Advances in Knowledge Discovery and Data Mining

Lecture notes in computer sciencePublished 1 January 2004Open access

Honghua Dai, Ramakrishnan Srikant

Citations436

TL;DR

The next chapter focuses on the mining of Evolving Data Streams with Privacy Preservation and the application of Emerging Patterns for Improving the Quality of Rare-Class Classification.

Abstract

In the context of mining frequent itemsets, numerous strategies have been proposed to push several types of constraints within the most well known algorithms. In this paper, we integrate the recently proposed ExAnte data reduction technique within the FP-growth algorithm. Together, they result in a very efficient frequent itemset mining algorithm that effectively exploits monotone constraints.

Keywords

Computer Science

Lecture notes in computer scienceEfficient Pattern-Growth Methods for Frequent Tree Pattern Mining

100 Citations2004Chen Wang, Mingsheng Hong +4 more

An extensive performance study shows that the two newly developed algorithms outperform TreeMinerV [13], one of the fastest methods proposed before, in mining large databases.

Lecture notes in computer scienceUsing Cluster-Based Sampling to Select Initial Training Set for Active Learning in Text Classification

69 Citations2004Jaeho Kang, Kwang Ryel Ryu +1 more

Experiments with various text data sets have shown that the active learner starting from the initial training set selected by the method reaches higher accuracy faster than that starting from randomly generatedInitial training set.

Lecture notes in computer scienceMining Expressive Process Models by Clustering Workflow Traces

64 Citations2004Gianluigi Greco, Antonella Guzzo +2 more

An effective technique for process mining based on the rather unexplored concept of clustering workflow executions, in which clusters of executions sharing the same structure and the same unexpected behavior are seen as a witness of the existence of global constraints.

Lecture notes in computer scienceProviding Diversity in K-Nearest Neighbor Query Results

61 Citations2004Anoop Jain, Parag Sarda +1 more

This paper proposes a user-tunable definition of diversity, and presents an algorithm, called MOTLEY, for producing a diverse result set as per this definition, and shows that MOTLEY can produce diverse result sets by reading only a small fraction of the tuples in the database.

Lecture notes in computer scienceDB-Subdue: Database Approach to Graph Mining

29 Citations2004Sharma Chakravarthy, Ramji Beera +1 more

This paper has not only shown how the Subdue class of algorithms can be translated to SQL-based algorithms, but also demonstrated that scalability can be achieved without sacrificing performance.

Lecture notes in computer sciencePeculiarity Oriented Analysis in Multi-people Tracking Images

12 Citations2004Muneaki Ohshima, Ning Zhong +2 more

An application of the peculiarity oriented mining approach for analysing in image sequences of tracking multiple walking people for finding suspicious people in the place in which many people gather.

Spectral analysis of text collection for similarity-based clustering

7 Citations2004Wenqing Li, Wee Keong Ng +1 more

This work proposes to use the spectral analysis of the similarity space of a text collection to predict clustering behavior before actual clustering is performed.

Lecture notes in computer scienceOn the Size of Training Set and the Benefit from Ensemble

5 Citations2004Zhi‐Hua Zhou, Dan Wei +2 more

The impact of the size of the training set on the benefit from ensemble, i.e. the gains obtained by employing ensemble learning paradigms, is empirically studied and it is observed that the benefit of ensemble of unpruned decision trees is usually bigger than that from ensemble of pruned decision Trees.

Lecture notes in computer scienceSelective Augmented Bayesian Network Classifiers Based on Rough Set Theory

5 Citations2004Zhihai Wang, Geoffrey I. Webb +1 more

A variant of TAN using rough sets theory is presented and it delivers lower error than both pre-existing TAN-based classifiers, with substantially less computation than is required by the SuperParent approach.

Lecture notes in computer scienceConstraint-Based Graph Clustering through Node Sequencing and Partitioning

5 Citations2004Qian Yu, Kang Zhang +1 more

A two-step graph partitioning method to discover constrained clusters with an objective function that follows the well-known min-max clustering principle that can be used to solve other practical constraints.