Adaptive record clustering

Yu, Clement; Suen, Cheing-mei; Lam, K. C.; Siu, Man‐Keung

doi:10.1145/3857.3861

Cited by 54 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For ease of discussion, we shall refer to each resource as a document. For this step any well-known single-server document clustering algorithm, such as K-Means (Forgy, 1965;MacQueen, 1967;Jain and Dubes, 1988;Frakes and Baeza-Yates, 1992), Single-Link (Hartigan, 1975;Gordon, 1981;Jain and Dubes, 1988), Complete-link (Gordon, 1981;Jain andDubes, 1988), Leader Algorithm (Hartigan, 1975), an adaptive clustering algorithm (Yu et al, 1985), etc., can be used in order to generate non-overlapping clusters of documents. The co-occurrence frequency of documents in complete user session records is used for determining the similarity of documents to each other in order to cluster documents based on access patterns in those clustering algorithms.…”

Section: Local Clustering Stepmentioning

confidence: 99%

Distributed Web Log Mining Using Maximal Large Itemsets

Sayal

Scheuermann

2001

Knowledge and Information Systems

View full text Add to dashboard Cite

We introduce a partitioning-based distributed document-clustering algorithm using user access patterns from multi-server web sites. Our algorithm makes it possible to exploit simultaneously adaptive document replication and persistent connections, two techniques that are most effective in decreasing the response time that is observed by web users. The algorithm first distributes the user access data evenly among the servers by using a hash function. Then, each server generates a local clustering on its fair share of the user sessions records by employing a traditional single-machine document-clustering algorithm. Finally, those local clustering results are combined together by using a novel procedure that generates maximal large itemsets of web documents. We present preliminary experimental results and discuss alternative approaches to be pursued in the future.

show abstract

Section: Local Clustering Stepmentioning

confidence: 99%

Distributed Web Log Mining Using Maximal Large Itemsets

Sayal

Scheuermann

2001

Knowledge and Information Systems

View full text Add to dashboard Cite

show abstract

“…The output from a software tool for such a purpose provides the input to DBAP or similar predictor. Some recent contributions have been addressed primarily at the problems associated with reporting sudden changes in access patterns and suggesting an appropriate assignment of records to physical storage in a time-efficient manner (Yu, 1985). This is a promising approach if automatic reorganization is to be contemplated.…”

Section: Placement Of Tuples In Databasesmentioning

confidence: 99%

Application of simulated annealing to clustering tuples in databases

Bell

McErlean

Stewart

et al. 1990

J. Am. Soc. Inf. Sci.

View full text Add to dashboard Cite

Techniques for general purpose optimization have been derived from the Metropolis Monte Carlo method of simulating the behavior of particles in substances as they are slowly cooled to form crystals. Simulated Annealing is such a derivative and its value for placement problems (e.g., in circuit board layout design) suggests that it could be advantageously applied to clustering tuples in databases in order to enhance responsiveness to queries. In this article we investigate this issue and compare the performance of this technique with a Graph-Collapsing clustering method which is known to perform very well, in order to gain insights into which approach is better for incorporation in a performanceoriented database design tool. We judge that, whilst the new method does give superior results to the graphbased method in many cases, these improvements are gained at such a very considerable expense of algorithm run time as to rule the new technique out of our consideration as a real world general purpose design tool (but perhaps not for some special-purpose databases).

show abstract

“…In [12], an adaptive record clustering scheme is introduced. They present an elegant as well as conceptually simple clustering algorithm.…”

Section: Previous Research On Cluster Based File Reorganizationmentioning

confidence: 99%

“…They present an elegant as well as conceptually simple clustering algorithm. Their algorithm does not classify queries into types nor does it collect individual query statistics, Preliminary experiments has shown very good results [12]. Once the clusters have been determined, they assign records in each cluster, i.e., from the first cluster to the last cluster, to pages.…”

Section: Previous Research On Cluster Based File Reorganizationmentioning

confidence: 99%

“…Record clustering algorithms [4,12] assign frequently and jointly accessed records to the same page(s) in such a way that the total number of pages accessed in response to a set of queries, with some probability of occurrence, can be minimized. Record clustering algorithms usually focus on finding an optimal clustering but stop short of specifying an optimal procedure for rearranging the records, in the file, to match the clustering.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Concurrent file reorganization for record clustering: a performance study

Omiecinski¹,

Lee²,

Scheuermann³

[1992] Eighth International Conference on Data Engineering

View full text Add to dashboard Cite

This paper presents a performance analysis of a concurrent file reorganization algorithm. W e examine the effect of ( i ) buffer size, (ii) degree of reorganization and (iii) write probability of transactions on system throughput. The problem of $le reorganization which we consider involves altering the placement of records on pages of a secondary storage device. In addition, we want this reorganization to be done in-place, i.e., using the file's original storage space for the newly reorganized file. Our approach is also appropriate for a non in-place reorganimtion as well The motivation for such a physical change, i.e., record clustering, is to improve the database system's performance, i.e., minimizing the number of page accesses made in answering a set of queries. In this work we show through simulation that our algorithm, when run concurrently with user transactions, provides an acceptable level of overall database system performance.

show abstract

Adaptive record clustering

Cited by 54 publications

References 16 publications

Distributed Web Log Mining Using Maximal Large Itemsets

Distributed Web Log Mining Using Maximal Large Itemsets

Application of simulated annealing to clustering tuples in databases

Concurrent file reorganization for record clustering: a performance study

Contact Info

Product

Resources

About