Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network

Marcos Fabietti; Mufti Mahmud; Ahmad Lotfi; Alberto Averna; David Guggenmos; Randolph Nudo; Michela Chiappalone

doi:10.1109/AICT50176.2020.9368638

Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network

Marcos Fabietti, Mufti Mahmud^*, Ahmad Lotfi, Alberto Averna, David Guggenmos, Randolph Nudo, Michela Chiappalone

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

22 Scopus citations

Abstract

The process of recording local fields potentials (LFP) can be contaminated by different internal and external sources of noise. To successfully use these recordings, noise must be removed, for which an automatic detection tool is needed to speed up the detection process. This work presents the use of a specific configuration of the recurrent neural network based machine learning approach, known as the long-short term memory (LSTM), in two different settings to identify artifacts and compares the obtained results to a feed forward neural network both in terms of classification performance and computational time. Using spontaneous LFP signals recorded chronically by multisite neuronal probes in behaving rats, our results show that the LSTM model with and without drop out can achieve an accuracy of 87.1%.

Original language	English
Title of host publication	14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728173856
DOIs	https://doi.org/10.1109/AICT50176.2020.9368638
State	Published - 7 Oct 2020
Externally published	Yes
Event	14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Virtual, Tashkent, Uzbekistan Duration: 7 Oct 2020 → 9 Oct 2020

Publication series

Name	14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings

Conference

Conference	14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020
Country/Territory	Uzbekistan
City	Virtual, Tashkent
Period	7/10/20 → 9/10/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Keywords

Computational neuroscience
machine learning
neuronal signals
neurophysiological signals
spontaneous neuronal activity

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Information Systems
Information Systems and Management
Computational Mathematics

Access to Document

10.1109/AICT50176.2020.9368638

Cite this

Fabietti, M., Mahmud, M., Lotfi, A., Averna, A., Guggenmos, D., Nudo, R., & Chiappalone, M. (2020). Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network. In 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings Article 9368638 (14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/AICT50176.2020.9368638

Fabietti, Marcos ; Mahmud, Mufti ; Lotfi, Ahmad et al. / Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network. 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings).

@inproceedings{cb3b4468709749d087212c08df995d13,

title = "Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network",

abstract = "The process of recording local fields potentials (LFP) can be contaminated by different internal and external sources of noise. To successfully use these recordings, noise must be removed, for which an automatic detection tool is needed to speed up the detection process. This work presents the use of a specific configuration of the recurrent neural network based machine learning approach, known as the long-short term memory (LSTM), in two different settings to identify artifacts and compares the obtained results to a feed forward neural network both in terms of classification performance and computational time. Using spontaneous LFP signals recorded chronically by multisite neuronal probes in behaving rats, our results show that the LSTM model with and without drop out can achieve an accuracy of 87.1\%.",

keywords = "Computational neuroscience, machine learning, neuronal signals, neurophysiological signals, spontaneous neuronal activity",

author = "Marcos Fabietti and Mufti Mahmud and Ahmad Lotfi and Alberto Averna and David Guggenmos and Randolph Nudo and Michela Chiappalone",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 ; Conference date: 07-10-2020 Through 09-10-2020",

year = "2020",

month = oct,

day = "7",

doi = "10.1109/AICT50176.2020.9368638",

language = "English",

series = "14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings",

address = "United States",

}

Fabietti, M, Mahmud, M, Lotfi, A, Averna, A, Guggenmos, D, Nudo, R & Chiappalone, M 2020, Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network. in 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings., 9368638, 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020, Virtual, Tashkent, Uzbekistan, 7/10/20. https://doi.org/10.1109/AICT50176.2020.9368638

Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network. / Fabietti, Marcos; Mahmud, Mufti; Lotfi, Ahmad et al.
14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9368638 (14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network

AU - Fabietti, Marcos

AU - Mahmud, Mufti

AU - Lotfi, Ahmad

AU - Averna, Alberto

AU - Guggenmos, David

AU - Nudo, Randolph

AU - Chiappalone, Michela

PY - 2020/10/7

Y1 - 2020/10/7

N2 - The process of recording local fields potentials (LFP) can be contaminated by different internal and external sources of noise. To successfully use these recordings, noise must be removed, for which an automatic detection tool is needed to speed up the detection process. This work presents the use of a specific configuration of the recurrent neural network based machine learning approach, known as the long-short term memory (LSTM), in two different settings to identify artifacts and compares the obtained results to a feed forward neural network both in terms of classification performance and computational time. Using spontaneous LFP signals recorded chronically by multisite neuronal probes in behaving rats, our results show that the LSTM model with and without drop out can achieve an accuracy of 87.1%.

AB - The process of recording local fields potentials (LFP) can be contaminated by different internal and external sources of noise. To successfully use these recordings, noise must be removed, for which an automatic detection tool is needed to speed up the detection process. This work presents the use of a specific configuration of the recurrent neural network based machine learning approach, known as the long-short term memory (LSTM), in two different settings to identify artifacts and compares the obtained results to a feed forward neural network both in terms of classification performance and computational time. Using spontaneous LFP signals recorded chronically by multisite neuronal probes in behaving rats, our results show that the LSTM model with and without drop out can achieve an accuracy of 87.1%.

KW - Computational neuroscience

KW - machine learning

KW - neuronal signals

KW - neurophysiological signals

KW - spontaneous neuronal activity

UR - https://www.scopus.com/pages/publications/85099709158

U2 - 10.1109/AICT50176.2020.9368638

DO - 10.1109/AICT50176.2020.9368638

M3 - Conference contribution

AN - SCOPUS:85099709158

T3 - 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings

BT - 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020

Y2 - 7 October 2020 through 9 October 2020

ER -

Fabietti M, Mahmud M, Lotfi A, Averna A, Guggenmos D, Nudo R et al. Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network. In 14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9368638. (14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings). doi: 10.1109/AICT50176.2020.9368638

Artifact Detection in Chronically Recorded Local Field Potentials using Long-Short Term Memory Neural Network

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this