检索结果-内蒙古大学图书馆

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

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

Data query based on data cache and channel switch in multi-radio wireless sensor networks

引用

Jisuanji Xuebao/Chinese Journal of Computers 2012年第11期35卷 2403-2414页

作者： Zhang, Yan-Qing Li, Jin-Bao Guo, Long-Jiang Zhu, Jing-Hua School of Computer Science and Technology Heilongjiang University Harbin 150080 China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin 150080 China

Due to the nature of multi-radio multi-channel wireless sensor networks, such as the quality of service of the links, channel conflict etc., we investigated the problem of data query based on data cache and channel switch, and proved it to be an NP-complete problem. Firstly, we constructed a LP equation based on the data flow conservation and link-channel constraint etc. to formulate the problem, then designed a polynomial approximate algorithm. The algorithm used dynamic programming strategy to minimize the delay of unit data packet transmission from cache nodes to the query node, greedily chose a cache node with the smallest delay of unit data packet transmission, and collected the new covered data packets. Theoretical analysis and experimental results indicate that the proposed algorithm can reduce the communicate delay and improve the efficiency of query effectively.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

DMSA: Dynamic Multi-Scale Unsupervised Semantic Segmentation Based On Adaptive Affinity 48

DMSA: Dynamic Multi-Scale Unsupervised Semantic Segmentation...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Yang, Kun Lu, Jun Heilongjiang University College of Computer Science and Technology Harbin150080 China Jiaxiang Industrial Technology Research Institute of Hlju Jining China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9781728163277

The proposed method in this paper proposes an end-to-end unsupervised semantic segmentation architecture DMSA based on four loss functions. The framework uses Atrous Spatial Pyramid Pooling (ASPP) module to enhance feature extraction. At the same time, a dynamic dilation strategy is designed to better capture multi-scale context information. Secondly, a Pixel-Adaptive Refinement (PAR) module is introduced, which can adaptively refine the initial pseudo labels after feature fusion to obtain high quality pseudo labels. Experiments show that the proposed DSMA framework is superior to the existing methods on the saliency dataset. On the COCO 80 dataset, the MIoU is improved by 2.0, and the accuracy is improved by 5.39. On the Pascal VOC 2012 Augmented dataset, the MIoU is improved by 4.9, and the accuracy is improved by 3.4. In addition, the convergence speed of the model is also greatly improved after the introduction of the PAR module. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

MPMC: An algorithm for data aggregation scheduling in multi-channel and multi-power wireless sensor networks

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2012年第7期49卷 1568-1578页

作者： Fan, Wenbin 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 150001 China

Data aggregation is a fundamental and yet time-consuming task in WSNs, especially in high-density WSNs. Therefore, people have focused on the problem of minimum-latency data aggregation. The problem has been already proved that it is an NP-hard. This paper proposes a cluster-based data aggregation scheduling algorithm called MPMC in multi-channel and multi-power WSNs to minimize the data aggregation latency. The paper adopts the idea of that the low power is used for packet transmission in inner-cluster and high power is used for packet transmission between clusters. This paper analyzes the number of channel under different topologies that approaches a constant. In simulation experiments, MPMC compares with the best algorithm based on single channel and the best algorithm based on multi-channel. Simulation results show that the MPMC algorithm proposed in this paper achieves the minimum average latency.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Cross-level Relational Graph Contrastive Learning for Bundle Recommendation

Cross-level Relational Graph Contrastive Learning for Bundle...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Wang, Nan Sun, Jiabao Li, Jinbao College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang University Harbin China Qilu University of Technology Shandong Artificial Intelligence Institute School of Mathematics and Statistics Jinan China

ISBN: (纸本)9798350304855

Different from the traditional recommendation system which regards a single item as an atomic unit, the purpose of bundle recommendation is to recommend a set of items to users. In recent years, some work often uses the model based on GNN to solve the bundle recommendation problem. However, compared with the traditional recommendation models, the GNN-based bundle recommendation has a more serious data sparse problem, which significantly reduces the performance of the model. Meanwhile, due to the lack of modeling ability of complex interactive information and dependent information, it is still far from enough to learn the representation of users and bundles. In view of the advantages of contrast learning in mining its own supervisory signals, we propose a model named Cross-level relational graph Contrastive Learning for Bundle Recommendation (CL2BRec). Different from previous contrastive learning methods, our method learns representations of users and bundles from multiple relational graphs of different levels through a crossview contrastive learning paradigm. Specifically, we regard the user-item/bundle graph as a local interaction relation view, the bundle-item graph as a local dependency relation view, and the user-bundle-item tripartite graph as a global structure view to build a cross-level bundle recommendation model. Extensive experiments conducted on two benchmark datasets demonstrate that CL2BRec outperforms the state-of-the-art methods by over 12.56% and 8.6%, respectively. © 2023 IEEE.

关键词： Recommender systems

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

A Bidirectional Representation Recommendation Based On Relevance Information Enhancement To Solve User Interest Drift

A Bidirectional Representation Recommendation Based On Relev...

引用

2023 IEEE International Conference on Web Services, ICWS 2023

作者： Wang, Nan Li, Kun Jiang, Xuefeng Li, Jinbao College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing Heilongjiang University Harbin China Qilu University of Technology Shandong Artificial Intelligence Institute School of Mathematics and Statistics Jinan China

ISBN: (纸本)9798350304855

The phenomenon that user interests change dynamically over time is called user interest drift, which makes it difficult for recommendation systems to obtain users' real interests. In order to better provide users with personalized services, it is very important to study recommendation methods that can be applied to user interest drift. However, the new interests of users are often very different from the interests that users have interacted with historically. It makes the correlation between the original user's historical interaction and the user's new interest very weak. Meanwhile, the information contained in user's sessions is not enough to support the inference of the new interest, resulting in a serious decrease in model performance. To alleviate the above problem, we propose a bidirectional representation recommendation based on relevance information enhancement to solve user interest drift (RA-Bert). The model is based on Bert and uses bidirectional self-attention mechanism to represent user sessions. In this model, we design a relevance information enhancement module to adaptively capture the information associated with the user's new interest from neighbors' sessions. Then, we integrate the relevance information into user's history sessions, which can effectively enhance the correlation between user's history sessions and the new interest. Further, in order to effectively supplement the missing relevance information in users' sessions, we design a new attention unit, which explicitly models the difference information between users and neighbors. Extensive experiments have demonstrated the effectiveness of our approach. Our code is publicly available at the link: https://***/LucasZen/paper_code. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Distributed multi-dimensional probabilistic Top-k query processing in sensor networks

引用

Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) 2012年第SUPPL.1期40卷 389-393+397页

作者： Zhu, Jinghua Guan, Xuemin Department of Computer Science and Technology Heilongjiang University Harbin 150080 China Key Laboratory of Database and Parallel Computing Heilongjiang Province Harbin 150080 China

A distributed multi-dimensional probabilistic Top-k (DMPT) query processing algorithm was proposed for sensor networks. DMPT exploited Skyline operator to get the Top-k results and reduced data transmissions and query delay through feedback and filtering mechanism. Data uncertainty, multi-dimensional attributes, distributed network and energy limitation were considered in DMPT, and the Top-k results were attained by computing Skylayers of data. Experiments on real and simulated data are conducted to demonstrate that DMPT has better energy efficiency and faster response compared with traditional algorithm.

关键词： Sensor networks

来源：评论

学校读者我要写书评

暂无评论

Research on Neutral Mutation Algorithm in DNA Polymorphism Testing based on OpenMP

Research on Neutral Mutation Algorithm in DNA Polymorphism T...

引用

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

作者： Jun Li Jun Lu Ruiqing Jing Qiong Wang Cheng Chang College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

ISBN: (纸本)9781479919819

Soybean genotypes are adopted as the data source and the Tajima's D statistical method is parallel implemented by OpenMP *** method is used for testing neutral mutation hypothesis of DNA *** setting the sliding window size,all chromosomes containing the massive windows with multiple SNP sites are parallel processed,then the number of individual in sample,the number of segregating sites(S) and average number of nucleotide differences(π) are *** parameters filtering,the Tajima's D values for the effective SNP sites in each sliding window are parallel *** to the experimental data,the serial/parallel algorithms are compared and the conclusion shows that the efficiency of testing neutral mutation can be improved by using the OpenMP *** is a realistic significance for processing massive biological information data.

关键词： genotype Tajima's D OpenMP SNP

来源：评论

学校读者我要写书评

暂无评论

Research on Jukes-Cantor Model parallel Algorithm Based on OpenMP

Research on Jukes-Cantor Model Parallel Algorithm Based on O...

引用

2015大数据技术及应用论坛

作者： Kang Wan Jun Lu Jiaju Zheng Zihan Ren College of Computer Science and Technology Heilongjiang University Key Laboratory of Database and Parallel Computing of Heilongjiang Province

The parallel algorithm of the evolutionary distance between different species is implemented by using Open MP parallel technique in this paper. In order to get the best degree of algorithm parallelism, the method of making loop variable corresponding to the rower and column labels of distance matrix is adopted. It is to say that the double loop can be converted into single loop to improve the parallel efficiency. The serial algorithm and parallel algorithm are compared in this paper. The experiment result shows that the highest speedup is14.1. It improves the running efficiency of the program. It is a great significance to dealing with massive bioinformatics data.

关键词： OpenMP parallel Evolutionary distance Distance matrix

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：