Adaptive learning of behavioral tasks for patients with Parkinson's disease using signals from deep brain stimulation

N. Zaker, A. Dutta, A. Maurer, J. J. Zhang, S. Hanrahan, A. O. Hebb, N. Kovvali, Antonia Papandreou-Suppappola

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

5 Citations (Scopus)

Abstract

We propose adaptive learning methods for identifying different behavioral tasks of patients with Parkinson's disease (PD). The methods use local field potential (LFP) signals that were collected during Deep Brain Stimulation (DBS) implantation surgeries. Using time-frequency signal processing methods, features are first extracted and then clustered in the feature space using two different methods. The first method requires training and uses a hybrid model that combines support vector machines and hidden Markov models. The second method does not require any a priori information and uses Dirichlet process Gaussian mixture models. Using the DBS acquired signals, we demonstrate the performance of both methods in clustering different behavioral tasks of PD patients and discuss the advantages of each method under different conditions.

Original languageEnglish (US)
Title of host publicationConference Record - Asilomar Conference on Signals, Systems and Computers
PublisherIEEE Computer Society
Pages208-212
Number of pages5
Volume2015-April
ISBN (Print)9781479982974
DOIs
StatePublished - Apr 24 2015
Event48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015 - Pacific Grove, United States
Duration: Nov 2 2014Nov 5 2014

Other

Other48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015
CountryUnited States
CityPacific Grove
Period11/2/1411/5/14

Fingerprint

Brain
Hidden Markov models
Surgery
Support vector machines
Signal processing

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Signal Processing

Cite this

Zaker, N., Dutta, A., Maurer, A., Zhang, J. J., Hanrahan, S., Hebb, A. O., ... Papandreou-Suppappola, A. (2015). Adaptive learning of behavioral tasks for patients with Parkinson's disease using signals from deep brain stimulation. In Conference Record - Asilomar Conference on Signals, Systems and Computers (Vol. 2015-April, pp. 208-212). [7094429] IEEE Computer Society. https://doi.org/10.1109/ACSSC.2014.7094429

Adaptive learning of behavioral tasks for patients with Parkinson's disease using signals from deep brain stimulation. / Zaker, N.; Dutta, A.; Maurer, A.; Zhang, J. J.; Hanrahan, S.; Hebb, A. O.; Kovvali, N.; Papandreou-Suppappola, Antonia.

Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2015-April IEEE Computer Society, 2015. p. 208-212 7094429.

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

Zaker, N, Dutta, A, Maurer, A, Zhang, JJ, Hanrahan, S, Hebb, AO, Kovvali, N & Papandreou-Suppappola, A 2015, Adaptive learning of behavioral tasks for patients with Parkinson's disease using signals from deep brain stimulation. in Conference Record - Asilomar Conference on Signals, Systems and Computers. vol. 2015-April, 7094429, IEEE Computer Society, pp. 208-212, 48th Asilomar Conference on Signals, Systems and Computers, ACSSC 2015, Pacific Grove, United States, 11/2/14. https://doi.org/10.1109/ACSSC.2014.7094429
Zaker N, Dutta A, Maurer A, Zhang JJ, Hanrahan S, Hebb AO et al. Adaptive learning of behavioral tasks for patients with Parkinson's disease using signals from deep brain stimulation. In Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2015-April. IEEE Computer Society. 2015. p. 208-212. 7094429 https://doi.org/10.1109/ACSSC.2014.7094429
Zaker, N. ; Dutta, A. ; Maurer, A. ; Zhang, J. J. ; Hanrahan, S. ; Hebb, A. O. ; Kovvali, N. ; Papandreou-Suppappola, Antonia. / Adaptive learning of behavioral tasks for patients with Parkinson's disease using signals from deep brain stimulation. Conference Record - Asilomar Conference on Signals, Systems and Computers. Vol. 2015-April IEEE Computer Society, 2015. pp. 208-212
@inproceedings{d3226d56019b4cbb8138abc034e0c450,
title = "Adaptive learning of behavioral tasks for patients with Parkinson's disease using signals from deep brain stimulation",
abstract = "We propose adaptive learning methods for identifying different behavioral tasks of patients with Parkinson's disease (PD). The methods use local field potential (LFP) signals that were collected during Deep Brain Stimulation (DBS) implantation surgeries. Using time-frequency signal processing methods, features are first extracted and then clustered in the feature space using two different methods. The first method requires training and uses a hybrid model that combines support vector machines and hidden Markov models. The second method does not require any a priori information and uses Dirichlet process Gaussian mixture models. Using the DBS acquired signals, we demonstrate the performance of both methods in clustering different behavioral tasks of PD patients and discuss the advantages of each method under different conditions.",
author = "N. Zaker and A. Dutta and A. Maurer and Zhang, {J. J.} and S. Hanrahan and Hebb, {A. O.} and N. Kovvali and Antonia Papandreou-Suppappola",
year = "2015",
month = "4",
day = "24",
doi = "10.1109/ACSSC.2014.7094429",
language = "English (US)",
isbn = "9781479982974",
volume = "2015-April",
pages = "208--212",
booktitle = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Adaptive learning of behavioral tasks for patients with Parkinson's disease using signals from deep brain stimulation

AU - Zaker, N.

AU - Dutta, A.

AU - Maurer, A.

AU - Zhang, J. J.

AU - Hanrahan, S.

AU - Hebb, A. O.

AU - Kovvali, N.

AU - Papandreou-Suppappola, Antonia

PY - 2015/4/24

Y1 - 2015/4/24

N2 - We propose adaptive learning methods for identifying different behavioral tasks of patients with Parkinson's disease (PD). The methods use local field potential (LFP) signals that were collected during Deep Brain Stimulation (DBS) implantation surgeries. Using time-frequency signal processing methods, features are first extracted and then clustered in the feature space using two different methods. The first method requires training and uses a hybrid model that combines support vector machines and hidden Markov models. The second method does not require any a priori information and uses Dirichlet process Gaussian mixture models. Using the DBS acquired signals, we demonstrate the performance of both methods in clustering different behavioral tasks of PD patients and discuss the advantages of each method under different conditions.

AB - We propose adaptive learning methods for identifying different behavioral tasks of patients with Parkinson's disease (PD). The methods use local field potential (LFP) signals that were collected during Deep Brain Stimulation (DBS) implantation surgeries. Using time-frequency signal processing methods, features are first extracted and then clustered in the feature space using two different methods. The first method requires training and uses a hybrid model that combines support vector machines and hidden Markov models. The second method does not require any a priori information and uses Dirichlet process Gaussian mixture models. Using the DBS acquired signals, we demonstrate the performance of both methods in clustering different behavioral tasks of PD patients and discuss the advantages of each method under different conditions.

UR - http://www.scopus.com/inward/record.url?scp=84940572803&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940572803&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2014.7094429

DO - 10.1109/ACSSC.2014.7094429

M3 - Conference contribution

AN - SCOPUS:84940572803

SN - 9781479982974

VL - 2015-April

SP - 208

EP - 212

BT - Conference Record - Asilomar Conference on Signals, Systems and Computers

PB - IEEE Computer Society

ER -