Applied Sciences

Research

Jump to: Review

32 pages, 5429 KiB

Open AccessArticle

Efficient Data Transfer by Evaluating Closeness Centrality for Dynamic Social Complex Network-Inspired Routing

by Manuel A. López-Rourich and Francisco J. Rodríguez-Pérez

Appl. Sci. 2023, 13(19), 10766; https://doi.org/10.3390/app131910766 - 27 Sep 2023

Viewed by 1200

Abstract

Social Complex Networks in communication networks are pivotal for comprehending the impact of human-like interactions on information flow and communication efficiency. These networks replicate social behavior patterns in the digital realm by modeling device interactions, considering friendship, influence, and information-sharing frequency. A key [...] Read more.

Social Complex Networks in communication networks are pivotal for comprehending the impact of human-like interactions on information flow and communication efficiency. These networks replicate social behavior patterns in the digital realm by modeling device interactions, considering friendship, influence, and information-sharing frequency. A key challenge in communication networks is their dynamic topologies, driven by dynamic user behaviors, fluctuating traffic patterns, and scalability needs. Analyzing these changes is essential for optimizing routing and enhancing the user experience. This paper introduces a network model tailored for Opportunistic Networks, characterized by intermittent device connections and disconnections, resulting in sporadic connectivity. The model analyzes node behavior, extracts vital properties, and ranks nodes by influence. Furthermore, it explores the evolution of node connections over time, gaining insights into changing roles and their impact on data exchange. Real-world datasets validate the model’s effectiveness. Applying it enables the development of refined routing protocols based on dynamic influence rankings. This approach fosters more efficient, adaptive communication systems that dynamically respond to evolving network conditions and user behaviors. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

22 pages, 3358 KiB

Open AccessArticle

Unsupervised Community Detection Algorithm with Stochastic Competitive Learning Incorporating Local Node Similarity

by Jian Huang and Yijun Gu

Appl. Sci. 2023, 13(18), 10496; https://doi.org/10.3390/app131810496 - 20 Sep 2023

Viewed by 1579

Abstract

Community detection is an important task in the analysis of complex networks, which is significant for mining and analyzing the organization and function of networks. As an unsupervised learning algorithm based on the particle competition mechanism, stochastic competitive learning has been applied in [...] Read more.

Community detection is an important task in the analysis of complex networks, which is significant for mining and analyzing the organization and function of networks. As an unsupervised learning algorithm based on the particle competition mechanism, stochastic competitive learning has been applied in the field of community detection in complex networks, but still has several limitations. In order to improve the stability and accuracy of stochastic competitive learning and solve the problem of community detection, we propose an unsupervised community detection algorithm LNSSCL (Local Node Similarity-Integrated Stochastic Competitive Learning). The algorithm calculates node degree as well as Salton similarity metrics to determine the starting position of particle walk; local node similarity is incorporated into the particle preferential walk rule; the particle is dynamically adjusted to control capability increments according to the control range; particles select the node with the strongest control capability within the node to be resurrected; and the LNSSCL algorithm introduces a node affiliation selection step to adjust the node community labels. Experimental comparisons with 12 representative community detection algorithms on real network datasets and synthetic networks show that the LNSSCL algorithm is overall better than other compared algorithms in terms of standardized mutual information (NMI) and modularity (Q). The improvement effect for the stochastic competition learning algorithm is evident, and it can effectively accomplish the community detection task in complex networks. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

16 pages, 669 KiB

Open AccessArticle

Integrating Spherical Fuzzy Sets and the Objective Weights Consideration of Risk Factors for Handling Risk-Ranking Issues

by Kuei-Hu Chang

Appl. Sci. 2023, 13(7), 4503; https://doi.org/10.3390/app13074503 - 2 Apr 2023

Cited by 3 | Viewed by 1463

Abstract

Risk assessments and risk prioritizations are crucial aspects of new product design before a product is launched into the market. Risk-ranking issues involve the information that is considered for the evaluation and objective weighting considerations of the evaluation factors that are presented by [...] Read more.

Risk assessments and risk prioritizations are crucial aspects of new product design before a product is launched into the market. Risk-ranking issues involve the information that is considered for the evaluation and objective weighting considerations of the evaluation factors that are presented by the data. However, typical risk-ranking methods cannot effectively grasp a comprehensive evaluation of this information and ignore the objective weight considerations of the risk factors, leading to inappropriate evaluation results. For a more accurate ranking result of the failure mode risk, this study proposes a novel, flexible risk-ranking approach that integrates spherical fuzzy sets and the objective weight considerations of the risk factors to process the risk-ranking issues. In the numerical case validation, a new product design risk assessment of electronic equipment was used as a numerically validated case, and the simulation results were compared with the risk priority number (RPN) method, improved risk priority number (IRPN) method, intuitionistic fuzzy weighted average (IFWA) method, and spherical weighted arithmetic average (SWAA) method. The test outcomes that were confirmed showed that the proposed novel, flexible risk-ranking approach could effectively grasp the comprehensive evaluation information and provide a more accurate ranking of the failure mode risk. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

18 pages, 3069 KiB

Open AccessArticle

Graph-Augmentation-Free Self-Supervised Learning for Social Recommendation

by Nan Xiang, Xiaoxia Ma, Huiling Liu, Xiao Tang and Lu Wang

Appl. Sci. 2023, 13(5), 3034; https://doi.org/10.3390/app13053034 - 27 Feb 2023

Viewed by 1842

Abstract

Social recommendation systems can improve recommendation quality in cases of sparse user–item interaction data, which has attracted the industry’s attention. In reality, social recommendation systems mostly mine real user preferences from social networks. However, trust relationships in social networks are complex and it [...] Read more.

Social recommendation systems can improve recommendation quality in cases of sparse user–item interaction data, which has attracted the industry’s attention. In reality, social recommendation systems mostly mine real user preferences from social networks. However, trust relationships in social networks are complex and it is difficult to extract valuable user preference information, which worsens recommendation performance. To address this problem, this paper proposes a social recommendation algorithm based on multi-graph contrastive learning. To ensure the reliability of user preferences, the algorithm builds multiple enhanced user relationship views of the user’s social network and encodes multi-view high-order relationship learning node representations using graph and hypergraph convolutional networks. Considering the effect of the long-tail phenomenon, graph-augmentation-free self-supervised learning is used as an auxiliary task to contrastively enhance node representations by adding uniform noise to each layer of encoder embeddings. Three open datasets were used to evaluate the algorithm, and it was compared to well-known recommendation systems. The experimental studies demonstrated the superiority of the algorithm. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

14 pages, 3451 KiB

Open AccessArticle

Multi-View Gait Recognition Based on a Siamese Vision Transformer

by Yanchen Yang, Lijun Yun, Ruoyu Li, Feiyan Cheng and Kun Wang

Appl. Sci. 2023, 13(4), 2273; https://doi.org/10.3390/app13042273 - 10 Feb 2023

Cited by 4 | Viewed by 1653

Abstract

Although the vision transformer has been used in gait recognition, its application in multi-view gait recognition remains limited. Different views significantly affect the accuracy with which the characteristics of gait contour are extracted and identified. To address this issue, this paper proposes a [...] Read more.

Although the vision transformer has been used in gait recognition, its application in multi-view gait recognition remains limited. Different views significantly affect the accuracy with which the characteristics of gait contour are extracted and identified. To address this issue, this paper proposes a Siamese mobile vision transformer (SMViT). This model not only focuses on the local characteristics of the human gait space, but also considers the characteristics of long-distance attention associations, which can extract multi-dimensional step status characteristics. In addition, it describes how different perspectives affect the gait characteristics and generates reliable features of perspective–relationship factors. The average recognition rate of SMViT for the CASIA B dataset reached 96.4%. The experimental results show that SMViT can attain a state-of-the-art performance when compared to advanced step-recognition models, such as GaitGAN, Multi_view GAN and Posegait. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

19 pages, 8389 KiB

Open AccessArticle

Infrared Small and Moving Target Detection on Account of the Minimization of Non-Convex Spatial-Temporal Tensor Low-Rank Approximation under the Complex Background

by Kun Wang, Defu Jiang, Lijun Yun and Xiaoyang Liu

Appl. Sci. 2023, 13(2), 1196; https://doi.org/10.3390/app13021196 - 16 Jan 2023

Viewed by 1609

Abstract

Infrared point-target detection is one of the key technologies in infrared guidance systems. Due to the long observation distance, the point target is often submerged in the background clutter and large noise in the process of atmospheric transmission and scattering, and the signal-to-noise [...] Read more.

Infrared point-target detection is one of the key technologies in infrared guidance systems. Due to the long observation distance, the point target is often submerged in the background clutter and large noise in the process of atmospheric transmission and scattering, and the signal-to-noise ratio is low. On the other hand, the target in the image appears in the form of fuzzy points, so that the target has no obvious features and texture information. Therefore, scholars have proposed many object detection methods for dimming infrared images, which has become a hot research topic on account of the flow-rank model based on the image patch. However, the result has a high false alarm rate because the most low-rank models based on the image patch do not consider the spatial-temporal characteristics of the infrared sequences. Therefore, we introduce 3D total variation (3D-TV) to regularize the foreground on account of the non-convex rank approximation minimization method, so as to consider the spatial-temporal continuity of the target and effectively suppress the interference caused by dynamic background and target movement on the foreground extraction. Finally, this paper proposes the minimization of the non-convex spatial-temporal tensor low-rank approximation algorithm (MNSTLA) by studying the related algorithms of the point infrared target detection, and the experimental results show strong robustness and a low false alarm rate for the proposed method compared with other advanced algorithms, such as NARM, RIPT, and WSNMSTIPT. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

17 pages, 533 KiB

Open AccessArticle

Leveraging Artificial Intelligence in Blockchain-Based E-Health for Safer Decision Making Framework

by Abdulatif Alabdulatif, Muneerah Al Asqah, Tarek Moulahi and Salah Zidi

Appl. Sci. 2023, 13(2), 1035; https://doi.org/10.3390/app13021035 - 12 Jan 2023

Cited by 7 | Viewed by 2053

Abstract

Machine learning-based (ML) systems are becoming the primary means of achieving the highest levels of productivity and effectiveness. Incorporating other advanced technologies, such as the Internet of Things (IoT), or e-Health systems, has made ML the first choice to help automate systems and [...] Read more.

Machine learning-based (ML) systems are becoming the primary means of achieving the highest levels of productivity and effectiveness. Incorporating other advanced technologies, such as the Internet of Things (IoT), or e-Health systems, has made ML the first choice to help automate systems and predict future events. The execution environment of ML is always presenting contrasting types of threats, such as adversarial poisoning of training datasets or model parameters manipulation. Blockchain technology is known as a decentralized network of blocks that symbolizes means of protecting block content integrity and ensuring secure execution of operations.Existing studies partially incorporated Blockchain into the learning process. This paper proposes a more extensive secure way to protect the decision process of the learning model. Using smart contracts, this study executed the model’s decision by the reversal engineering of the learning model’s decision function from the extracted learning parameters. We deploy Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) classifiers decision functions on-chain for more comprehensive integration of Blockchain. The effectiveness of this proposed approach is measured by applying a case study of medical records. In a safe environment, SVM prediction scores were found to be higher than MLP. However, MLP had higher time efficiency. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

17 pages, 2586 KiB

Open AccessArticle

TRAL: A Tag-Aware Recommendation Algorithm Based on Attention Learning

by Yi Zuo, Shengzong Liu, Yun Zhou and Huanhua Liu

Appl. Sci. 2023, 13(2), 814; https://doi.org/10.3390/app13020814 - 6 Jan 2023

Cited by 6 | Viewed by 2661

Abstract

A social tagging system improves recommendation performance by introducing tags as auxiliary information. These tags are text descriptions of target items provided by individual users, which can be arbitrary words or phrases, so they can provide more abundant information about user interests and [...] Read more.

A social tagging system improves recommendation performance by introducing tags as auxiliary information. These tags are text descriptions of target items provided by individual users, which can be arbitrary words or phrases, so they can provide more abundant information about user interests and item characteristics. However, there are many problems to be solved in tag information, such as data sparsity, ambiguity, and redundancy. In addition, it is difficult to capture multi-aspect user interests and item characteristics from these tags, which is essential to the recommendation performance. In the view of these situations, we propose a tag-aware recommendation model based on attention learning, which can capture diverse tag-based potential features for users and items. The proposed model adopts the embedding method to produce dense tag-based feature vectors for each user and each item. To compress these vectors into a fixed-length feature vector, we construct an attention pooling layer that can automatically allocate different weights to different features according to their importance. We concatenate the feature vectors of users and items as the input of a multi-layer fully connected network to learn non-linear high-level interaction features. In addition, a generalized linear model is also conducted to extract low-level interaction features. By integrating these features of different types, the proposed model can provide more accurate recommendations. We establish extensive experiments on two real-world datasets to validate the effect of the proposed model. Comparable results show that our model perform better than several state-of-the-art tag-aware recommendation methods in terms of HR and NDCG metrics. Further ablation studies also demonstrate the effectiveness of attention learning. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

15 pages, 7225 KiB

Open AccessArticle

Directed Network Disassembly Method Based on Non-Backtracking Matrix

by Jinlong Ma, Peng Wang and Huijia Li

Appl. Sci. 2022, 12(23), 12047; https://doi.org/10.3390/app122312047 - 25 Nov 2022

Viewed by 1517

Abstract

Network disassembly refers to the removal of the minimum set of nodes to split the network into disconnected sub-part to achieve effective control of the network. However, most of the existing work only focuses on the disassembly of undirected networks, and there are [...] Read more.

Network disassembly refers to the removal of the minimum set of nodes to split the network into disconnected sub-part to achieve effective control of the network. However, most of the existing work only focuses on the disassembly of undirected networks, and there are few studies on directed networks, because when the edges in the network are directed, the application of the existing methods will lead to a higher cost of disassembly. Aiming at fixing the problem, an effective edge module disassembly method based on a non-backtracking matrix is proposed. This method combines the edge module spectrum partition and directed network disassembly problem to find the minimum set of key points connecting different edge modules for removal. This method is applied to large-scale artificial and real networks to verify its effectiveness. Multiple experimental results show that the proposed method has great advantages in disassembly accuracy and computational efficiency. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

17 pages, 4468 KiB

Open AccessArticle

BChainGuard: A New Framework for Cyberthreats Detection in Blockchain Using Machine Learning

by Suliman Aladhadh, Huda Alwabli, Tarek Moulahi and Muneerah Al Asqah

Appl. Sci. 2022, 12(23), 12026; https://doi.org/10.3390/app122312026 - 24 Nov 2022

Cited by 9 | Viewed by 1971

Abstract

Recently, blockchain technology has appeared as a powerful decentralized tool for data integrity protection. The use of smart contracts in blockchain helped to provide a secure environment for developing peer-to-peer applications. Blockchain has been used by the research community as a tool for [...] Read more.

Recently, blockchain technology has appeared as a powerful decentralized tool for data integrity protection. The use of smart contracts in blockchain helped to provide a secure environment for developing peer-to-peer applications. Blockchain has been used by the research community as a tool for protection against attacks. The blockchain itself can be the objective of many cyberthreats. In the literature, there are few research works aimed to protect the blockchain against cyberthreats adopting, in most cases, statistical schemes based on smart contracts and causing deployment and runtime overheads. Although, the power of machine learning tools there is insufficient use of these techniques to protect blockchain against attacks. For that reason, we aim, in this paper, to propose a new framework called BChainGuard for cyberthreat detection in blockchain. Our framework’s main goal is to distinguish between normal and abnormal behavior of the traffic linked to the blockchain network. In BChainGuard, the execution of the classification technique will be local. Next, we embed only the decision function as a smart contract. The experimental result shows encouraging results with an accuracy of detection of around 95% using SVM and 98.02% using MLP with a low runtime and overhead in terms of consumed gas. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

17 pages, 1336 KiB

Open AccessArticle

A Graph Convolution Collaborative Filtering Integrating Social Relations Recommendation Method

by Min Ma, Qiong Cao and Xiaoyang Liu

Appl. Sci. 2022, 12(22), 11653; https://doi.org/10.3390/app122211653 - 16 Nov 2022

Cited by 1 | Viewed by 1809

Abstract

Traditional collaborative filtering recommendation algorithms only consider the interaction between users and items leading to low recommendation accuracy. Aiming to solve this problem, a graph convolution collaborative filtering recommendation method integrating social relations is proposed. Firstly, a social recommendation model based on graph [...] Read more.

Traditional collaborative filtering recommendation algorithms only consider the interaction between users and items leading to low recommendation accuracy. Aiming to solve this problem, a graph convolution collaborative filtering recommendation method integrating social relations is proposed. Firstly, a social recommendation model based on graph convolution representation learning and general collaborative filtering (SRGCF) is constructed; then, based on this model, a social relationship recommendation algorithm (SRRA) is proposed; secondly, the algorithm learns the representations of users and items by linear propagation on the user–item bipartite graph; then the user representations are updated by learning the representations with social information through the neighbor aggregation operation in the social network to form the final user representations. Finally, the prediction scores are calculated, and the recommendation list is generated. The comparative experimental results on four real-world datasets show that: the proposed SRRA algorithm performs the best over existing baselines on Recall@10 and NDCG@10; specifically, SRRA improved by an average of 4.40% and 9.62% compared to DICER and GraphRec, respectively, which validates that the proposed SRGCF model and SRRA algorithm are reasonable and effective. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

26 pages, 6449 KiB

Open AccessArticle

A Modeling Approach for Measuring the Performance of a Human-AI Collaborative Process

by Ganesh Sankaran, Marco A. Palomino, Martin Knahl and Guido Siestrup

Appl. Sci. 2022, 12(22), 11642; https://doi.org/10.3390/app122211642 - 16 Nov 2022

Cited by 1 | Viewed by 2495

Abstract

Despite the unabated growth of algorithmic decision-making in organizations, there is a growing consensus that numerous situations will continue to require humans in the loop. However, the blending of a formal machine and bounded human rationality also amplifies the risk of what is [...] Read more.

Despite the unabated growth of algorithmic decision-making in organizations, there is a growing consensus that numerous situations will continue to require humans in the loop. However, the blending of a formal machine and bounded human rationality also amplifies the risk of what is known as local rationality. Therefore, it is crucial, especially in a data-abundant environment that characterizes algorithmic decision-making, to devise means to assess performance holistically. In this paper, we propose a simulation-based model to address the current lack of research on quantifying algorithmic interventions in a broader organizational context. Our approach allows the combining of causal modeling and data science algorithms to represent decision settings involving a mix of machine and human rationality to measure performance. As a testbed, we consider the case of a fictitious company trying to improve its forecasting process with the help of a machine learning approach. The example demonstrates that a myopic assessment obscures problems that only a broader framing reveals. It highlights the value of a systems view since the effects of the interplay between human and algorithmic decisions can be largely unintuitive. Such a simulation-based approach can be an effective tool in efforts to delineate roles for humans and algorithms in hybrid contexts. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

14 pages, 2964 KiB

Open AccessArticle

Bridge Node Detection between Communities Based on GNN

by Hairu Luo, Peng Jia, Anmin Zhou, Yuying Liu and Ziheng He

Appl. Sci. 2022, 12(20), 10337; https://doi.org/10.3390/app122010337 - 13 Oct 2022

Cited by 3 | Viewed by 2261

Abstract

In a complex network, some nodes are relatively concentrated in topological structure, thus forming a relatively independent node group, which we call a community. Usually, there are multiple communities on a network, and these communities are interconnected and exchange information with each other. [...] Read more.

In a complex network, some nodes are relatively concentrated in topological structure, thus forming a relatively independent node group, which we call a community. Usually, there are multiple communities on a network, and these communities are interconnected and exchange information with each other. A node that plays an important role in the process of information exchange between communities is called an inter-community bridge node. Traditional methods of defining and detecting bridge nodes mostly quantify the bridging effect of nodes by collecting local structural information of nodes and defining index operations. However, on the one hand, it is often difficult to capture the deep topological information in complex networks based on a single indicator, resulting in inaccurate evaluation results; on the other hand, for networks without community structure, such methods may rely on community partitioning algorithms, which require significant computing power. In this paper, considering the multi-dimensional attributes and structural characteristics of nodes, a deep learning-based framework named BND is designed to quickly and accurately detect bridge nodes. Considering that the bridging function of nodes between communities is abstract and complex, and may be related to the multi-dimensional information of nodes, we construct an attribute graph on the basis of the original graph according to the features of the five dimensions of the node to meet our needs for extracting bridging-related attributes. In the deep learning model, we overlay graph neural network layers to process the input attribute graph and add fully connected layers to improve the final classification effect of the model. Graph neural network algorithms including GCN, GAT, and GraphSAGE are compatible with our proposed framework. To the best of our knowledge, our work is the first application of graph neural network techniques in the field of bridge node detection. Experiments show that our designed framework can effectively capture network topology information and accurately detect bridge nodes in the network. In the overall model effect evaluation results based on indicators such as Accuracy and F1 score, our proposed graph neural network model is generally better than baseline methods. In the best case, our model has an Accuracy of 0.9050 and an F1 score of 0.8728. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

14 pages, 2912 KiB

Open AccessArticle

5G Price Competition with Social Equilibrium Optimality for Social Networks

by Yuhao Feng, Shenpeng Song, Wenzhe Xu and Huijia Li

Appl. Sci. 2022, 12(17), 8798; https://doi.org/10.3390/app12178798 - 1 Sep 2022

Viewed by 1447

Abstract

Due to the leaps of progress in the 5G telecommunication industry, commodity pricing and consumer choice are frequently subject to change and competition in the search for optimal supply and demand. We here utilize a two-stage extensive game with complete information to mathematically [...] Read more.

Due to the leaps of progress in the 5G telecommunication industry, commodity pricing and consumer choice are frequently subject to change and competition in the search for optimal supply and demand. We here utilize a two-stage extensive game with complete information to mathematically describe user-supplier interactions on a social network. Firstly, an example of how to apply our model in a practical 5G wireless system is shown. Then we build a prototype that offers multiple services to users and provides different outputs for suppliers, where in addition, the user and supplier quantities are independently distributed. Secondly, we then consider a scenario in which we wish to maximize social welfare and determine if there is a perfect answer. We seek the subgame perfect Nash equilibrium and show that it exists, and also show that when both sides reach it, social welfare likewise reaches its maximum. Finally, we provide numerical results that corroborate the efficacy of our approach on a practical example in the 5G background. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

17 pages, 1352 KiB

Open AccessArticle

A Graph-Cut-Based Approach to Community Detection in Networks

by Hyungsik Shin, Jeryang Park and Dongwoo Kang

Appl. Sci. 2022, 12(12), 6218; https://doi.org/10.3390/app12126218 - 18 Jun 2022

Cited by 5 | Viewed by 3272

Abstract

Networks can be used to model various aspects of our lives as well as relations among many real-world entities and objects. To detect a community structure in a network can enhance our understanding of the characteristics, properties, and inner workings of the network. [...] Read more.

Networks can be used to model various aspects of our lives as well as relations among many real-world entities and objects. To detect a community structure in a network can enhance our understanding of the characteristics, properties, and inner workings of the network. Therefore, there has been significant research on detecting and evaluating community structures in networks. Many fields, including social sciences, biology, engineering, computer science, and applied mathematics, have developed various methods for analyzing and detecting community structures in networks. In this paper, a new community detection algorithm, which repeats the process of dividing a community into two smaller communities by finding a minimum cut, is proposed. The proposed algorithm is applied to some example network data and shows fairly good community detection results with comparable modularity Q values. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

8 pages, 603 KiB

Open AccessArticle

Mining Algorithm of Relatively Important Nodes Based on Edge Importance Greedy Strategy

by Jie Li, Chunlin Yin, Hao Wang, Jian Wang and Na Zhao

Appl. Sci. 2022, 12(12), 6099; https://doi.org/10.3390/app12126099 - 15 Jun 2022

Cited by 5 | Viewed by 1817

Abstract

Relatively important node mining has always been an essential research topic in complex networks. Existing relatively important node mining algorithms suffer from high time complexity and poor accuracy. Therefore, this paper proposes an algorithm for mining relatively important nodes based on the edge [...] Read more.

Relatively important node mining has always been an essential research topic in complex networks. Existing relatively important node mining algorithms suffer from high time complexity and poor accuracy. Therefore, this paper proposes an algorithm for mining relatively important nodes based on the edge importance greedy strategy (EG). This method considers the importance of the edge to represent the degree of association between two connected nodes. Therefore, the greater the value of the connection between a node and a known important node, the more likely it is to be an important node. If the importance of the edges in an undirected network is measured, a greedy strategy can find important nodes. Compared with other relatively important node mining methods on real network data sets, such as SARS and 9/11, the experimental results show that the EG algorithm excels in both accuracy and applicability, which makes it a competitive algorithm in the mining of important nodes in a network. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

19 pages, 4019 KiB

Open AccessArticle

Dynamic Community Discovery Method Based on Phylogenetic Planted Partition in Temporal Networks

by Xiaoyang Liu, Nan Ding, Giacomo Fiumara, Pasquale De Meo and Annamaria Ficara

Appl. Sci. 2022, 12(8), 3795; https://doi.org/10.3390/app12083795 - 9 Apr 2022

Viewed by 1693

Abstract

As most of the community discovery methods are researched by static thought, some community discovery algorithms cannot represent the whole dynamic network change process efficiently. This paper proposes a novel dynamic community discovery method (Phylogenetic Planted Partition Model, PPPM) for phylogenetic evolution. Firstly, [...] Read more.

As most of the community discovery methods are researched by static thought, some community discovery algorithms cannot represent the whole dynamic network change process efficiently. This paper proposes a novel dynamic community discovery method (Phylogenetic Planted Partition Model, PPPM) for phylogenetic evolution. Firstly, the time dimension is introduced into the typical migration partition model, and all states are treated as variables, and the observation equation is constructed. Secondly, this paper takes the observation equation of the whole dynamic social network as the constraint between variables and the error function. Then, the quadratic form of the error function is minimized. Thirdly, the Levenberg–Marquardt (L–M) method is used to calculate the gradient of the error function, and the iteration is carried out. Finally, simulation experiments are carried out under the experimental environment of artificial networks and real networks. The experimental results show that: compared with FaceNet, SBM + MLE, CLBM, and PisCES, the proposed PPPM model improves accuracy by 5% and 3%, respectively. It is proven that the proposed PPPM method is robust, reasonable, and effective. This method can also be applied to the general social networking community discovery field. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

17 pages, 4768 KiB

Open AccessArticle

Deep-Learning Based Algorithm for Detecting Targets in Infrared Images

by Lifeng Yang, Shengzong Liu and Yiqi Zhao

Appl. Sci. 2022, 12(7), 3322; https://doi.org/10.3390/app12073322 - 24 Mar 2022

Cited by 10 | Viewed by 2906

Abstract

Infrared image target detection technology has been one of the essential research topics in computer vision, which has promoted the development of automatic driving, infrared guidance, infrared surveillance, and other fields. However, traditional target detection algorithms for infrared images have difficulty adapting to [...] Read more.

Infrared image target detection technology has been one of the essential research topics in computer vision, which has promoted the development of automatic driving, infrared guidance, infrared surveillance, and other fields. However, traditional target detection algorithms for infrared images have difficulty adapting to the target’s multiscale characteristics. In addition, the accuracy of the detection algorithm is significantly reduced when the target is occluded. The corresponding solutions are proposed in this paper to solve these two problems. The final experiments show that this paper’s infrared image target detection model improves significantly. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

14 pages, 977 KiB

Open AccessArticle

DDMF: A Method for Mining Relatively Important Nodes Based on Distance Distribution and Multi-Index Fusion

by Na Zhao, Qian Liu, Ming Jing, Jie Li, Zhidan Zhao and Jian Wang

Appl. Sci. 2022, 12(1), 522; https://doi.org/10.3390/app12010522 - 5 Jan 2022

Cited by 5 | Viewed by 2511

Abstract

In research on complex networks, mining relatively important nodes is a challenging and practical work. However, little research has been done on mining relatively important nodes in complex networks, and the existing relatively important node mining algorithms cannot take into account the indicators [...] Read more.

In research on complex networks, mining relatively important nodes is a challenging and practical work. However, little research has been done on mining relatively important nodes in complex networks, and the existing relatively important node mining algorithms cannot take into account the indicators of both precision and applicability. Aiming at the scarcity of relatively important node mining algorithms and the limitations of existing algorithms, this paper proposes a relatively important node mining method based on distance distribution and multi-index fusion (DDMF). First, the distance distribution of each node is generated according to the shortest path between nodes in the network; then, the cosine similarity, Euclidean distance and relative entropy are fused, and the entropy weight method is used to calculate the weights of different indexes; Finally, by calculating the relative importance score of nodes in the network, the relatively important nodes are mined. Through verification and analysis on real network datasets in different fields, the results show that the DDMF method outperforms other relatively important node mining algorithms in precision, recall, and AUC value. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

Review

Jump to: Research

17 pages, 1171 KiB

Open AccessEditor’s ChoiceReview

Comparing Vision Transformers and Convolutional Neural Networks for Image Classification: A Literature Review

by José Maurício, Inês Domingues and Jorge Bernardino

Appl. Sci. 2023, 13(9), 5521; https://doi.org/10.3390/app13095521 - 28 Apr 2023

Cited by 105 | Viewed by 25796

Abstract

Transformers are models that implement a mechanism of self-attention, individually weighting the importance of each part of the input data. Their use in image classification tasks is still somewhat limited since researchers have so far chosen Convolutional Neural Networks for image classification and [...] Read more.

Transformers are models that implement a mechanism of self-attention, individually weighting the importance of each part of the input data. Their use in image classification tasks is still somewhat limited since researchers have so far chosen Convolutional Neural Networks for image classification and transformers were more targeted to Natural Language Processing (NLP) tasks. Therefore, this paper presents a literature review that shows the differences between Vision Transformers (ViT) and Convolutional Neural Networks. The state of the art that used the two architectures for image classification was reviewed and an attempt was made to understand what factors may influence the performance of the two deep learning architectures based on the datasets used, image size, number of target classes (for the classification problems), hardware, and evaluated architectures and top results. The objective of this work is to identify which of the architectures is the best for image classification and under what conditions. This paper also describes the importance of the Multi-Head Attention mechanism for improving the performance of ViT in image classification. Full article

(This article belongs to the Special Issue Artificial Intelligence in Complex Networks)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence in Complex Networks

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (20 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI