Title

A study of quadratic discriminant analysis-based motor imagery classification using functional near- infrared spectroscopy

Alternative Title

기능적 근적외선 분광법을 이용한 2차 판별분석 기반 운동 상상 상태 분류에 관한 연구

DGIST Authors

Seungjun Lee ; Okkyun Lee ; Kyonghwan Jin

Advisor

이옥균

Co-Advisor(s)

Kyonghwan Jin

Issued Date

2024

Awarded Date

2024-02-01

Citation

Seungjun Lee. (2024). A study of quadratic discriminant analysis-based motor imagery classification using functional near- infrared spectroscopy. doi: 10.22677/THESIS.200000731466

Type

Thesis

Description

뇌-컴퓨터 인터페이스; 근적외선 분광기; 신호처리; 선형 판별 분석; 부분공간방법

Table Of Contents

Abstract i
List of contents ii
List of figures iii


Ⅰ. Introduction 1
Ⅱ. Background · 3
1. Modified Beer-Lambert Law (MBLL) 3
2. Temporal derivative distribution repair (TDDR) · 4
3. Mutual Subspace method (MSM) · 5
4. Linear discriminant analysis (LDA) · 6
Ⅲ. Method 8
1. Data acquisition 8
2. Data pre-processing 9
3. Conventional methods · 10
3.1 Statistical feature extraction for LDA 10
3.2 Mutual Subspace Method (MSM) · 11
4. Proposed Method · 11
5. Performance evaluation 13
Ⅳ. Result 14
Ⅴ. Conclusion 16
Ⅵ. Reference · 17

URI

http://hdl.handle.net/20.500.11750/48070
http://dgist.dcollection.net/common/orgView/200000731466

DOI

10.22677/THESIS.200000731466

Degree

Master

Department

Department of Robotics and Mechatronics Engineering

Publisher

DGIST

Show Full Item Record