Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
2 files | 7.18 MB
Add to list
  1. Search results
  2. A novel multi-classifier information ...

A novel multi-classifier information fusion based on Dempster-Shafer theory : application to vibration-based fault detection

Vahid Yaghoubi Nasrabadi (UGent) , Liangliang Cheng, Wim Van Paepegem (UGent) and Mathias Kersemans (UGent)
(2022) STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL. 21(2). p.596-612
Author
Organization
Project
Abstract
Achieving a high prediction rate is a crucial task in fault detection. Although various classification procedures are available, none of them can give high accuracy in all applications. Therefore, in this paper, a novel multi-classifier fusion approach is developed to boost the performance of the individual classifiers. This is acquired by using Dempster-Shafer theory (DST). However, in cases with conflicting evidences, the DST may give counter-intuitive results. In this regard, a preprocessing technique based on a new metric is devised in order to measure and mitigate the conflict between the evidences. To evaluate and validate the effectiveness of the proposed approach, the method is applied to 15 benchmarks datasets from UCI and KEEL. Further, it is applied for classifying polycrystalline Nickel alloy first-stage turbine blades based on their broadband vibrational response. Through statistical analysis with different noise levels, and by comparing with four state-of-the-art fusion techniques, it is shown that that the proposed method improves the classification accuracy and outperforms the individual classifiers.
Keywords
Ensemble learning, Classifier fusion, Fault detection, Dempster-Shafer theory, Vibration data, OPTIMIZATION, COMBINATION, EVIDENCES, MODEL

Downloads

  • Download
    (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 3.36 MB
  • Download
    manuscript Rev1.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 3.82 MB

Citation

Please use this url to cite or link to this publication:

MLA
Yaghoubi Nasrabadi, Vahid, et al. “A Novel Multi-Classifier Information Fusion Based on Dempster-Shafer Theory : Application to Vibration-Based Fault Detection.” STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, vol. 21, no. 2, 2022, pp. 596–612, doi:10.1177/14759217211007130.
APA
Yaghoubi Nasrabadi, V., Cheng, L., Van Paepegem, W., & Kersemans, M. (2022). A novel multi-classifier information fusion based on Dempster-Shafer theory : application to vibration-based fault detection. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 21(2), 596–612. https://doi.org/10.1177/14759217211007130
Chicago author-date
Yaghoubi Nasrabadi, Vahid, Liangliang Cheng, Wim Van Paepegem, and Mathias Kersemans. 2022. “A Novel Multi-Classifier Information Fusion Based on Dempster-Shafer Theory : Application to Vibration-Based Fault Detection.” STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 21 (2): 596–612. https://doi.org/10.1177/14759217211007130.
Chicago author-date (all authors)
Yaghoubi Nasrabadi, Vahid, Liangliang Cheng, Wim Van Paepegem, and Mathias Kersemans. 2022. “A Novel Multi-Classifier Information Fusion Based on Dempster-Shafer Theory : Application to Vibration-Based Fault Detection.” STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL 21 (2): 596–612. doi:10.1177/14759217211007130.
Vancouver
1.
Yaghoubi Nasrabadi V, Cheng L, Van Paepegem W, Kersemans M. A novel multi-classifier information fusion based on Dempster-Shafer theory : application to vibration-based fault detection. STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL. 2022;21(2):596–612.
IEEE
[1]
V. Yaghoubi Nasrabadi, L. Cheng, W. Van Paepegem, and M. Kersemans, “A novel multi-classifier information fusion based on Dempster-Shafer theory : application to vibration-based fault detection,” STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, vol. 21, no. 2, pp. 596–612, 2022.
@article{8696251,
  abstract     = {{Achieving a high prediction rate is a crucial task in fault detection. Although various classification procedures are available, none of them can give high accuracy in all applications. Therefore, in this paper, a novel multi-classifier fusion approach is developed to boost the performance of the individual classifiers. This is acquired by using Dempster-Shafer theory (DST). However, in cases with conflicting evidences, the DST may give counter-intuitive results. In this regard,  a preprocessing technique based on a new metric is devised in order to measure and mitigate the conflict between the evidences. To evaluate and validate the effectiveness of the proposed approach, the method is applied to 15 benchmarks datasets from UCI and KEEL. Further, it is applied for classifying polycrystalline Nickel alloy first-stage turbine blades based on their broadband vibrational response. Through statistical analysis with different noise levels, and by comparing with four state-of-the-art fusion techniques, it is shown that that the proposed method improves the classification accuracy and outperforms the individual classifiers.}},
  author       = {{Yaghoubi Nasrabadi, Vahid and Cheng, Liangliang and Van Paepegem, Wim and Kersemans, Mathias}},
  issn         = {{1475-9217}},
  journal      = {{STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL}},
  keywords     = {{Ensemble learning,Classifier fusion,Fault detection,Dempster-Shafer theory,Vibration data,OPTIMIZATION,COMBINATION,EVIDENCES,MODEL}},
  language     = {{eng}},
  number       = {{2}},
  pages        = {{596--612}},
  title        = {{A novel multi-classifier information fusion based on Dempster-Shafer theory : application to vibration-based fault detection}},
  url          = {{http://doi.org/10.1177/14759217211007130}},
  volume       = {{21}},
  year         = {{2022}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: