在物件追蹤感測網路中使用資料探勘機制設 計動態分群物件追蹤演算法

A Dynamic Clustering Algorithm for Object Tracking Sensor Networks Using Data Mining Mechanism

張國強(Kuo-Chiang Chang)

指導教授 ： 廖文華

大同大學/經營設計學院/資訊經營學系所/碩士(2010年)

摘要

在本篇論文中，我們提出了一種在物件追踪感測器網絡（OTSNs）當中，基於
無線感測器節點頻率度之動態聚類算法，我們改進關聯規則演算法Apriori，用於物
件追踪傳感器網路（OTSNs）中挖掘物件移動頻繁項目，使之適用於物件追踪感測
器網路（OTSNs），能夠提取有關於感測器數據的頻繁，讓挖掘出的頻繁項目可以找
到移動物體的路徑。確定主要節點的頻率度和使用它們進行K -mean 分群和挖掘適
當的物件頻繁項目，這將提高網路生命週期和物件預測的準確性。幾個實驗研究已
經進行評估我們所提出的動態分群方法用於物件追踪感測器網路。

關鍵字

資料探勘 ； 物件追蹤網路 ； 無線感測網路

並列摘要

In this paper, we propose a dynamic clustering algorithm based on sensor node
frequency for object tracking sensor networks, and we improved apriori algorithm for
mining object move association rules, make it applies to the object tracking sensor
networks , which is able to extract data regarding the sensors’ patterns, let dig out the item
make the path of moving objects can be found. The main goal of determine node
frequency is to use them to K-mean clustering and appropriate association item, that will
improve the network live time and forecast accuracy. Several experimental studies have
been conducted to evaluate our proposed dynamic clustering method for clustering object
tracking sensor networks.

並列關鍵字

wireless senso ； datamining ； object tracking sensor networks

參考文獻

[1] R. Agrawal, R. Srikant, “Fast Algorithms for Mining Association Rules,” IEEE

International Conference on Very Large Data Bases, 1979.

[2] I.F. Akyildiz and E.P. Stuntebeck, “Wireless Underground Sensor Networks:

Mechanisms for Generating Association Rules in Wireless Sensor Networks,” IEEE

Transactions on Vehicular Technology, Vol. 58, No. 8, October 2009.