检索结果-内蒙古大学图书馆

2020国际计算机前沿大会

作者： Yuhang Li Yan Yang Yingli Zhong School of Computer Science Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

Graph similarity search is a common operation of graph database,and graph editing distance constraint is the most common similarity measure to solve graph similarity search problem. However, accurate calculation of graph editing distance is proved to be NP hard, and the filter and verification framework are adopted in current method. In this paper, a dictionary tree based clustering index structure is proposed to reduce the cost of candidate graph, and is verified in the filtering stage. An efficient incremental partition algorithm was designed. By calculating the distance between query graph and candidate graph partition, the filtering effect was further enhanced. Experiments on real large graph datasets show that the performance of this algorithm is significantly better than that of the existing algorithms.

关键词： Graphsimilaritysearch Similaritysearch Graphpartition

来源：评论

学校读者我要写书评

暂无评论

PSHCAR: A Position-Irrelevant Scene-Aware Human Complex Activities Recognizing Algorithm on Mobile Phones

PSHCAR: A Position-Irrelevant Scene-Aware Human Complex Acti...

引用

2018国际计算机前沿大会（原国际青年计算机大会）

作者： Boxuan Jia Jinbao Li Hui Xu School of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

Recognizing human complex activities has become an essential topic in pervasive computing research area. With the growing popularity of mobile phones, more and more studies have been dedicated to identifying human complex activities using mobile phones in recent years. However, previous works often restrain the position and orientation of cell phones which limit the applicability of their methods. To overcome this limitation, we propose a novel position-irrelevant activities identification method named PSHCAR, which efficiently utilize information from multiple sensors on smartphones. Moreover,besides commonly-used features such as accelerometer and gyroscope,PSHCAR also employ the knowledge about scenes of activities, which is helpful but ignored by previous works, to identify complex activities of mobile phone users. Comparative experiments show that our method performs better than several strong baselines on the task of human complex activities recognition. In conclusion, our method achieves state-of-the-art performance without any limitation on position or orientation of mobile phones.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on parallel F-statistics estimation algorithm based on OpenMP

Research on Parallel F-statistics estimation algorithm based...

引用

2015 IEEE Advanced Information Technology,Electronic and Automation Control Conference(IAEAC 2015)

作者： Ruiqing Jing Jun Lu Jun Li Kang Wan Haoyu Zhang College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

ISBN: (纸本)9781479919819

The genetic variation information file of glycine max is adopted as experimental data in this *** genetic variation information of soybean is processed and the corresponding algorithm is paralleled by the OpenMP parallel *** experiment extracted the corresponding biologic information of population individuals from genetic variation information,implemented corresponding process and *** relevant serial algorithm and parallel algorithm are compared and *** experiment results show that the efficiency of the data processing and analysis of F statistic are effectively improved by OpenMP parallel technology[l].It has actual significance on processing massive bioinformatic data.

关键词： F-statistics OpenMP population differentiation variation site

来源：评论

学校读者我要写书评

暂无评论

CTS: Combine Temporal Influence and Spatial Influence for Time-Aware POI Recommendation

CTS: Combine Temporal Influence and Spatial Influence for Ti...

引用

The Second International Conference of Young Computer Scientists, Engineers and Educators,ICYCSEE 2016

作者： Hanbing Zhang Yan Yang Zhaogong Zhang School of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

As location-based social network(LBSN) services become more popular in people's lives, Point of Interest(POI) recommendation has become an important research *** recommendation is to recommend places where users have not visited before. There are two problems in POI recommendation:sparsity and precision. Most users only check-in a few POIs in an LBSN. To tackle the sparse problem in a certain extent, we compute the similarity between the check-in datasets of different times. For the precision problem, we incorporate temporal information and geographical information. The temporal information will influence how the user chooses and allow the user to visit different distance point on different day. The geographical information is also used as a control for points which are too far away from the user's check-in *** experimental results on real life LBSN datasets show that the proposed approach outperforms the other POI recommendation methods substantially.

关键词： Recommendation Point-of-interest Location-based social network Collaborative filtering Spatio-temporal

来源：评论

学校读者我要写书评

暂无评论

Incremental Influence Maximization for Dynamic Social Networks

Incremental Influence Maximization for Dynamic Social Networ...

引用

The Third International Conference of Pioneering Computer Scientists, Engineers and Educators,ICPCSEE 2017(originally ICYCSEE)

作者： Yake Wang Jinghua Zhu Qian Ming School of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

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 *** 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.

关键词： Influence maximization Dynamic social network Linear threshold model Pruning strategy

来源：评论

学校读者我要写书评

暂无评论

Using Gaussian Mixture Model to Fix Errors in SFS Approach Based on Propagation

Using Gaussian Mixture Model to Fix Errors in SFS Approach B...

引用

The Second International Conference of Young Computer Scientists, Engineers and Educators,ICYCSEE 2016

作者： Wenmin Huang Jiquan Ma Enbin Zhang College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

A new Gaussian mixture model is used to improve the quality of propagation method for SFS in this paper. The improved algorithm can overcome most difficulties of propagation SFS method including slow convergence, inter-dependence of propagation nodes and error accumulation. To slow convergence and interdependence of propagation nodes, stable propagation source and inte-gration path are used to make sure that the reconstruction work of each pixel in the image is independent. A Gaussian mixture model based on prior conditions is proposed to fix the error of integration. Good result has been achieved in the experiment for Lambert composite image of the front illumination.

关键词： Shape from shading Propagation method Silhouette Gaussian mixture model Surface reconstruction

来源：评论

学校读者我要写书评

暂无评论

Sensitivity loss training based implicit feedback

Sensitivity loss training based implicit feedback

引用

International Conference on parallel and Distributed Systems (ICPADS)

作者： Kun Li Nan Wang Xinyu Liu Key Laboratory of Database and Parallel Computing of Heilongjiang Province School of Computer Science and Technology Heilongjiang University Harbin China

ISBN: (纸本)9781665408790

In recommender systems, due to the lack of explicit feedback features, datasets with implicit feedback are always accustomed to train all samples without separating them during model training, without considering the non-consistency of samples. This leads to a significant decrease in sample utilization and creates challenges for model training. Also, little work has been done to explore the intrinsic laws implied in the implicit feedback dataset and how to effectively train the implicit feedback data. In this paper, we first summarize the variation pattern of loss with model training for different rating samples in the explicit feedback dataset, and find that model training is highly sensitive to the ratings. Second, we design an adaptive hierarchical training function with dynamic thresholds that can effectively distinguish different rating samples in the dataset, thus optimizing the implicit feedback dataset into an explicit feedback dataset to some extent. Finally, to better learn samples with different ratings, we also propose an adaptive hierarchical training strategy to obtain better training results in the implicit feedback dataset. Extensive experiments on three datasets show that our approach achieves excellent performance and greatly improves the performance of the model.

关键词： Training Learning systems Adaptation models Sensitivity Conferences Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Node classification problem based on potential information and representation learning between nodes

Node classification problem based on potential information a...

引用

International Conference on Information Science and Control Engineering (ICISCE)

作者： Mingming Li Yan Yang School of Computer Science Technology Heilongjiang University Hearbin Province China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin Province China

Representation learning of social network nodes refers to the feature expression of nodes in low-dimensional vector space. Most of the current methods are based on the network topology to achieve node feature learning, but the potential information of the network topology is not fully utilized. To solve this problem, we propose a graph embedding algorithm based on the similarity between nodes. This method obtains a new network topology through the second-order similarity between nodes. This network topology can enhance the correlation between nodes, thereby improving the effect of node classification in the network. We use Macro-F1 and Micro-F1 evaluation indicators to evaluate the benchmark algorithm and the SNE algorithm proposed in this paper on four real data sets. The experimental results show that the SNE algorithm can improve the effect of node classification.

关键词： Information science Electronic publishing Correlation Control engineering Network topology Social networking (online) Information services

来源：评论

学校读者我要写书评

暂无评论

Optimization and parallelization of MRF community detection algorithm for a specific network

引用

International Journal of Performability Engineering 2019年第8期15卷 2153-2164页

作者： Lu, Jun Zhang, Yuanzhong College of Computer Science and Technology Heilongjiang University Harbin150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin150080 China

Research on the optimization and parallelization of the MRF network community detection algorithm for a specific network is carried out in this paper. Firstly, the principle of the existing algorithm is expounded, the algorithm is analyzed, and some problems are pointed out. Some optimization strategies and rules are proposed, including the extraction of variables and operations from inner loops to outer loops, the merging of related operations in loops, the removal of redundant loops, and the split of loops. In order to achieve better parallelism, OpenMP parallel computing of this method is realized by reversing the order of inner and outer loops. The influence of the density of network edges on the algorithm efficiency is also analyzed in this paper. The optimization and parallel algorithm can be applied to the module partition of Alzheimer's disease gene data, and the efficiency of the algorithm is greatly improved. The optimization strategies and rules proposed in this paper can be further extended to general situations. It is significant in practical applications. © 2019 Totem Publisher, Inc. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Notice of Retraction: Collaborative filtering based on time division

Notice of Retraction: Collaborative filtering based on time ...

引用

International Conference on Computer Science and Information Technology (CSIT)

作者： Yan Yang Long Yun Key Laboratory of Database and Parallel Computing of Heilongjiang Province Department of Computer Science and Technology Heilongjiang University Harbin China

This article has been retracted by the publisher.

关键词：

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：