Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.5
2.4
Journals
Mathematics
Special Issues
Theory and Application of Neural Networks and Complex Networks
share announcement

Theory and Application of Neural Networks and Complex Networks

A special issue of Mathematics (ISSN 2227-7390). This special issue belongs to the section "Network Science".

Deadline for manuscript submissions: 15 October 2024 | Viewed by 4073

Special Issue Editors

Prof. Dr. José F. Vicent

E-Mail Website1 Website2
Guest Editor
Department of Computer Science and Artificial Intelligence, University of Alicante, Carretera San Vicente del Raspeig s/n, 03690 San Vicente del Raspeig-Alicante, Spain
Interests: complex networks; machine learning; spatial networks; multilayer networks
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Leandro Tortosa

E-Mail Website
Guest Editor
Department of computer Science and Artificial Intelligence, University of Alicante, Carretera San Vicente del Raspeig s/n, 03690 San Vicente del Raspeig-Alicante, Spain
Interests: complex networks; urban networks; multilayer networks; spatial networks
Dr. Manuel Curado

E-Mail Website
Guest Editor
Polytechnic School, Catholic University of Murcia, Campus Los Jeronimos, s/n, E-30107 Murcia, Spain
Interests: complex networks; machine learning; spatial networks; multilayer networks
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

The analysis of complex networks has focused the attention of researchers in recent years. The Complex Network Theory allows us to understand, model and try to solve a great diversity of real systems such as transport networks, urban networks, or social networks between others.

Artificial neural networks are recognized as a powerful tool that can help identify intertwined and complex relationships in a large number of systems. With the advent of new information technologies, the ability to generate data has increased considerably, representing a phenomenon that, when studied and analyzed, can provide important advances in science. In this context, Artificial Intelligence and, particularly, Artificial Neural Networks can lead to more interpretable models and results. 

This Special Issue aims to collect theories or applications that utilize Artificial Neural Networks or Complex network methods to address all types of challenges. The topics of interest include, but are not limited to:

  • Artificial neural networks.
  • Machine and deep learning models.
  • Clustering and classification algorithms.
  • Predictive models.
  • Graph neural networks.
  • Models of complex networks.
  • Centrality measures.
  • Multiplex networks.
  • Algorithms for network analysis.
  • Spatial networks.
  • Dynamic networks.
  • Complex networks and epidemics.
  • Applications of neural networks and complex networks domains: transport, energy, IoT, smart cities, etc.

Prof. Dr. José F. Vicent
Prof. Dr. Leandro Tortosa
Dr. Manuel Curado
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • centrality measures
  • neural networks
  • machine learning
  • complex networks
  • predictive models
  • multiplex networks
  • graph neural networks

Published Papers (5 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

16 pages, 1839 KiB  
Article
Link Prediction and Graph Structure Estimation for Community Detection
by Dongming Chen, Mingshuo Nie, Fei Xie, Dongqi Wang and Huilin Chen
Mathematics 2024, 12(8), 1269; https://doi.org/10.3390/math12081269 - 22 Apr 2024
Viewed by 342
Abstract
In real-world scenarios, obtaining the relationships between nodes is often challenging, resulting in incomplete network topology. This limitation significantly reduces the applicability of community detection methods, particularly neighborhood aggregation-based approaches, on structurally incomplete networks. Therefore, in this situation, it is crucial to obtain [...] Read more.
In real-world scenarios, obtaining the relationships between nodes is often challenging, resulting in incomplete network topology. This limitation significantly reduces the applicability of community detection methods, particularly neighborhood aggregation-based approaches, on structurally incomplete networks. Therefore, in this situation, it is crucial to obtain meaningful community information from the limited network structure. To address this challenge, the LPGSE algorithm was designed and implemented, which includes four parts: link prediction, structure observation, network estimation, and community partitioning. LPGSE demonstrated its performance in community detection in structurally incomplete networks with 10% missing edges on multiple datasets. Compared with traditional community detection algorithms, LPGSE achieved improvements in NMI and ARI metrics of 1.5781% to 29.0780% and 0.4332% to 31.9820%, respectively. Compared with similar community detection algorithms for structurally incomplete networks, LPGSE also outperformed other algorithms on all datasets. In addition, different edge-missing ratio settings were also attempted, and the performance of different algorithms in these situations was compared and analyzed. The results showed that the algorithm can still maintain high accuracy and stability in community detection across different edge-missing ratios. Full article
(This article belongs to the Special Issue Theory and Application of Neural Networks and Complex Networks)
►▼ Show Figures

Figure 1

15 pages, 4438 KiB  
Article
Attribute Graph Embedding Based on Multi-Order Adjacency Views and Attention Mechanisms
by Jinfang Sheng, Zili Yang, Bin Wang and Yu Chen
Mathematics 2024, 12(5), 697; https://doi.org/10.3390/math12050697 - 27 Feb 2024
Viewed by 510
Abstract
Graph embedding plays an important role in the analysis and study of typical non-Euclidean data, such as graphs. Graph embedding aims to transform complex graph structures into vector representations for further machine learning or data mining tasks. It helps capture relationships and similarities [...] Read more.
Graph embedding plays an important role in the analysis and study of typical non-Euclidean data, such as graphs. Graph embedding aims to transform complex graph structures into vector representations for further machine learning or data mining tasks. It helps capture relationships and similarities between nodes, providing better representations for various tasks on graphs. Different orders of neighbors have different impacts on the generation of node embedding vectors. Therefore, this paper proposes a multi-order adjacency view encoder to fuse the feature information of neighbors at different orders. We generate different node views for different orders of neighbor information, consider different orders of neighbor information through different views, and then use attention mechanisms to integrate node embeddings from different views. Finally, we evaluate the effectiveness of our model through downstream tasks on the graph. Experimental results demonstrate that our model achieves improvements in attributed graph clustering and link prediction tasks compared to existing methods, indicating that the generated embedding representations have higher expressiveness. Full article
(This article belongs to the Special Issue Theory and Application of Neural Networks and Complex Networks)
►▼ Show Figures

Figure 1

12 pages, 654 KiB  
Article
Influential Yield Strength of Steel Materials with Return Random Walk Gravity Centrality
by Rocío Rodríguez, Manuel Curado, Francy D. Rodríguez and José F. Vicent
Mathematics 2024, 12(3), 439; https://doi.org/10.3390/math12030439 - 30 Jan 2024
Viewed by 553
Abstract
In complex networks, important nodes have a significant impact, both functional and structural. From the perspective of data flow pattern detection, the evaluation of the importance of a node in a network, taking into account the role it plays as a transition element [...] Read more.
In complex networks, important nodes have a significant impact, both functional and structural. From the perspective of data flow pattern detection, the evaluation of the importance of a node in a network, taking into account the role it plays as a transition element in random paths between two other nodes, has important applications in many areas. Advances in complex networks and improved data generation are very important for the growth of computational materials science. The search for patterns of behavior of the elements that make up steels through complex networks can be very useful in understanding their mechanical properties. This work aims to study the influence of the connections between the elements of steel and the impact of these connections on their mechanical properties, more specifically on the yield strength. The patterns found in the results show the significance of the proposed approach for the development of new steel compositions. Full article
(This article belongs to the Special Issue Theory and Application of Neural Networks and Complex Networks)
►▼ Show Figures

Figure 1

18 pages, 809 KiB  
Article
Shunting Inhibitory Cellular Neural Networks with Compartmental Unpredictable Coefficients and Inputs
by Marat Akhmet, Madina Tleubergenova and Akylbek Zhamanshin
Mathematics 2023, 11(6), 1367; https://doi.org/10.3390/math11061367 - 11 Mar 2023
Viewed by 896
Abstract
Shunting inhibitory cellular neural networks with compartmental periodic unpredictable coefficients and inputs is the focus of this research. A new algorithm is suggested, to enlarge the set of known unpredictable functions by applying diagonalization in arguments of functions of several variables. Sufficient conditions [...] Read more.
Shunting inhibitory cellular neural networks with compartmental periodic unpredictable coefficients and inputs is the focus of this research. A new algorithm is suggested, to enlarge the set of known unpredictable functions by applying diagonalization in arguments of functions of several variables. Sufficient conditions for the existence and uniqueness of exponentially stable unpredictable and Poisson stable outputs are obtained. To attain theoretical results, the included intervals method and the contraction mapping principle are used. Appropriate examples with numerical simulations that support the theoretical results are provided. It is shown how dynamics of the neural network depend on a new numerical characteristic, the degree of periodicity. Full article
(This article belongs to the Special Issue Theory and Application of Neural Networks and Complex Networks)
►▼ Show Figures

Figure 1

19 pages, 1398 KiB  
Article
Dynamic Network Resource Autonomy Management and Task Scheduling Method
by Xiuhong Li, Jiale Yang and Huilong Fan
Mathematics 2023, 11(5), 1232; https://doi.org/10.3390/math11051232 - 03 Mar 2023
Cited by 2 | Viewed by 1320
Abstract
Satellite network resource management and scheduling technology are significant to constructing integrated information networks in heaven and earth. The difficulty in realizing this technology lies in improving resource utilization efficiency while ensuring the service quality of satellites and efficiently coordinating complex satellite network [...] Read more.
Satellite network resource management and scheduling technology are significant to constructing integrated information networks in heaven and earth. The difficulty in realizing this technology lies in improving resource utilization efficiency while ensuring the service quality of satellites and efficiently coordinating complex satellite network systems and services. This paper proposes a model, A Dynamic task scheduling method based on a UNified resource Management architecture(DUNM), based on the designed resource management architecture supported by dynamic scheduling algorithms to address the problems of low resource utilization, resource allocation, and task completion rate. First, with sufficient resources, the task execution time to complete a task is calculated based on the number of resources, task transmission time, task waiting time, etc. Secondly, based on the tasks assigned to satellites, the execution time of all functions with different transmission rates of communication links between satellites is calculated, and the total sum of all time consumption is analyzed. Finally, after simulation experiments and comparison with various baseline algorithms, about a 40% reduction in time to complete scheduled tasks and an almost 25% reduction in the average cost to finish a scheduling task, our method has higher scheduling efficiency and lower task completion revenue. It also guarantees a higher task completion rate while completing the tasks. Our approach attained a nearly 100% completion rate for scheduling tasks, which means that our algorithm can achieve the scheduling tasks faster and at high task revenue, thus improving the efficiency and economic efficiency of the whole system. Therefore, it validates the advantages of our method, such as high efficiency and high revenue. Full article
(This article belongs to the Special Issue Theory and Application of Neural Networks and Complex Networks)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-5
Back to TopTop