• Publications
  • Influence
Efficient time series matching by wavelets
  • K. Chan, A. Fu
  • Computer Science
  • Proceedings 15th International Conference on Data…
  • 23 March 1999
TLDR
Time series stored as feature vectors can be indexed by multidimensional index trees like R-Trees for fast retrieval. Expand
  • 1,147
  • 88
  • PDF
HOT SAX: efficiently finding the most unusual time series subsequence
TLDR
In this work, we introduce the new problem of finding time series discords, a new primitive for time series data mining. Expand
  • 641
  • 86
  • PDF
Utility-based anonymization using local recoding
TLDR
In this paper, we study the problem of utility-based anonymization. Expand
  • 402
  • 47
  • PDF
Entropy-based subspace clustering for mining numerical data
TLDR
We propose an entropybased algorithm called ENCLUS to prune away uninteresting subspaces which are of interest because of strong clustering in high-dimensional data set. Expand
  • 573
  • 45
Mining association rules with weighted items
TLDR
In this paper, we propose new algorithms to mine weighted association rules. Expand
  • 459
  • 35
  • PDF
Anonymizing transaction databases for publication
TLDR
This paper considers the problem of publishing "transaction data" for research purposes. Expand
  • 203
  • 34
  • PDF
(α, k)-anonymity: an enhanced k-anonymity model for privacy preserving data publishing
TLDR
We propose an (α, k)-anonymity model to protect both identifications and relationships to sensitive information in data. Expand
  • 630
  • 33
  • PDF
Enhancing Effectiveness of Outlier Detections for Low Density Patterns
TLDR
In this paper, we introduce a connectivity-based outlier factor (COF) scheme that improves the effectiveness of an existing local outlier factors (LOF) scheme when a pattern itself has similar neighbourhood density as an outlier. Expand
  • 348
  • 33
A fast distributed algorithm for mining association rules
TLDR
We propose a fast distributed mining algorithm, FDM, which generates a small number of candidate sets and substantially reduces the number of messages to be passed at mining association rules. Expand
  • 530
  • 32
  • PDF
K-isomorphism: privacy preserving network publication against structural attacks
TLDR
We show that k-isomorphism, or anonymization by forming k pairwise isomorphic subgraphs, is both sufficient and necessary for the protection. Expand
  • 316
  • 30
  • PDF