Home > Research > Publications & Outputs > Optimising Terahertz Waveform Selection of a Ph...

Electronic data

  • Named XXXX_final

    Rights statement: ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

    Accepted author manuscript, 1.31 MB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Optimising Terahertz Waveform Selection of a Pharmaceutical Film Coating Process Using Recurrent Network

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Optimising Terahertz Waveform Selection of a Pharmaceutical Film Coating Process Using Recurrent Network. / Li, Xiaoran; Williams, Bryan; May, Robert K. et al.
In: IEEE Transactions on Terahertz Science and Technology, Vol. 12, No. 4, 31.07.2022, p. 392-400.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Li, X, Williams, B, May, RK, Evans, MJ, Zhong, S, Gladden, LF, Shen, YC, Zeitler, JA & Lin, H 2022, 'Optimising Terahertz Waveform Selection of a Pharmaceutical Film Coating Process Using Recurrent Network', IEEE Transactions on Terahertz Science and Technology, vol. 12, no. 4, pp. 392-400. https://doi.org/10.1109/TTHZ.2022.3164353

APA

Li, X., Williams, B., May, R. K., Evans, M. J., Zhong, S., Gladden, L. F., Shen, Y. C., Zeitler, J. A., & Lin, H. (2022). Optimising Terahertz Waveform Selection of a Pharmaceutical Film Coating Process Using Recurrent Network. IEEE Transactions on Terahertz Science and Technology, 12(4), 392-400. https://doi.org/10.1109/TTHZ.2022.3164353

Vancouver

Li X, Williams B, May RK, Evans MJ, Zhong S, Gladden LF et al. Optimising Terahertz Waveform Selection of a Pharmaceutical Film Coating Process Using Recurrent Network. IEEE Transactions on Terahertz Science and Technology. 2022 Jul 31;12(4):392-400. Epub 2022 Apr 1. doi: 10.1109/TTHZ.2022.3164353

Author

Li, Xiaoran ; Williams, Bryan ; May, Robert K. et al. / Optimising Terahertz Waveform Selection of a Pharmaceutical Film Coating Process Using Recurrent Network. In: IEEE Transactions on Terahertz Science and Technology. 2022 ; Vol. 12, No. 4. pp. 392-400.

Bibtex

@article{da24a78a3c674a619110194e50f5d1fb,
title = "Optimising Terahertz Waveform Selection of a Pharmaceutical Film Coating Process Using Recurrent Network",
abstract = "In-line terahertz pulsed imaging (TPI) has been utilised to measure the film coating thickness of individual tablets during the coating process in a production-scale pan coater. A criteria-based waveform selection algorithm (WSA) was developed to select terahertz signals reflected from the surface of coating tablets and determine the coating thickness. Since the WSA uses many criteria thresholds to select terahertz waveforms of sufficiently high quality, it could reject some potential candidate tablet waveforms that are close but do not reach the threshold boundary. On the premise of the availability of large datasets, we aim to improve the efficiency of WSA with machine learning. This paper presents a recurrent neural network approach to optimise waveform selection. In comparison with the conventional method of WSA, our approach allows more than double the number of waveforms to be selected while maintain great agreement with off-line thickness measurement. Moreover, the processing time of waveform selection decreases so that it can be applied for real-time coating monitoring in the pharmaceutical industry, which leads more advancement on the quality control for the pharmaceutical film coating.",
keywords = "Coatings, Thickness measurement, Pharmaceuticals, Logic gates, Terahertz wave imaging, Refractive index, Convolutional neural networks",
author = "Xiaoran Li and Bryan Williams and May, {Robert K.} and Evans, {Michael J.} and Shuncong Zhong and Gladden, {Lynn F.} and Shen, {Yao chun} and Zeitler, {J. Axel} and Hungyen Lin",
note = "{\textcopyright}2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.",
year = "2022",
month = jul,
day = "31",
doi = "10.1109/TTHZ.2022.3164353",
language = "English",
volume = "12",
pages = "392--400",
journal = "IEEE Transactions on Terahertz Science and Technology",
issn = "2156-342X",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

RIS

TY - JOUR

T1 - Optimising Terahertz Waveform Selection of a Pharmaceutical Film Coating Process Using Recurrent Network

AU - Li, Xiaoran

AU - Williams, Bryan

AU - May, Robert K.

AU - Evans, Michael J.

AU - Zhong, Shuncong

AU - Gladden, Lynn F.

AU - Shen, Yao chun

AU - Zeitler, J. Axel

AU - Lin, Hungyen

N1 - ©2022 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2022/7/31

Y1 - 2022/7/31

N2 - In-line terahertz pulsed imaging (TPI) has been utilised to measure the film coating thickness of individual tablets during the coating process in a production-scale pan coater. A criteria-based waveform selection algorithm (WSA) was developed to select terahertz signals reflected from the surface of coating tablets and determine the coating thickness. Since the WSA uses many criteria thresholds to select terahertz waveforms of sufficiently high quality, it could reject some potential candidate tablet waveforms that are close but do not reach the threshold boundary. On the premise of the availability of large datasets, we aim to improve the efficiency of WSA with machine learning. This paper presents a recurrent neural network approach to optimise waveform selection. In comparison with the conventional method of WSA, our approach allows more than double the number of waveforms to be selected while maintain great agreement with off-line thickness measurement. Moreover, the processing time of waveform selection decreases so that it can be applied for real-time coating monitoring in the pharmaceutical industry, which leads more advancement on the quality control for the pharmaceutical film coating.

AB - In-line terahertz pulsed imaging (TPI) has been utilised to measure the film coating thickness of individual tablets during the coating process in a production-scale pan coater. A criteria-based waveform selection algorithm (WSA) was developed to select terahertz signals reflected from the surface of coating tablets and determine the coating thickness. Since the WSA uses many criteria thresholds to select terahertz waveforms of sufficiently high quality, it could reject some potential candidate tablet waveforms that are close but do not reach the threshold boundary. On the premise of the availability of large datasets, we aim to improve the efficiency of WSA with machine learning. This paper presents a recurrent neural network approach to optimise waveform selection. In comparison with the conventional method of WSA, our approach allows more than double the number of waveforms to be selected while maintain great agreement with off-line thickness measurement. Moreover, the processing time of waveform selection decreases so that it can be applied for real-time coating monitoring in the pharmaceutical industry, which leads more advancement on the quality control for the pharmaceutical film coating.

KW - Coatings

KW - Thickness measurement

KW - Pharmaceuticals

KW - Logic gates

KW - Terahertz wave imaging

KW - Refractive index

KW - Convolutional neural networks

U2 - 10.1109/TTHZ.2022.3164353

DO - 10.1109/TTHZ.2022.3164353

M3 - Journal article

VL - 12

SP - 392

EP - 400

JO - IEEE Transactions on Terahertz Science and Technology

JF - IEEE Transactions on Terahertz Science and Technology

SN - 2156-342X

IS - 4

ER -