检索结果-内蒙古大学图书馆

13th Annual International Conference on Combinatorial Optimization and Applications, COCOA 2019

作者： Wang, Zhen Zhu, Jinghua Li, Doudou School of Computer Science and Technology Heilongjiang University Harbin150001 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9783030364113

With the rapid development of the Internet, Mobile Crowdsensing System (MCS) is widely used in various fields. Because of the insufficient number of users’ participation and the insufficient amount of uploaded sensing data, the research of incentive mechanism is particularly important in MCS. Reverse auction mechanism is one of the efficient incentive mechanism in MCS. The platform is responsible for publishing a group of tasks which are bidded by the workers, and only the winning workers are authorized to complete the tasks. One of the critical factors for successful bidding is the distance between the tasks and the workers. However, most workers in MCS always keep moving. So this paper proposes a prediction based reverse auction incentive mechanism—RMMP. We use the Semi-Markov model to predict the position of workers at the next moment. According to the predicated positions, our reverse auction incentive mechanism selects the winner workers with the minimum movement distance and bidding price. Experiment results on real dataset show that our RMMP mechanism has remarkable performance compared with the existing mechanisms. © 2019, Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Design of Radio-over-Fiber Distributed Antenna System and Application of Wireless Positioning

Design of Radio-over-Fiber Distributed Antenna System and Ap...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Hao Yun Wei Ji Rui Yin Key Laboratory of Database and Parallel Computing of Heilongjiang Province Laboratory of Intelligent Communications and Multimedia Information Processing ShanDong University Qingdao China School of Information Science and Engineering ShanDong University Qingdao China

ISBN: (数字)9781728143903

ISBN: (纸本)9781728143910

In this paper, a radio-over-fiber distributed antenna system (ROF-DAS) and application of wireless positioning are proposed. The modified Medium Access Control (MAC) frame, optical switch array, ROF network based on star topology and Reflective Semiconductor Optical Amplifier (RSOA) are employed to design the system. Based on the structure, wireless positioning could be achieved by Time Division Multiplexing-Time Difference of Arrival (TDM-TDOA) technology combined with Chan assisted Taylor algorithm. The quality of signal transmission is evaluated by Q Factor, and the positioning accuracy is performed in terms of the antennas amount using the positioning algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

User Local and Global Interest Depth Interaction for Recommendation Algorithm

User Local and Global Interest Depth Interaction for Recomme...

引用

International Conference on Information Science and Control Engineering (ICISCE)

作者： Xufeng Zhang Yan Yang School of Computer Science Technology Heilongiiang University Harbin China Key Laboratory of Database and Parallel Computing Harbin Heilongiiang Province China

Using auxiliary information such as social networks or item attributes to improve the performance of recommender systems is a key issue in the research of recommender systems. It plays a very important role in alleviating the interactive sparsity of collaborative filtering methods. In response to this problem, a recommendation algorithm that user local and global interest depth interaction is proposed, which analyzes the user’s implicit preferences from two perspectives: based on the user’s historical behavior records, using a fully connected neural network to extract the user’s local interests; based on the user’s historical behavior items, through the association between entities in the knowledge graph, mines the entities associated with the user’s historical behavior, forming a multi-layer global interest layer to generalize user interests. The user’s local interest vector activates the item entity in the global interest layer to generate the user’s global interest vector. Finally, the deep neural network is used to complete the feature interaction of users’ local interests, global interests and recommended items. The user’s local and global interests accurately describe user preferences and improve the accuracy of click-through rate prediction. Experiments show that the recommendation performance of the algorithm on the two public data sets is better than the comparison baseline and the classic recommendation algorithm.

关键词： Knowledge engineering Deep learning Information science Control engineering Social networking (online) Neural networks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Community Search in Spatial Uncertain Network

引用

Journal of Physics: Conference Series 2021年第4期1952卷

作者： Wenqian Zhang Yingli Zhong Yan Yang School of Computer Science Technology Heilongjiang University Harbin 150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin 150080 China

Community search is to explore valuable target community structure from a large social network. In real community, every point has a geographic location information, and many edges are uncertain. Such a network is called spatial uncertain network. In order to meet the existing needs, this paper studies the community search in the spatial uncertain network so that the searched communities can be relatively close in the geographical location and the relationship between each other is also very close. Based on the spatial uncertain graph, this paper proposes K-R-τ community, and proposes a linear algorithm and a two-dimensional algorithm for community search in the spatial uncertain network. A large number of experiments are carried out on several real datasets, and the results show that the algorithm proposed in this paper is effective and accurate.

关键词：

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

Negative influence maximization in social networks 4th

Negative influence maximization in social networks

引用

4th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2018

作者： Zhu, Jinghua Li, Bochong Zhang, Yuekai Li, Yaqiong School of Computer Science and Technology Heilongjiang University Harbin150001 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9789811322020

Influence maximization is one of the key research problems in social networks due to its wide applications like spread of ideas and viral marketing of products. Most of the existing work focus on social networks containing only positive relationships (e.g. friend or trust) between users, but in reality social networks containing both positive and negative relationships (e.g. foe or distrust). Ignoring the negative relations may lead to over-estimation of positive influence in practical applications. Thus, in this paper, we study influence maximization problem with negative effects (NIM). To address the NIM problem, we use the polarity Independent Cascade (IC-P) diffusion model which extends the standard Independent Cascade (IC) model with negative opinions. Then we propose the positive influence maximization algorithm (PIM) and negative influence maximization (NIM) problem. We prove that influence function of the NIM problem is monotonic and submodular, so we propose a CELF based algorithm (CELF_NIM) to solve it. Experiments results show that our algorithm has matching influence spread compared with greedy algorithm and achieves several orders of magnitude time improvement. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Economic and social effects

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 1

引用

4th International Conference of Pioneer Computer Scientists, Engineers and Educators, ICPCSEE 2018

作者： Jia, Boxuan Li, Jinbao Xu, Hui School of Computer Science and Technology Heilongjiang University HarbinHeilongjiang150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province HarbinHeilongjiang150080 China

ISBN: (数字)9789811322037

ISBN: (纸本)9789811322020

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. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Ubiquitous computing

来源：评论

学校读者我要写书评

暂无评论

Negative Influence Maximization in Social Networks

Negative Influence Maximization in Social Networks

引用

2018国际计算机前沿大会（原国际青年计算机大会）

作者： Jinghua Zhu Bochong Li Yuekai Zhang Yaqiong Li School of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

Influence maximization is one of the key research problems in social networks due to its wide applications like spread of ideas and viral marketing of products. Most of the existing work focus on social networks containing only positive relationships（e.g. friend or trust） between users, but in reality social networks containing both positive and negative relationships（e.g. foe or distrust）. Ignoring the negative relations may lead to over-estimation of positive influence in practical applications. Thus, in this paper, we study influence maximization problem with negative effects（NIM）. To address the NIM problem, we use the polarity Independent Cascade（IC-P） diffusion model which extends the standard Independent Cascade（IC） model with negative *** we propose the positive influence maximization algorithm（PIM） and negative influence maximization（NIM） problem. We prove that influence function of the NIM problem is monotonic and submodular, so we propose a CELF based algorithm（CELFIM） to solve it. Experiments results show that our algorithm has matching influence spread compared with greedy algorithm and achieves several orders of magnitude time improvement.

关键词：

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

Visual Tracking via Spatio-temporal Context Learning using Multi-Templates 3rd

Visual Tracking via Spatio-temporal Context Learning using M...

引用

2017 IEEE 第3届信息技术与机电一体化工程国际学术会议(ITOEC 2017)

作者： Zhengyu Zhu Wei Zhu Shuai Li College of Computer Science Chongqing University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

Probabilistic tracking algorithms typically using linear structure to update the learning *** linear structure is not appropriate for long-term robust tracking as the occlusion and other challe

ISBN: (纸本)9781509053643;9781509053636

Probabilistic tracking algorithms typically using linear structure to update the learning *** linear structure is not appropriate for long-term robust tracking as the occlusion and other challe

关键词： Target tracking Adaptation models Robustness Computational modeling Bayes methods Context modeling

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：