Clustering Based Multi Sensor Data Fusion for Honeycomb Detection in Concrete

Christoph Völker, Parisa Shokouhi

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

We use three clustering algorithms to aggregate a three-modal non-destructive testing data set into defect and not-defect groups. Our data set consist of impact-echo, ultrasound (US) and ground penetrating radar data collected on a large concrete slab with embedded simulated honeycombing defects. US performs best in defect discriminating and sizing, however the false positive rate is still high. We fuse the data set using K-Means, Fuzzy C-Means and DBSCAN clustering at feature-level. We discern that DBSCAN improves the detectability up to 10 %. A discussion of its advantages over commonly used K-Means and Fuzzy C-Means clustering are provided.

Original languageEnglish (US)
Article number32
Pages (from-to)1-10
Number of pages10
JournalJournal of Nondestructive Evaluation
Volume34
Issue number4
DOIs
StatePublished - Nov 1 2015

Fingerprint

Sensor data fusion
Concretes
Defects
Ultrasonics
Concrete slabs
Electric fuses
Nondestructive examination
Clustering algorithms
Radar

All Science Journal Classification (ASJC) codes

  • Mechanics of Materials
  • Mechanical Engineering

Cite this

@article{e7be5ac70c9e46aa977d821411537101,
title = "Clustering Based Multi Sensor Data Fusion for Honeycomb Detection in Concrete",
abstract = "We use three clustering algorithms to aggregate a three-modal non-destructive testing data set into defect and not-defect groups. Our data set consist of impact-echo, ultrasound (US) and ground penetrating radar data collected on a large concrete slab with embedded simulated honeycombing defects. US performs best in defect discriminating and sizing, however the false positive rate is still high. We fuse the data set using K-Means, Fuzzy C-Means and DBSCAN clustering at feature-level. We discern that DBSCAN improves the detectability up to 10 {\%}. A discussion of its advantages over commonly used K-Means and Fuzzy C-Means clustering are provided.",
author = "Christoph V{\"o}lker and Parisa Shokouhi",
year = "2015",
month = "11",
day = "1",
doi = "10.1007/s10921-015-0307-7",
language = "English (US)",
volume = "34",
pages = "1--10",
journal = "Journal of Nondestructive Evaluation",
issn = "0195-9298",
publisher = "Springer New York",
number = "4",

}

Clustering Based Multi Sensor Data Fusion for Honeycomb Detection in Concrete. / Völker, Christoph; Shokouhi, Parisa.

In: Journal of Nondestructive Evaluation, Vol. 34, No. 4, 32, 01.11.2015, p. 1-10.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Clustering Based Multi Sensor Data Fusion for Honeycomb Detection in Concrete

AU - Völker, Christoph

AU - Shokouhi, Parisa

PY - 2015/11/1

Y1 - 2015/11/1

N2 - We use three clustering algorithms to aggregate a three-modal non-destructive testing data set into defect and not-defect groups. Our data set consist of impact-echo, ultrasound (US) and ground penetrating radar data collected on a large concrete slab with embedded simulated honeycombing defects. US performs best in defect discriminating and sizing, however the false positive rate is still high. We fuse the data set using K-Means, Fuzzy C-Means and DBSCAN clustering at feature-level. We discern that DBSCAN improves the detectability up to 10 %. A discussion of its advantages over commonly used K-Means and Fuzzy C-Means clustering are provided.

AB - We use three clustering algorithms to aggregate a three-modal non-destructive testing data set into defect and not-defect groups. Our data set consist of impact-echo, ultrasound (US) and ground penetrating radar data collected on a large concrete slab with embedded simulated honeycombing defects. US performs best in defect discriminating and sizing, however the false positive rate is still high. We fuse the data set using K-Means, Fuzzy C-Means and DBSCAN clustering at feature-level. We discern that DBSCAN improves the detectability up to 10 %. A discussion of its advantages over commonly used K-Means and Fuzzy C-Means clustering are provided.

UR - http://www.scopus.com/inward/record.url?scp=84947419113&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84947419113&partnerID=8YFLogxK

U2 - 10.1007/s10921-015-0307-7

DO - 10.1007/s10921-015-0307-7

M3 - Article

AN - SCOPUS:84947419113

VL - 34

SP - 1

EP - 10

JO - Journal of Nondestructive Evaluation

JF - Journal of Nondestructive Evaluation

SN - 0195-9298

IS - 4

M1 - 32

ER -