Comparison analysis between PLS and NN in noninvasive blood glucose concentration prediction

Chuah Zheng Ming; P. Raveendran

doi:10.1109/TECHPOS.2009.5412048

Comparison analysis between PLS and NN in noninvasive blood glucose concentration prediction

Chuah Zheng Ming, P. Raveendran

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

8 Citations (Scopus)

Abstract

A series pair data of NIR spectral and measured BGL are collected for an OGTT experiment from a healthy volunteer. The collected data are then calibrated by using partial least squares (PLS) regression and feed-forward backpropagation neural network (NN). A comparative analysis between both calibration models is analysed. From the PLS and NN calibration models, root mean square error prediction of 0.5282mmol/L and 0.2952mmol/L, respectively, were achieved. The correlation factor of 0.9247 and 0.9863 were obtained from PLS and NN calibration models respectively.

Original language	English
Title of host publication	International Conference for Technical Postgraduates 2009, TECHPOS 2009
Publisher	IEEE, Institute of Electrical and Electronics Engineers
ISBN (Print)	9781424452231
DOIs	https://doi.org/10.1109/TECHPOS.2009.5412048
Publication status	Published - 2009
Externally published	Yes
Event	International Conference for Technical Postgraduates 2009 - Kuala Lumpur, Malaysia Duration: 14 Dec 2009 → 15 Dec 2009 https://ieeexplore.ieee.org/xpl/conhome/5403229/proceeding (Proceedings)

Conference

Conference	International Conference for Technical Postgraduates 2009
Abbreviated title	TECHPOS 2009
Country/Territory	Malaysia
City	Kuala Lumpur
Period	14/12/09 → 15/12/09
Internet address	https://ieeexplore.ieee.org/xpl/conhome/5403229/proceeding (Proceedings)

Access to Document

10.1109/TECHPOS.2009.5412048

Cite this

@inproceedings{488ad085c9484608af593fd84c270b3d,

title = "Comparison analysis between PLS and NN in noninvasive blood glucose concentration prediction",

abstract = "A series pair data of NIR spectral and measured BGL are collected for an OGTT experiment from a healthy volunteer. The collected data are then calibrated by using partial least squares (PLS) regression and feed-forward backpropagation neural network (NN). A comparative analysis between both calibration models is analysed. From the PLS and NN calibration models, root mean square error prediction of 0.5282mmol/L and 0.2952mmol/L, respectively, were achieved. The correlation factor of 0.9247 and 0.9863 were obtained from PLS and NN calibration models respectively.",

author = "Ming, {Chuah Zheng} and P. Raveendran",

year = "2009",

doi = "10.1109/TECHPOS.2009.5412048",

language = "English",

isbn = "9781424452231",

booktitle = "International Conference for Technical Postgraduates 2009, TECHPOS 2009",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States of America",

note = "International Conference for Technical Postgraduates 2009, TECHPOS 2009 ; Conference date: 14-12-2009 Through 15-12-2009",

url = "https://ieeexplore.ieee.org/xpl/conhome/5403229/proceeding",

}

Ming, CZ & Raveendran, P 2009, Comparison analysis between PLS and NN in noninvasive blood glucose concentration prediction. in International Conference for Technical Postgraduates 2009, TECHPOS 2009. IEEE, Institute of Electrical and Electronics Engineers, International Conference for Technical Postgraduates 2009, Kuala Lumpur, Malaysia, 14/12/09. https://doi.org/10.1109/TECHPOS.2009.5412048

Comparison analysis between PLS and NN in noninvasive blood glucose concentration prediction. / Ming, Chuah Zheng; Raveendran, P.
International Conference for Technical Postgraduates 2009, TECHPOS 2009. IEEE, Institute of Electrical and Electronics Engineers, 2009.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Comparison analysis between PLS and NN in noninvasive blood glucose concentration prediction

AU - Ming, Chuah Zheng

AU - Raveendran, P.

PY - 2009

Y1 - 2009

N2 - A series pair data of NIR spectral and measured BGL are collected for an OGTT experiment from a healthy volunteer. The collected data are then calibrated by using partial least squares (PLS) regression and feed-forward backpropagation neural network (NN). A comparative analysis between both calibration models is analysed. From the PLS and NN calibration models, root mean square error prediction of 0.5282mmol/L and 0.2952mmol/L, respectively, were achieved. The correlation factor of 0.9247 and 0.9863 were obtained from PLS and NN calibration models respectively.

AB - A series pair data of NIR spectral and measured BGL are collected for an OGTT experiment from a healthy volunteer. The collected data are then calibrated by using partial least squares (PLS) regression and feed-forward backpropagation neural network (NN). A comparative analysis between both calibration models is analysed. From the PLS and NN calibration models, root mean square error prediction of 0.5282mmol/L and 0.2952mmol/L, respectively, were achieved. The correlation factor of 0.9247 and 0.9863 were obtained from PLS and NN calibration models respectively.

UR - http://www.scopus.com/inward/record.url?scp=77951000892&partnerID=8YFLogxK

U2 - 10.1109/TECHPOS.2009.5412048

DO - 10.1109/TECHPOS.2009.5412048

M3 - Conference Paper

AN - SCOPUS:77951000892

SN - 9781424452231

BT - International Conference for Technical Postgraduates 2009, TECHPOS 2009

PB - IEEE, Institute of Electrical and Electronics Engineers

T2 - International Conference for Technical Postgraduates 2009

Y2 - 14 December 2009 through 15 December 2009

ER -

Comparison analysis between PLS and NN in noninvasive blood glucose concentration prediction

Abstract

Conference

Access to Document

Other files and links

Cite this