检索结果-内蒙古大学图书馆

Cluster-based superseding nearest neighbor queries on uncertain data

Journal of Convergence Information technology 2012年第17期7卷 392-401页

作者： Liu, Wenyuan Li, Wei Du, Ying Chen, Zijun He, Yourui College of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China College of Economics and Management Yanshan University Qinhuangdao Hebei 066004 China The Key Lab. for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao Hebei 066004 China

Recently, query processing based on uncertain data is becoming research focuses. Cluster-based superseding nearest neighbor (CSNN) query algorithm on uncertain data is proposed in this paper. We divide the instances of each object into k clusters by applying the clustering algorithm k-means, and then store these clustered objects in R-tree like index structures. Ranked list will be retrieved through traversing R-tree, which could include instances, clusters, or objects. While unfolding the ranked list, the superseding graph G will be constructed gradually based on the superseding relationship. The final result sets will be found through pruning and validating the superseding graph G. Finally, the experimental results show that the algorithm is efficient and effective.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Mining critical nodes in software execution network based on complex network

引用

ICIC Express Letters, Part B: Applications 2016年第9期7卷 1879-1884页

作者： Wang, Lei Dong, Jun Ren, Jiadong College of Information Science and Engineering Yanshan University No. 360 Hebei Ave Qinhuangdao066004 China E & A College Hebei Normal University of Science and Technology No. 360 Hebei Ave Qinhuangdao066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province No. 438 Hebei Ave Qinhuangdao066004 China

It is significant for measuring the importance of nodes accurately to improve software stability and robustness in software network. A software execution directed network takes function as a node and relationship of function as an edge in this paper. To nd the critical nodes in the network, a novel method is proposed to measure the nodes' importance by means of depth search mining in software execution. According to the principle of cascading failure, a novel critical nodes metrics FID is dened for nodes measuring and sorting. Critical nodes mining (CNM) algorithm is put forward for calculating FID value of each node and sorting. We choose top-ranking nodes as critical nodes which play an important role in software execution process. Experimental results show that CNM algorithm can measure the critical nodes accurately in software network. © 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

Collosion detection research based on capsule bounding volume

引用

Journal of Computational Information systems 2014年第7期10卷 2743-2750页

作者： Kong, Dehan Liu, Yongshan Cui, Na Department of Information Science and Engineering Yanshan University Qinhuangdao 066004 China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004 China The Data Industry Research Lab. Qinhuangdao 066004 China

A collision detection algorithm based on capsule bounding volume (CBV for short) is presented improve the efficiency of Collision detection in three-dimensional scene. This algorithm use CBV to encircle roles and achieve collision detection between the virtual characters and static objects and dynamic objects in the scene. It includes collision detection between CBV and AABB, triangular and capsule. Theoretical analysis and experimental results show that this algorithm can improve real time for collision detection. © 2014 Binary Information Press.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

A new estimator analysis method to synchronization among multivariate neural series of mild cognitive impairment

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content technology and its Applications 2012年第23期6卷 868-874页

作者： Wen, Dong Guan, Xinyong Chen, Ruihong The Key Laboratory for Computer Virtual Technology System Integration of HeBei Province Yanshan University Qinhuangdao Hebei 066004 China Liren College Yanshan University Qinhuangdao Hebei 066004 China Division of General Internal Medicine Xiantao First People's Hospital Xiantao Hubei 433000 China

Synchronization decay of resting state EEG has shown that cognitive dysfunction in mild cognitive impairment (MCI) was relevant to a loss of functional connectivity in intermediate frequency bands. A new estimator analysis method called new S estimator (NSE) proposed recently by us quantifies synchronization between neuronal signals at multiple *** paper meant to explore the behavior of synchronization of multichannel EEG in MCI and healthy normal controls at rest, and preliminarily make clear the clinical significance of the NSE in MCI *** (EEG) were recorded from 10 MCI patients and 12 age-matched healthy normal controls (NC). NSE values were computed both across the all frequency band and separately in the delta, theta, alpha, beta (including beta1, beta2 and beta3), and gamma bands. The Montreal Cognitive Assessment (MoCA) was used to assess the symptom severity of MCI patients and *** values in the alpha and beta1 bands were significantly lower in MCI patients than in NC. NSE values in the alpha and beta1 bands were positively correlated with the MoCA scores in all participants (MCI and NC). In MCI patients, NSE values in the alpha and beta1 bands were also positively correlated with MoCA *** results suggest that NSE values are a useful correlate of EEG synchronization in MCI patients.

关键词： Synchronization

来源：评论

学校读者我要写书评

暂无评论

An algorithm based on bit vector decomposition and hash linklist for mining frequent patterns in data streams

International Journal of Digital Content Technology and its ...

引用

International Journal of Digital Content technology and its Applications 2012年第22期6卷 570-579页

作者： Ren, Jiadong Zhang, Yuanyuan Yu, Shiying College of Information Science and Engineering Yanshan University Qinhuangdao Hebei 066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao City 066004 China Hebei Provincial S and T Management Information Center 159 Dongfeng Road Shijiazhuang 050021 China

Most of algorithms based on bit vector for mining frequent pattern always produce candidate itemsets and scan the same data repeatedly;this increases the running time and the space consumption. In this paper, an algorithm BVDAHL based on bit vector decomposition and hash linklist for mining frequent patterns on data streams which solves the above issues, is proposed. The itemsets (transactions) whose corresponding number of 1 is k, denoted as k-one itemsets (k-one transactions). The arrival transactions are converted into bit vectors, and permutations and combinations are used to decompose converted results, then the decomposed itemsets are stored in the hash linklist. In hash function, according to the position of 1 of bit vector to compute the address, if the transaction has same address and same content that already exists in data domain, then the value adds one in count domain, otherwise the pointer in pointer domain points to the next node directly, it is no need to deal with conflict. Afterwards the property of anti-monotonic will be used to prune the k+1-one transactions in bit vector table if there exists infrequent k-one itemsets that decomposed by such k+1-one transactions. Then the algorithm repeats the above processes until the transaction in bit vector table can not be decomposed. Finally we will receive the frequent itemsets by comparing the obtained value of count domain in hash linklist with minSup. Experiment results show that BVDAHL is very efficiency and scalable.

关键词： Hash functions

来源：评论

学校读者我要写书评

暂无评论

Learning to Cluster Person in the Video via Graph Convolution Network

Learning to Cluster Person in the Video via Graph Convolutio...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Wei Li Sixin Liang Ang Bian Guodong Du College of Computer Science Sichuan University Chengdu China The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province School of Information Science and Engineering Yanshan University Qinhuangdao P.R. China

Video person re-identification is receiving academic interest. However, the practical application of the algorithm is hardly supported because of prohibitive annotated data. Hence, the study for unlabeled data will lead to an attractive alternative. This work explores an innovative strategy, namely, learning to cluster unlabeled person in the video through graph convolutional networks. In this paper, we find that the possibility of inter-frame linkage can be inferred from context. Therefore, a pose-guided topology linkage clustering framework is proposed. Our framework consists of three modules: (i) a pose-guided representation module; (ii) a pose-guided embedding module; (iii) a link prediction module. Firstly, the representation coding alone is performed at the level of relational induction bias, embedding the implicit pose structure information in image features. Then, based on the consideration of the topology relationship between adjacent and cross-frame, graph convolutional network is introduced to infer the likelihood of linkage between frame nodes. Experiments show that the method demonstrates excellent scalability in addition to being an effective response to person clustering in case of changes, and does not need the number of clusters as a prior.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A hierarchical residual network with compact triplet-center loss for sketch recognition

arXiv

引用

arXiv 2021年

作者： Wang, Lei Zhang, Shihui He, Huan Zhang, Xiaoxiao Sang, Yu School of Information Science and Engineering Yanshan University Hebei Qinhuangdao066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Hebei Qinhuangdao066004 China School of Mathematics and Information Science and Technology Hebei Normal University of Science and Technology Qinhuangdao066004 China

With the widespread use of touch-screen devices, it is more and more convenient for people to draw sketches on screen. This results in the demand for automatically understanding the sketches. Thus, the sketch recognition task becomes more significant than before. To accomplish this task, it is necessary to solve the critical issue of improving the distinction of the sketch features. To this end, we have made efforts in three aspects. First, a novel multi-scale residual block is designed. Compared with the conventional basic residual block, it can better perceive multi-scale information and reduce the number of parameters during training. Second, a hierarchical residual structure is built by stacking multi-scale residual blocks in a specific way. In contrast with the single-level residual structure, the learned features from this structure are more sufficient. Last but not least, the compact triplet-center loss is proposed specifically for the sketch recognition task. It can solve the problem that the triplet-center loss does not fully consider too large intra-class space and too small inter-class space in sketch field. By studying the above modules, a hierarchical residual network as a whole is proposed for sketch recognition and evaluated on Tu-Berlin benchmark thoroughly. The experimental results show that the proposed network outperforms most of baseline methods and it is excellent among non-sequential models at present. Copyright © 2021, The Authors. All rights reserved.

关键词： Touch screens

来源：评论

学校读者我要写书评

暂无评论

Adaptive multilevel meshes for cloth simulation

引用

Journal of Information and Computational Science 2014年第11期11卷 3865-3872页

作者： Zhao, Jing Pei, Shanshan Lv, Mengya Li, Ying Tang, Yong Yang, Meiling Zhang, Mingmin Pan, Zhigeng The 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 The College of Computer Science and Technology Zhejiang University Hangzhou China Institute of Service Engineering Hangzhou Normal University Hangzhou China

A novel method based on multilevel meshes is proposed to simulate the cloth draping process rapidly on a complex model. Considering of the difficulty of computing the realtime collision between cloth and complex models by normally methods, the draping process of cloth is divided into several phases and at each phase the mesh size is smaller than its previous one. The optimized 1-to-4 split is used to drive the rapid changes in the grid hierarchy and to simplify the calculations. We choose the widely used ellipsoid as the bounding cell to enclose the complex models in the environment. The ellipsoid avoids the complex structure of hierarchical bounding box and eliminates the impossible collision model area rapidly. Experiments demonstrate that this method can accelerate the draping process of cloth and decrease the number of iterations and the calculation of collision detection. Further mesh refinement improves the reality of cloth when it reaches the final position and ensures the realism of the simulation in real time. ©2014 Binary Information Press

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

An improved algorithm for detecting community structure based on node similarity

引用

Journal of Computational Information systems 2014年第9期10卷 3805-3813页

作者： Guo, Jingfeng Wei, Aiying Lv, Jiaguo Liu, Zhen College of Information Science and Engineering Yanshan University Qinhuangdao 066004 China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Qinhuangdao 066004 China College of Information Science and Engineering Zaozhuang University Zaozhuang 277100 China

Detecting community structure based on node similarity cost lower time complexity, but they ignore the indirect relationships of nodes. We proposed an improved algorithm for detecting community structure based on node similarity (AINS). The algorithm presents a neighbor subgraph model based on akincore node pair, considering the direct and indirect relations between nodes. It introduced node indirect similarity to solve the problem which only pay attention to direct relationships, ensuring that the results meet the common definition of community structure (the number of edges between community is greater than that within community). The experimental results show that the AINS algorithm can obtain better community classification result effectively. © 2014 Binary Information Press.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

A Practical Cloud API Complementary Recommendation Service for Mashup Creation

A Practical Cloud API Complementary Recommendation Service f...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Xiaowei Liu Wenhui Chen Mengmeng Sun Yali Si Zhen Chen School of Information Science and Engineering Yanshan University Qinhuangdao China School of Computer Science and Engineering Changshu Institute of Technology Changshu China Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University Qinhuangdao China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

With the popularity of the service-oriented development paradigm in the cloud era, numerous cloud APIs have been developed. The continuous proliferation of cloud APIs has submerged developers in a sea of options, bringing the need for cloud API recommendation techniques. Most existing cloud API recommendation methods focus on theoretical studies and neglect practical applications. As a result, these methods face several challenges, such as covering recommendation scenarios, generating real-time responses, and handling concurrent requests. In this paper, we propose and implement a practical cloud API complementary recommendation service for mashup creation. To address the above challenges, we first propose a cloud API complementary recommendation framework named FICR, which exploits feature interactions to mine implicit complementarity and models complementarity from the mashup side and the target cloud API side for scenario coverage. Then, we conduct performance optimization via precoding and batch size tuning to optimize FICR for real-time responses. Finally, we design a minimum-connection load balancing algorithm with resource early warning and build a distributed system for concurrent requests. Experiments conducted on real-world datasets show that FICR outperforms state-of-the-art baseline models in complementary recommendation scenarios, and demonstrate that the implemented service meets the real-time and concurrency requirements. The service will serve as a practical tool to help developers during mashup creation.

关键词： Concurrent computing Federated learning Mashups Precoding Load management Real-time systems Tuning

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：