透過您的圖書館登入
IP:18.118.12.222
  • 學位論文

運用微群集策略於階層式分群法

A Novel Hierarchical Clustering Algorithm Using the Micro-Cluster Strategy

指導教授 : 李維平

摘要


本研究提出以微群集為基礎的階層式分群法,簡稱為HCMC演算法。將密度法的概念應用在資料分割,並過濾雜訊資料,降低雜訊對分群的品質。HCMC演算法屬於二階段演算法,第一階段為分割階段,利用密度法的概念將資料分割出許多微群集,並將雜訊資料過濾,保留群聚主幹的資料;第二階段為合併階段,採用階層法中的,單一連接聚合法進行聚合,達到探索任意形狀的能力,經過分割階段的處理,使聚合的過程更有效率。 最後實驗結果,證明HCMC能降低雜訊資料影響分群結果,同時也有不錯的分群品質,時間複雜度計算上,也優於同類型的分群演算法。

並列摘要


This paper proposes a novel Hierarchical Clustering algorithm based on the Micro-Cluster strategy, called HCMC algorithm. In order to alleviate the influence caused by noise on the quality of clustering, the concept of density-based is applied to data partitioning and filtration of noise ratio. HCMC algorithm consists in two phases clustering. The first phase aims to partition several micro-clusters and to filter noise ratio with the operation of density-based, which saves the main materials of clusters. The second phase proceeds to encapsulate, applying single-linkage agglomerative algorithm to explore of arbitrary shapes. With this phase of partitioning, the process of encapsulation develops efficiency. Lastly, this experiment demonstrates that HCMC algorithm is capable of reducing the impact on clustering caused by noise ratio and keeping a fair quality of clustering as well. In the meantime, HCMC algorithm also proves to be superior to other clustering algorithms among the same categories as far as the complicated time calculation is concerned.

參考文獻


(1) 余佳玲、黃智嘉、陳靜慧、陳建誌(民100)。使用數位影像處理的模糊分群法檢測咬翼x光片影像找出牙齒鄰接面的齲齒。中華民國家庭牙醫學雜誌,5(4),14-19。
(2) 周歆凱、黃興進、蔡明足、翁林仲、蘇喜、陳真吟(民98)。運用資料探勘之叢集分析技術探討急診72小時再返診病患特性。澄清醫護管理雜誌,5(3),13-20。
(4) 陳榮昌、林育臣(民92)。群聚演算法及群聚參數的分析與探討。朝陽學報,8,327-353。
(6) 黃書猛、張中權(民99)。應用空間資料探勘於未來需求規劃之研究─以都會區捷運系統為例。電子商務研究,8(1),頁105-122。
(1) Cao, F., Ester, M., Qian, W., & Zhou, A. (2006). Density-based clustering over an evolving data stream with noise. In: Proc. SIAM Conf. Data Mining.

延伸閱讀