Analyzing trends by symbolic episode representation and sequence alignment

B. Balasko, Z. Banko, J. Abonyi

Research output: Conference contribution

2 Citations (Scopus)

Abstract

Data analysis is often associated with quantitative techniques because of the large amount of data and easy-to-use statistical tools. Qualitative trend analysis (QTA) techniques always have to be guided with some data reduction method, e.g. principal component analysis (PCA) or segmentation, and the preprocessed, lowered size data can be analyzed for further aims. Derivative-based segmentation methods are presented which are popular in fault diagnosis. If there is an adequate distance measure, one is able to qualify, compare or classify different time series. This article proposes segmentation-based alignment techniques based on dynamic distance measure: time warping (DTW) and a recently developed one, which uses pairwise sequence alignment - a common tool in Bioinformatics - to align triangular episode sequences. Both techniques highly depend on the pre-defined distance or similarity measure between the trends because they try to find the minimal distance or maximal similarity path. These two techniques are compared and qualified on handwriting data based case study. It has been shown that symbolic episode segmentation based sequence alignment aided by prior knowledge of the operators can handle qualitative trend analysis and thus it is able to monitor and qualify operating processes.

Original languageEnglish
Title of host publication2007 Mediterranean Conference on Control and Automation, MED
DOIs
Publication statusPublished - 2007
Event2007 Mediterranean Conference on Control and Automation, MED - Athens, Greece
Duration: júl. 27 2007júl. 29 2007

Other

Other2007 Mediterranean Conference on Control and Automation, MED
CountryGreece
CityAthens
Period7/27/077/29/07

Fingerprint

Bioinformatics
Principal component analysis
Failure analysis
Time series
Data reduction
Derivatives

ASJC Scopus subject areas

  • Artificial Intelligence
  • Control and Systems Engineering

Cite this

Balasko, B., Banko, Z., & Abonyi, J. (2007). Analyzing trends by symbolic episode representation and sequence alignment. In 2007 Mediterranean Conference on Control and Automation, MED [4433862] https://doi.org/10.1109/MED.2007.4433862

Analyzing trends by symbolic episode representation and sequence alignment. / Balasko, B.; Banko, Z.; Abonyi, J.

2007 Mediterranean Conference on Control and Automation, MED. 2007. 4433862.

Research output: Conference contribution

Balasko, B, Banko, Z & Abonyi, J 2007, Analyzing trends by symbolic episode representation and sequence alignment. in 2007 Mediterranean Conference on Control and Automation, MED., 4433862, 2007 Mediterranean Conference on Control and Automation, MED, Athens, Greece, 7/27/07. https://doi.org/10.1109/MED.2007.4433862
Balasko B, Banko Z, Abonyi J. Analyzing trends by symbolic episode representation and sequence alignment. In 2007 Mediterranean Conference on Control and Automation, MED. 2007. 4433862 https://doi.org/10.1109/MED.2007.4433862
Balasko, B. ; Banko, Z. ; Abonyi, J. / Analyzing trends by symbolic episode representation and sequence alignment. 2007 Mediterranean Conference on Control and Automation, MED. 2007.
@inproceedings{1ccda2c00bd544659c2c39378cd357c8,
title = "Analyzing trends by symbolic episode representation and sequence alignment",
abstract = "Data analysis is often associated with quantitative techniques because of the large amount of data and easy-to-use statistical tools. Qualitative trend analysis (QTA) techniques always have to be guided with some data reduction method, e.g. principal component analysis (PCA) or segmentation, and the preprocessed, lowered size data can be analyzed for further aims. Derivative-based segmentation methods are presented which are popular in fault diagnosis. If there is an adequate distance measure, one is able to qualify, compare or classify different time series. This article proposes segmentation-based alignment techniques based on dynamic distance measure: time warping (DTW) and a recently developed one, which uses pairwise sequence alignment - a common tool in Bioinformatics - to align triangular episode sequences. Both techniques highly depend on the pre-defined distance or similarity measure between the trends because they try to find the minimal distance or maximal similarity path. These two techniques are compared and qualified on handwriting data based case study. It has been shown that symbolic episode segmentation based sequence alignment aided by prior knowledge of the operators can handle qualitative trend analysis and thus it is able to monitor and qualify operating processes.",
author = "B. Balasko and Z. Banko and J. Abonyi",
year = "2007",
doi = "10.1109/MED.2007.4433862",
language = "English",
isbn = "142441282X",
booktitle = "2007 Mediterranean Conference on Control and Automation, MED",

}

TY - GEN

T1 - Analyzing trends by symbolic episode representation and sequence alignment

AU - Balasko, B.

AU - Banko, Z.

AU - Abonyi, J.

PY - 2007

Y1 - 2007

N2 - Data analysis is often associated with quantitative techniques because of the large amount of data and easy-to-use statistical tools. Qualitative trend analysis (QTA) techniques always have to be guided with some data reduction method, e.g. principal component analysis (PCA) or segmentation, and the preprocessed, lowered size data can be analyzed for further aims. Derivative-based segmentation methods are presented which are popular in fault diagnosis. If there is an adequate distance measure, one is able to qualify, compare or classify different time series. This article proposes segmentation-based alignment techniques based on dynamic distance measure: time warping (DTW) and a recently developed one, which uses pairwise sequence alignment - a common tool in Bioinformatics - to align triangular episode sequences. Both techniques highly depend on the pre-defined distance or similarity measure between the trends because they try to find the minimal distance or maximal similarity path. These two techniques are compared and qualified on handwriting data based case study. It has been shown that symbolic episode segmentation based sequence alignment aided by prior knowledge of the operators can handle qualitative trend analysis and thus it is able to monitor and qualify operating processes.

AB - Data analysis is often associated with quantitative techniques because of the large amount of data and easy-to-use statistical tools. Qualitative trend analysis (QTA) techniques always have to be guided with some data reduction method, e.g. principal component analysis (PCA) or segmentation, and the preprocessed, lowered size data can be analyzed for further aims. Derivative-based segmentation methods are presented which are popular in fault diagnosis. If there is an adequate distance measure, one is able to qualify, compare or classify different time series. This article proposes segmentation-based alignment techniques based on dynamic distance measure: time warping (DTW) and a recently developed one, which uses pairwise sequence alignment - a common tool in Bioinformatics - to align triangular episode sequences. Both techniques highly depend on the pre-defined distance or similarity measure between the trends because they try to find the minimal distance or maximal similarity path. These two techniques are compared and qualified on handwriting data based case study. It has been shown that symbolic episode segmentation based sequence alignment aided by prior knowledge of the operators can handle qualitative trend analysis and thus it is able to monitor and qualify operating processes.

UR - http://www.scopus.com/inward/record.url?scp=50249110652&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=50249110652&partnerID=8YFLogxK

U2 - 10.1109/MED.2007.4433862

DO - 10.1109/MED.2007.4433862

M3 - Conference contribution

AN - SCOPUS:50249110652

SN - 142441282X

SN - 9781424412822

BT - 2007 Mediterranean Conference on Control and Automation, MED

ER -