Deep multi-view models for glitch classification

Deep multi-view models for glitch classification. Bahaadini, S., Rohani, N., Coughlin, S., Zevin, M., Kalogera, V., & Katsaggelos, A. K. In 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pages 2931–2935, mar, 2017. IEEE, IEEE.

Paper doi abstract bibtex

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.

@inproceedings{bahaadini2017deep,
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.},
archivePrefix = {arXiv},
arxivId = {1705.00034},
author = {Bahaadini, Sara and Rohani, Neda and Coughlin, Scott and Zevin, Michael and Kalogera, Vicky and Katsaggelos, Aggelos K.},
booktitle = {2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},
doi = {10.1109/ICASSP.2017.7952693},
eprint = {1705.00034},
isbn = {978-1-5090-4117-6},
issn = {15206149},
keywords = {Multi-view learning,deep learning,image classification,neural network},
month = {mar},
organization = {IEEE},
pages = {2931--2935},
publisher = {IEEE},
title = {{Deep multi-view models for glitch classification}},
url = {http://ieeexplore.ieee.org/document/7952693/},
year = {2017}
}

Downloads: 0

{"_id":"wkNCsn78nWGwn55SN","bibbaseid":"bahaadini-rohani-coughlin-zevin-kalogera-katsaggelos-deepmultiviewmodelsforglitchclassification-2017","author_short":["Bahaadini, S.","Rohani, N.","Coughlin, S.","Zevin, M.","Kalogera, V.","Katsaggelos, A. K."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","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.","archiveprefix":"arXiv","arxivid":"1705.00034","author":[{"propositions":[],"lastnames":["Bahaadini"],"firstnames":["Sara"],"suffixes":[]},{"propositions":[],"lastnames":["Rohani"],"firstnames":["Neda"],"suffixes":[]},{"propositions":[],"lastnames":["Coughlin"],"firstnames":["Scott"],"suffixes":[]},{"propositions":[],"lastnames":["Zevin"],"firstnames":["Michael"],"suffixes":[]},{"propositions":[],"lastnames":["Kalogera"],"firstnames":["Vicky"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"booktitle":"2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","doi":"10.1109/ICASSP.2017.7952693","eprint":"1705.00034","isbn":"978-1-5090-4117-6","issn":"15206149","keywords":"Multi-view learning,deep learning,image classification,neural network","month":"mar","organization":"IEEE","pages":"2931–2935","publisher":"IEEE","title":"Deep multi-view models for glitch classification","url":"http://ieeexplore.ieee.org/document/7952693/","year":"2017","bibtex":"@inproceedings{bahaadini2017deep,\nabstract = {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.},\narchivePrefix = {arXiv},\narxivId = {1705.00034},\nauthor = {Bahaadini, Sara and Rohani, Neda and Coughlin, Scott and Zevin, Michael and Kalogera, Vicky and Katsaggelos, Aggelos K.},\nbooktitle = {2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)},\ndoi = {10.1109/ICASSP.2017.7952693},\neprint = {1705.00034},\nisbn = {978-1-5090-4117-6},\nissn = {15206149},\nkeywords = {Multi-view learning,deep learning,image classification,neural network},\nmonth = {mar},\norganization = {IEEE},\npages = {2931--2935},\npublisher = {IEEE},\ntitle = {{Deep multi-view models for glitch classification}},\nurl = {http://ieeexplore.ieee.org/document/7952693/},\nyear = {2017}\n}\n","author_short":["Bahaadini, S.","Rohani, N.","Coughlin, S.","Zevin, M.","Kalogera, V.","Katsaggelos, A. K."],"key":"bahaadini2017deep","id":"bahaadini2017deep","bibbaseid":"bahaadini-rohani-coughlin-zevin-kalogera-katsaggelos-deepmultiviewmodelsforglitchclassification-2017","role":"author","urls":{"Paper":"http://ieeexplore.ieee.org/document/7952693/"},"keyword":["Multi-view learning","deep learning","image classification","neural network"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","37Qfzv6wRptYkoSCL","zFPgsTDAW8aDnb5iN","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["multi-view learning","deep learning","image classification","neural network"],"search_terms":["deep","multi","view","models","glitch","classification","bahaadini","rohani","coughlin","zevin","kalogera","katsaggelos"],"title":"Deep multi-view models for glitch classification","year":2017}