Cited 0 time in webofscience Cited 0 time in scopus

Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain-computer interface: Three-class classification of rest, right-, and left-hand motor execution

Title
Convolutional neural network for high-accuracy functional near-infrared spectroscopy in a brain-computer interface: Three-class classification of rest, right-, and left-hand motor execution
Authors
Trakoolwilaiwan, ThanawinBehboodi, BaharehLee, Jae-SeokKim, Kyung-SooChoi, Ji-Woong
DGIST Authors
Choi, Ji-Woong
Issue Date
2018
Citation
Neurophotonics, 5(1)
Type
Article
Article Type
Article
Keywords
Artificial Neural NetworkBiomedical Signal ProcessingBrain Computer InterfaceBrain-Computer InterfaceClassification (of Information)Classification AccuracyClinical ArticleComputer NetworksControlled StudyConventional MethodsConvolutionConvolutional Neural NetworkDegradationExtractionFeature ExtractionFunctional Near Infrared SpectroscopyFunctional Near-Infrared SpectroscopyFunctional Near-Infrared Spectroscopy (FNIRS)Functional NeuroimagingHandHemodynamic ResponseHemodynamicsHigher Order StatisticsHumanInfrared DevicesInterfaces (Computer)Near Infrared SpectroscopyNervous SystemNeural NetworksPerformance DegradationRestStatistical MethodsSupport Vector MachineSupport Vector MachinesThree-Class Classification
ISSN
2329-423X
Abstract
The aim of this work is to develop an effective brain-computer interface (BCI) method based on functional near-infrared spectroscopy (fNIRS). In order to improve the performance of the BCI system in terms of accuracy, the ability to discriminate features from input signals and proper classification are desired. Previous studies have mainly extracted features from the signal manually, but proper features need to be selected carefully. To avoid performance degradation caused by manual feature selection, we applied convolutional neural networks (CNNs) as the automatic feature extractor and classifier for fNIRS-based BCI. In this study, the hemodynamic responses evoked by performing rest, right-, and left-hand motor execution tasks were measured on eight healthy subjects to compare performances. Our CNN-based method provided improvements in classification accuracy over conventional methods employing the most commonly used features of mean, peak, slope, variance, kurtosis, and skewness, classified by support vector machine (SVM) and artificial neural network (ANN). Specifically, up to 6.49% and 3.33% improvement in classification accuracy was achieved by CNN compared with SVM and ANN, respectively. © 2017 The Authors.
URI
http://hdl.handle.net/20.500.11750/4990
DOI
10.1117/1.NPh.5.1.011008
Publisher
SPIE
Related Researcher
  • Author Choi, Ji Woong CSP(Communication and Signal Processing) Lab
  • Research Interests Communication System; Signal Processing; Communication Circuit Design; 생체 신호 통신 및 신호 처리; 뇌-기계 인터페이스(BMI); 차세대 교차계층 통신 및 신호 처리; 5G 모바일 통신
Files:
There are no files associated with this item.
Collection:
Information and Communication EngineeringCSP(Communication and Signal Processing) Lab1. Journal Articles


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE