Towards the Appropriate Feature Extraction and Event Classification Methods for NIRS Data

Md Faisal Kabir, Sheikh Md Rabiul Islam, Xu Huang

Research output: A Conference proceeding or a Chapter in BookChapter

Abstract

This work aims to find the appropriate feature extraction as well as classification method for different event classifications from NIRS data. NIRS is used to measure the oxygenated and deoxygenated hemoglobin concentration (HbO HbR) in the super-facial layers of the human cortex. Using NIRS data, BCI can be achieved and to achieve BCI feature extraction and classifications are two major steps. Many features have been proved to be unique and good enough to use in all brain related medical applications. However, different statistical features extracted by principal component analysis (PCA), Non-linear Principal Component Analysis (NLPCA), and Independent Component Analysis (ICA) show different discriminative ability for event classifications. In addition, there exists a number of classification methods like Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest Neighbor Algorithm (kNN) etc. those can be applicable to classify the NIRS data. In this study, we have investigated different statistical feature extraction and classification methods using NIRS data of left and right-hand movement from University of Canberra, Australia. Eventually, the goal is to explore the most suitable feature extraction and classification methods for NIRS data.

Original languageEnglish
Title of host publication2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2)
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages1-4
Number of pages4
ISBN (Electronic)9781538647752
ISBN (Print)9781538647769
DOIs
Publication statusPublished - 8 Feb 2018
Event2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018 - Rajshahi, Bangladesh
Duration: 8 Feb 20189 Feb 2018
http://dept.ru.ac.bd/ic4me2/2018/ (Website)

Publication series

NameInternational Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018

Conference

Conference2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018
CountryBangladesh
CityRajshahi
Period8/02/189/02/18
Internet address

Fingerprint

Feature extraction
Principal component analysis
Hemoglobin
Independent component analysis
Medical applications
Support vector machines
Brain
Hemoglobins
Neural networks

Cite this

Kabir, M. F., Rabiul Islam, S. M., & Huang, X. (2018). Towards the Appropriate Feature Extraction and Event Classification Methods for NIRS Data. In 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2) (pp. 1-4). [8465635] (International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/IC4ME2.2018.8465635
Kabir, Md Faisal ; Rabiul Islam, Sheikh Md ; Huang, Xu. / Towards the Appropriate Feature Extraction and Event Classification Methods for NIRS Data. 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2). IEEE, Institute of Electrical and Electronics Engineers, 2018. pp. 1-4 (International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018).
@inbook{76f15478907d4de484118a2ed38ffa49,
title = "Towards the Appropriate Feature Extraction and Event Classification Methods for NIRS Data",
abstract = "This work aims to find the appropriate feature extraction as well as classification method for different event classifications from NIRS data. NIRS is used to measure the oxygenated and deoxygenated hemoglobin concentration (HbO HbR) in the super-facial layers of the human cortex. Using NIRS data, BCI can be achieved and to achieve BCI feature extraction and classifications are two major steps. Many features have been proved to be unique and good enough to use in all brain related medical applications. However, different statistical features extracted by principal component analysis (PCA), Non-linear Principal Component Analysis (NLPCA), and Independent Component Analysis (ICA) show different discriminative ability for event classifications. In addition, there exists a number of classification methods like Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest Neighbor Algorithm (kNN) etc. those can be applicable to classify the NIRS data. In this study, we have investigated different statistical feature extraction and classification methods using NIRS data of left and right-hand movement from University of Canberra, Australia. Eventually, the goal is to explore the most suitable feature extraction and classification methods for NIRS data.",
keywords = "Hbo, HbO, HbR, ICA, NIRS, NLPCA, PCA",
author = "Kabir, {Md Faisal} and {Rabiul Islam}, {Sheikh Md} and Xu Huang",
year = "2018",
month = "2",
day = "8",
doi = "10.1109/IC4ME2.2018.8465635",
language = "English",
isbn = "9781538647769",
series = "International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
pages = "1--4",
booktitle = "2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2)",
address = "United States",

}

Kabir, MF, Rabiul Islam, SM & Huang, X 2018, Towards the Appropriate Feature Extraction and Event Classification Methods for NIRS Data. in 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2)., 8465635, International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018, IEEE, Institute of Electrical and Electronics Engineers, pp. 1-4, 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018, Rajshahi, Bangladesh, 8/02/18. https://doi.org/10.1109/IC4ME2.2018.8465635

Towards the Appropriate Feature Extraction and Event Classification Methods for NIRS Data. / Kabir, Md Faisal; Rabiul Islam, Sheikh Md; Huang, Xu.

2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2). IEEE, Institute of Electrical and Electronics Engineers, 2018. p. 1-4 8465635 (International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018).

Research output: A Conference proceeding or a Chapter in BookChapter

TY - CHAP

T1 - Towards the Appropriate Feature Extraction and Event Classification Methods for NIRS Data

AU - Kabir, Md Faisal

AU - Rabiul Islam, Sheikh Md

AU - Huang, Xu

PY - 2018/2/8

Y1 - 2018/2/8

N2 - This work aims to find the appropriate feature extraction as well as classification method for different event classifications from NIRS data. NIRS is used to measure the oxygenated and deoxygenated hemoglobin concentration (HbO HbR) in the super-facial layers of the human cortex. Using NIRS data, BCI can be achieved and to achieve BCI feature extraction and classifications are two major steps. Many features have been proved to be unique and good enough to use in all brain related medical applications. However, different statistical features extracted by principal component analysis (PCA), Non-linear Principal Component Analysis (NLPCA), and Independent Component Analysis (ICA) show different discriminative ability for event classifications. In addition, there exists a number of classification methods like Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest Neighbor Algorithm (kNN) etc. those can be applicable to classify the NIRS data. In this study, we have investigated different statistical feature extraction and classification methods using NIRS data of left and right-hand movement from University of Canberra, Australia. Eventually, the goal is to explore the most suitable feature extraction and classification methods for NIRS data.

AB - This work aims to find the appropriate feature extraction as well as classification method for different event classifications from NIRS data. NIRS is used to measure the oxygenated and deoxygenated hemoglobin concentration (HbO HbR) in the super-facial layers of the human cortex. Using NIRS data, BCI can be achieved and to achieve BCI feature extraction and classifications are two major steps. Many features have been proved to be unique and good enough to use in all brain related medical applications. However, different statistical features extracted by principal component analysis (PCA), Non-linear Principal Component Analysis (NLPCA), and Independent Component Analysis (ICA) show different discriminative ability for event classifications. In addition, there exists a number of classification methods like Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest Neighbor Algorithm (kNN) etc. those can be applicable to classify the NIRS data. In this study, we have investigated different statistical feature extraction and classification methods using NIRS data of left and right-hand movement from University of Canberra, Australia. Eventually, the goal is to explore the most suitable feature extraction and classification methods for NIRS data.

KW - Hbo

KW - HbO

KW - HbR

KW - ICA

KW - NIRS

KW - NLPCA

KW - PCA

UR - http://www.scopus.com/inward/record.url?scp=85055889665&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/towards-appropriate-feature-extraction-event-classification-methods-nirs-data

U2 - 10.1109/IC4ME2.2018.8465635

DO - 10.1109/IC4ME2.2018.8465635

M3 - Chapter

SN - 9781538647769

T3 - International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018

SP - 1

EP - 4

BT - 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2)

PB - IEEE, Institute of Electrical and Electronics Engineers

ER -

Kabir MF, Rabiul Islam SM, Huang X. Towards the Appropriate Feature Extraction and Event Classification Methods for NIRS Data. In 2018 International Conference on Computer, Communication, Chemical, Material and Electronic Engineering (IC4ME2). IEEE, Institute of Electrical and Electronics Engineers. 2018. p. 1-4. 8465635. (International Conference on Computer, Communication, Chemical, Material and Electronic Engineering, IC4ME2 2018). https://doi.org/10.1109/IC4ME2.2018.8465635