Neural decoding of finger movements using skellam-based maximum-likelihood decoding

Hyun Chool Shin, Vikram Aggarwal, Soumyadipta Acharya, Marc H. Schieber, Nitish V Thakor

Research output: Contribution to journalArticle

Abstract

We present an optimal method for decoding the activity of primary motor cortex (M1) neurons in a nonhuman primate during single finger movements. The method is based on the maximum-likelihood (ML) inference, which assuming the probability of finger movements is uniform, is equivalent to the maximum a posteriori (MAP) inference. Each neurons activation is first quantified by the change in firing rate before and after finger movement. We then estimate the probability density function of this activation given finger movement, i.e., Pr(neuronal activation (x)| finger movements (m)). Based on the ML criterion, we choose finger movements to maximize Pr(x|m). Experimentally, data were collected from 115 task-related neurons in M1 as the monkey performed flexion and extension of each finger and the wrist (12 movements). With as few as 20-25 randomly selected neurons, the proposed method decoded single-finger movements with 99% accuracy. Since the training and decoding procedures in the proposed method are simple and computationally efficient, the method can be extended for real-time neuroprosthetic control of a dexterous hand.

Original languageEnglish (US)
Article number4895277
Pages (from-to)754-760
Number of pages7
JournalIEEE Transactions on Biomedical Engineering
Volume57
Issue number3
DOIs
StatePublished - Mar 2010

Fingerprint

Maximum likelihood
Neurons
Decoding
Chemical activation
Real time control
Probability density function

Keywords

  • Finger movements
  • Maximum likelihood
  • Neural decoding
  • Neural prosthetics
  • Skellam

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

Neural decoding of finger movements using skellam-based maximum-likelihood decoding. / Shin, Hyun Chool; Aggarwal, Vikram; Acharya, Soumyadipta; Schieber, Marc H.; Thakor, Nitish V.

In: IEEE Transactions on Biomedical Engineering, Vol. 57, No. 3, 4895277, 03.2010, p. 754-760.

Research output: Contribution to journalArticle

@article{a11d14ed98964107b8c1ae15f01e2f90,
title = "Neural decoding of finger movements using skellam-based maximum-likelihood decoding",
abstract = "We present an optimal method for decoding the activity of primary motor cortex (M1) neurons in a nonhuman primate during single finger movements. The method is based on the maximum-likelihood (ML) inference, which assuming the probability of finger movements is uniform, is equivalent to the maximum a posteriori (MAP) inference. Each neurons activation is first quantified by the change in firing rate before and after finger movement. We then estimate the probability density function of this activation given finger movement, i.e., Pr(neuronal activation (x)| finger movements (m)). Based on the ML criterion, we choose finger movements to maximize Pr(x|m). Experimentally, data were collected from 115 task-related neurons in M1 as the monkey performed flexion and extension of each finger and the wrist (12 movements). With as few as 20-25 randomly selected neurons, the proposed method decoded single-finger movements with 99{\%} accuracy. Since the training and decoding procedures in the proposed method are simple and computationally efficient, the method can be extended for real-time neuroprosthetic control of a dexterous hand.",
keywords = "Finger movements, Maximum likelihood, Neural decoding, Neural prosthetics, Skellam",
author = "Shin, {Hyun Chool} and Vikram Aggarwal and Soumyadipta Acharya and Schieber, {Marc H.} and Thakor, {Nitish V}",
year = "2010",
month = "3",
doi = "10.1109/TBME.2009.2020791",
language = "English (US)",
volume = "57",
pages = "754--760",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "3",

}

TY - JOUR

T1 - Neural decoding of finger movements using skellam-based maximum-likelihood decoding

AU - Shin, Hyun Chool

AU - Aggarwal, Vikram

AU - Acharya, Soumyadipta

AU - Schieber, Marc H.

AU - Thakor, Nitish V

PY - 2010/3

Y1 - 2010/3

N2 - We present an optimal method for decoding the activity of primary motor cortex (M1) neurons in a nonhuman primate during single finger movements. The method is based on the maximum-likelihood (ML) inference, which assuming the probability of finger movements is uniform, is equivalent to the maximum a posteriori (MAP) inference. Each neurons activation is first quantified by the change in firing rate before and after finger movement. We then estimate the probability density function of this activation given finger movement, i.e., Pr(neuronal activation (x)| finger movements (m)). Based on the ML criterion, we choose finger movements to maximize Pr(x|m). Experimentally, data were collected from 115 task-related neurons in M1 as the monkey performed flexion and extension of each finger and the wrist (12 movements). With as few as 20-25 randomly selected neurons, the proposed method decoded single-finger movements with 99% accuracy. Since the training and decoding procedures in the proposed method are simple and computationally efficient, the method can be extended for real-time neuroprosthetic control of a dexterous hand.

AB - We present an optimal method for decoding the activity of primary motor cortex (M1) neurons in a nonhuman primate during single finger movements. The method is based on the maximum-likelihood (ML) inference, which assuming the probability of finger movements is uniform, is equivalent to the maximum a posteriori (MAP) inference. Each neurons activation is first quantified by the change in firing rate before and after finger movement. We then estimate the probability density function of this activation given finger movement, i.e., Pr(neuronal activation (x)| finger movements (m)). Based on the ML criterion, we choose finger movements to maximize Pr(x|m). Experimentally, data were collected from 115 task-related neurons in M1 as the monkey performed flexion and extension of each finger and the wrist (12 movements). With as few as 20-25 randomly selected neurons, the proposed method decoded single-finger movements with 99% accuracy. Since the training and decoding procedures in the proposed method are simple and computationally efficient, the method can be extended for real-time neuroprosthetic control of a dexterous hand.

KW - Finger movements

KW - Maximum likelihood

KW - Neural decoding

KW - Neural prosthetics

KW - Skellam

UR - http://www.scopus.com/inward/record.url?scp=77649141839&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77649141839&partnerID=8YFLogxK

U2 - 10.1109/TBME.2009.2020791

DO - 10.1109/TBME.2009.2020791

M3 - Article

C2 - 19403361

AN - SCOPUS:77649141839

VL - 57

SP - 754

EP - 760

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 3

M1 - 4895277

ER -