检索结果-内蒙古大学图书馆

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Yanrong Ding Xiaodong Wang Hu Shen Pengyu Guo National Key Laboratory for Parallel and Distributed Processing Changsha China

Nested Circular Directional MAC, a modified medium access control protocol of DMAC protocol, is proposed in this paper to support both directional antennas and omni-directional antennas simultaneously in one Ad Hoc network. Omni-directional antennas follow the RTS/CTS mechanism which is multi-hop and directional antennas follow the DRTS/DCTS mechanism, ensuring the asymmetric communication effectively. In order to resolve new deafness problem and hidden terminal problem, the directional antennas also use circular DRTS and nested antenna circumrotation. Simulation results show that NCDMAC supports hybrid antennas effectively and is better than MMAC and Circular-MAC in terms of increasing throughput, but it also increases the communication delay.

关键词： Delay Deafness Directive antennas Throughput Directional antennas Media Access Protocol

来源：评论

学校读者我要写书评

暂无评论

CD-Sched: An Automated Scheduling Framework for Accelerating Neural Network Training on Shared Memory CPU-DSP Platforms 23

CD-Sched: An Automated Scheduling Framework for Accelerating...

引用

Proceedings of the 2023 International Conference on Power, Communication, Computing and Networking Technologies

作者： Yuanyuan Xiao Zhiquan Lai Dongsheng Li National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology China National Key Laboratory of Parallel and Distributed Processing National University of Defense Technology China

ISBN: (纸本)9781450399951

DSP holds significant potential for important applications in Deep Neural Networks. However, there is currently a lack of research focused on shared-memory CPU-DSP heterogeneous chips. This paper proposes CD-Sched, an automated scheduling framework that aims to address this gap. By predicting the latency of operators on both CPU and DSP, CD-Sched automatically schedules the computation of operators to the appropriate computing device. This scheduling optimization accelerates the computation of individual operators and ultimately improves the overall training time of neural networks. In end-to-end training tasks, CD-Sched can significantly reduce the overall training time, with an average reduction of approximately 10.77%.

关键词： computation offloading

来源：评论

学校读者我要写书评

暂无评论

A load balancing-supported constant degree DHT ID assignment method

引用

Tien Tzu Hsueh Pao/Acta Electronica Sinica 2010年第11期38卷 2649-2654页

作者： Wang, Xiao-Hai Peng, Yu-Xing Li, Dong-Sheng Key Laboratory of Science and Technology for Parallel and Distributed Processing National University of Defense Technology Changsha Hunan 410073 China

A Load Balancing-Supported ID assignment method is the foundation to implement and maintain DHT overlays, realized constant degree DHTs usually use simple pure centralized or distributed ID management strategies, which cannot resolve the contradiction between cost of maintaining topologies' information and topologies' balance. Analyzing the universal tree structures in the topologies, an ID Assignment method RFIDAM based on the internal structure Routing Forest is proposed, which regularly aggregates local balancing information to guide new nodes' joining for overall balance. The experimental results show, with low maintenance and routing message overhead, the system's loading balance is efficiently ensured with the length of IDs differ by at most 2.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Temporal Inconsistency-Based Intrinsic Reward for Multi-Agent Reinforcement Learning

Temporal Inconsistency-Based Intrinsic Reward for Multi-Agen...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Shaoqi Sun Kele Xu National Key Lab of Parallel and Distributed Processing National University of Defense Technology Changsha China

Multi-agent reinforcement learning (MARL) has shown promising results in many challenging sequential decision-making tasks. Recently, deep neural networks have dominated this field. However, the policy networks of agent's may fall into local optimum during the training phase, which severely constrains the performance of exploration. To address this issue, we propose a novel MARL learning framework named PSAM, which contains a new temporal inconsistency-based intrinsic reward and a diversity control strategy. Specifically, we save the parameters of the deep models along the optimization path of the agent's policy network, which can be denoted as snapshots. Through measuring the difference between snapshots, we can employ the difference as an intrinsic reward. Moreover, we propose a diversity control strategy to improve the performance further. Finally, to verify the effectiveness of the proposed method, we conduct extensive experiments in several widely used MARL environments. The results show that in many environments, PSAM can not only achieve state-of-the-art performance and prevent the policy network from getting stuck in local minima but also accelerate the agent's learning of the policy. It is worth noting that the proposed regularizer can be used using a plug-and-play manner without introducing any additional hyper-parameters and training costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using NMFAS to identify key biological pathways associated with human diseases

Using NMFAS to identify key biological pathways associated w...

引用

2012 IEEE 6th International Conference on Systems Biology, ISB 2012

作者： Guo, Hao Zhu, Yunping Li, Dong He, Fuchu Liu, Qijun State Key Laboratory of Proteomics Beijing Proteome Research Centre Beijing Institute of Radiation Medicine Beijing China National Laboratory for Parallel and Distributed Processing National University of Deference and Technology Changsha China

ISBN: (纸本)9781467343985

Gene expression microarray enables us to measure the gene expression levels for thousands of genes at the same time. Here, we constructed the non-negative matrix factorization analysis strategy (NMFAS) to dig the underlying biological pathways related with various diseases by factorizing the pathway expression matrix, which was extracted from microarray matrix using pathway membership information, into the product of row and column vectors. We defined row vector as the pathway activity and column vector as the gene contribution weight. Via comparing the pathway activity of two different sample groups, we can identify significantly expressed pathways. We applied this strategy on two different cases: smoking and type 2 diabetes (DM2). We found 152 differentially expressed pathways by the comparison of pathway activity between smoker and never smoker, including pathways that have been validated in literature, such as "O-Glycans biosynthesis" and "Glutathione metabolism". We also found important genes related to smoking phenotype, such as NQO, HSPA1A, ALDH3A1. As for DM2 analysis, our results suggested 9 pathways were significantly expressed, including typical pathways like "Oxidative phosphorylation" and "mTOR signaling pathway", and found genes like CAPNS1, APP, COX7A1, COX7B, which might play important roles in the cellular regulations of DM2. In conclusion, Our strategy can be efficiently used to integrate gene expression profiles and biological pathway information to identify the key processes underlying human disease and can identify gene pathways missed by alternative approaches. © 2012 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Two improved GPU acceleration strategies for force-directed graph layout

Two improved GPU acceleration strategies for force-directed ...

引用

International Conference on Computer Application and System Modeling (ICCASM)

作者： Yong-Xian Wang Zong-Zhe Li Lu Yao Wei Cao Zheng-Hua Wang National Key Laboratory of Parallel and Distributed Processing National University of Defense Technology Changsha China National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha China

Force directed approach is one of the most widely used methods in graph drawing research. However, the running time is increased intolerablely along with the enlargement of the graph size, which restricts the algorithm's practicability. By the aid of GPU (graphics processing unit) computing platform, we can speed-up the graph layout with low cost, but the existing GPU implementation mainly employees an “one-by-one” style to update the vertex' coordination per iteration, which has a lower convergent rate than the “batch” style which is instead used commonly in traditional CPU implementation. As a result, the aesthetics of graph layout would be decreased if the total running time is restricted. It is hard to achieve both a high speedup factor of GPU over CPU and a high convergent rate in existing GPU computing implementation. In order to solve this problem partially, this paper presents two new strategies to implement the large-scale graph layout on CPU+GPU heteromerous platform to accelerate the force directed layout for graph drawing problem. The numerical computation results show that our GPU implementation can dramatically improve the performance of force-direct layout and is 20 times on a NVIDIA GeForce 9800 GT GPU at 1.44 GHz faster than the one on single-CPU core of Intel Pentium 4 PC at 3.0 GHz for the graph layout with moderate size (typically 1000 vertices).

关键词： Graphics processing unit Gallium nitride Heating

来源：评论

学校读者我要写书评

暂无评论

Understanding User Interests Acquisition in Personalized Online Course Recommendation

Understanding User Interests Acquisition in Personalized Onl...

引用

Asia Pacific Web (APWeb) and Web-Age Information Management (WAIM) Joint Conference on Web and Big Data, APWeb-WAIM 2018

作者： Li, Xiao Wang, Ting Wang, Huaimin Tang, Jintao Information Center National University of Defense Technology Changsha China College of Computer National University of Defense Technology Changsha China National Key Laboratory of Parallel and Distributed Processing National University of Defense Technology Changsha China

ISBN: (纸本)9783030012977

MOOCs have attracted a large number of learners with different education background all over the world. Despite its increasing popularity, MOOCs still suffer from the problem of high drop-out rate. One important reason may be due to the difficulty in understanding learning demand and user interests. To helper users find the most suitable courses, personalized course recommendation technology has become a hot research topic in e-learning and data mining community. One of the keys to the success of personalized course recommendation is a good user modeling method. Previous works in course recommendation often focus on developing user modeling methodology which learns latent user interests from historic learning data. Recently, interactive course recommendation has become more and more popular. In this paradigm, recommender systems can directly query user interests through survey tables or questionnaires and thus the learned interests may be more accurate. In this paper, we study the user interest acquisition problem based on the interactive course recommendation framework (ICRF). Under this framework, we systematically discuss different settings on querying user interests. To reduce performance-cost score, we propose the ICRF user interest acquisition algorithm that combines representative sampling and interest propagation algorithm to acquire user interests in a cost-effective way. With extensive experiments on real-world MOOC course enrollment datasets, we empirically demonstrate that our selective acquisition strategy is very effective and it can reduce the performance-cost score by 30.25% compared to the traditional aggressive acquisition strategies. © 2018, Springer Nature Switzerland AG.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Cooperative spectrum sharing in relay-trading mode: A fairness view

Cooperative spectrum sharing in relay-trading mode: A fairne...

引用

4th International Conference on Cyber-Enabled distributed Computing and Knowledge Discovery, CyberC 2012

作者： Liu, Lixia Hu, Gang Xu, Ming Peng, Yuxing National Key Laboratory for Parallel and Distributed Processing School of Computer National University of Defense Technology Changsha 410073 China Department of Networks Engineering School of Computer National University of Defense Technology Changsha 410073 China

ISBN: (纸本)9780769548104

In the relay-trading mode of wireless cognitive radio networks the secondary user (SU) can achieve a promised spectrum access opportunity by relaying for the primary user (PU). How to utilize the exchanged resource efficiently and fairly is an interesting and practical problem. In this paper we proposed a cooperative spectrum sharing strategy (RT-CSS) for the relay-trading mode from the fairness view. The cooperative SUs are gathered in a cooperative sharing group (CSG), and contribution metric (CM) is proposed to measure each CSG member's contribution to CSG as well as benefit from CSG. The adjustment of CM can guarantee the fairness and efficiency of spectrum sharing. The numerical simulation shows that RT-CSS can achieve better performance than the sense-uncooperative mode. © 2012 IEEE.

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid architecture for high speed regular expression matching 1

引用

1st International Symposium on Mobile Internet Security, MobiSec 2016

作者： Xu, Chengcheng Zhao, Baokang Chen, Shuhui Su, Jinshu College of Computer National University of Defense Technology No. 137 Yanwachi Street ChangshaHunan410073 China National Key Laboratory for Parallel and Distributed Processing National University of Defense Technology Changsha410073 China

ISBN: (数字)9789811078507

ISBN: (纸本)9789811078491

Mobile devices play an important role in our everyday lives, but they also bring great security threats. Deep packet inspection (DPI) is one of the most efficient methods to detect the malicious information hidden in the mobile traffic, and regular expression matching is widely used in DPI for its powerful expressive ability. However, with the increasing complexity of regular expressions, traditional solutions cannot meet the requirements of both storage and high performance. In this paper, we propose a novel hybrid matching architecture and two-stage memory architecture for the state of the art hybrid FA to solve this problem. Experiment results confirm that our architecture is scalable to complex rule sets, and the matching performance outperforms state of the art memory centric solution by up to 15x. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Memory architecture

来源：评论

学校读者我要写书评

暂无评论

An optimized method for automatic test oracle generation from real-time specification

An optimized method for automatic test oracle generation fro...

引用

IEEE International Conference on Engineering of Complex Computer Systems

作者： Xin Wang Zhi-Chang Qi Shuhao Li National Laboratory for Parallel and Distributed Processing Changsha China National Lab. for Parallel & Distributed Process. Changsha China

Test oracles are widely used to verify whether a system under test is running as desired. Since the correctness of real-time systems depends on the logical results of the computation and the time when results are produced at the same time, an optimized model checking-based method for test oracles generation is proposed to check if the system traces satisfy their real-time specifications at run time. Inspired by the idea of real-time model checking, the test oracles can be automatically generated from their specifications in the real-time logic MITL/sub [o,d]/ in a simpler way and modelled by a variant of the timed automata. Assertions are chosen to acquire the traces of real-time systems. A case study is presented to demonstrate the usefulness of the method proposed in this paper.

关键词： Optimization methods Automatic testing Real time systems System testing Software testing laboratories Logic testing Automata Aerospace testing distributed processing

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：