Model on Complete Networks
This paper investigates the asymptotic behavior of the solution to a fractional-order Susceptible–Infected–Susceptible (SIS) epidemic model on complete networks. This model couples integer-order and tempered fractional-order derivatives; arises from the generalized continuous-time random walk (CTRW) framework introduced by Angstmann, Henry, and McGann; and is referred to as the Angstmann–Henry–McGann fractional-order SIS model. To handle the difficulties caused by the coupled derivatives in the attractivity analysis, we adopt an approach based on the asymptotic theory of Volterra integro-differential equations with positive-type kernels. By constructing an appropriate Lyapunov functional, we establish the global attractivity of the endemic equilibrium and further discuss its stability. The proposed framework could avoid the complications and difficulties that arise when directly manipulating the differential forms of the models (such as unifying derivatives or extending the state space).
- 11 September 2026
- Published by MDPI AG in Fractal and Fractional
- Vol. 10 (9) , 636
Open AccessAsymptotic Behavior of Angstmann–Henry–McGann Fractional SIS Model on Complete Networks
This paper investigates the asymptotic behavior of the solution to a fractional-order Susceptible–Infected–Susceptible (SIS) epidemic model on complete networks. This model couples integer-order and tempered fractional-order derivatives; arises from the generalized continuous-time random walk (CTRW) framework introduced by Angstmann, Henry, and McGann; and is referred to as the Angstmann–Henry–McGann fractional-order SIS model. To handle the difficulties caused by the coupled derivatives in the attractivity analysis, we adopt an approach based on the asymptotic theory of Volterra integro-differential equations with positive-type kernels. By constructing an appropriate Lyapunov functional, we establish the global attractivity of the endemic equilibrium and further discuss its stability. The proposed framework could avoid the complications and difficulties that arise when directly manipulating the differential forms of the models (such as unifying derivatives or extending the state space).
- 25 July 2026
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 211
Multifractal analysis of curvature-based geometric measure for complex networks
- 25 July 2026
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 211
Multifractal analysis of curvature-based geometric measure for complex networks
- 10 April 2026
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 208
Multifractal analysis of structural perturbation time series in hyperbolic growing networks
- 10 April 2026
- Published by Elsevier in Chaos, Solitons & Fractals
- Vol. 208
Multifractal analysis of structural perturbation time series in hyperbolic growing networks
- Open Access
- 9 April 2026
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 22 (4) , e1014130
PhageCGRNet: Integrating Chaos Game Representation of Genomes with Convolutional Neural Network for accurate phage host classification prediction
Phages (or bacteriophages) play a critical role in microbial communities, and accurately predicting the hosts of phages is essential for understanding the dynamics of these viruses and their impact on bacterial populations. In the prediction of classification of phage hosts, feature extraction is a critical step that directly affects the accuracy of the predictions. Among the techniques used for feature extraction, k -mers are the most commonly employed method. Although many methods based on k -mers have been proposed, these methods typically use only the frequency information of k -mers as features. However, when frequencies are identical, the frequency information of these k -mers becomes less useful. To address this limitation, we propose a novel method called PhageCGRNet, which not only utilizes the frequency information of k -mers but also incorporates the positional information of k -mers. In our method, we represent each genome sequence as a three-dimensional matrix containing k -mers frequency features and positional features, and then utilize the Convolutional Neural Network model to predict the host category. Specifically, we combine the frequency information of k -mers directly extracted from the sequences with the positional information of k -mers obtained using the Chaos Game Representation method to construct the feature matrix, which serves as the input to the Convolutional Neural Network. We conducted experiments on two benchmark datasets, and compared PhageCGRNet with existing advanced methods for phage host classification. The experimental results demonstrate that PhageCGRNet achieves higher accuracy at both taxonomy levels of species and genus on these two datasets compared to other state-of-the-art methods.
- 9 April 2026
- Published by Public Library of Science (PLoS) in PLOS Computational Biology
- Vol. 22 (4) , e1014130
Open AccessPhageCGRNet: Integrating Chaos Game Representation of Genomes with Convolutional Neural Network for accurate phage host classification prediction
Phages (or bacteriophages) play a critical role in microbial communities, and accurately predicting the hosts of phages is essential for understanding the dynamics of these viruses and their impact on bacterial populations. In the prediction of classification of phage hosts, feature extraction is a critical step that directly affects the accuracy of the predictions. Among the techniques used for feature extraction, k -mers are the most commonly employed method. Although many methods based on k -mers have been proposed, these methods typically use only the frequency information of k -mers as features. However, when frequencies are identical, the frequency information of these k -mers becomes less useful. To address this limitation, we propose a novel method called PhageCGRNet, which not only utilizes the frequency information of k -mers but also incorporates the positional information of k -mers. In our method, we represent each genome sequence as a three-dimensional matrix containing k -mers frequency features and positional features, and then utilize the Convolutional Neural Network model to predict the host category. Specifically, we combine the frequency information of k -mers directly extracted from the sequences with the positional information of k -mers obtained using the Chaos Game Representation method to construct the feature matrix, which serves as the input to the Convolutional Neural Network. We conducted experiments on two benchmark datasets, and compared PhageCGRNet with existing advanced methods for phage host classification. The experimental results demonstrate that PhageCGRNet achieves higher accuracy at both taxonomy levels of species and genus on these two datasets compared to other state-of-the-art methods.
- 19 March 2026
- Published by Elsevier in Communications in Nonlinear Science and Numerical Simulation
- Vol. 160
Composite multiscale interval cross-sample entropy based on interval similarity measure
- 19 March 2026
- Published by Elsevier in Communications in Nonlinear Science and Numerical Simulation
- Vol. 160
Composite multiscale interval cross-sample entropy based on interval similarity measure
- Open Access
- 10 February 2026
- Published by Elsevier in Journal of Energy Storage
- Vol. 153
Coordinated optimization of photovoltaics-battery and electric vehicles in residential communities
- 10 February 2026
- Published by Elsevier in Journal of Energy Storage
- Vol. 153
Open AccessCoordinated optimization of photovoltaics-battery and electric vehicles in residential communities
- 15 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 309
DualBind: Dual-module protein-ligand binding affinity prediction with adaptive GNN and structure-aware transformer
- 15 January 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 309
DualBind: Dual-module protein-ligand binding affinity prediction with adaptive GNN and structure-aware transformer
- Open Access
- 3 November 2025
- Published by Springer Nature in BMC Biology
- Vol. 23 (1) , 331
ProGraphTrans: multimodal dynamic collaborative framework for protein representation learning
As the core functional carrier of life activities, the quality of protein representation directly affects the accuracy of downstream functional prediction. In recent years, multimodal deep learning methods have significantly improved the effectiveness of protein representation learning by virtue of their advantages in fusing sequence, structure, and chemical characteristics. However, current research still faces two core challenges: first, the guiding mechanism for structural information during multi-modal feature interaction has not been fully explored; second, existing fusion strategies mostly use static weight allocation mechanisms, which is difficult to adapt to sequence-structural features. The dynamic correlation between features leads to limited accuracy in identifying key functional residues. We proposed ProGraphTrans, a multimodal dynamic collaborative framework for protein representation learning. ProGraphTrans builds a dynamic attention multimodal fusion mechanism and captures local sequential patterns through a multi-scale convolutional neural network. Experimental results on four protein downstream tasks show that ProGraphTrans not only outperforms other methods in various indicators but also demonstrates excellent interpretability, demonstrating its advantages and effectiveness as a protein representation method.
- 3 November 2025
- Published by Springer Nature in BMC Biology
- Vol. 23 (1) , 331
Open AccessProGraphTrans: multimodal dynamic collaborative framework for protein representation learning
As the core functional carrier of life activities, the quality of protein representation directly affects the accuracy of downstream functional prediction. In recent years, multimodal deep learning methods have significantly improved the effectiveness of protein representation learning by virtue of their advantages in fusing sequence, structure, and chemical characteristics. However, current research still faces two core challenges: first, the guiding mechanism for structural information during multi-modal feature interaction has not been fully explored; second, existing fusion strategies mostly use static weight allocation mechanisms, which is difficult to adapt to sequence-structural features. The dynamic correlation between features leads to limited accuracy in identifying key functional residues. We proposed ProGraphTrans, a multimodal dynamic collaborative framework for protein representation learning. ProGraphTrans builds a dynamic attention multimodal fusion mechanism and captures local sequential patterns through a multi-scale convolutional neural network. Experimental results on four protein downstream tasks show that ProGraphTrans not only outperforms other methods in various indicators but also demonstrates excellent interpretability, demonstrating its advantages and effectiveness as a protein representation method.