An Unsorted Spike-Based Pattern Recognition Method for Real-Time Continuous Sensory Event Detection from Dorsal Root Ganglion Recording

Sungmin Han, Jun Uk Chu, Hyungmin Kim, Kuiwon Choi, Jong Woong Park, Inchan Youn

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

In functional neuromuscular stimulation systems, sensory information-based closed-loop control can be useful for restoring lost function in patients with hemiplegia or quadriplegia. The goal of this study was to detect sensory events from tactile afferent signals continuously in real time using a novel unsorted spike-based pattern recognition method. The tactile afferent signals were recorded with a 16-channel microelectrode in the dorsal root ganglion, and unsorted spike-based feature vectors were extracted as a novel combination of the time and time-frequency domain features. Principal component analysis was used to reduce the dimensionality of the feature vectors, and a multilayer perceptron classifier was used to detect sensory events. The proposed method showed good performance for classification accuracy, and the processing time delay of sensory event detection was less than 200 ms. These results indicated that the proposed method could be applicable for sensory feedback in closed-loop control systems.

Original languageEnglish
Article number7350222
Pages (from-to)1310-1320
Number of pages11
JournalIEEE Transactions on Biomedical Engineering
Volume63
Issue number6
DOIs
Publication statusPublished - 2016 Jun 1

Fingerprint

Spinal Ganglia
Pattern recognition
Sensory feedback
Closed loop control systems
Microelectrodes
Touch
Multilayer neural networks
Principal component analysis
Time delay
Classifiers
Sensory Feedback
Quadriplegia
Neural Networks (Computer)
Hemiplegia
Processing
Principal Component Analysis
Information Systems

Keywords

  • Pattern recognition
  • sensory event detection
  • sensory feedback
  • unsorted spike

ASJC Scopus subject areas

  • Biomedical Engineering

Cite this

An Unsorted Spike-Based Pattern Recognition Method for Real-Time Continuous Sensory Event Detection from Dorsal Root Ganglion Recording. / Han, Sungmin; Chu, Jun Uk; Kim, Hyungmin; Choi, Kuiwon; Park, Jong Woong; Youn, Inchan.

In: IEEE Transactions on Biomedical Engineering, Vol. 63, No. 6, 7350222, 01.06.2016, p. 1310-1320.

Research output: Contribution to journalArticle

@article{d7edd541910649d997dbf41c76ae9b4c,
title = "An Unsorted Spike-Based Pattern Recognition Method for Real-Time Continuous Sensory Event Detection from Dorsal Root Ganglion Recording",
abstract = "In functional neuromuscular stimulation systems, sensory information-based closed-loop control can be useful for restoring lost function in patients with hemiplegia or quadriplegia. The goal of this study was to detect sensory events from tactile afferent signals continuously in real time using a novel unsorted spike-based pattern recognition method. The tactile afferent signals were recorded with a 16-channel microelectrode in the dorsal root ganglion, and unsorted spike-based feature vectors were extracted as a novel combination of the time and time-frequency domain features. Principal component analysis was used to reduce the dimensionality of the feature vectors, and a multilayer perceptron classifier was used to detect sensory events. The proposed method showed good performance for classification accuracy, and the processing time delay of sensory event detection was less than 200 ms. These results indicated that the proposed method could be applicable for sensory feedback in closed-loop control systems.",
keywords = "Pattern recognition, sensory event detection, sensory feedback, unsorted spike",
author = "Sungmin Han and Chu, {Jun Uk} and Hyungmin Kim and Kuiwon Choi and Park, {Jong Woong} and Inchan Youn",
year = "2016",
month = "6",
day = "1",
doi = "10.1109/TBME.2015.2490739",
language = "English",
volume = "63",
pages = "1310--1320",
journal = "IEEE Transactions on Biomedical Engineering",
issn = "0018-9294",
publisher = "IEEE Computer Society",
number = "6",

}

TY - JOUR

T1 - An Unsorted Spike-Based Pattern Recognition Method for Real-Time Continuous Sensory Event Detection from Dorsal Root Ganglion Recording

AU - Han, Sungmin

AU - Chu, Jun Uk

AU - Kim, Hyungmin

AU - Choi, Kuiwon

AU - Park, Jong Woong

AU - Youn, Inchan

PY - 2016/6/1

Y1 - 2016/6/1

N2 - In functional neuromuscular stimulation systems, sensory information-based closed-loop control can be useful for restoring lost function in patients with hemiplegia or quadriplegia. The goal of this study was to detect sensory events from tactile afferent signals continuously in real time using a novel unsorted spike-based pattern recognition method. The tactile afferent signals were recorded with a 16-channel microelectrode in the dorsal root ganglion, and unsorted spike-based feature vectors were extracted as a novel combination of the time and time-frequency domain features. Principal component analysis was used to reduce the dimensionality of the feature vectors, and a multilayer perceptron classifier was used to detect sensory events. The proposed method showed good performance for classification accuracy, and the processing time delay of sensory event detection was less than 200 ms. These results indicated that the proposed method could be applicable for sensory feedback in closed-loop control systems.

AB - In functional neuromuscular stimulation systems, sensory information-based closed-loop control can be useful for restoring lost function in patients with hemiplegia or quadriplegia. The goal of this study was to detect sensory events from tactile afferent signals continuously in real time using a novel unsorted spike-based pattern recognition method. The tactile afferent signals were recorded with a 16-channel microelectrode in the dorsal root ganglion, and unsorted spike-based feature vectors were extracted as a novel combination of the time and time-frequency domain features. Principal component analysis was used to reduce the dimensionality of the feature vectors, and a multilayer perceptron classifier was used to detect sensory events. The proposed method showed good performance for classification accuracy, and the processing time delay of sensory event detection was less than 200 ms. These results indicated that the proposed method could be applicable for sensory feedback in closed-loop control systems.

KW - Pattern recognition

KW - sensory event detection

KW - sensory feedback

KW - unsorted spike

UR - http://www.scopus.com/inward/record.url?scp=84971663725&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84971663725&partnerID=8YFLogxK

U2 - 10.1109/TBME.2015.2490739

DO - 10.1109/TBME.2015.2490739

M3 - Article

C2 - 26672029

AN - SCOPUS:84971663725

VL - 63

SP - 1310

EP - 1320

JO - IEEE Transactions on Biomedical Engineering

JF - IEEE Transactions on Biomedical Engineering

SN - 0018-9294

IS - 6

M1 - 7350222

ER -