Cited 0 time in webofscience Cited 0 time in scopus

Convolutional Neural Network for Functional Near-Infrared Spectroscopy-Based Brain-Computer Interface

Convolutional Neural Network for Functional Near-Infrared Spectroscopy-Based Brain-Computer Interface
Thanawin, Trakoolwilaiwan
DGIST Authors
Choi, Ji WoongLee, Ki Joon
Choi, Ji Woong
Lee, Ki Joon
Issue Date
Available Date
Degree Date
2017. 8
Access Rights
The original item will not be provided upon request from the author
Functional near-infrared spectroscopybrain-computer interfaceconvolutional neural networksupport vector machineartificial neural networkfeature extraction
Brain-computer interface (BCI) is a communication system that translates the brain signal directly to a computer or external devices. It is a promising solution for the patients with neurological disorders as the system is able to restore the movement ability. Various neuroimaging modalities have been utilized for brain signal acquisition, however, functional near-infrared spectroscopy (fNIRS) provides many advantages over other modalities. Hence, it has gained attention for implementing in BCI system. For developing BCI system, the appropriate machine learning algorithm and discriminating features from the hemodynamic response signal are desired, as the previous studies have reported the performance enhancement of fNIRS-based BCI in terms of classification accuracy by focusing on the classifier as well as signal features. The aim of this thesis is to improve the classification accuracy in fNIRS-based BCI by classifying and extracting feature automatically. The convolutional neural network (CNN) was applied owing to the automatic feature extractor and classifier instead of manual feature extraction in the conventional methods. In the experiment, four healthy subjects were measured the hemodynamic response signal evoked by performing tasks including rest, right and left hand motor executions. The conventional methods of fNIRS-based BCI using signal mean, slope, peak, variance, skewness, and kurtosis as the features, and support vector machine (SVM) and artificial neural network (ANN) as the classification methods were compared with CNN-based method. The results show the improvement of classification accuracy of CNN-based method over SVM-based and ANN-based method 6.92% and 3.75%, respectively. The main contributions of this thesis are (1) the promising feature extraction and classification method for fNIRS-based BCI using CNN and (2) the analysis of the feature extracted by conventional methods and convolutional filter of the CNN. ⓒ 2017 DGIST
Table Of Contents
I. INTRODUCTION 1-- 1. Motivation 1-- 2. Objective 2-- II. BACKGROUND AND RELATEDWORK 4-- 1. Functional Near-Infrared Spectroscopy (fNIRS) 4-- 2. fNIRS-based BCI 5-- 3. Feature Extraction and Classification 6-- 3.1 Feature Extraction 6-- 3.2 Support Vector Machine (SVM) 7-- 3.3 Artificial Neural Network (ANN) 7-- 3.4 Convolutional Neural Network (CNN) 9-- 4. Evaluation 11-- III. METHOD 12-- 1. Participants 12-- 2. Data Acquisition 12-- 3. Experimental Procedure 12-- 4. Preprocessing 13-- 4.1 Concentration Changes of Hemoglobin 13-- 4.2 Filtering 14-- 5. Feature Extraction and Classification 16-- 5.1 Conventional Method 16-- 5.2 Proposed Structures of CNN 17-- 6. Feature Visualization 20-- IV. RESULTS AND DISCUSSIONS 23-- 1. Measured Hemodynamic Responses 23-- 2. Classification Accuracy 24-- 3. Feature Visualization 26-- 4. Future Work 28-- V. CONCLUSION 30-- References 31-- Acknowledgments 38-- Curriculum Vitae 39
Information and Communication Engineering
Related Researcher
  • Author Lee, Kijoon  
  • Research Interests Biomedical Optics; DOT; DSCA; NIRS; OCT; LSCI; Nonlinear Optics; Random Laser; Coherent Backscattering
Department of Emerging Materials ScienceThesesMaster

qrcode mendeley

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