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

Estimation of the number of distinct values over data stream based on compound sliding window

Journal of Software

引用

Journal of Software 2013年第1期8卷 19-24页

作者： Zhong, Yingli Zhu, Jinghua Ren, Meirui Yang, Yan School of Computer Science and Technology Heilongjiang University Harbin 150080 China Key Laboratory of Database and Parallel Computing Heilongjiang Province Harbin 150080 China

Estimating the number of distinct values in a data stream is a vital problem with many applications such as complex join query over multiple data streams. In this paper, we focus on the continuous and periodic distinct values estimation over sliding windows. We propose a compound sliding window model to compute the distinct values over basic sliding windows in an incremental way. LDV, HDV and AHDV are the three algorithms that are based on compound sliding windows. The basic idea behind the compound sliding windows is to organize the basic windows into a Hash table according to distinct values. Whenever a new data arrives at the data stream, it is inserted into a basic window. Once the basic window is full, a scan using distinct values is executed and the distinct values number is updated incrementally. Theoretical analysis and experiment results show that the distinct values estimation algorithms based on compound sliding windows have a great performance benefits. © 2013 ACADEMY PUBLISHER.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A novel data broadcast strategy for traffic information query in the VANETs

A novel data broadcast strategy for traffic information quer...

引用

14th International Conference on Web-Age Information Management, WAIM 2013

作者： Wang, Xinjing Guo, Longjiang Li, Jinbao Ren, Meirui School of Computer Science and Technology Heilongjiang University China Key Laboratory of Database and Parallel Computing Heilongjiang China

ISBN: (纸本)9783642385612

This paper proposes a data broadcast strategy for traffic information query. Traffic information query is an important application in VANETs. Real-time traffic information query makes users to select path in a short time. By this data broadcast strategy, traffic information query can be quick and accurate after data is broadcast and forwarded. According to the restricted condition in the strategy, the vehicles broadcast their packets, and update, combine-forward or drop the data after receiving them in VANETs. In this way, more vehicles can receive data from source region. This algorithm can reduce the redundant data and control the communication congestion effectively. This paper adopts NS2 and SUMO as simulation platform. Simulation results show that, data collision rate is no more than 30%, and information area coverage rate reaches more than 80% with the strategy proposed in this paper after setting proper parameters. © 2013 Springer-Verlag Berlin Heidelberg.

关键词： Vehicular ad hoc networks

来源：评论

学校读者我要写书评

暂无评论

GPU acceleration of finding LPRs in DNA sequence based on SUA index

GPU acceleration of finding LPRs in DNA sequence based on SU...

引用

IEEE International Conference on Performance, computing and Communications (IPCCC)

作者： Shufang Du Longjiang Guo Chunyu Ai Meirui Ren Hao Qu Jinbao Li School of Computer Science and Technology Heilongjiang University Harbin Heilongjiang China Heilongjiang University Harbin Heilongjiang CN Division of Math & Computer Science University of South Carolina Upstate Spartanburg SC USA Key Laboratory of Database and Parallel Computing. Harbin Heilongiian China

ISBN: (纸本)9781479975761

The repetitions in biological sequence analysis are of great biological significance. Finding the repetitions has been a hot topic in gene projects naturally. In recent years, graphics processing unit (GPU) has been far exceeded the CPU in terms of computing capability and memory bandwidth, especially CUDA dramatically increases in computing performance by harnessing the power of the GPUs. This paper proposes efficient parallel algorithms on CUDA to accelerate finding PTRs which is redefined as LPRs based on the SUA Index. The proposed parallel algorithms have been utilized with the parallel primitives offered by Thrust library and the effective parallel bit compression technology based on division to achieve better acceleration. Optimization techniques include CUDA streams technology are also realized to reduce transmission latency. Experimental results show that the proposed parallel algorithms are faster than the benchmark with 1.6~5.4 speedup.

关键词： Graphics processing units parallel algorithms Arrays Acceleration Sorting Algorithm design and analysis DNA

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

GPU acceleration of finding frequent patterns over large biological sequence

GPU acceleration of finding frequent patterns over large bio...

引用

International Conference on parallel and Distributed Systems (ICPADS)

作者： Shufang Du Longjiang Guo Chunyu Ai Jinbao Li Meirui Ren Yahong Guo School of Computer Science and Technology Heilongjiang University Harbin Heilongjiang China Key Laboratory of Database and Parallel Computing Harbin Heilongjiang China Division of Math & Computer Science University of South Carolina Upstate Spartanburg SC USA School of Information Science and Technology Heilongjiang University Harbin Heilongjiang China

Biological frequent patterns usually correspond to the important function (or structure) in biological sequences. Along with the rapid growth of biological sequences, it is significant to find frequent patterns over a large bio-sequence efficiently. However, most of existing algorithms need to produce lots of short patterns or projected databases, which influence the efficiency badly and also increase the cost of space. Graphics processing units (GPUs) embracing many core computing devices, have been extensively applied to accelerate computation performance in many areas. In order to meet the demand of biologists, we redefine the frequent pattern problem with length constraints for finding frequent patterns. We present pruning optimization method for the serial algorithm (POSA), and based on this technique, we propose a parallel algorithm (POPA) which not only reduces the time complexity with a low space cost but also obtains better performance on CUDA. To validate the presented algorithms, we implemented the algorithms on multiple-core CPU and various GPU devices. Also, CUDA optimization techniques are applied to speed up calculation in the paper. Finally, experimental results show that compared with the serial algorithm on CPU with six cores, POSA achieves 1.2~4.5 speedup, and POPA gains 3~20 speedup.

关键词： Arrays Graphics processing units Biology Data mining Indexes parallel algorithms

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

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：