Prediction of active substance content in pharmaceutical tablets using wavelet compressed NIR and Raman spectroscopic data

C. S. Soh; P. Raveendran

doi:10.1109/ICBPE.2006.348569

Prediction of active substance content in pharmaceutical tablets using wavelet compressed NIR and Raman spectroscopic data

C. S. Soh, P. Raveendran

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

1 Citation (Scopus)

Abstract

Wavelet transformation is performed on NIR transmittance and Raman spectroscopic data followed by prediction of active substance content of pharmaceutical tablet from the spectral data. Partial least squares regression (PLSR) is used to build the prediction models. Comparison is made between prediction models with and without wavelet compression. Results show that wavelet-transformed NIR spectral data extracted from certain wavelet scales could improve the prediction accuracy of the PLSR model. In addition, wavelet transformation of NIR spectral data reduces the number of variables used in calibration and prediction. However, there is no improvement in prediction accuracy for wavelet-transformed Raman spectral data.

Original language	English
Title of host publication	ICBPE 2006 - Proceedings of the 2006 International Conference on Biomedical and Pharmaceutical Engineering
Pages	133-136
Number of pages	4
DOIs	https://doi.org/10.1109/ICBPE.2006.348569
Publication status	Published - 2006
Externally published	Yes
Event	International Conference on Biomedical and Pharmaceutical Engineering 2006 - Singapore, Singapore Duration: 11 Dec 2006 → 14 Dec 2006 Conference number: 1st https://ieeexplore.ieee.org/xpl/conhome/4155848/proceeding (Proceedings)

Conference

Conference	International Conference on Biomedical and Pharmaceutical Engineering 2006
Abbreviated title	ICBPE 2006
Country/Territory	Singapore
City	Singapore
Period	11/12/06 → 14/12/06
Internet address	https://ieeexplore.ieee.org/xpl/conhome/4155848/proceeding (Proceedings)

Keywords

Near infrared
Pharmaceutical tablet
Raman
Wavelet

Access to Document

10.1109/ICBPE.2006.348569

Cite this

@inproceedings{210322a9fa0445eeadb1bfb673d1abd1,

title = "Prediction of active substance content in pharmaceutical tablets using wavelet compressed NIR and Raman spectroscopic data",

abstract = "Wavelet transformation is performed on NIR transmittance and Raman spectroscopic data followed by prediction of active substance content of pharmaceutical tablet from the spectral data. Partial least squares regression (PLSR) is used to build the prediction models. Comparison is made between prediction models with and without wavelet compression. Results show that wavelet-transformed NIR spectral data extracted from certain wavelet scales could improve the prediction accuracy of the PLSR model. In addition, wavelet transformation of NIR spectral data reduces the number of variables used in calibration and prediction. However, there is no improvement in prediction accuracy for wavelet-transformed Raman spectral data.",

keywords = "Near infrared, Pharmaceutical tablet, Raman, Wavelet",

author = "Soh, {C. S.} and P. Raveendran",

year = "2006",

doi = "10.1109/ICBPE.2006.348569",

language = "English",

isbn = "8190426249",

pages = "133--136",

booktitle = "ICBPE 2006 - Proceedings of the 2006 International Conference on Biomedical and Pharmaceutical Engineering",

note = "International Conference on Biomedical and Pharmaceutical Engineering 2006, ICBPE 2006 ; Conference date: 11-12-2006 Through 14-12-2006",

url = "https://ieeexplore.ieee.org/xpl/conhome/4155848/proceeding",

}

Soh, CS & Raveendran, P 2006, Prediction of active substance content in pharmaceutical tablets using wavelet compressed NIR and Raman spectroscopic data. in ICBPE 2006 - Proceedings of the 2006 International Conference on Biomedical and Pharmaceutical Engineering. pp. 133-136, International Conference on Biomedical and Pharmaceutical Engineering 2006, Singapore, Singapore, 11/12/06. https://doi.org/10.1109/ICBPE.2006.348569

Prediction of active substance content in pharmaceutical tablets using wavelet compressed NIR and Raman spectroscopic data. / Soh, C. S.; Raveendran, P.
ICBPE 2006 - Proceedings of the 2006 International Conference on Biomedical and Pharmaceutical Engineering. 2006. p. 133-136.

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

TY - GEN

T1 - Prediction of active substance content in pharmaceutical tablets using wavelet compressed NIR and Raman spectroscopic data

AU - Soh, C. S.

AU - Raveendran, P.

N1 - Conference code: 1st

PY - 2006

Y1 - 2006

N2 - Wavelet transformation is performed on NIR transmittance and Raman spectroscopic data followed by prediction of active substance content of pharmaceutical tablet from the spectral data. Partial least squares regression (PLSR) is used to build the prediction models. Comparison is made between prediction models with and without wavelet compression. Results show that wavelet-transformed NIR spectral data extracted from certain wavelet scales could improve the prediction accuracy of the PLSR model. In addition, wavelet transformation of NIR spectral data reduces the number of variables used in calibration and prediction. However, there is no improvement in prediction accuracy for wavelet-transformed Raman spectral data.

AB - Wavelet transformation is performed on NIR transmittance and Raman spectroscopic data followed by prediction of active substance content of pharmaceutical tablet from the spectral data. Partial least squares regression (PLSR) is used to build the prediction models. Comparison is made between prediction models with and without wavelet compression. Results show that wavelet-transformed NIR spectral data extracted from certain wavelet scales could improve the prediction accuracy of the PLSR model. In addition, wavelet transformation of NIR spectral data reduces the number of variables used in calibration and prediction. However, there is no improvement in prediction accuracy for wavelet-transformed Raman spectral data.

KW - Near infrared

KW - Pharmaceutical tablet

KW - Raman

KW - Wavelet

UR - http://www.scopus.com/inward/record.url?scp=46249091326&partnerID=8YFLogxK

U2 - 10.1109/ICBPE.2006.348569

DO - 10.1109/ICBPE.2006.348569

M3 - Conference Paper

AN - SCOPUS:46249091326

SN - 8190426249

SN - 9788190426244

SP - 133

EP - 136

BT - ICBPE 2006 - Proceedings of the 2006 International Conference on Biomedical and Pharmaceutical Engineering

T2 - International Conference on Biomedical and Pharmaceutical Engineering 2006

Y2 - 11 December 2006 through 14 December 2006

ER -

Prediction of active substance content in pharmaceutical tablets using wavelet compressed NIR and Raman spectroscopic data

Abstract

Conference

Keywords

Access to Document

Other files and links

Cite this