Bitcoin is a cryptocurrency based on blockchain.All historical Bitcoin transactions are stored in the Bitcoin blockchain,but Bitcoin owners are generally unknown.This is the reason for Bitcoin's pseudo-anonymity,t...Bitcoin is a cryptocurrency based on blockchain.All historical Bitcoin transactions are stored in the Bitcoin blockchain,but Bitcoin owners are generally unknown.This is the reason for Bitcoin's pseudo-anonymity,therefore it is often used for illegal transactions.Bitcoin addresses are related to Bitcoin users'identities.Some Bitcoin addresses have the potential to be analyzed due to the behavior patterns of Bitcoin transactions.However,existing Bitcoin analysis methods do not consider the fusion of new blocks'data,resulting in low efficiency of Bitcoin address analysis.In order to address this problem,this paper proposes an incremental Bitcoin address cluster method to avoid re-clustering when new block data is added.Besides,a heuristic Bitcoin address clustering algorithm is developed to improve clustering accuracy for the Bitcoin Blockchain.Experimental results show that the proposed method increases Bitcoin address cluster efficiency and accuracy.展开更多
Social networks are inevitable parts of our daily life,where an unprecedented amount of complex data corresponding to a diverse range of applications are generated.As such,it is imperative to conduct research on socia...Social networks are inevitable parts of our daily life,where an unprecedented amount of complex data corresponding to a diverse range of applications are generated.As such,it is imperative to conduct research on social events and patterns from the perspectives of conventional sociology to optimize services that originate from social networks.Event tracking in social networks finds various applications,such as network security and societal governance,which involves analyzing data generated by user groups on social networks in real time.Moreover,as deep learning techniques continue to advance and make important breakthroughs in various fields,researchers are using this technology to progressively optimize the effectiveness of Event Detection(ED)and tracking algorithms.In this regard,this paper presents an in-depth comprehensive review of the concept and methods involved in ED and tracking in social networks.We introduce mainstream event tracking methods,which involve three primary technical steps:ED,event propagation,and event evolution.Finally,we introduce benchmark datasets and evaluation metrics for ED and tracking,which allow comparative analysis on the performance of mainstream methods.Finally,we present a comprehensive analysis of the main research findings and existing limitations in this field,as well as future research prospects and challenges.展开更多
Online social networks are increasingly connecting people around the world.Influence maximization is a key area of research in online social networks,which identifies influential users during information dissemination...Online social networks are increasingly connecting people around the world.Influence maximization is a key area of research in online social networks,which identifies influential users during information dissemination.Most of the existing influence maximization methods only consider the transmission of a single channel,but real-world networks mostly include multiple channels of information transmission with competitive relationships.The problem of influence maximization in an environment involves selecting the seed node set for certain competitive information,so that it can avoid the influence of other information,and ultimately affect the largest set of nodes in the network.In this paper,the influence calculation of nodes is achieved according to the local community discovery algorithm,which is based on community dispersion and the characteristics of dynamic community structure.Furthermore,considering two various competitive information dissemination cases as an example,a solution is designed for self-interested information based on the assumption that the seed node set of competitive information is known,and a novel influence maximization algorithm of node avoidance based on user interest is proposed.Experiments conducted based on real-world Twitter dataset demonstrates the efficiency of our proposed algorithm in terms of accuracy and time against notable influence maximization algorithms.展开更多
Cross-project software defect prediction solves the problem of insufficient training data for traditional defect prediction,and overcomes the challenge of applying models learned from multiple different source project...Cross-project software defect prediction solves the problem of insufficient training data for traditional defect prediction,and overcomes the challenge of applying models learned from multiple different source projects to target project.At the same time,two new problems emerge:(1)too many irrelevant and redundant features in the model training process will affect the training efficiency and thus decrease the prediction accuracy of the model;(2)the distribution of metric values will vary greatly from project to project due to the development environment and other factors,resulting in lower prediction accuracy when the model achieves cross-project prediction.In the proposed method,the Pearson feature selection method is introduced to address data redundancy,and the metric compensation based transfer learning technique is used to address the problem of large differences in data distribution between the source project and target project.In this paper,we propose a software defect prediction method with metric compensation based on feature selection and transfer learning.The experimental results show that the model constructed with this method achieves better results on area under the receiver operating characteristic curve(AUC)value and F1-measure metric.展开更多
Much recent progress in monaural speech separation(MSS)has been achieved through a series of deep learning architectures based on autoencoders,which use an encoder to condense the input signal into compressed features...Much recent progress in monaural speech separation(MSS)has been achieved through a series of deep learning architectures based on autoencoders,which use an encoder to condense the input signal into compressed features and then feed these features into a decoder to construct a specific audio source of interest.However,these approaches can neither learn generative factors of the original input for MSS nor construct each audio source in mixed speech.In this study,we propose a novel weighted-factor autoencoder(WFAE)model for MSS,which introduces a regularization loss in the objective function to isolate one source without containing other sources.By incorporating a latent attention mechanism and a supervised source constructor in the separation layer,WFAE can learn source-specific generative factors and a set of discriminative features for each source,leading to MSS performance improvement.Experiments on benchmark datasets show that our approach outperforms the existing methods.In terms of three important metrics,WFAE has great success on a relatively challenging MSS case,i.e.,speaker-independent MSS.展开更多
Large-scale datasets are driving the rapid developments of deep convolutional neural networks for visual sentiment analysis.However,the annotation of large-scale datasets is expensive and time consuming.Instead,it ise...Large-scale datasets are driving the rapid developments of deep convolutional neural networks for visual sentiment analysis.However,the annotation of large-scale datasets is expensive and time consuming.Instead,it iseasy to obtain weakly labeled web images from the Internet.However,noisy labels st.ill lead to seriously degraded performance when we use images directly from the web for training networks.To address this drawback,we propose an end-to-end weakly supervised learning network,which is robust to mislabeled web images.Specifically,the proposed attention module automatically eliminates the distraction of those samples with incorrect labels bv reducing their attention scores in the training process.On the other hand,the special-class activation map module is designed to stimulate the network by focusing on the significant regions from the samples with correct labels in a weakly supervised learning approach.Besides the process of feature learning,applying regularization to the classifier is considered to minimize the distance of those samples within the same class and maximize the distance between different class centroids.Quantitative and qualitative evaluations on well-and mislabeled web image datasets demonstrate that the proposed algorithm outperforms the related methods.展开更多
基金The work reported in this paper has been partially supported by the National Key Research and Development Project(2020YFB1005503)the NSFC Projects(61502209 and U1836116)+2 种基金the Leading-edge Technology Program of Jiangsu Natural Science Foundation(BK20202001)the NSFC of Jiangsu Province Project(BK20201415)the UK-Jiangsu 20-20 World Class University Initiative programme,and the Natural Science Foundation of the Jiangsu Higher Education Institutions(Grant number:22KJB520016).
文摘Bitcoin is a cryptocurrency based on blockchain.All historical Bitcoin transactions are stored in the Bitcoin blockchain,but Bitcoin owners are generally unknown.This is the reason for Bitcoin's pseudo-anonymity,therefore it is often used for illegal transactions.Bitcoin addresses are related to Bitcoin users'identities.Some Bitcoin addresses have the potential to be analyzed due to the behavior patterns of Bitcoin transactions.However,existing Bitcoin analysis methods do not consider the fusion of new blocks'data,resulting in low efficiency of Bitcoin address analysis.In order to address this problem,this paper proposes an incremental Bitcoin address cluster method to avoid re-clustering when new block data is added.Besides,a heuristic Bitcoin address clustering algorithm is developed to improve clustering accuracy for the Bitcoin Blockchain.Experimental results show that the proposed method increases Bitcoin address cluster efficiency and accuracy.
基金This work was supported by the National Natural Science Foundation of China(No.62302199)the China Postdoctoral Science Foundation(No.2023M731368)+3 种基金the Natural Science Foundation of the Jiangsu Higher Education Institutions(No.22KJB520016)the Jiangsu University Innovative Research Project(No.KYCX22_3671)the Youth Foundation Project of Humanities and Social Sciences of Ministry of Education in China(No.22YJC870007)the Jiangsu University Undergraduate Student English Teaching Excellence Program,and the Ministry of Education's Industry-Education Cooperation Collaborative Education Project(No.202102306005).
文摘Social networks are inevitable parts of our daily life,where an unprecedented amount of complex data corresponding to a diverse range of applications are generated.As such,it is imperative to conduct research on social events and patterns from the perspectives of conventional sociology to optimize services that originate from social networks.Event tracking in social networks finds various applications,such as network security and societal governance,which involves analyzing data generated by user groups on social networks in real time.Moreover,as deep learning techniques continue to advance and make important breakthroughs in various fields,researchers are using this technology to progressively optimize the effectiveness of Event Detection(ED)and tracking algorithms.In this regard,this paper presents an in-depth comprehensive review of the concept and methods involved in ED and tracking in social networks.We introduce mainstream event tracking methods,which involve three primary technical steps:ED,event propagation,and event evolution.Finally,we introduce benchmark datasets and evaluation metrics for ED and tracking,which allow comparative analysis on the performance of mainstream methods.Finally,we present a comprehensive analysis of the main research findings and existing limitations in this field,as well as future research prospects and challenges.
基金supported by the National Natural Science Foundation of China(Nos.61502209 and 61502207)
文摘Online social networks are increasingly connecting people around the world.Influence maximization is a key area of research in online social networks,which identifies influential users during information dissemination.Most of the existing influence maximization methods only consider the transmission of a single channel,but real-world networks mostly include multiple channels of information transmission with competitive relationships.The problem of influence maximization in an environment involves selecting the seed node set for certain competitive information,so that it can avoid the influence of other information,and ultimately affect the largest set of nodes in the network.In this paper,the influence calculation of nodes is achieved according to the local community discovery algorithm,which is based on community dispersion and the characteristics of dynamic community structure.Furthermore,considering two various competitive information dissemination cases as an example,a solution is designed for self-interested information based on the assumption that the seed node set of competitive information is known,and a novel influence maximization algorithm of node avoidance based on user interest is proposed.Experiments conducted based on real-world Twitter dataset demonstrates the efficiency of our proposed algorithm in terms of accuracy and time against notable influence maximization algorithms.
基金Project supported by the National Natural Science Foundation of China(Nos.62172194 and U1836116)the National Key R&D Program of China(No.2020YFB1005500)+3 种基金the Leadingedge Technology Program of Jiangsu Provincial Natural Science Foundation,China(No.BK20202001)the China Postdoctoral Science Foundation(No.2021M691310)the Postdoctoral Science Foundation of Jiangsu Province,China(No.2021K636C)the Future Network Scientific Research Fund Project,China(No.FNSRFP-2021-YB-50)。
文摘Cross-project software defect prediction solves the problem of insufficient training data for traditional defect prediction,and overcomes the challenge of applying models learned from multiple different source projects to target project.At the same time,two new problems emerge:(1)too many irrelevant and redundant features in the model training process will affect the training efficiency and thus decrease the prediction accuracy of the model;(2)the distribution of metric values will vary greatly from project to project due to the development environment and other factors,resulting in lower prediction accuracy when the model achieves cross-project prediction.In the proposed method,the Pearson feature selection method is introduced to address data redundancy,and the metric compensation based transfer learning technique is used to address the problem of large differences in data distribution between the source project and target project.In this paper,we propose a software defect prediction method with metric compensation based on feature selection and transfer learning.The experimental results show that the model constructed with this method achieves better results on area under the receiver operating characteristic curve(AUC)value and F1-measure metric.
基金the Key Project of the National Natural Science Foundation of China(No.U1836220)the National Natural Science Foundation of China(No.61672267)+1 种基金the Qing Lan Talent Program of Jiangsu Province,Chinathe Key Innovation Project of Undergraduate Students in Jiangsu Province,China(No.201810299045Z)。
文摘Much recent progress in monaural speech separation(MSS)has been achieved through a series of deep learning architectures based on autoencoders,which use an encoder to condense the input signal into compressed features and then feed these features into a decoder to construct a specific audio source of interest.However,these approaches can neither learn generative factors of the original input for MSS nor construct each audio source in mixed speech.In this study,we propose a novel weighted-factor autoencoder(WFAE)model for MSS,which introduces a regularization loss in the objective function to isolate one source without containing other sources.By incorporating a latent attention mechanism and a supervised source constructor in the separation layer,WFAE can learn source-specific generative factors and a set of discriminative features for each source,leading to MSS performance improvement.Experiments on benchmark datasets show that our approach outperforms the existing methods.In terms of three important metrics,WFAE has great success on a relatively challenging MSS case,i.e.,speaker-independent MSS.
基金Project supported by the Key Project of the National Natural Science Foundation of China(No.U1836220)the National Nat-ural Science Foundation of China(No.61672267)+1 种基金the Qing Lan Talent Program of Jiangsu Province,China,the Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace,China,the Finnish Cultural Foundation,the Jiangsu Specially-Appointed Professor Program,China(No.3051107219003)the liangsu Joint Research Project of Sino-Foreign Cooperative Education Platform,China,and the Talent Startup Project of Nanjing Institute of Technology,China(No.YKJ201982)。
文摘Large-scale datasets are driving the rapid developments of deep convolutional neural networks for visual sentiment analysis.However,the annotation of large-scale datasets is expensive and time consuming.Instead,it iseasy to obtain weakly labeled web images from the Internet.However,noisy labels st.ill lead to seriously degraded performance when we use images directly from the web for training networks.To address this drawback,we propose an end-to-end weakly supervised learning network,which is robust to mislabeled web images.Specifically,the proposed attention module automatically eliminates the distraction of those samples with incorrect labels bv reducing their attention scores in the training process.On the other hand,the special-class activation map module is designed to stimulate the network by focusing on the significant regions from the samples with correct labels in a weakly supervised learning approach.Besides the process of feature learning,applying regularization to the classifier is considered to minimize the distance of those samples within the same class and maximize the distance between different class centroids.Quantitative and qualitative evaluations on well-and mislabeled web image datasets demonstrate that the proposed algorithm outperforms the related methods.