Harmony Search algorithm for optimal word size in symbolic time series representation

Almahdi Mohammed Ahmed, Azuraliza Abu Bakar, Abdul Razak Hamdan

Research output: Chapter in Book/Report/Conference proceedingConference contribution

13 Citations (Scopus)

Abstract

Fast and high quality time series representation is a crucial task in data mining pre-pre-processing. Recent studies have shown that most representation methods based on improving classification accuracy and compress data sets rather than maximize data information. We attempt to improve the number of SAX (time series representation method) word size and alphabet size by searching for the optimal word size. In this paper we propose a new representation algorithm (HSAX) that deals with Harmony Search algorithm (HS) to explore optimal word size (Ws) and alphabet size (a) for SAX time series. Harmony search algorithm is an optimization algorithm that generates randomly solutions (Ws, a) and select two best solutions. H SAX algorithm is developed to maximize information, rather than improve classification accuracy. We have applied HSAX algorithm on some standard time series data sets. We also compare the HSAX with other meta-heuristic GENEBLA and original SAX algorithms The experimental results showed that the HSAX Algorithm compare to SAX manage to generate more word size and achieve less error rates, whereas HSAX compared to GENEBLA the quality of error rate is comparable with the advantage that HSAX generated high number of word and alphabet size.

Original languageEnglish
Title of host publicationConference on Data Mining and Optimization
Pages57-62
Number of pages6
DOIs
Publication statusPublished - 2011
Event2011 3rd Conference on Data Mining and Optimization, DMO 2011 - Putrajaya
Duration: 28 Jun 201129 Jun 2011

Other

Other2011 3rd Conference on Data Mining and Optimization, DMO 2011
CityPutrajaya
Period28/6/1129/6/11

Fingerprint

Time series
Data mining
Processing

Keywords

  • data minin
  • discretization time series
  • Harmony algorithm
  • optimization
  • pre-processing

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Software

Cite this

Mohammed Ahmed, A., Abu Bakar, A., & Hamdan, A. R. (2011). Harmony Search algorithm for optimal word size in symbolic time series representation. In Conference on Data Mining and Optimization (pp. 57-62). [5976505] https://doi.org/10.1109/DMO.2011.5976505

Harmony Search algorithm for optimal word size in symbolic time series representation. / Mohammed Ahmed, Almahdi; Abu Bakar, Azuraliza; Hamdan, Abdul Razak.

Conference on Data Mining and Optimization. 2011. p. 57-62 5976505.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mohammed Ahmed, A, Abu Bakar, A & Hamdan, AR 2011, Harmony Search algorithm for optimal word size in symbolic time series representation. in Conference on Data Mining and Optimization., 5976505, pp. 57-62, 2011 3rd Conference on Data Mining and Optimization, DMO 2011, Putrajaya, 28/6/11. https://doi.org/10.1109/DMO.2011.5976505
Mohammed Ahmed A, Abu Bakar A, Hamdan AR. Harmony Search algorithm for optimal word size in symbolic time series representation. In Conference on Data Mining and Optimization. 2011. p. 57-62. 5976505 https://doi.org/10.1109/DMO.2011.5976505
Mohammed Ahmed, Almahdi ; Abu Bakar, Azuraliza ; Hamdan, Abdul Razak. / Harmony Search algorithm for optimal word size in symbolic time series representation. Conference on Data Mining and Optimization. 2011. pp. 57-62
@inproceedings{e029c83dc5fc4bad8d6c6f3d222f3352,
title = "Harmony Search algorithm for optimal word size in symbolic time series representation",
abstract = "Fast and high quality time series representation is a crucial task in data mining pre-pre-processing. Recent studies have shown that most representation methods based on improving classification accuracy and compress data sets rather than maximize data information. We attempt to improve the number of SAX (time series representation method) word size and alphabet size by searching for the optimal word size. In this paper we propose a new representation algorithm (HSAX) that deals with Harmony Search algorithm (HS) to explore optimal word size (Ws) and alphabet size (a) for SAX time series. Harmony search algorithm is an optimization algorithm that generates randomly solutions (Ws, a) and select two best solutions. H SAX algorithm is developed to maximize information, rather than improve classification accuracy. We have applied HSAX algorithm on some standard time series data sets. We also compare the HSAX with other meta-heuristic GENEBLA and original SAX algorithms The experimental results showed that the HSAX Algorithm compare to SAX manage to generate more word size and achieve less error rates, whereas HSAX compared to GENEBLA the quality of error rate is comparable with the advantage that HSAX generated high number of word and alphabet size.",
keywords = "data minin, discretization time series, Harmony algorithm, optimization, pre-processing",
author = "{Mohammed Ahmed}, Almahdi and {Abu Bakar}, Azuraliza and Hamdan, {Abdul Razak}",
year = "2011",
doi = "10.1109/DMO.2011.5976505",
language = "English",
isbn = "9781612842127",
pages = "57--62",
booktitle = "Conference on Data Mining and Optimization",

}

TY - GEN

T1 - Harmony Search algorithm for optimal word size in symbolic time series representation

AU - Mohammed Ahmed, Almahdi

AU - Abu Bakar, Azuraliza

AU - Hamdan, Abdul Razak

PY - 2011

Y1 - 2011

N2 - Fast and high quality time series representation is a crucial task in data mining pre-pre-processing. Recent studies have shown that most representation methods based on improving classification accuracy and compress data sets rather than maximize data information. We attempt to improve the number of SAX (time series representation method) word size and alphabet size by searching for the optimal word size. In this paper we propose a new representation algorithm (HSAX) that deals with Harmony Search algorithm (HS) to explore optimal word size (Ws) and alphabet size (a) for SAX time series. Harmony search algorithm is an optimization algorithm that generates randomly solutions (Ws, a) and select two best solutions. H SAX algorithm is developed to maximize information, rather than improve classification accuracy. We have applied HSAX algorithm on some standard time series data sets. We also compare the HSAX with other meta-heuristic GENEBLA and original SAX algorithms The experimental results showed that the HSAX Algorithm compare to SAX manage to generate more word size and achieve less error rates, whereas HSAX compared to GENEBLA the quality of error rate is comparable with the advantage that HSAX generated high number of word and alphabet size.

AB - Fast and high quality time series representation is a crucial task in data mining pre-pre-processing. Recent studies have shown that most representation methods based on improving classification accuracy and compress data sets rather than maximize data information. We attempt to improve the number of SAX (time series representation method) word size and alphabet size by searching for the optimal word size. In this paper we propose a new representation algorithm (HSAX) that deals with Harmony Search algorithm (HS) to explore optimal word size (Ws) and alphabet size (a) for SAX time series. Harmony search algorithm is an optimization algorithm that generates randomly solutions (Ws, a) and select two best solutions. H SAX algorithm is developed to maximize information, rather than improve classification accuracy. We have applied HSAX algorithm on some standard time series data sets. We also compare the HSAX with other meta-heuristic GENEBLA and original SAX algorithms The experimental results showed that the HSAX Algorithm compare to SAX manage to generate more word size and achieve less error rates, whereas HSAX compared to GENEBLA the quality of error rate is comparable with the advantage that HSAX generated high number of word and alphabet size.

KW - data minin

KW - discretization time series

KW - Harmony algorithm

KW - optimization

KW - pre-processing

UR - http://www.scopus.com/inward/record.url?scp=80055034204&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80055034204&partnerID=8YFLogxK

U2 - 10.1109/DMO.2011.5976505

DO - 10.1109/DMO.2011.5976505

M3 - Conference contribution

SN - 9781612842127

SP - 57

EP - 62

BT - Conference on Data Mining and Optimization

ER -