检索结果-内蒙古大学图书馆

Frequent jump pattern mining based on complex network

Journal of Computational Information systems 2015年第17期11卷 6451-6458页

作者： Wang, Lei Jiang, Liya Dong, Jun Huang, Guoyan Ren, Jiadong College of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China Hebei Normal University of Science and Technology Qinhuangdao China

Many researchers are devoted to find frequent pattern in static network. Due to these frequent patterns are usually defined as frequent existence patterns which satisfy given support threshold in network. However, the temporal feature in dynamic network is ignored. In this paper, frequent jump pattern (FJP) is proposed, it not only represents frequent pattern but also can show regular behavior in evolving social network. Furthermore, jump patterns are robust against noise in the analysis of dynamical process. We construct matrix of directed graph (MDG) to present the evolution of complex directed network over time. Moreover, a frequent jump pattern searching algorithm (FJPSA) based on MDG is proposed to find dynamic evolution rule of social network. FJP mining is a technique which can be used in many application fields, such as explaining biological evolution and mining customer behavior regularity in social network. Experimental results demonstrate that our method could effectively mining FJP-graph. © 2015, by Binary Information Press

关键词： Directed graphs

来源：评论

学校读者我要写书评

暂无评论

Identifying important nodes in complex software network based on ripple effects

引用

ICIC Express Letters, Part B: Applications 2016年第2期7卷 257-264页

作者： Ren, Jiadong Wu, Hongfei Gao, Rui Huang, Guoyan Dong, Jun College of Information Science and Engineering Yanshan University China Computer Virtual Technology and System Integration Laboratory of Hebei Province No. 438 Hebei Avenue Qinhuangdao China

The structure of complex software systems can be extracted as a complex software network, and the quality of software systems largely depends on the topological structure of the software network. A small portion of important nodes plays a critical role in ensuring the stability and quality of the software system. Identifying these important nodes in software network has become an important and challenging task of software engineering. In this paper, firstly we construct a model of directed weighted software network. Then, by analyzing the bug propagation process on weighted software network, the values of some metrics related to ripple effects are calculated. Finally, important nodes whose ripple effects are larger than average ripple effect are identified by our proposed approach. Experimental results on real software data show the utility of the approach. © 2016 ICIC International.

关键词： computer software

来源：评论

学校读者我要写书评

暂无评论

A novel approach for mining important nodes in directed-weighted complex software network

引用

Journal of Computational Information systems 2015年第8期11卷 3059-3071页

作者： Ren, Jiadong Wu, Hongfei Yin, Tengteng Bai, Lan Zhang, Bing College of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China Hebei Institute of Foreign Languages Qinhuangdao China

If the software system is abstracted as a software network, its quality largely depends on the topology structure. A tiny fraction key function nodes play a critical role in improving the stability, reliability and robustness of complex software network. How to identify the top-k key nodes accurately and effectively becomes more and more significant both in theoretical and practical. In this paper, a novel approach based on semi-global information of mining top-k key nodes in directed-weighted complex software network is proposed. Firstly, we map the function and relationship of function calling or dependency to a directed function dependency network (DFDN). Secondly, an algorithm DFS-WEIGHT based on Depth-First-Search strategy is used to transform a DFDN into a directed-weighted function dependency network (DWFDN). Thirdly, we treat function nodes of DWFDN as two different roles - the caller or callee. Callers with high ability of accumulating vulnerabilities and callees with high ability of propagating vulnerabilities are considered as key nodes. Then, two metrics SABAC and SABPR are defined to measure the importance of callers and callees respectively. Finally, a Software Network key Node miNing (SN-KNN) algorithm is proposed to mine most important callers and callees. Experimental results indicate that the algorithm SN-KNN is effective in mining key nodes. ©, 2015, Binary Information Press. All right reserved.

关键词： Software reliability

来源：评论

学校读者我要写书评

暂无评论

A new method of identifying influential nodes in complex software network based on leaderrank

引用

ICIC Express Letters 2016年第12期10卷 2837-2844页

作者： Huang, Guoyan Liu, Jing Chen, Xiaojuan Ren, Jiadong College of Information Science and Engineering Yanshan University China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province No. 438 West Hebei Ave. Qinhuangdao066004 China

Identifying influential nodes is crucial for understanding and improving the stability and robustness of complex software network. This paper presents a new method based on LeaderRank information to identify top-k influential nodes in directed-weighted complex software network. Firstly, the function and relationship of function calling or dependency are mapped to a Directed function dependency network (DN). Secondly, a so-called stem node connected with every other node by a bidirectional link is introduced into the original network. Thirdly, an algorithm Constructing DWN (C-DWN) is used to transform a DN into a Directed-Weighted function dependency network (DWN). Finally, the Identifying Influential Node in Software Network (IIN-SN) algorithm is proposed to identify influential nodes. Experimental results show that the proposed method is effective for identifying influential nodes with the final score ranking following power-laws. The top-k most influential nodes are the same and the final score (NS) of each node is a little larger during the software evolution. What is more, we present that some factors such as in-degree of nodes and influence of connected nodes are related to the influence of nodes. © 2016 ICIC International.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

An improved algorithm for community discovery in weighted social networks

引用

Journal of Information and Computational Science 2015年第18期12卷 6873-6881页

作者： Guo, Jingfeng Liu, Miaomiao Liu, Linlin College of Information Science and Engineering Yanshan University QinhuangdaoHebei China Northeast Petroleum University DaqingHeilongjiang China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province QinhuangdaoHebei China

The problems of AGMA (Automatic Graph Mining Algorithm) are improved and a novel algorithm, namely CRMA (Clustering Re-clustering Merging Algorithm) is proposed which can realize more reasonable community division for weighted social networks. Firstly, when re-clustering nodes, AGMA neglected the clustering situation of its neighbors and didn't take into account the weight of the edge connecting the current node and its unclustered neighbor, which led to unreasonable clustering. Aiming to this, the concept of the connection compactness is introduced. Then according to the node weight, the edge weight and the friend coefficient, each node would be clustered into the community has the largest connection compactness with itself. Secondly, for community division in some unweighted networks and signed networks, if there are many nodes whose clustered neighbors is less than its unclustered neighbors, the division results of AGMA tend to produce many small communities, which would result in the lower modularity. In view of this problem, the concepts of positive edge weight density, the cluster density and the connection coefficient between clusters are proposed. Lastly, we merge communities based on the above three concepts and the modularity is effectively enhanced finally. The higher correctness and better generality of the improved algorithm are verified through experiments. © 2015 by Binary Information Press.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

An efficient approach to mine maximal continuous frequent patterns from software function call sequence

引用

Journal of Computational Information systems 2015年第8期11卷 3073-3085页

作者： He, Haitao Yin, Tengteng Wu, Hongfei Bai, Lan Ren, Jiadong College of Information Science and Engineering Yanshan University Qinhuangdao China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao China Hebei Institute of Foreign Languages Qinhuangdao China

Certain characteristics of software are often hidden in its structure and can only be discovered when the software is executed dynamically. So mining important patterns from dynamic call graph of software plays an important role in analyzing software security. However the general sequential pattern mining algorithms may lead to poor performance due to the lack of consideration on the continuous property of software function call sequence. In this paper, combining with the characteristics of software itself, function call sequence is modeled firstly. The sequence represents the call relationship among functions of software. Then a novel structure called Nitem-List is put forward. The structure stores both the next item and the support information which is heuristic information for pruning the search space about a pattern. On the basis of that, an efficient algorithm called Maximal Continuous Frequent Pattern Miner (MCFP-Miner) and an update algorithm UMCFP-Miner are proposed. After constructing the initial Nitem-Lists from a mined database, MCFP-Miner can mine continuous frequent patterns from these Nitem-Lists. In UMCFP-Miner, a tighter bound for pruning is proposed. Finally, extensive experiments on various databases show that algorithm MCFP-Miner and UMCFP-Miner have better efficiency. ©, 2015, Binary Information Press. All right reserved.

关键词： Miners

来源：评论

学校读者我要写书评

暂无评论

A Time-aware POI Recommendation Method Exploiting User-based Collaborative Filtering and Location Popularity

A Time-aware POI Recommendation Method Exploiting User-based...

引用

2017 2nd International Conference on Communications, Information Management and Network Security (CIMNS2017)

作者： Ya-li SI Fu-zhi ZHANG Wen-yuan LIU School of Information Science and Engineering Yanshan University School of Liren Yanshan University The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province

Point-of-interest(POI) recommendation becomes an important research for location-based social networks, since it helps modern citizens to explore new locations in unvisited cites effectively according to their preferences. However, the current POI recommendation methods are lack of a deep mining in all time slots features and their effects on recommendation. To this end, in this paper we propose a POI recommendation method(called UPT) by combining time slot features, user-based collaborative filtering and spatial influence. Firstly, we extract time interval feature and time slot based popularity feature from history check-in datasets on LBSNs using probability statistical analysis method. Then, we devise a POI recommendation method based on the proposed temporal features to achieve better performance. In UPT, user-based collaborative filtering and smoothing technique are used by adding each time slot influence, and the overall popularity of a location is combined with each time slot feature. Our experimental results on Foursquare and Gowalla datasets show that UPT outperforms baseline POI recommendation methods in precision and recall.

关键词： Location-based social networks Point-of-interest recommendation User-based collaborative filtering Location popularity Temporal feature

来源：评论

学校读者我要写书评

暂无评论

Multi-Update Patterns and Validity Verification for Robust Visual Tracking

引用

Journal of computers (Taiwan) 2020年第4期31卷 77-90页

作者： Wen, Jia Wang, Hong-Jun Li, Yan-Nan Zhao, Ji-Wei Yang, Yu-Ying School of Information Science and Engineering Yanshan University Qinhuangdao China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province China Key Laboratory of Software Engineering of Hebei Province China

The Object tracking is a challenging problem in computer vision field. Now, deep learning has made outstanding achievements in feature extraction. There are already some examples of deep learning applications in visual tracking. But, they almost paid attention to precision and sacrificed efficiency. So we propose a tracker named adaptive combination tracker(ACT), based on neural network model, which gives consideration to both precision and efficiency. Our ACT tracker gets rich features offline through Stacked Denoising Autoencoders (SDAE) and transfers them to online tracking. In tracking, a dynamic particle filter algorithm is proposed to speed up tracking. We update our tracker with different patterns according to the change in appearance. In order to ensure efficiency, our tracker regulates speed adaptively. Our tracker regulates speed precisely to avoid drift caused by fast motion as much as possible, and confirm and optimize the effectiveness of the results by comparison with previous target. We evaluate our tracker on OTB2013 datasets. Extensive experiments on OTB2013 datasets demonstrate that the proposed tracker performs favorably in relation to the state-of-the-art methods. © 2020 computer Society of the Republic of China. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Object Tracking by Jointly Utilizing Template Updating and Relocation Mechanisms⋆

SSRN

引用

SSRN 2023年

作者： Wen, Jia Ren, Kejun School of Information Science and Engineering Yanshan University Qinhuangdao066099 China The Key Laboratory for Computer Virtual Technology System Integration of Hebei Province China

The Siamese network-based tracker has achieved competitive performance in the field of single target tracking because of its excellent tracking speed and tracking accuracy. When faced with target deformations, most Siamese trackers rely on fixed template features from the initial frame, severely constraining the tracker’s performance. To mitigate this situation, we introduce a novel tracking framework(SiamTAR) that allows adaptive template updates based on past tracking information. In addition, we design a feature refinement module which can capture the target information more accurately at the full scale on the search image through an integrated attention mechanism, thus enabling the tracker to pay less attention to redundant information. Notably, we introduce a relocalization mechanism to solve the problems of random drift of the tracking box and inaccurate scale estimation in online tracking. Extensive experiments on GOT-10K, UAV123, OTB100 and DTB70 datasets show that the tracker achieves good tracking results and real-time performance. © 2023, The Authors. All rights reserved.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Subspace clustering over high-dimensional data stream based on grid density and attribute relativity

引用

Advances in Information Sciences and Service Sciences 2012年第17期4卷 91-99页

作者： Huang, Guoyan Miao, Liyun Ren, Jiadong College of Information Science and Engineering Yanshan University Qinhuangdao City 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China

The traditional clustering algorithms often fail to detect meaningful clusters in high-dimensional data space. To improve the above shortcoming, we propose GDRH-Stream, a clustering method based on the attribute relativity and grid density for high-dimensional data stream, which consists of an online component and an offline component. First, the algorithm filters out redundant attributes by computing the relative entropy. Then we define a weighted attribute relativity measure and estimate the relativity of the non-redundant attributes, and form the attribute triple. At last, the best interesting subspaces are searched by the attribute triple. On the online component, GDRH-Stream maps each data object into a grid and updates the characteristic vector of the grid. On the offline component, when a clustering request arrives, the best interesting subspaces will be generated by attribute relativity. Then the original grid structure is projected to the subspace and a new grid structure is formed. The clustering will be performed on the new grid structure by adopting an approach based on the density grid. Experimental results show that GDRH-Stream algorithm has better quality and scalability.

关键词： Relativity

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：