R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan. Authomatic subspace clustering of high dimensional data for data mining applications. In SIGMOD, 1998.  Home/Search   Document Not in Database   Summary   Related Articles   Check

....spaces is problematic as theoretical results [2] questioned the meaning of closest matching in high dimensional spaces. Recent research work has focused on discovering clusters embedded in the subspaces of a high dimensional data set. This problem is known as subspace clustering. CLIQUE [1] is the first to address the subspace clustering problem. It is a density and grid based clustering method. It discretizes the data space into non overlapping rectangular cells by partitioning each dimension to a fixed number of bins of equal length. A bin is dense if the fraction of total data ....

....result produced by this modified version of the FLOC algorithm is guaranteed to satisfy the specified constraints. 4. 4 Alternative Algorithm Another way to find the # clusters is to map it to the traditional (subspace) clustering problem and apply an existing clustering algorithm (e.g. CLIQUE [1]) This can be achieved in three steps. 1) For each pair of attributes A j1 and A j2 , a new attribute A j1j2 is derived to store the difference A j1 , A j2 .IfthereareM attributes, then derived attributes will be introduced. Given the data matrix shown in Figure 4(a) Figure 7 shows derived ....

[Article contains additional citation context not shown here]

R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan, Authomatic subspace clustering of high dimensional data for data mining applications, Proc. ACM SIGMOD, pp. 94-105, 1998.

....performance study is reported in Section 5. Section 6 concludes the paper. 2. RELATED WORK 2.1 Subspace Clustering Clustering in high dimensional space is often problematic as theoretical results [7] questioned the meaning of closest matching in high dimensional spaces. Recent research work [23, 24, 3, 4, 6, 8, 14] has focused on discovering clusters embedded in the subspaces of a high dimensional data set. This problem is known as subspace clustering. Based on the measure of similarity, there are two categories of clustering model. Distance based clustering. In this category, one of the well known ....

....embedded in the subspaces of a high dimensional data set. This problem is known as subspace clustering. Based on the measure of similarity, there are two categories of clustering model. Distance based clustering. In this category, one of the well known subspace clustering algorithms is CLIQUE [6]. CLIQUE is a density and grid based clustering method. It discretizes the data space into non overlapping rectangular cells by partitioning each dimension to a fixed number of bins of equal length. A bin is dense if the fraction of total data points contained in the bin is greater than a ....

[Article contains additional citation context not shown here]

R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan. Authomatic subspace clustering of high dimensional data for data mining applications. In SIGMOD, 1998.

....spaces is problematic as theoretical results [2] questioned the meaning of closest matching in high dimensional spaces. Recent research work has focused on discovering clusters embedded in the subspaces of a high dimensional data set. This problem is known as subspace clustering. CLIQUE [1] is the first to address the subspace clustering problem. It is a density and grid based clustering method. It discretizes the data space into non overlapping rectangular cells by partitioning each dimension to a fixed number of bins of equal length. A bin is dense if the fraction of total data ....

....result produced by this modified version of the FLOC algorithm is guaranteed to satisfy the specified constraints. 4. 4 Alternative Algorithm Another way to find the ffi clusters is to map it to the traditional (subspace) clustering problem and apply an existing clustering algorithm (e.g. CLIQUE [1]) This can be achieved in three steps. 1) For each pair of attributes A j1 and A j2 , a new attribute A j1j2 is derived to store the difference A j1 Gamma A j2 . If there are M attributes, then derived attributes will be introduced. Given the data matrix shown in Figure 4(a) Figure 7 shows ....

[Article contains additional citation context not shown here]

R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan, Authomatic subspace clustering of high dimensional data for data mining applications, Proc. ACM SIGMOD, pp. 94-105, 1998.

....been devoted to areas such as the scalability of clustering methods and the techniques for highdimensional clustering. Clustering in high dimensional spaces is often problematic as theoretical results [5] questioned the meaning of closest matching in high dimensional spaces. Recent research work[2,3,4,6,12]hasfocusedondiscoveringclustersembedded in the subspaces of a high dimensional data set. This problem is known as subspace clustering. In this paper, we explore a more general type of subspace clustering which uses pattern similarity to measure the distance between two objects. 1.1 Goal Most ....

....in Section 3. Section 4 explains our clustering algorithm in detail. Experimental results are shown in Section 5 and we conclude the paper in Section 6. 2. RELATED WORK as theoretical results [5] questioned the meaning of closest matching in high dimensional spaces. Recent research work [4, 2, 3, 12, 6, 15] has focused on discovering clusters embedded in the subspaces of a high dimensional data set. This problem is known as subspace clustering. pCluster stands for Pattern Cluster A well known clustering algorithm capable of finding clusters in subspaces is CLIQUE [4] CLIQUE is a density and ....

[Article contains additional citation context not shown here]

R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan. Authomatic subspace clustering of high dimensional data for data mining applications. In SIGMOD, 1998.

No context found.

R. Agrawal, J. Gehrke, D. Gunopulos, and P. Raghavan. Authomatic subspace clustering of high dimensional data for data mining applications. In SIGMOD, 1998.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC