Discovery of corrosion patterns using symbolic time series representation and N-gram model

Shakirah Mohd Taib, Zahiah Akhma Mohd Zabidi, Izzatdin Abdul Aziz, Farahida Hanim Mousor, Azuraliza Abu Bakar, Ainul Akmar Mokhtar

Research output: Contribution to journalArticle

Abstract

There are many factors that can contribute to corrosion in the pipeline. Therefore, it is important for decision makers to analyze and identify the main factor of corrosion in order to take appropriate actions. The factor of corrosion can be analyzed using data mining based on historical datasets collected from monitoring sensors. The purpose of this study is to analyze the trends of corroding agents for pipeline corrosion based on symbolic representation of time series corrosion dataset using Symbolic Aggregation Approximation (SAX). The paper presents the analysis and evaluation of the patterns using Ngram model. Text mining using N-gram model is proposed to mine trend changes from corrosion time series dataset that are transformed as symbolic representation. N-gram was applied for the analysis in order to find significant symbolic patterns that are represented as text. Pattern analysis is performed and the results are discussed according to each environmental factor of pipeline corrosion.

Original languageEnglish
Pages (from-to)554-560
Number of pages7
JournalInternational Journal of Advanced Computer Science and Applications
Volume9
Issue number12
DOIs
Publication statusPublished - 1 Jan 2018

Fingerprint

Time series
Corrosion
Pipelines
Data mining
Agglomeration
Monitoring
Sensors

Keywords

  • Corrosion factor
  • Corrosion patterns
  • Pipelines corrosion analysis
  • Symbolic Aggregation Approximation (SAX) representation

ASJC Scopus subject areas

  • Computer Science(all)

Cite this

Discovery of corrosion patterns using symbolic time series representation and N-gram model. / Taib, Shakirah Mohd; Mohd Zabidi, Zahiah Akhma; Aziz, Izzatdin Abdul; Mousor, Farahida Hanim; Abu Bakar, Azuraliza; Mokhtar, Ainul Akmar.

In: International Journal of Advanced Computer Science and Applications, Vol. 9, No. 12, 01.01.2018, p. 554-560.

Research output: Contribution to journalArticle

Taib, Shakirah Mohd ; Mohd Zabidi, Zahiah Akhma ; Aziz, Izzatdin Abdul ; Mousor, Farahida Hanim ; Abu Bakar, Azuraliza ; Mokhtar, Ainul Akmar. / Discovery of corrosion patterns using symbolic time series representation and N-gram model. In: International Journal of Advanced Computer Science and Applications. 2018 ; Vol. 9, No. 12. pp. 554-560.
@article{e118100e711e4fdf80e9f1d898c75dc4,
title = "Discovery of corrosion patterns using symbolic time series representation and N-gram model",
abstract = "There are many factors that can contribute to corrosion in the pipeline. Therefore, it is important for decision makers to analyze and identify the main factor of corrosion in order to take appropriate actions. The factor of corrosion can be analyzed using data mining based on historical datasets collected from monitoring sensors. The purpose of this study is to analyze the trends of corroding agents for pipeline corrosion based on symbolic representation of time series corrosion dataset using Symbolic Aggregation Approximation (SAX). The paper presents the analysis and evaluation of the patterns using Ngram model. Text mining using N-gram model is proposed to mine trend changes from corrosion time series dataset that are transformed as symbolic representation. N-gram was applied for the analysis in order to find significant symbolic patterns that are represented as text. Pattern analysis is performed and the results are discussed according to each environmental factor of pipeline corrosion.",
keywords = "Corrosion factor, Corrosion patterns, Pipelines corrosion analysis, Symbolic Aggregation Approximation (SAX) representation",
author = "Taib, {Shakirah Mohd} and {Mohd Zabidi}, {Zahiah Akhma} and Aziz, {Izzatdin Abdul} and Mousor, {Farahida Hanim} and {Abu Bakar}, Azuraliza and Mokhtar, {Ainul Akmar}",
year = "2018",
month = "1",
day = "1",
doi = "10.14569/IJACSA.2018.091278",
language = "English",
volume = "9",
pages = "554--560",
journal = "International Journal of Advanced Computer Science and Applications",
issn = "2158-107X",
publisher = "Science and Information Organization",
number = "12",

}

TY - JOUR

T1 - Discovery of corrosion patterns using symbolic time series representation and N-gram model

AU - Taib, Shakirah Mohd

AU - Mohd Zabidi, Zahiah Akhma

AU - Aziz, Izzatdin Abdul

AU - Mousor, Farahida Hanim

AU - Abu Bakar, Azuraliza

AU - Mokhtar, Ainul Akmar

PY - 2018/1/1

Y1 - 2018/1/1

N2 - There are many factors that can contribute to corrosion in the pipeline. Therefore, it is important for decision makers to analyze and identify the main factor of corrosion in order to take appropriate actions. The factor of corrosion can be analyzed using data mining based on historical datasets collected from monitoring sensors. The purpose of this study is to analyze the trends of corroding agents for pipeline corrosion based on symbolic representation of time series corrosion dataset using Symbolic Aggregation Approximation (SAX). The paper presents the analysis and evaluation of the patterns using Ngram model. Text mining using N-gram model is proposed to mine trend changes from corrosion time series dataset that are transformed as symbolic representation. N-gram was applied for the analysis in order to find significant symbolic patterns that are represented as text. Pattern analysis is performed and the results are discussed according to each environmental factor of pipeline corrosion.

AB - There are many factors that can contribute to corrosion in the pipeline. Therefore, it is important for decision makers to analyze and identify the main factor of corrosion in order to take appropriate actions. The factor of corrosion can be analyzed using data mining based on historical datasets collected from monitoring sensors. The purpose of this study is to analyze the trends of corroding agents for pipeline corrosion based on symbolic representation of time series corrosion dataset using Symbolic Aggregation Approximation (SAX). The paper presents the analysis and evaluation of the patterns using Ngram model. Text mining using N-gram model is proposed to mine trend changes from corrosion time series dataset that are transformed as symbolic representation. N-gram was applied for the analysis in order to find significant symbolic patterns that are represented as text. Pattern analysis is performed and the results are discussed according to each environmental factor of pipeline corrosion.

KW - Corrosion factor

KW - Corrosion patterns

KW - Pipelines corrosion analysis

KW - Symbolic Aggregation Approximation (SAX) representation

UR - http://www.scopus.com/inward/record.url?scp=85059533377&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059533377&partnerID=8YFLogxK

U2 - 10.14569/IJACSA.2018.091278

DO - 10.14569/IJACSA.2018.091278

M3 - Article

AN - SCOPUS:85059533377

VL - 9

SP - 554

EP - 560

JO - International Journal of Advanced Computer Science and Applications

JF - International Journal of Advanced Computer Science and Applications

SN - 2158-107X

IS - 12

ER -