Deep multi-view models for glitch classification

Sara Bahaadini, Neda Rohani, Scott Coughlin, Michael Zevin, Vicky Kalogera, Aggelos K Katsaggelos

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

7 Citations (Scopus)

Abstract

Non-cosmic, non-Gaussian disturbances known as 'glitches', show up in gravitational-wave data of the Advanced Laser Interferometer Gravitational-wave Observatory, or aLIGO. In this paper, we propose a deep multi-view convolutional neural network to classify glitches automatically. The primary purpose of classifying glitches is to understand their characteristics and origin, which facilitates their removal from the data or from the detector entirely. We visualize glitches as spectrograms and leverage the state-of-the-art image classification techniques in our model. The suggested classifier is a multi-view deep neural network that exploits four different views for classification. The experimental results demonstrate that the proposed model improves the overall accuracy of the classification compared to traditional single view algorithms.

Original languageEnglish (US)
Title of host publication2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages2931-2935
Number of pages5
ISBN (Electronic)9781509041176
DOIs
StatePublished - Jun 16 2017
Event2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - New Orleans, United States
Duration: Mar 5 2017Mar 9 2017

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Other

Other2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017
CountryUnited States
CityNew Orleans
Period3/5/173/9/17

Fingerprint

Gravity waves
Image classification
Observatories
Interferometers
Classifiers
Detectors
Neural networks
Lasers
Deep neural networks

Keywords

  • Multi-view learning
  • deep learning
  • image classification
  • neural network

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Bahaadini, S., Rohani, N., Coughlin, S., Zevin, M., Kalogera, V., & Katsaggelos, A. K. (2017). Deep multi-view models for glitch classification. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings (pp. 2931-2935). [7952693] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2017.7952693
Bahaadini, Sara ; Rohani, Neda ; Coughlin, Scott ; Zevin, Michael ; Kalogera, Vicky ; Katsaggelos, Aggelos K. / Deep multi-view models for glitch classification. 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 2931-2935 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{44ddba93dd2744aa8445261df69ba7c8,
title = "Deep multi-view models for glitch classification",
abstract = "Non-cosmic, non-Gaussian disturbances known as 'glitches', show up in gravitational-wave data of the Advanced Laser Interferometer Gravitational-wave Observatory, or aLIGO. In this paper, we propose a deep multi-view convolutional neural network to classify glitches automatically. The primary purpose of classifying glitches is to understand their characteristics and origin, which facilitates their removal from the data or from the detector entirely. We visualize glitches as spectrograms and leverage the state-of-the-art image classification techniques in our model. The suggested classifier is a multi-view deep neural network that exploits four different views for classification. The experimental results demonstrate that the proposed model improves the overall accuracy of the classification compared to traditional single view algorithms.",
keywords = "Multi-view learning, deep learning, image classification, neural network",
author = "Sara Bahaadini and Neda Rohani and Scott Coughlin and Michael Zevin and Vicky Kalogera and Katsaggelos, {Aggelos K}",
year = "2017",
month = "6",
day = "16",
doi = "10.1109/ICASSP.2017.7952693",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "2931--2935",
booktitle = "2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings",
address = "United States",

}

Bahaadini, S, Rohani, N, Coughlin, S, Zevin, M, Kalogera, V & Katsaggelos, AK 2017, Deep multi-view models for glitch classification. in 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings., 7952693, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, Institute of Electrical and Electronics Engineers Inc., pp. 2931-2935, 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017, New Orleans, United States, 3/5/17. https://doi.org/10.1109/ICASSP.2017.7952693

Deep multi-view models for glitch classification. / Bahaadini, Sara; Rohani, Neda; Coughlin, Scott; Zevin, Michael; Kalogera, Vicky; Katsaggelos, Aggelos K.

2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2931-2935 7952693 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

TY - GEN

T1 - Deep multi-view models for glitch classification

AU - Bahaadini, Sara

AU - Rohani, Neda

AU - Coughlin, Scott

AU - Zevin, Michael

AU - Kalogera, Vicky

AU - Katsaggelos, Aggelos K

PY - 2017/6/16

Y1 - 2017/6/16

N2 - Non-cosmic, non-Gaussian disturbances known as 'glitches', show up in gravitational-wave data of the Advanced Laser Interferometer Gravitational-wave Observatory, or aLIGO. In this paper, we propose a deep multi-view convolutional neural network to classify glitches automatically. The primary purpose of classifying glitches is to understand their characteristics and origin, which facilitates their removal from the data or from the detector entirely. We visualize glitches as spectrograms and leverage the state-of-the-art image classification techniques in our model. The suggested classifier is a multi-view deep neural network that exploits four different views for classification. The experimental results demonstrate that the proposed model improves the overall accuracy of the classification compared to traditional single view algorithms.

AB - Non-cosmic, non-Gaussian disturbances known as 'glitches', show up in gravitational-wave data of the Advanced Laser Interferometer Gravitational-wave Observatory, or aLIGO. In this paper, we propose a deep multi-view convolutional neural network to classify glitches automatically. The primary purpose of classifying glitches is to understand their characteristics and origin, which facilitates their removal from the data or from the detector entirely. We visualize glitches as spectrograms and leverage the state-of-the-art image classification techniques in our model. The suggested classifier is a multi-view deep neural network that exploits four different views for classification. The experimental results demonstrate that the proposed model improves the overall accuracy of the classification compared to traditional single view algorithms.

KW - Multi-view learning

KW - deep learning

KW - image classification

KW - neural network

UR - http://www.scopus.com/inward/record.url?scp=85014965185&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85014965185&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2017.7952693

DO - 10.1109/ICASSP.2017.7952693

M3 - Conference contribution

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 2931

EP - 2935

BT - 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Bahaadini S, Rohani N, Coughlin S, Zevin M, Kalogera V, Katsaggelos AK. Deep multi-view models for glitch classification. In 2017 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2931-2935. 7952693. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2017.7952693