There are many community detection algorithms for discovering communities in networks, but very few deal with networks that change structure. The SCAN (Structural Clustering Algorithm for Networks) algorithm is one of...There are many community detection algorithms for discovering communities in networks, but very few deal with networks that change structure. The SCAN (Structural Clustering Algorithm for Networks) algorithm is one of these algorithms that detect communities in static networks. To make SCAN more effective for the dynamic social networks that are continually changing their structure, we propose the algorithm DSCAN (Dynamic SCAN) which improves SCAN to allow it to update a local structure in less time than it would to run SCAN on the entire network. We also improve SCAN by removing the need for parameter tuning. DSCAN, tested on real world dynamic networks, performs faster and comparably to SCAN from one timestamp to another, relative to the size of the change. We also devised an approach to genetic algorithms for detecting communities in dynamic social networks, which performs well in speed and modularity.展开更多
Using Kripke semantics, we have identified and reduced an epistemic incompleteness in the metaphor commonly employed in Social Networks Analysis (SNA), which basically compares information flows with current flows in ...Using Kripke semantics, we have identified and reduced an epistemic incompleteness in the metaphor commonly employed in Social Networks Analysis (SNA), which basically compares information flows with current flows in advanced centrality measures. Our theoretical approach defines a new paradigm for the semantic and dynamic analysis of social networks including shared content. Based on our theoretical findings, we define a semantic and predictive model of dynamic SNA for Enterprises Social Networks (ESN), and experiment it on a real dataset.展开更多
Influence maximization is one fundamental and important problem to identify a set of most influential individuals to develop effective viral marketing strategies in social network. Most existing studies mainly focus o...Influence maximization is one fundamental and important problem to identify a set of most influential individuals to develop effective viral marketing strategies in social network. Most existing studies mainly focus on designing efficient algorithms or heuristics to find Top-K influential individuals for static network. However, when the network is evolving over time, the static algorithms have to be re-executed which will incur tremendous execution time. In this paper, an incremental algorithm DIM is proposed which can efficiently identify the Top-K influential individuals in dynamic social network based on the previous information instead of calculating from scratch. DIM is designed for Linear Threshold Model and it consists of two phases: initial seeding and seeds updating. In order to further reduce the running time, two pruning strategies are designed for the seeds updating phase. We carried out extensive experiments on real dynamic social network and the experimental results demonstrate that our algorithms could achieve good performance in terms of influence spread and significantly outperform those traditional static algorithms with respect to running time.展开更多
Identifying critical nodes or sets in large-scale networks is a fundamental scientific problem and one of the key research directions in the fields of data mining and network science when implementing network attacks,...Identifying critical nodes or sets in large-scale networks is a fundamental scientific problem and one of the key research directions in the fields of data mining and network science when implementing network attacks, defense, repair and control.Traditional methods usually begin from the centrality, node location or the impact on the largest connected component after node destruction, mainly based on the network structure.However, these algorithms do not consider network state changes.We applied a model that combines a random connectivity matrix and minimal low-dimensional structures to represent network connectivity.By using mean field theory and information entropy to calculate node activity,we calculated the overlap between the random parts and fixed low-dimensional parts to quantify the influence of node impact on network state changes and ranked them by importance.We applied this algorithm and the proposed importance algorithm to the overall analysis and stratified analysis of the C.elegans neural network.We observed a change in the critical entropy of the network state and by utilizing the proposed method we can calculate the nodes that indirectly affect muscle cells through neural layers.展开更多
As highly social animals,Indo-Pacific humpback dolphins(Sousa chinensis)exhibit community differentiation.Nevertheless,our understanding of the external and internal factors influencing these dynamics,as well as their...As highly social animals,Indo-Pacific humpback dolphins(Sousa chinensis)exhibit community differentiation.Nevertheless,our understanding of the external and internal factors influencing these dynamics,as well as their spatiotemporal variations,is still limited.In the present study,variations in the social structure of an endangered Indo-Pacific humpback dolphin population in Xiamen Bay,China,were monitored over two distinct periods(2007–2010 and 2017–2019)to analyze the effects of habitat utilization and the composition of individuals within the population.In both periods,the population demonstrated a strikingly similar pattern of social differentiation,characterized by the division of individuals into two main clusters and one small cluster.Spatially,the two primary clusters occupied the eastern and western waters,respectively,although the core distribution area of the eastern cluster shifted further eastward between the two periods.Despite this distribution shift,the temporal stability of the social structure and inter-associations within the eastern cluster remained unaffected.A subset of 16individuals observed in both periods,comprising 51.6%and 43.2%of the population in each respective period,emerged as a foundational element of the social structure and may be responsible for sustaining social structure stability,especially during the 2007–2010 period.These observations suggest that the composition of dominant individuals,an internal factor,had a more substantial influence on the formation of the social network than changes in habitat use,an external factor.Consequently,the study proposes distinct conservation measures tailored to each of the two main clusters.展开更多
We investigate the impact of pairwise and group interactions on the spread of epidemics through an activity-driven model based on time-dependent networks.The effects of pairwise/group interaction proportion and pairwi...We investigate the impact of pairwise and group interactions on the spread of epidemics through an activity-driven model based on time-dependent networks.The effects of pairwise/group interaction proportion and pairwise/group interaction intensity are explored by extensive simulation and theoretical analysis.It is demonstrated that altering the group interaction proportion can either hinder or enhance the spread of epidemics,depending on the relative social intensity of group and pairwise interactions.As the group interaction proportion decreases,the impact of reducing group social intensity diminishes.The ratio of group and pairwise social intensity can affect the effect of group interaction proportion on the scale of infection.A weak heterogeneous activity distribution can raise the epidemic threshold,and reduce the scale of infection.These results benefit the design of epidemic control strategy.展开更多
In many engineering networks, only a part of target state variables are required to be estimated.On the other hand,multi-layer complex network exists widely in practical situations.In this paper, the state estimation ...In many engineering networks, only a part of target state variables are required to be estimated.On the other hand,multi-layer complex network exists widely in practical situations.In this paper, the state estimation of target state variables in multi-layer complex dynamical networks with nonlinear node dynamics is studied.A suitable functional state observer is constructed with the limited measurement.The parameters of the designed functional observer are obtained from the algebraic method and the stability of the functional observer is proven by the Lyapunov theorem.Some necessary conditions that need to be satisfied for the design of the functional state observer are obtained.Different from previous studies, in the multi-layer complex dynamical network with nonlinear node dynamics, the proposed method can estimate the state of target variables on some layers directly instead of estimating all the individual states.Thus, it can greatly reduce the placement of observers and computational cost.Numerical simulations with the three-layer complex dynamical network composed of three-dimensional nonlinear dynamical nodes are developed to verify the effectiveness of the method.展开更多
Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social life.Existing social robot detection methods based on graph ...Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social life.Existing social robot detection methods based on graph neural networks suffer from the problem of many social network nodes and complex relationships,which makes it difficult to accurately describe the difference between the topological relations of nodes,resulting in low detection accuracy of social robots.This paper proposes a social robot detection method with the use of an improved neural network.First,social relationship subgraphs are constructed by leveraging the user’s social network to disentangle intricate social relationships effectively.Then,a linear modulated graph attention residual network model is devised to extract the node and network topology features of the social relation subgraph,thereby generating comprehensive social relation subgraph features,and the feature-wise linear modulation module of the model can better learn the differences between the nodes.Next,user text content and behavioral gene sequences are extracted to construct social behavioral features combined with the social relationship subgraph features.Finally,social robots can be more accurately identified by combining user behavioral and relationship features.By carrying out experimental studies based on the publicly available datasets TwiBot-20 and Cresci-15,the suggested method’s detection accuracies can achieve 86.73%and 97.86%,respectively.Compared with the existing mainstream approaches,the accuracy of the proposed method is 2.2%and 1.35%higher on the two datasets.The results show that the method proposed in this paper can effectively detect social robots and maintain a healthy ecological environment of social networks.展开更多
The influence maximization problem aims to select a small set of influential nodes, termed a seed set, to maximize their influence coverage in social networks. Although the methods that are based on a greedy strategy ...The influence maximization problem aims to select a small set of influential nodes, termed a seed set, to maximize their influence coverage in social networks. Although the methods that are based on a greedy strategy can obtain good accuracy, they come at the cost of enormous computational time, and are therefore not applicable to practical scenarios in large-scale networks. In addition, the centrality heuristic algorithms that are based on network topology can be completed in relatively less time. However, they tend to fail to achieve satisfactory results because of drawbacks such as overlapped influence spread. In this work, we propose a discrete two-stage metaheuristic optimization combining quantum-behaved particle swarm optimization with Lévy flight to identify a set of the most influential spreaders. According to the framework,first, the particles in the population are tasked to conduct an exploration in the global solution space to eventually converge to an acceptable solution through the crossover and replacement operations. Second, the Lévy flight mechanism is used to perform a wandering walk on the optimal candidate solution in the population to exploit the potentially unidentified influential nodes in the network. Experiments on six real-world social networks show that the proposed algorithm achieves more satisfactory results when compared to other well-known algorithms.展开更多
The present study addresses the problem of fault estimation for a specific class of nonlinear time-varying complex networks,utilizing an unknown-input-observer approach within the framework of dynamic event-triggered ...The present study addresses the problem of fault estimation for a specific class of nonlinear time-varying complex networks,utilizing an unknown-input-observer approach within the framework of dynamic event-triggered mechanism(DETM).In order to optimize communication resource utilization,the DETM is employed to determine whether the current measurement data should be transmitted to the estimator or not.To guarantee a satisfactory estimation performance for the fault signal,an unknown-input-observer-based estimator is constructed to decouple the estimation error dynamics from the influence of fault signals.The aim of this paper is to find the suitable estimator parameters under the effects of DETM such that both the state estimates and fault estimates are confined within two sets of closed ellipsoid domains.The techniques of recursive matrix inequality are applied to derive sufficient conditions for the existence of the desired estimator,ensuring that the specified performance requirements are met under certain conditions.Then,the estimator gains are derived by minimizing the ellipsoid domain in the sense of trace and a recursive estimator parameter design algorithm is then provided.Finally,a numerical example is conducted to demonstrate the effectiveness of the designed estimator.展开更多
Influence maximization of temporal social networks(IMT)is a problem that aims to find the most influential set of nodes in the temporal network so that their information can be the most widely spread.To solve the IMT ...Influence maximization of temporal social networks(IMT)is a problem that aims to find the most influential set of nodes in the temporal network so that their information can be the most widely spread.To solve the IMT problem,we propose an influence maximization algorithm based on an improved K-shell method,namely improved K-shell in temporal social networks(KT).The algorithm takes into account the global and local structures of temporal social networks.First,to obtain the kernel value Ks of each node,in the global scope,it layers the network according to the temporal characteristic of nodes by improving the K-shell method.Then,in the local scope,the calculation method of comprehensive degree is proposed to weigh the influence of nodes.Finally,the node with the highest comprehensive degree in each core layer is selected as the seed.However,the seed selection strategy of KT can easily lose some influential nodes.Thus,by optimizing the seed selection strategy,this paper proposes an efficient heuristic algorithm called improved K-shell in temporal social networks for influence maximization(KTIM).According to the hierarchical distribution of cores,the algorithm adds nodes near the central core to the candidate seed set.It then searches for seeds in the candidate seed set according to the comprehensive degree.Experiments showthatKTIMis close to the best performing improved method for influence maximization of temporal graph(IMIT)algorithm in terms of effectiveness,but runs at least an order of magnitude faster than it.Therefore,considering the effectiveness and efficiency simultaneously in temporal social networks,the KTIM algorithm works better than other baseline algorithms.展开更多
The public is increasingly using social media platforms such as Twitter and Facebook to express their views on a variety of topics.As a result,social media has emerged as the most effective and largest open source for...The public is increasingly using social media platforms such as Twitter and Facebook to express their views on a variety of topics.As a result,social media has emerged as the most effective and largest open source for obtaining public opinion.Single node computational methods are inefficient for sentiment analysis on such large datasets.Supercomputers or parallel or distributed proces-sing are two options for dealing with such large amounts of data.Most parallel programming frameworks,such as MPI(Message Processing Interface),are dif-ficult to use and scale in environments where supercomputers are expensive.Using the Apache Spark Parallel Model,this proposed work presents a scalable system for sentiment analysis on Twitter.A Spark-based Naive Bayes training technique is suggested for this purpose;unlike prior research,this algorithm does not need any disk access.Millions of tweets have been classified using the trained model.Experiments with various-sized clusters reveal that the suggested strategy is extremely scalable and cost-effective for larger data sets.It is nearly 12 times quicker than the Map Reduce-based model and nearly 21 times faster than the Naive Bayes Classifier in Apache Mahout.To evaluate the framework’s scalabil-ity,we gathered a large training corpus from Twitter.The accuracy of the classi-fier trained with this new dataset was more than 80%.展开更多
One of the major factors inhibiting the construction of deep underground projects is the risk posed by rockbursts.A study was conducted on the access tunnel of the Shuangjiangkou hydropower station to determine the ev...One of the major factors inhibiting the construction of deep underground projects is the risk posed by rockbursts.A study was conducted on the access tunnel of the Shuangjiangkou hydropower station to determine the evolutionary mechanism of microfractures within the surrounding rock mass during rockburst development and develop a rockburst warning model.The study area was chosen through the combination of field studies with an analysis of the spatial and temporal distribution of microseismic(MS)events.The moment tensor inversion method was adopted to study rockburst mechanism,and a dynamic Bayesian network(DBN)was applied to investigating the sensitivity of MS source parameters for rockburst warnings.A MS multivariable rockburst warning model was proposed and validated using two case studies.The results indicate that fractures in the surrounding rock mass during the development of strain-structure rockbursts initially show shear failure and are then followed by tensile failure.The effectiveness of the DBN-based rockburst warning model was demonstrated using self-validation and K-fold cross-validation.Moment magnitude and source radius are the most sensitive factors based on an investigation of the influence on the parent and child nodes in the model,which can serve as important standards for rockburst warnings.The proposed rockburst warning model was found to be effective when applied to two actual projects.展开更多
The dynamic wireless communication network is a complex network that needs to consider various influence factors including communication devices,radio propagation,network topology,and dynamic behaviors.Existing works ...The dynamic wireless communication network is a complex network that needs to consider various influence factors including communication devices,radio propagation,network topology,and dynamic behaviors.Existing works focus on suggesting simplified reliability analysis methods for these dynamic networks.As one of the most popular modeling methodologies,the dynamic Bayesian network(DBN)is proposed.However,it is insufficient for the wireless communication network which contains temporal and non-temporal events.To this end,we present a modeling methodology for a generalized continuous time Bayesian network(CTBN)with a 2-state conditional probability table(CPT).Moreover,a comprehensive reliability analysis method for communication devices and radio propagation is suggested.The proposed methodology is verified by a reliability analysis of a real wireless communication network.展开更多
Influence Maximization(IM)aims to select a seed set of size k in a social network so that information can be spread most widely under a specific information propagation model through this set of nodes.However,most exi...Influence Maximization(IM)aims to select a seed set of size k in a social network so that information can be spread most widely under a specific information propagation model through this set of nodes.However,most existing studies on the IM problem focus on static social network features,while neglecting the features of temporal social networks.To bridge this gap,we focus on node features reflected by their historical interaction behavior in temporal social networks,i.e.,interaction attributes and self-similarity,and incorporate them into the influence maximization algorithm and information propagation model.Firstly,we propose a node feature-aware voting algorithm,called ISVoteRank,for seed nodes selection.Specifically,before voting,the algorithm sets the initial voting ability of nodes in a personalized manner by combining their features.During the voting process,voting weights are set based on the interaction strength between nodes,allowing nodes to vote at different extents and subsequently weakening their voting ability accordingly.The process concludes by selecting the top k nodes with the highest voting scores as seeds,avoiding the inefficiency of iterative seed selection in traditional voting-based algorithms.Secondly,we extend the Independent Cascade(IC)model and propose the Dynamic Independent Cascade(DIC)model,which aims to capture the dynamic features in the information propagation process by combining node features.Finally,experiments demonstrate that the ISVoteRank algorithm has been improved in both effectiveness and efficiency compared to baseline methods,and the influence spread through the DIC model is improved compared to the IC model.展开更多
This paper proposes a deep neural network(DNN)approach for detecting fake profiles in social networks.The DNN model is trained on a large dataset of real and fake profiles and is designed to learn complex features and...This paper proposes a deep neural network(DNN)approach for detecting fake profiles in social networks.The DNN model is trained on a large dataset of real and fake profiles and is designed to learn complex features and patterns that distinguish between the two types of profiles.In addition,the present research aims to determine the minimum set of profile data required for recognizing fake profiles on Facebook and propose the deep convolutional neural network method for fake accounts detection on social networks,which has been developed using 16 features based on content-based and profilebased features.The results demonstrated that the proposed method could detect fake profiles with an accuracy of 99.4%,equivalent to the achieved findings based on bigger data sets and more extensive profile information.The results were obtained with the minimum available profile data.In addition,in comparison with the other methods that use the same amount and kind of data,the proposed deep neural network gives an increase in accuracy of roughly 14%.The proposed model outperforms existing methods,achieving high accuracy and F1 score in identifying fake profiles.The associated findings indicate that the proposed model attained an average accuracy of 99%while considering two distinct scenarios:one with a single theme and another with a miscellaneous one.The results demonstrate the potential of DNNs in addressing the challenging problem of detecting fake profiles,which has significant implications for maintaining the authenticity and trustworthiness of online social networks.展开更多
Recent developments on Internet and social networking have led to the growth of aggressive language and hate speech.Online provocation,abuses,and attacks are widely termed cyberbullying(CB).The massive quantity of use...Recent developments on Internet and social networking have led to the growth of aggressive language and hate speech.Online provocation,abuses,and attacks are widely termed cyberbullying(CB).The massive quantity of user generated content makes it difficult to recognize CB.Current advancements in machine learning(ML),deep learning(DL),and natural language processing(NLP)tools enable to detect and classify CB in social networks.In this view,this study introduces a spotted hyena optimizer with deep learning driven cybersecurity(SHODLCS)model for OSN.The presented SHODLCS model intends to accomplish cybersecurity from the identification of CB in the OSN.For achieving this,the SHODLCS model involves data pre-processing and TF-IDF based feature extraction.In addition,the cascaded recurrent neural network(CRNN)model is applied for the identification and classification of CB.Finally,the SHO algorithm is exploited to optimally tune the hyperparameters involved in the CRNN model and thereby results in enhanced classifier performance.The experimental validation of the SHODLCS model on the benchmark dataset portrayed the better outcomes of the SHODLCS model over the recent approaches.展开更多
Dynamics is a key issue about understanding recurrent neural networks(RNNs).Because of the complexity,the problem still remains unanswered in spite of many important progresses.Echo state network(ESN)is a simple appro...Dynamics is a key issue about understanding recurrent neural networks(RNNs).Because of the complexity,the problem still remains unanswered in spite of many important progresses.Echo state network(ESN)is a simple approach to design RNNs.It is possible to investigate ESNs’dynamics deeply.However,most of dynamic studies have mainly concentrated on the shallow ESNs and seldom of them explain the dynamics of the deep ones.Therefore,this paper investigates the dynamics of four typical ESNs under a unified theoretical framework.These ESNs contain both the shallow versions and the deep ones.This investigation is helpful to clarify the dynamics of ESNs in a general sense.Also,the short-term memory(STM)of different ESNs is analyzed,which is closely related to the dynamics.This analysis is helpful to determine the hyper-parameters of ESNs for given problems.In addition,the problem-solving abilities of ESNs are investigated through modeling two time series tasks.It further explains the influence of the dynamics on ESN’s performance.展开更多
The structure and function of brain networks have been altered in patients with end-stage renal disease(ESRD).Manifold regularization(MR)only considers the pairing relationship between two brain regions and cannot rep...The structure and function of brain networks have been altered in patients with end-stage renal disease(ESRD).Manifold regularization(MR)only considers the pairing relationship between two brain regions and cannot represent functional interactions or higher-order relationships between multiple brain regions.To solve this issue,we developed a method to construct a dynamic brain functional network(DBFN)based on dynamic hypergraph MR(DHMR)and applied it to the classification of ESRD associated with mild cognitive impairment(ESRDaMCI).The construction of DBFN with Pearson’s correlation(PC)was transformed into an optimization model.Node convolution and hyperedge convolution superposition were adopted to dynamically modify the hypergraph structure,and then got the dynamic hypergraph to form the manifold regular terms of the dynamic hypergraph.The DHMR and L_(1) norm regularization were introduced into the PC-based optimization model to obtain the final DHMR-based DBFN(DDBFN).Experiment results demonstrated the validity of the DDBFN method by comparing the classification results with several related brain functional network construction methods.Our work not only improves better classification performance but also reveals the discriminative regions of ESRDaMCI,providing a reference for clinical research and auxiliary diagnosis of concomitant cognitive impairments.展开更多
Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and ...Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.展开更多
文摘There are many community detection algorithms for discovering communities in networks, but very few deal with networks that change structure. The SCAN (Structural Clustering Algorithm for Networks) algorithm is one of these algorithms that detect communities in static networks. To make SCAN more effective for the dynamic social networks that are continually changing their structure, we propose the algorithm DSCAN (Dynamic SCAN) which improves SCAN to allow it to update a local structure in less time than it would to run SCAN on the entire network. We also improve SCAN by removing the need for parameter tuning. DSCAN, tested on real world dynamic networks, performs faster and comparably to SCAN from one timestamp to another, relative to the size of the change. We also devised an approach to genetic algorithms for detecting communities in dynamic social networks, which performs well in speed and modularity.
文摘Using Kripke semantics, we have identified and reduced an epistemic incompleteness in the metaphor commonly employed in Social Networks Analysis (SNA), which basically compares information flows with current flows in advanced centrality measures. Our theoretical approach defines a new paradigm for the semantic and dynamic analysis of social networks including shared content. Based on our theoretical findings, we define a semantic and predictive model of dynamic SNA for Enterprises Social Networks (ESN), and experiment it on a real dataset.
文摘Influence maximization is one fundamental and important problem to identify a set of most influential individuals to develop effective viral marketing strategies in social network. Most existing studies mainly focus on designing efficient algorithms or heuristics to find Top-K influential individuals for static network. However, when the network is evolving over time, the static algorithms have to be re-executed which will incur tremendous execution time. In this paper, an incremental algorithm DIM is proposed which can efficiently identify the Top-K influential individuals in dynamic social network based on the previous information instead of calculating from scratch. DIM is designed for Linear Threshold Model and it consists of two phases: initial seeding and seeds updating. In order to further reduce the running time, two pruning strategies are designed for the seeds updating phase. We carried out extensive experiments on real dynamic social network and the experimental results demonstrate that our algorithms could achieve good performance in terms of influence spread and significantly outperform those traditional static algorithms with respect to running time.
基金Project supported by the National Natural Science Foundation of China (Grant Nos.72071153 and 72231008)Laboratory of Science and Technology on Integrated Logistics Support Foundation (Grant No.6142003190102)the Natural Science Foundation of Shannxi Province (Grant No.2020JM486)。
文摘Identifying critical nodes or sets in large-scale networks is a fundamental scientific problem and one of the key research directions in the fields of data mining and network science when implementing network attacks, defense, repair and control.Traditional methods usually begin from the centrality, node location or the impact on the largest connected component after node destruction, mainly based on the network structure.However, these algorithms do not consider network state changes.We applied a model that combines a random connectivity matrix and minimal low-dimensional structures to represent network connectivity.By using mean field theory and information entropy to calculate node activity,we calculated the overlap between the random parts and fixed low-dimensional parts to quantify the influence of node impact on network state changes and ranked them by importance.We applied this algorithm and the proposed importance algorithm to the overall analysis and stratified analysis of the C.elegans neural network.We observed a change in the critical entropy of the network state and by utilizing the proposed method we can calculate the nodes that indirectly affect muscle cells through neural layers.
基金supported by the National Natural Science Foundation of China (32030011,31630071)National Key Research and Development Program of China (2022YFF1301600)Priority Academic Program Development of Jiangsu Higher Education Institutions。
文摘As highly social animals,Indo-Pacific humpback dolphins(Sousa chinensis)exhibit community differentiation.Nevertheless,our understanding of the external and internal factors influencing these dynamics,as well as their spatiotemporal variations,is still limited.In the present study,variations in the social structure of an endangered Indo-Pacific humpback dolphin population in Xiamen Bay,China,were monitored over two distinct periods(2007–2010 and 2017–2019)to analyze the effects of habitat utilization and the composition of individuals within the population.In both periods,the population demonstrated a strikingly similar pattern of social differentiation,characterized by the division of individuals into two main clusters and one small cluster.Spatially,the two primary clusters occupied the eastern and western waters,respectively,although the core distribution area of the eastern cluster shifted further eastward between the two periods.Despite this distribution shift,the temporal stability of the social structure and inter-associations within the eastern cluster remained unaffected.A subset of 16individuals observed in both periods,comprising 51.6%and 43.2%of the population in each respective period,emerged as a foundational element of the social structure and may be responsible for sustaining social structure stability,especially during the 2007–2010 period.These observations suggest that the composition of dominant individuals,an internal factor,had a more substantial influence on the formation of the social network than changes in habitat use,an external factor.Consequently,the study proposes distinct conservation measures tailored to each of the two main clusters.
基金This work was supported by the National Natural Science Foundation of China(Grant No.12072340)the China Postdoctoral Science Foundation(Grant No.2022M720727)the Jiangsu Funding Program for Excellent Postdoctoral Talent(Grant No.2022ZB130).
文摘We investigate the impact of pairwise and group interactions on the spread of epidemics through an activity-driven model based on time-dependent networks.The effects of pairwise/group interaction proportion and pairwise/group interaction intensity are explored by extensive simulation and theoretical analysis.It is demonstrated that altering the group interaction proportion can either hinder or enhance the spread of epidemics,depending on the relative social intensity of group and pairwise interactions.As the group interaction proportion decreases,the impact of reducing group social intensity diminishes.The ratio of group and pairwise social intensity can affect the effect of group interaction proportion on the scale of infection.A weak heterogeneous activity distribution can raise the epidemic threshold,and reduce the scale of infection.These results benefit the design of epidemic control strategy.
基金Project supported by the National Natural Science Foundation of China (Grant Nos.62373197 and 61873326)。
文摘In many engineering networks, only a part of target state variables are required to be estimated.On the other hand,multi-layer complex network exists widely in practical situations.In this paper, the state estimation of target state variables in multi-layer complex dynamical networks with nonlinear node dynamics is studied.A suitable functional state observer is constructed with the limited measurement.The parameters of the designed functional observer are obtained from the algebraic method and the stability of the functional observer is proven by the Lyapunov theorem.Some necessary conditions that need to be satisfied for the design of the functional state observer are obtained.Different from previous studies, in the multi-layer complex dynamical network with nonlinear node dynamics, the proposed method can estimate the state of target variables on some layers directly instead of estimating all the individual states.Thus, it can greatly reduce the placement of observers and computational cost.Numerical simulations with the three-layer complex dynamical network composed of three-dimensional nonlinear dynamical nodes are developed to verify the effectiveness of the method.
基金This work was supported in part by the National Natural Science Foundation of China under Grants 62273272,62303375 and 61873277in part by the Key Research and Development Program of Shaanxi Province under Grant 2023-YBGY-243+2 种基金in part by the Natural Science Foundation of Shaanxi Province under Grants 2022JQ-606 and 2020-JQ758in part by the Research Plan of Department of Education of Shaanxi Province under Grant 21JK0752in part by the Youth Innovation Team of Shaanxi Universities.
文摘Social robot accounts controlled by artificial intelligence or humans are active in social networks,bringing negative impacts to network security and social life.Existing social robot detection methods based on graph neural networks suffer from the problem of many social network nodes and complex relationships,which makes it difficult to accurately describe the difference between the topological relations of nodes,resulting in low detection accuracy of social robots.This paper proposes a social robot detection method with the use of an improved neural network.First,social relationship subgraphs are constructed by leveraging the user’s social network to disentangle intricate social relationships effectively.Then,a linear modulated graph attention residual network model is devised to extract the node and network topology features of the social relation subgraph,thereby generating comprehensive social relation subgraph features,and the feature-wise linear modulation module of the model can better learn the differences between the nodes.Next,user text content and behavioral gene sequences are extracted to construct social behavioral features combined with the social relationship subgraph features.Finally,social robots can be more accurately identified by combining user behavioral and relationship features.By carrying out experimental studies based on the publicly available datasets TwiBot-20 and Cresci-15,the suggested method’s detection accuracies can achieve 86.73%and 97.86%,respectively.Compared with the existing mainstream approaches,the accuracy of the proposed method is 2.2%and 1.35%higher on the two datasets.The results show that the method proposed in this paper can effectively detect social robots and maintain a healthy ecological environment of social networks.
基金Project supported by the Zhejiang Provincial Natural Science Foundation (Grant No.LQ20F020011)the Gansu Provincial Foundation for Distinguished Young Scholars (Grant No.23JRRA766)+1 种基金the National Natural Science Foundation of China (Grant No.62162040)the National Key Research and Development Program of China (Grant No.2020YFB1713600)。
文摘The influence maximization problem aims to select a small set of influential nodes, termed a seed set, to maximize their influence coverage in social networks. Although the methods that are based on a greedy strategy can obtain good accuracy, they come at the cost of enormous computational time, and are therefore not applicable to practical scenarios in large-scale networks. In addition, the centrality heuristic algorithms that are based on network topology can be completed in relatively less time. However, they tend to fail to achieve satisfactory results because of drawbacks such as overlapped influence spread. In this work, we propose a discrete two-stage metaheuristic optimization combining quantum-behaved particle swarm optimization with Lévy flight to identify a set of the most influential spreaders. According to the framework,first, the particles in the population are tasked to conduct an exploration in the global solution space to eventually converge to an acceptable solution through the crossover and replacement operations. Second, the Lévy flight mechanism is used to perform a wandering walk on the optimal candidate solution in the population to exploit the potentially unidentified influential nodes in the network. Experiments on six real-world social networks show that the proposed algorithm achieves more satisfactory results when compared to other well-known algorithms.
基金supported in part by the National Natural Science Foundation of China (62233012,62273087)the Research Fund for the Taishan Scholar Project of Shandong Province of Chinathe Shanghai Pujiang Program of China (22PJ1400400)。
文摘The present study addresses the problem of fault estimation for a specific class of nonlinear time-varying complex networks,utilizing an unknown-input-observer approach within the framework of dynamic event-triggered mechanism(DETM).In order to optimize communication resource utilization,the DETM is employed to determine whether the current measurement data should be transmitted to the estimator or not.To guarantee a satisfactory estimation performance for the fault signal,an unknown-input-observer-based estimator is constructed to decouple the estimation error dynamics from the influence of fault signals.The aim of this paper is to find the suitable estimator parameters under the effects of DETM such that both the state estimates and fault estimates are confined within two sets of closed ellipsoid domains.The techniques of recursive matrix inequality are applied to derive sufficient conditions for the existence of the desired estimator,ensuring that the specified performance requirements are met under certain conditions.Then,the estimator gains are derived by minimizing the ellipsoid domain in the sense of trace and a recursive estimator parameter design algorithm is then provided.Finally,a numerical example is conducted to demonstrate the effectiveness of the designed estimator.
基金Thiswork is supported by theYouth Science and Technology Innovation Personnel Training Project of Heilongjiang(No.UNPYSCT-2020072)the FundamentalResearch Funds for the Universities of Heilongjiang(Nos.145109217,135509234)+1 种基金the Education Science Fourteenth Five-Year Plan 2021 Project of Heilongjiang(No.GJB1421344)the Innovative Research Projects for Postgraduates of Qiqihar University(No.YJSCX2022048).
文摘Influence maximization of temporal social networks(IMT)is a problem that aims to find the most influential set of nodes in the temporal network so that their information can be the most widely spread.To solve the IMT problem,we propose an influence maximization algorithm based on an improved K-shell method,namely improved K-shell in temporal social networks(KT).The algorithm takes into account the global and local structures of temporal social networks.First,to obtain the kernel value Ks of each node,in the global scope,it layers the network according to the temporal characteristic of nodes by improving the K-shell method.Then,in the local scope,the calculation method of comprehensive degree is proposed to weigh the influence of nodes.Finally,the node with the highest comprehensive degree in each core layer is selected as the seed.However,the seed selection strategy of KT can easily lose some influential nodes.Thus,by optimizing the seed selection strategy,this paper proposes an efficient heuristic algorithm called improved K-shell in temporal social networks for influence maximization(KTIM).According to the hierarchical distribution of cores,the algorithm adds nodes near the central core to the candidate seed set.It then searches for seeds in the candidate seed set according to the comprehensive degree.Experiments showthatKTIMis close to the best performing improved method for influence maximization of temporal graph(IMIT)algorithm in terms of effectiveness,but runs at least an order of magnitude faster than it.Therefore,considering the effectiveness and efficiency simultaneously in temporal social networks,the KTIM algorithm works better than other baseline algorithms.
文摘The public is increasingly using social media platforms such as Twitter and Facebook to express their views on a variety of topics.As a result,social media has emerged as the most effective and largest open source for obtaining public opinion.Single node computational methods are inefficient for sentiment analysis on such large datasets.Supercomputers or parallel or distributed proces-sing are two options for dealing with such large amounts of data.Most parallel programming frameworks,such as MPI(Message Processing Interface),are dif-ficult to use and scale in environments where supercomputers are expensive.Using the Apache Spark Parallel Model,this proposed work presents a scalable system for sentiment analysis on Twitter.A Spark-based Naive Bayes training technique is suggested for this purpose;unlike prior research,this algorithm does not need any disk access.Millions of tweets have been classified using the trained model.Experiments with various-sized clusters reveal that the suggested strategy is extremely scalable and cost-effective for larger data sets.It is nearly 12 times quicker than the Map Reduce-based model and nearly 21 times faster than the Naive Bayes Classifier in Apache Mahout.To evaluate the framework’s scalabil-ity,we gathered a large training corpus from Twitter.The accuracy of the classi-fier trained with this new dataset was more than 80%.
基金funding support from the National Natural Science Foundation of China(Grant No.42177143 and 51809221)the Science Foundation for Distinguished Young Scholars of Sichuan Province,China(Grant No.2020JDJQ0011).
文摘One of the major factors inhibiting the construction of deep underground projects is the risk posed by rockbursts.A study was conducted on the access tunnel of the Shuangjiangkou hydropower station to determine the evolutionary mechanism of microfractures within the surrounding rock mass during rockburst development and develop a rockburst warning model.The study area was chosen through the combination of field studies with an analysis of the spatial and temporal distribution of microseismic(MS)events.The moment tensor inversion method was adopted to study rockburst mechanism,and a dynamic Bayesian network(DBN)was applied to investigating the sensitivity of MS source parameters for rockburst warnings.A MS multivariable rockburst warning model was proposed and validated using two case studies.The results indicate that fractures in the surrounding rock mass during the development of strain-structure rockbursts initially show shear failure and are then followed by tensile failure.The effectiveness of the DBN-based rockburst warning model was demonstrated using self-validation and K-fold cross-validation.Moment magnitude and source radius are the most sensitive factors based on an investigation of the influence on the parent and child nodes in the model,which can serve as important standards for rockburst warnings.The proposed rockburst warning model was found to be effective when applied to two actual projects.
基金supported by the Chinese Universities Scientific Fund(ZYGX2020ZB022)the National Natural Science Foundation of China(51775090).
文摘The dynamic wireless communication network is a complex network that needs to consider various influence factors including communication devices,radio propagation,network topology,and dynamic behaviors.Existing works focus on suggesting simplified reliability analysis methods for these dynamic networks.As one of the most popular modeling methodologies,the dynamic Bayesian network(DBN)is proposed.However,it is insufficient for the wireless communication network which contains temporal and non-temporal events.To this end,we present a modeling methodology for a generalized continuous time Bayesian network(CTBN)with a 2-state conditional probability table(CPT).Moreover,a comprehensive reliability analysis method for communication devices and radio propagation is suggested.The proposed methodology is verified by a reliability analysis of a real wireless communication network.
基金supported by the Fundamental Research Funds for the Universities of Heilongjiang(Nos.145109217,135509234)the Youth Science and Technology Innovation Personnel Training Project of Heilongjiang(No.UNPYSCT-2020072)the Innovative Research Projects for Postgraduates of Qiqihar University(No.YJSCX2022048).
文摘Influence Maximization(IM)aims to select a seed set of size k in a social network so that information can be spread most widely under a specific information propagation model through this set of nodes.However,most existing studies on the IM problem focus on static social network features,while neglecting the features of temporal social networks.To bridge this gap,we focus on node features reflected by their historical interaction behavior in temporal social networks,i.e.,interaction attributes and self-similarity,and incorporate them into the influence maximization algorithm and information propagation model.Firstly,we propose a node feature-aware voting algorithm,called ISVoteRank,for seed nodes selection.Specifically,before voting,the algorithm sets the initial voting ability of nodes in a personalized manner by combining their features.During the voting process,voting weights are set based on the interaction strength between nodes,allowing nodes to vote at different extents and subsequently weakening their voting ability accordingly.The process concludes by selecting the top k nodes with the highest voting scores as seeds,avoiding the inefficiency of iterative seed selection in traditional voting-based algorithms.Secondly,we extend the Independent Cascade(IC)model and propose the Dynamic Independent Cascade(DIC)model,which aims to capture the dynamic features in the information propagation process by combining node features.Finally,experiments demonstrate that the ISVoteRank algorithm has been improved in both effectiveness and efficiency compared to baseline methods,and the influence spread through the DIC model is improved compared to the IC model.
文摘This paper proposes a deep neural network(DNN)approach for detecting fake profiles in social networks.The DNN model is trained on a large dataset of real and fake profiles and is designed to learn complex features and patterns that distinguish between the two types of profiles.In addition,the present research aims to determine the minimum set of profile data required for recognizing fake profiles on Facebook and propose the deep convolutional neural network method for fake accounts detection on social networks,which has been developed using 16 features based on content-based and profilebased features.The results demonstrated that the proposed method could detect fake profiles with an accuracy of 99.4%,equivalent to the achieved findings based on bigger data sets and more extensive profile information.The results were obtained with the minimum available profile data.In addition,in comparison with the other methods that use the same amount and kind of data,the proposed deep neural network gives an increase in accuracy of roughly 14%.The proposed model outperforms existing methods,achieving high accuracy and F1 score in identifying fake profiles.The associated findings indicate that the proposed model attained an average accuracy of 99%while considering two distinct scenarios:one with a single theme and another with a miscellaneous one.The results demonstrate the potential of DNNs in addressing the challenging problem of detecting fake profiles,which has significant implications for maintaining the authenticity and trustworthiness of online social networks.
基金Princess Nourah bint Abdulrahman University Researchers Supporting Project number(PNURSP2022R140)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.The authors would like to thank the Deanship of Scientific Research at Umm Al-Qura University for supporting this work by Grant Code:22UQU4310373DSR15.
文摘Recent developments on Internet and social networking have led to the growth of aggressive language and hate speech.Online provocation,abuses,and attacks are widely termed cyberbullying(CB).The massive quantity of user generated content makes it difficult to recognize CB.Current advancements in machine learning(ML),deep learning(DL),and natural language processing(NLP)tools enable to detect and classify CB in social networks.In this view,this study introduces a spotted hyena optimizer with deep learning driven cybersecurity(SHODLCS)model for OSN.The presented SHODLCS model intends to accomplish cybersecurity from the identification of CB in the OSN.For achieving this,the SHODLCS model involves data pre-processing and TF-IDF based feature extraction.In addition,the cascaded recurrent neural network(CRNN)model is applied for the identification and classification of CB.Finally,the SHO algorithm is exploited to optimally tune the hyperparameters involved in the CRNN model and thereby results in enhanced classifier performance.The experimental validation of the SHODLCS model on the benchmark dataset portrayed the better outcomes of the SHODLCS model over the recent approaches.
基金Sponsored by the Shandong Provincial Natural Science Foundation(Grant No.ZR2021MF105).
文摘Dynamics is a key issue about understanding recurrent neural networks(RNNs).Because of the complexity,the problem still remains unanswered in spite of many important progresses.Echo state network(ESN)is a simple approach to design RNNs.It is possible to investigate ESNs’dynamics deeply.However,most of dynamic studies have mainly concentrated on the shallow ESNs and seldom of them explain the dynamics of the deep ones.Therefore,this paper investigates the dynamics of four typical ESNs under a unified theoretical framework.These ESNs contain both the shallow versions and the deep ones.This investigation is helpful to clarify the dynamics of ESNs in a general sense.Also,the short-term memory(STM)of different ESNs is analyzed,which is closely related to the dynamics.This analysis is helpful to determine the hyper-parameters of ESNs for given problems.In addition,the problem-solving abilities of ESNs are investigated through modeling two time series tasks.It further explains the influence of the dynamics on ESN’s performance.
基金supported by the National Natural Science Foundation of China (No.51877013),(ZJ),(http://www.nsfc.gov.cn/)the Jiangsu Provincial Key Research and Development Program (No.BE2021636),(ZJ),(http://kxjst.jiangsu.gov.cn/)+1 种基金the Science and Technology Project of Changzhou City (No.CE20205056),(ZJ),(http://kjj.changzhou.gov.cn/)by Qing Lan Project of Jiangsu Province (no specific grant number),(ZJ),(http://jyt.jiangsu.gov.cn/).
文摘The structure and function of brain networks have been altered in patients with end-stage renal disease(ESRD).Manifold regularization(MR)only considers the pairing relationship between two brain regions and cannot represent functional interactions or higher-order relationships between multiple brain regions.To solve this issue,we developed a method to construct a dynamic brain functional network(DBFN)based on dynamic hypergraph MR(DHMR)and applied it to the classification of ESRD associated with mild cognitive impairment(ESRDaMCI).The construction of DBFN with Pearson’s correlation(PC)was transformed into an optimization model.Node convolution and hyperedge convolution superposition were adopted to dynamically modify the hypergraph structure,and then got the dynamic hypergraph to form the manifold regular terms of the dynamic hypergraph.The DHMR and L_(1) norm regularization were introduced into the PC-based optimization model to obtain the final DHMR-based DBFN(DDBFN).Experiment results demonstrated the validity of the DDBFN method by comparing the classification results with several related brain functional network construction methods.Our work not only improves better classification performance but also reveals the discriminative regions of ESRDaMCI,providing a reference for clinical research and auxiliary diagnosis of concomitant cognitive impairments.
基金supported in part by the National Natural Science Foundation of China(62222301, 62073085, 62073158, 61890930-5, 62021003)the National Key Research and Development Program of China (2021ZD0112302, 2021ZD0112301, 2018YFC1900800-5)Beijing Natural Science Foundation (JQ19013)。
文摘Reinforcement learning(RL) has roots in dynamic programming and it is called adaptive/approximate dynamic programming(ADP) within the control community. This paper reviews recent developments in ADP along with RL and its applications to various advanced control fields. First, the background of the development of ADP is described, emphasizing the significance of regulation and tracking control problems. Some effective offline and online algorithms for ADP/adaptive critic control are displayed, where the main results towards discrete-time systems and continuous-time systems are surveyed, respectively.Then, the research progress on adaptive critic control based on the event-triggered framework and under uncertain environment is discussed, respectively, where event-based design, robust stabilization, and game design are reviewed. Moreover, the extensions of ADP for addressing control problems under complex environment attract enormous attention. The ADP architecture is revisited under the perspective of data-driven and RL frameworks,showing how they promote ADP formulation significantly.Finally, several typical control applications with respect to RL and ADP are summarized, particularly in the fields of wastewater treatment processes and power systems, followed by some general prospects for future research. Overall, the comprehensive survey on ADP and RL for advanced control applications has d emonstrated its remarkable potential within the artificial intelligence era. In addition, it also plays a vital role in promoting environmental protection and industrial intelligence.