检索结果-内蒙古大学图书馆

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Jinliang Zheng Jun Lu Xinyi Shi Yan Shi Ruiqing Jing College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China University of Chinese Academy of Sciences

In this paper, a GPU-based parallel algorithm is proposed to improve the processing efficiency of motif recognition algorithm. The work includes a serial motif recognition algorithm and a parallel algorithm based on GPU. Our GPU parallel algorithm is compared with the serial algorithm by using of 1 KB promoter data of five kinds of plant genes upstream regions. The experimental results show that a factor of 20 speeds can be achieved. It means that there are a lot of advantages by GPU parallel technology on gene motif recognition algorithm. It is significant to the great amount of data analysis work of genetic sequence.

关键词： Graphics processing units Instruction sets Algorithm design and analysis parallel algorithms Bioinformatics Synchronization Biology

来源：评论

学校读者我要写书评

暂无评论

The key Algorithms of Promoter Data parallel Processing Based on OpenMP

The Key Algorithms of Promoter Data Parallel Processing Base...

引用

International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery, CyberC

作者： Yan Shi Jun Lu Xinyi Shi Jinliang Zheng Jun Li College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China University of Chinese Academy of Sciences Heilongjiang University Harbin Heilongjiang CN

The key algorithm of parallel technology based on OpenMP is advanced to dispose the promoter data. The promoter data are intercepted from the upstream area of five plants sequences. The five plants contain Arabidopsis Thaliana, Soybean, Alfalfa, Rice and Beans. The processing includes disturbing the sequences in random, calculating the P value, selecting the significant motifs from the frequent motifs, labeling the sequence number and so on. The serial algorithm and the parallel algorithm are compared in the implementation procedure. The experimental result shows that the OpenMP parallel technology can effectively improve the efficiency of the promoter data analysis and processing. It is a realistic significance to the vast amounts of biological information data processing.

关键词： Instruction sets parallel algorithms Algorithm design and analysis Gene expression Distributed databases Labeling

来源：评论

学校读者我要写书评

暂无评论

A probabilistic group reverse k-nearest-neighbor query in sensor networks 1

引用

7th China Conference of Wireless Sensor Networks, CWSN 2013

作者： Zhu, Jinghua Kan, Bin Liu, Yong Wang, Tong Pan, Liqiang Liu, Dan School of Computer Science and Technology Heilongjiang University Harbin 150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin 150080 China College of Information and Communication Engineering Harbin Engineering University Harbin 150001 China School of Computer and Science Technology Harbin School of Technology Harbin 150001 China School of Computer Science Northeast Forestry University Harbin 150001 China

ISBN: (数字)9783642541742

ISBN: (纸本)9783642541735

Group Reverse k-Nearest-Neighbor Query (GRkNN) can be used to evaluate the influences of query objects and has wide applications. Traditional algorithms are not able to obtain satisfied results for uncertain sensor network data. A probabilistic threshold group reverse k nearest neighbor query (PT-GRkNN) is proposed in this paper. PT-GRkNN exploits filter-refine framework, geometric filter and probability filter are proposed to shrink the search space, the final query results can be obtained by refine phase. Experimental results show that the efficiency of PT-GRkNN is better than the existing methods. © 2014 Springer-Verlag Berlin Heidelberg.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Channel allocation and routing strategy in multi-radio multi-channel wireless sensor networks

引用

Ruan Jian Xue Bao/Journal of Software 2014年 25卷 103-112页

作者： Ni, Lin-Yu Li, Jin-Bao School of Computer Science and Technology Heilongjiang University Harbin150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin150080 China

To address the problems of transmission delay, transmission conflicts and low throughput in Wireless sensor networks, this paper proposes a channel allocation and routing strategy in Multi-Radio Multi-Channel Networks. The strategy is to dynamically establish a k-ary n-cube topology. It not only uses the optimal static channel allocation algorithm to improve the throughput of nodes but also employs the dimension order routing algorithm to reduce transmission conflicts. This method is suitable for the network of density nodes with many communication conflicts. It can also be used in both single hop and multi hop network environment. The experiment results show that compared with traditional methods, the channel allocation and routing strategy based on the k-ary n-cube topology can effectively reduce end to end delay, network conflicts and energy consumption, prolong the network lifetime and increase the throughput of network. ©2014 ISCAS.

关键词： Throughput

来源：评论

学校读者我要写书评

暂无评论

MND: An information of detected neighbors based multi-channel neighbor discovery protocol for wireless sensor networks

MND: An information of detected neighbors based multi-channe...

引用

6th China Conference of Wireless Sensor Networks, CWSN 2012

作者： Li, Jinbao Wang, Zhigang Yao, Liang Guo, Longjiang School of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin 150080 China

ISBN: (纸本)9783642362514

Multi-channel neighbor discovery protocol based on information of detected neighbors for wireless sensor networks is proposed in this paper, called MND. To make sure that the discovery among nodes is as quick as possible, MND uses the schedule mechanism in which the nodes compute the potential neighbors set so as to calculate the sleep and wake schedule of the node. To minimize the influence of channel conflict to the performance, MND uses multi-channel mechanism and calculates the required total number of channels according to the duty cycle and network density. Through analysis, we can get how to choose the total number of channels for each node and the fact that the common neighbor node of the neighbors of a node is the neighbor of this node in a large probability. The simulation and test-bed experiment results show the discovery rate and discovery latency of MND is higher and lower, respectively. © 2013 Springer-Verlag.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Opportunistic routing in multi-power wireless sensor networks

Opportunistic routing in multi-power wireless sensor network...

引用

6th China Conference of Wireless Sensor Networks, CWSN 2012

作者： Guo, Yahong Guo, Xiaohang Zhang, Yanqing Zhu, Jinghua Li, Jinbao School of Information Science and Technology Heilongjiang University Harbin Heilongjiang 150080 China School of Computer Science and Technology Heilongjiang University Harbin Heilongjiang 150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Heilongjiang University Harbin Heilongjiang 150080 China

ISBN: (纸本)9783642362514

In this paper, we investigate on the opportunistic routing in Multi-Power Wireless Sensor Networks (MP WSNs). We first propose a routing metric called METT of opportunistic routing in MP WSNs, and model the power selecting process as a Markov decision process for computing the METT metric. We describe the METT-based opportunistic routing problem, and design a polynomial time optimal algorithm for getting the optimal routing and power selection scheme. Theory analysis and experiments show that the proposed multi-power opportunistic routing can improve the data transmission efficiency, significantly reduce the energy consumption and the end-to-end transmission delay. © 2013 Springer-Verlag.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Neighbor discovery algorithm based on the regulation of duty-cycle in mobile sensor network

Neighbor discovery algorithm based on the regulation of duty...

引用

8th International Conference on Wireless Algorithms, Systems, and Applications, WASA 2013

作者： Li, Jinbao Yang, Jian Zhang, Yanqing Guo, Longjiang Li, Yingshu School of Computer Science and Technology Heilongjiang University Harbin Heilongjiang 150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin Heilongjiang 150080 China Department of Computer Science Georgia State University Atlanta GA 30303 United States

ISBN: (纸本)9783642397004

In this paper, aiming at the problem that the node discovers its neighbor nodes, when it is moving in mobile sensor network, we propose an algorithm for dynamical regulating the duty cycle of the node which needs to discover it neighbor node. This algorithm uses the boundary nodes in the communication range of the node to predict potential neighbor nodes, applies passion point process to predict the number of nodes in communication range of the node, regulates the duty-cycle of the node based on the model of balls and boxes, and then schedules the waking time of the node periodically by using the duty-cycle which is regulated to finish the detection. Finally, theoretical analysis and simulation experiments show that the proposed algorithm can discover more neighbor nodes in the short period of time with less energy. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

Data collection using wavelet-segment constant compression in wireless sensor networks

引用

Yi Qi Yi Biao Xue Bao/Chinese Journal of Scientific Instrument 2013年第1期34卷 119-127页

作者： Li, Yang Guo, Longjiang Li, Jinbao Ren, Meirui School of Computer Science and Technology Heilongjiang University Harbin 150080 China Key Laboratory of Database and Parallel Computing Heilongjiang Province Harbin 150080 China

In structural health monitoring system, it usually needs to arrange lots of sensor nodes. In order to get the monitoring data in real time, frequent data collection is essential will consume so much energy, especially when the data is multi-dimensional. To reduce communication messages in the frequent data collection applications and as far as possible to extend the network lifetime. This paper proposes a data collection algorithm based on wavelet-segment constant compression(W-SDC), applies compressive sampling theory, and compress the messages with W-SDC before data transmitted, thereby this algorithm reduces the amount of data transmission. When the network is large-scale, it could save communication costs greatly, and extend the network lifetime. The total messages of traditional data collection method is O(N2), compressive data gathering method is O(MN), while the total communication costs of this algorithm is O(mN), where m

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

An implementation of the QR iterations for finding eigenvalues of matrices with CUDA on GPU

An implementation of the QR iterations for finding eigenvalu...

引用

2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer, MEC 2013

作者： Ren, Meirui Ren, Meihui Zhang, Wei Ping Wang, Tao Tian, Ning Li, Jinbao Guo, Longjiang School of Computer Science and Technology Heilongjiang University Harbin150080 China Harbin Research Institute of Electrical Instrumentation Harbin150028 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin150080 China

ISBN: (纸本)9781479925650

Based on the principle of QR loop iterations, this paper implements a parallel algorithm based on the hardware of GPU (Graphic Process Unit) by using routines from CUDA (Computer Unified Device Architecture) to find the eigenvalues of general matrices. CPU and GPU computing card form a client-server computing framework. Here, CPU can be regarded as a client and GPU card is considered as a computing server. For the experiment environment, this paper chooses a GPU card with the model of NVIDIA GeForce GTX460 as a server side and a CPU with the model of Intel Core is-760 quad-core as a client side. Win7 64-bit is selected as the operating system. The parallel implementation consists of two parts: PA-H and PA-QR. PA-H is a procedure that transforms a matrix A into the Hessenberg matrix B. PA-QR is the actual parallel algorithm of the QR iterations that is imposed on the Hessenberg matrix B for finding eigenvalues of the general matrix A. The speedup ratio of the proposed algorithm is jarless when the number of iterations becomes greater. The experimental results show that the parallel implementation with CUDA on GPU only makes use of less running time than traditional sequential algorithms. The speedup ratio of PA-H is between 1.79 and 7.81. The speedup ratio of PA-QR is between 3.24 and 118.9. Especially, when the order of general matrix equals 8192, the amount of iterations becomes 10000. The speedup ratio of the PA-H and the PA-QR can run up to 7.81 and 118.9 respectively. © 2013 IEEE.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Quick-merge sort algorithm based on Multi-core linux

Quick-merge sort algorithm based on Multi-core linux

引用

International Conference on Mechatronic Science, Electric Engineering and Computer

作者： Yong Liu Yan Yang School of Computer Science and Technology Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9781479925667

Sorting a list of input numbers is one of the most fundamental problems in the field of computer science. This paper presents an efficient implementation and detailed analysis of quick sort algorithm called QM-sort on Multi-core CPU architectures. Our QM-sort has two stages. The first stage is making blocks sorted, and the second stage is merging the sorted blocks. At the first stage, we propose a parallel quick sort algorithm named BPQsort. The run time of BPQsort achieves 40%-50% better than Qsort (STL), so we make blocks sorted more efficient. On the other hand, our algorithm can read file in parallel, thus reduce the time of reading file from disk. At the second stage, our parallel merge algorithm can operate the data on consecutive memory. Thus we avoid the expensive unaligned load/store operations, thus make our merge algorithm faster. At last, the run time of QM-sort is 10%-15% better than quick sort based on OpenMP.

关键词： Linux Instruction sets Hardware Algorithm design and analysis

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：