無線異質型感測網路上協同合作之事件偵測與追蹤機制

Collaborative Event Detection and Tracking in Wireless Heterogeneous Sensor Networks

楊寶華(Pwa-Hua Yang)

指導教授 ： 石貴平

淡江大學/工學院/資訊工程學系碩士班/碩士(2005年)

https://doi.org/10.6846/TKU.2005.00240

摘要

由低成本、低耗電感測器(Sensor Node)構成的無線感測網路(Wireless Sensor Network)可以運作在感測區域(Sensing Field)以偵測與追蹤事件。本論文提出一個應用於無線異質型感測網路（Wireless Heterogeneous Sensor Network，WHSN）之事件偵測與追蹤演算法，稱為CoEDT。CoEDT的基本概念係由可以感測事件屬性的Sensor Node各自建立屬性異常的區域，再藉由這些Sensor Node之間的協同合作判斷鄰近區域是否發生事件，並選取適合的Sensor Nodes表示事件的範圍。CoEDT主要包含「Vicinity Triangulation」、「Event Detection」和「Border Node Determination」三個部分，其中前兩者的目的為事件的偵測，而第三個部分則是要追蹤事件。基本上，CoEDT是一個完全分散式的方法，除了可以透過不同種類Sensor Node間協同合作的特性完成事件的偵測，更能動態地追蹤事件的範圍。本論文的實驗結果顯示位於事件區域內的Sensor Node中，約有90%的Sensor Node可以被正確地判斷出位於事件的區域內，而CoEDT選出的邊界點（Border Node）亦能充分表現事件的範圍。

關鍵字

協同合作 ； 偵測 ； 事件 ； 追蹤 ； 無線異質型感測網路

並列摘要

Wireless Sensor Networks (WSNs) formed by sensor nodes are operated on sensing field to detect and track events. The thesis proposes a collaborative protocol, called CoEDT, for event detection and tracking in Wireless Heterogeneous Sensor Networks (WHSNs). The main idea of CoEDT is for the same kind of sensor nodes to respectively construct the attribute region, collaborately determine whether the event occurs in the vicinity of the sensing region of different kinds of sensor nodes, and dynamically identify the event boundary via the border nodes. CoEDT comprises three major components, Vicinity Triangulation, Event Detection, and Border Node Determination. “Vicinity Triangulation” and “Event Detection” are used for the detection of events. “Border Node Determination” is exploited in tracking events. Basically, CoEDT is a fully distributed protocol for event detection and tracking. In CoEDT, event detection is achieved by means of all kinds of sensor nodes in the collaborative manner. Additionally, CoEDT is able to dynamically track the event via the suitable border nodes. The simulation results validate the performances of CoEDT in terms of the accuracy and fitness. Approximately 90% sensor nodes within the event region can be correctly identified. Besides, the border nodes identified by CoEDT can well reflect the event boundary.

並列關鍵字

collaborative ； detection ； event ； tracking ； wireless heterogeneous sensor networks

參考文獻

[2] N. Bulusu, J. Heidemann, and D. Estrin, “GPS-less Low Cost Outdoor Localization for Very Small Devices,” IEEE Personal Communications Magazine, vol. 7, no. 5, pp. 28-34, 2000.

[3] W. Chen, J. C. Hou, and L. Sha, “Dynamic Clustering for Acoustic Target Tracking in Wireless Sensor Networks,” IEEE Transactions on Mobile Computing, vol. 3, no. 3, pp. 258-271, 2004.

[4] K. Chintalapudi and R. Govindan, “Localized Edge Detection in Sensor Fields,” Ad-Hoc Networks Journal, vol. 1, pp. 273-291, Sep. 2003.

[8] X. Ji and H. Zha, “Detection and Tracking Large Continuous Objects in Wireless Ad-Hoc Sensor Networks”, Technical Report, Departmentn of Computer Science and Engineering, Pennsylvania State University, 2003.

[9] X. Ji, H. Zha, J. J. Metzner, and G. Kesidis, “Dynamic Cluster Structure for Object Detection and Tracking in Wireless Ad-Hoc Sensor Networks,” in Proceedings of the IEEE International Conference on Communications (ICC), June 2004, pp. 3807-3811.