Aggressive pruning strategy for time series retrieval using a multi-resolution representation based on vector quantization coupled with discrete wavelet transform

Research output: Contribution to journalReview article

2 Citations (Scopus)

Abstract

Time series representation methods are widely used to handle time series data by projecting them onto low-dimensional spaces where queries are processed. Multi-resolution representation methods speed up the similarity search process by using pre-computed distances, which are calculated and stored at the indexing stage and then used at the query stage, together with filters in the form of exclusion conditions. In this paper, we present a new multi-resolution representation method that combines the Haar wavelet-based multi-resolution method with vector quantization to maximize the pruning power of the similarity search algorithm. The new method is validated through extensive experiments on different datasets from several time series repositories. The results obtained prove the efficiency of the new method.

Original languageEnglish
Article numbere12171
JournalExpert Systems
Volume34
Issue number1
Early online date26 Dec 2016
DOIs
Publication statusPublished - Feb 2017
Externally publishedYes

Fingerprint

Vector Quantization
Discrete wavelet transforms
Vector quantization
Pruning
Multiresolution
Wavelet Transform
Time series
Retrieval
Similarity Search
Query
Haar Wavelet
Series Representation
Time Series Data
Indexing
Repository
Search Algorithm
Strategy
Speedup
Experiments
Maximise

Keywords

  • dimensionality reduction
  • Haar wavelets
  • multi-resolution
  • time series
  • vector quantization

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computational Theory and Mathematics
  • Artificial Intelligence

Cite this

@article{2e1ebcb1a51b4b40b04794d2334bb7c0,
title = "Aggressive pruning strategy for time series retrieval using a multi-resolution representation based on vector quantization coupled with discrete wavelet transform",
abstract = "Time series representation methods are widely used to handle time series data by projecting them onto low-dimensional spaces where queries are processed. Multi-resolution representation methods speed up the similarity search process by using pre-computed distances, which are calculated and stored at the indexing stage and then used at the query stage, together with filters in the form of exclusion conditions. In this paper, we present a new multi-resolution representation method that combines the Haar wavelet-based multi-resolution method with vector quantization to maximize the pruning power of the similarity search algorithm. The new method is validated through extensive experiments on different datasets from several time series repositories. The results obtained prove the efficiency of the new method.",
keywords = "dimensionality reduction, Haar wavelets, multi-resolution, time series, vector quantization",
author = "{Muhammad Fuad}, {Muhammad Marwan}",
year = "2017",
month = "2",
doi = "10.1111/exsy.12171",
language = "English",
volume = "34",
journal = "Expert Systems",
issn = "0266-4720",
publisher = "Wiley",
number = "1",

}

TY - JOUR

T1 - Aggressive pruning strategy for time series retrieval using a multi-resolution representation based on vector quantization coupled with discrete wavelet transform

AU - Muhammad Fuad, Muhammad Marwan

PY - 2017/2

Y1 - 2017/2

N2 - Time series representation methods are widely used to handle time series data by projecting them onto low-dimensional spaces where queries are processed. Multi-resolution representation methods speed up the similarity search process by using pre-computed distances, which are calculated and stored at the indexing stage and then used at the query stage, together with filters in the form of exclusion conditions. In this paper, we present a new multi-resolution representation method that combines the Haar wavelet-based multi-resolution method with vector quantization to maximize the pruning power of the similarity search algorithm. The new method is validated through extensive experiments on different datasets from several time series repositories. The results obtained prove the efficiency of the new method.

AB - Time series representation methods are widely used to handle time series data by projecting them onto low-dimensional spaces where queries are processed. Multi-resolution representation methods speed up the similarity search process by using pre-computed distances, which are calculated and stored at the indexing stage and then used at the query stage, together with filters in the form of exclusion conditions. In this paper, we present a new multi-resolution representation method that combines the Haar wavelet-based multi-resolution method with vector quantization to maximize the pruning power of the similarity search algorithm. The new method is validated through extensive experiments on different datasets from several time series repositories. The results obtained prove the efficiency of the new method.

KW - dimensionality reduction

KW - Haar wavelets

KW - multi-resolution

KW - time series

KW - vector quantization

UR - http://www.scopus.com/inward/record.url?scp=85007398905&partnerID=8YFLogxK

U2 - 10.1111/exsy.12171

DO - 10.1111/exsy.12171

M3 - Review article

VL - 34

JO - Expert Systems

JF - Expert Systems

SN - 0266-4720

IS - 1

M1 - e12171

ER -