Predicting local field potentials with recurrent neural networks

Louis Kim, Jacob Harer, Akshay Rangamani, James Moran, Philip D. Parks, Alik Widge, Emad N. Eskandar, Darin Dougherty, Sang Peter Chin

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

3 Citations (Scopus)

Abstract

We present a Recurrent Neural Network using LSTM (Long Short Term Memory) that is capable of modeling and predicting Local Field Potentials. We train and test the network on real data recorded from epilepsy patients. We construct networks that predict multi-channel LFPs for 1, 10, and 100 milliseconds forward in time. Our results show that prediction using LSTM outperforms regression when predicting 10 and 100 millisecond forward in time.

Original languageEnglish (US)
Title of host publication2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages808-811
Number of pages4
Volume2016-October
ISBN (Electronic)9781457702204
DOIs
StatePublished - Oct 13 2016
Externally publishedYes
Event38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 - Orlando, United States
Duration: Aug 16 2016Aug 20 2016

Other

Other38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
CountryUnited States
CityOrlando
Period8/16/168/20/16

Fingerprint

Long-Term Memory
Recurrent neural networks
Short-Term Memory
Epilepsy
Long short-term memory

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Kim, L., Harer, J., Rangamani, A., Moran, J., Parks, P. D., Widge, A., ... Chin, S. P. (2016). Predicting local field potentials with recurrent neural networks. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 (Vol. 2016-October, pp. 808-811). [7590824] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2016.7590824

Predicting local field potentials with recurrent neural networks. / Kim, Louis; Harer, Jacob; Rangamani, Akshay; Moran, James; Parks, Philip D.; Widge, Alik; Eskandar, Emad N.; Dougherty, Darin; Chin, Sang Peter.

2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. p. 808-811 7590824.

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

Kim, L, Harer, J, Rangamani, A, Moran, J, Parks, PD, Widge, A, Eskandar, EN, Dougherty, D & Chin, SP 2016, Predicting local field potentials with recurrent neural networks. in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. vol. 2016-October, 7590824, Institute of Electrical and Electronics Engineers Inc., pp. 808-811, 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016, Orlando, United States, 8/16/16. https://doi.org/10.1109/EMBC.2016.7590824
Kim L, Harer J, Rangamani A, Moran J, Parks PD, Widge A et al. Predicting local field potentials with recurrent neural networks. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October. Institute of Electrical and Electronics Engineers Inc. 2016. p. 808-811. 7590824 https://doi.org/10.1109/EMBC.2016.7590824
Kim, Louis ; Harer, Jacob ; Rangamani, Akshay ; Moran, James ; Parks, Philip D. ; Widge, Alik ; Eskandar, Emad N. ; Dougherty, Darin ; Chin, Sang Peter. / Predicting local field potentials with recurrent neural networks. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Vol. 2016-October Institute of Electrical and Electronics Engineers Inc., 2016. pp. 808-811
@inproceedings{97587d0274af4dbc94c9b41c7953c199,
title = "Predicting local field potentials with recurrent neural networks",
abstract = "We present a Recurrent Neural Network using LSTM (Long Short Term Memory) that is capable of modeling and predicting Local Field Potentials. We train and test the network on real data recorded from epilepsy patients. We construct networks that predict multi-channel LFPs for 1, 10, and 100 milliseconds forward in time. Our results show that prediction using LSTM outperforms regression when predicting 10 and 100 millisecond forward in time.",
author = "Louis Kim and Jacob Harer and Akshay Rangamani and James Moran and Parks, {Philip D.} and Alik Widge and Eskandar, {Emad N.} and Darin Dougherty and Chin, {Sang Peter}",
year = "2016",
month = "10",
day = "13",
doi = "10.1109/EMBC.2016.7590824",
language = "English (US)",
volume = "2016-October",
pages = "808--811",
booktitle = "2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Predicting local field potentials with recurrent neural networks

AU - Kim, Louis

AU - Harer, Jacob

AU - Rangamani, Akshay

AU - Moran, James

AU - Parks, Philip D.

AU - Widge, Alik

AU - Eskandar, Emad N.

AU - Dougherty, Darin

AU - Chin, Sang Peter

PY - 2016/10/13

Y1 - 2016/10/13

N2 - We present a Recurrent Neural Network using LSTM (Long Short Term Memory) that is capable of modeling and predicting Local Field Potentials. We train and test the network on real data recorded from epilepsy patients. We construct networks that predict multi-channel LFPs for 1, 10, and 100 milliseconds forward in time. Our results show that prediction using LSTM outperforms regression when predicting 10 and 100 millisecond forward in time.

AB - We present a Recurrent Neural Network using LSTM (Long Short Term Memory) that is capable of modeling and predicting Local Field Potentials. We train and test the network on real data recorded from epilepsy patients. We construct networks that predict multi-channel LFPs for 1, 10, and 100 milliseconds forward in time. Our results show that prediction using LSTM outperforms regression when predicting 10 and 100 millisecond forward in time.

UR - http://www.scopus.com/inward/record.url?scp=85009110562&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009110562&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2016.7590824

DO - 10.1109/EMBC.2016.7590824

M3 - Conference contribution

VL - 2016-October

SP - 808

EP - 811

BT - 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -