在多簇处理器情况下,指令应用所带来的簇间数据交互问题已经成为制约处理器性能的关键问题。针对此问题提出了在一般的调度后进行一次后溯重调度优化过程,减少了簇间的数据交互量,提高了编译器关于处理器的利用率,同时减少了编译生成的...在多簇处理器情况下,指令应用所带来的簇间数据交互问题已经成为制约处理器性能的关键问题。针对此问题提出了在一般的调度后进行一次后溯重调度优化过程,减少了簇间的数据交互量,提高了编译器关于处理器的利用率,同时减少了编译生成的指令序列运行时所消耗的功耗。实验结果表明,利用该方法进行调度,比列表调度算法簇间数据交互量减少平均44.36%,调度后的指令执行时间的平均减少量为24.93%,比UAS(unified assign and schedule)调度算法簇间数据交互量减少平均31.25%,调度后的指令执行时间的平均减少量为14.62%。展开更多
For many clustering algorithms,it is very important to determine an appropriate number of clusters,which is called cluster validity problem.In this paper,a new clustering validity assessment index is proposed based on...For many clustering algorithms,it is very important to determine an appropriate number of clusters,which is called cluster validity problem.In this paper,a new clustering validity assessment index is proposed based on a novel method to select the margin point between two clusters for in-ter-cluster similarity more accurately,and provides an improved scatter function for intra-cluster similarity.Simulation results show the effectiveness of the proposed index on the data sets under consideration regardless of the choice of a clustering algorithm.展开更多
Privacy is becoming one of the most notable challenges threatening wireless sensor networks(WSNs).Adversaries may use RF(radio frequency) localization techniques to perform hop-by-hop trace back to the source sensor&#...Privacy is becoming one of the most notable challenges threatening wireless sensor networks(WSNs).Adversaries may use RF(radio frequency) localization techniques to perform hop-by-hop trace back to the source sensor's location.A multiple k-hop clusters based routing strategy(MHCR) is proposed to preserve source-location privacy as well as enhance energy efficiency for WSNs.Owing to the inherent characteristics of intra-cluster data aggregation,each sensor of the interference clusters is able to act as a fake source to confuse the adversary.Moreover,dummy traffic could be filtered efficiently by the cluster heads during the data aggregation,ensuring no energy consumption be burdened in the hotspot of the network.Through careful analysis and calculation on the distribution and the number of interference clusters,energy efficiency is significantly enhanced without reducing the network lifetime.Finally,the security and delay performance of MHCR scheme are theoretically analyzed.Extensive analysis and simulation results demonstrate that MHCR scheme can improve both the location privacy security and energy efficiency markedly,especially in large-scale WSNs.展开更多
文摘在多簇处理器情况下,指令应用所带来的簇间数据交互问题已经成为制约处理器性能的关键问题。针对此问题提出了在一般的调度后进行一次后溯重调度优化过程,减少了簇间的数据交互量,提高了编译器关于处理器的利用率,同时减少了编译生成的指令序列运行时所消耗的功耗。实验结果表明,利用该方法进行调度,比列表调度算法簇间数据交互量减少平均44.36%,调度后的指令执行时间的平均减少量为24.93%,比UAS(unified assign and schedule)调度算法簇间数据交互量减少平均31.25%,调度后的指令执行时间的平均减少量为14.62%。
文摘For many clustering algorithms,it is very important to determine an appropriate number of clusters,which is called cluster validity problem.In this paper,a new clustering validity assessment index is proposed based on a novel method to select the margin point between two clusters for in-ter-cluster similarity more accurately,and provides an improved scatter function for intra-cluster similarity.Simulation results show the effectiveness of the proposed index on the data sets under consideration regardless of the choice of a clustering algorithm.
基金Project(2013DFB10070)supported by the International Science & Technology Cooperation Program of ChinaProject(2012GK4106)supported by the Hunan Provincial Science & Technology Program,ChinaProject(12MX15)supported by the Mittal Innovation Project of Central South University,China
文摘Privacy is becoming one of the most notable challenges threatening wireless sensor networks(WSNs).Adversaries may use RF(radio frequency) localization techniques to perform hop-by-hop trace back to the source sensor's location.A multiple k-hop clusters based routing strategy(MHCR) is proposed to preserve source-location privacy as well as enhance energy efficiency for WSNs.Owing to the inherent characteristics of intra-cluster data aggregation,each sensor of the interference clusters is able to act as a fake source to confuse the adversary.Moreover,dummy traffic could be filtered efficiently by the cluster heads during the data aggregation,ensuring no energy consumption be burdened in the hotspot of the network.Through careful analysis and calculation on the distribution and the number of interference clusters,energy efficiency is significantly enhanced without reducing the network lifetime.Finally,the security and delay performance of MHCR scheme are theoretically analyzed.Extensive analysis and simulation results demonstrate that MHCR scheme can improve both the location privacy security and energy efficiency markedly,especially in large-scale WSNs.
