Numerical time-series pattern extraction based on irregular piecewise aggregate approximation and gradient specification

Miho Ohsaki, Hidenao Abe, Takahira Yamaguchi

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

This paper proposes and evaluates a method for extracting interesting patterns from numerical time-series data which takes account of user subjectivity. The proposed method conducts irregular sampling on the data preserving the subjectively noteworthy features using a user specified gradient. It also conducts irregular quantization, preserving the intrinsically objective characteristics of the data using statistical distributions. It then extracts representative patterns from the discretized data using group average clustering. Experimental results using benchmark datasets indicate that the proposed method does not destroy the intrinsically objective features, since it has the same performance as the basic subsequence clustering using K-Means algorithm. Results using a dataset from a clinical hepatitis study indicate that it extracts interesting patterns for a medical expert.

Original languageEnglish
Pages (from-to)213-222
Number of pages10
JournalNew Generation Computing
Volume25
Issue number3
DOIs
Publication statusPublished - 2007

Fingerprint

Irregular
Time series
Specification
Sampling
Gradient
Specifications
Approximation
Irregular Sampling
K-means Algorithm
Statistical Distribution
Data Distribution
Time Series Data
Subsequence
Clustering Algorithm
Quantization
Clustering
Benchmark
Evaluate
Experimental Results

Keywords

  • Data mining
  • Knowledge discovery in databases
  • Numerical time-series
  • Pattern extraction
  • Piecewise aggregate approximation

ASJC Scopus subject areas

  • Hardware and Architecture
  • Theoretical Computer Science
  • Computational Theory and Mathematics

Cite this

Numerical time-series pattern extraction based on irregular piecewise aggregate approximation and gradient specification. / Ohsaki, Miho; Abe, Hidenao; Yamaguchi, Takahira.

In: New Generation Computing, Vol. 25, No. 3, 2007, p. 213-222.

Research output: Contribution to journalArticle

@article{92fd55206486473d9ba72871d27875ed,
title = "Numerical time-series pattern extraction based on irregular piecewise aggregate approximation and gradient specification",
abstract = "This paper proposes and evaluates a method for extracting interesting patterns from numerical time-series data which takes account of user subjectivity. The proposed method conducts irregular sampling on the data preserving the subjectively noteworthy features using a user specified gradient. It also conducts irregular quantization, preserving the intrinsically objective characteristics of the data using statistical distributions. It then extracts representative patterns from the discretized data using group average clustering. Experimental results using benchmark datasets indicate that the proposed method does not destroy the intrinsically objective features, since it has the same performance as the basic subsequence clustering using K-Means algorithm. Results using a dataset from a clinical hepatitis study indicate that it extracts interesting patterns for a medical expert.",
keywords = "Data mining, Knowledge discovery in databases, Numerical time-series, Pattern extraction, Piecewise aggregate approximation",
author = "Miho Ohsaki and Hidenao Abe and Takahira Yamaguchi",
year = "2007",
doi = "10.1007/s00354-007-0013-9",
language = "English",
volume = "25",
pages = "213--222",
journal = "New Generation Computing",
issn = "0288-3635",
publisher = "Springer Japan",
number = "3",

}

TY - JOUR

T1 - Numerical time-series pattern extraction based on irregular piecewise aggregate approximation and gradient specification

AU - Ohsaki, Miho

AU - Abe, Hidenao

AU - Yamaguchi, Takahira

PY - 2007

Y1 - 2007

N2 - This paper proposes and evaluates a method for extracting interesting patterns from numerical time-series data which takes account of user subjectivity. The proposed method conducts irregular sampling on the data preserving the subjectively noteworthy features using a user specified gradient. It also conducts irregular quantization, preserving the intrinsically objective characteristics of the data using statistical distributions. It then extracts representative patterns from the discretized data using group average clustering. Experimental results using benchmark datasets indicate that the proposed method does not destroy the intrinsically objective features, since it has the same performance as the basic subsequence clustering using K-Means algorithm. Results using a dataset from a clinical hepatitis study indicate that it extracts interesting patterns for a medical expert.

AB - This paper proposes and evaluates a method for extracting interesting patterns from numerical time-series data which takes account of user subjectivity. The proposed method conducts irregular sampling on the data preserving the subjectively noteworthy features using a user specified gradient. It also conducts irregular quantization, preserving the intrinsically objective characteristics of the data using statistical distributions. It then extracts representative patterns from the discretized data using group average clustering. Experimental results using benchmark datasets indicate that the proposed method does not destroy the intrinsically objective features, since it has the same performance as the basic subsequence clustering using K-Means algorithm. Results using a dataset from a clinical hepatitis study indicate that it extracts interesting patterns for a medical expert.

KW - Data mining

KW - Knowledge discovery in databases

KW - Numerical time-series

KW - Pattern extraction

KW - Piecewise aggregate approximation

UR - http://www.scopus.com/inward/record.url?scp=34548097601&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34548097601&partnerID=8YFLogxK

U2 - 10.1007/s00354-007-0013-9

DO - 10.1007/s00354-007-0013-9

M3 - Article

AN - SCOPUS:34548097601

VL - 25

SP - 213

EP - 222

JO - New Generation Computing

JF - New Generation Computing

SN - 0288-3635

IS - 3

ER -