As one of the commonly used queries in modern databases, skyline query has received extensive attention from database research community. The uncertainty of the data in wireless sensor networks makes the corresponding...As one of the commonly used queries in modern databases, skyline query has received extensive attention from database research community. The uncertainty of the data in wireless sensor networks makes the corresponding skyline uncertain and not unique. This paper investigates the Pr-Skyline problem, i.e., how to compute the skyline with the highest existence probability in a computational and energy-efficient way. We formulate the problem and prove that it is NP-Complete and cannot be approximated in a given expression. However, the proposed algorithm SKY-SEARCH with pruning techniques can guarantee the computational efficiency given relatively large input size, while the filter-based distributed optimization strategy significantly reduces the transmission cost and the required storage space of the sensor nodes. Extensive experiments verify the efficiency and scalability of SKY-SEARCH and the distributed optimizing strategy.展开更多
在无线传感器网络定位的距离估计方法研究中,普遍假设到达信号强度(received signal strength indicator,RSSI)与对应通信距离的对数成线性关系,但是该假设在实际无线通信环境下几乎不能满足。针对此问题本文提出一种基于区间数聚类的RS...在无线传感器网络定位的距离估计方法研究中,普遍假设到达信号强度(received signal strength indicator,RSSI)与对应通信距离的对数成线性关系,但是该假设在实际无线通信环境下几乎不能满足。针对此问题本文提出一种基于区间数聚类的RSSI-距离(RSSI-D)估计方法(distance estimation method using interval data clustering,DEMIDC),首先利用区间数表示方法结合实际定位环境中RSSI数据的统计信息表示RSSI的分布区域,然后针对不同环境中RSSI不确定性程度不同,分别采用基于区间数软聚类和硬聚类的方法对RSSI-D进行估计。最后采用3种典型通信环境下真实的RSSI测量数据完成的实验结果表明,该方法具有较高的距离估计精度,同时具备一定的实用价值。展开更多
文摘As one of the commonly used queries in modern databases, skyline query has received extensive attention from database research community. The uncertainty of the data in wireless sensor networks makes the corresponding skyline uncertain and not unique. This paper investigates the Pr-Skyline problem, i.e., how to compute the skyline with the highest existence probability in a computational and energy-efficient way. We formulate the problem and prove that it is NP-Complete and cannot be approximated in a given expression. However, the proposed algorithm SKY-SEARCH with pruning techniques can guarantee the computational efficiency given relatively large input size, while the filter-based distributed optimization strategy significantly reduces the transmission cost and the required storage space of the sensor nodes. Extensive experiments verify the efficiency and scalability of SKY-SEARCH and the distributed optimizing strategy.
文摘针对无线传感器网络(Wireless Sensor Networks,WSN)中的节点在真实环境中的不可靠感知现象及其对目标跟踪精度的影响,首先分析计算了成对传感器节点感知存在的不确定区域及其边界,在此基础上,提出了一种基于成对节点探测不确定性的目标容错跟踪方法(Tracking with Pairwise Uncertainty of RSSI,TPU-RSSI),即通过匹配分组感知采样得到的感知向量(sampling vector)和跟踪区域划分面(face)的特征向量(signature vector)来进行移动目标容错跟踪。该方法在保持跟踪方法灵活性的基础上,能够减小由环境因素带来的跟踪误差。为了降低计算复杂度,提出了一种基于邻居面连接的启发式匹配算法。大量的仿真实验结果均表明,所提方法相比同类的其他方法具有更强的灵活性和更高的定位精度。
文摘在无线传感器网络定位的距离估计方法研究中,普遍假设到达信号强度(received signal strength indicator,RSSI)与对应通信距离的对数成线性关系,但是该假设在实际无线通信环境下几乎不能满足。针对此问题本文提出一种基于区间数聚类的RSSI-距离(RSSI-D)估计方法(distance estimation method using interval data clustering,DEMIDC),首先利用区间数表示方法结合实际定位环境中RSSI数据的统计信息表示RSSI的分布区域,然后针对不同环境中RSSI不确定性程度不同,分别采用基于区间数软聚类和硬聚类的方法对RSSI-D进行估计。最后采用3种典型通信环境下真实的RSSI测量数据完成的实验结果表明,该方法具有较高的距离估计精度,同时具备一定的实用价值。
