Evaluation And Selection Of Optimal Deep Learning Architecture For Predicting The Endpoint In High Shear Wet Granulation For Antacid Tablet Production

Authors

  • Irvan Maulana Faculty of Pharmacy, Universitas Indonesia, Jawa Barat, Indonesia
  • Arry Yanuar Faculty of Pharmacy, Universitas Indonesia, Jawa Barat, Indonesia
  • Sutriyo Faculty of Pharmacy, Universitas Indonesia, Jawa Barat, Indonesia
  • Alhadi Bustamam Department of Mathematics, Faculty of Mathematics and Natural Sciences, Universitas Indonesia, Jawa Barat, Indonesia

DOI:

https://doi.org/10.59188/eduvest.v4i5.1274

Keywords:

Wet Granulation, Image Processing, Deep Learning, Image-based inspection, MobileNetV2, EfficientNetB0, ResNet50V2

Abstract

Objective: The purpose of this research was to evaluate and select the best architecture among native convolutional neural network (CNN), MobileNetV2, ResNet50V2, and EfficientNetB0 for predicting the endpoint of the high shear wet granulation process, with accuracy as the main evaluation metric. Methods: The dataset was captured from an industrial camera using static image analysis and was manually labeled as “NOT READY” and “READY” according to the traditional endpoint method based on the mixer’s ampere point in the granulator. The dataset contained a total of 180 images, which were split between training and validation sets. Native CNN and TensorFlow Keras application programming interface (API) were utilized with MobileNetV2, EfficientNetB0, and ResNet50V2 as base feature encoders. Hyperparameters, such as final Fully Connected (FC) layer width, dropout rate, and learning rate, were optimized for binary classification using Keras hyper tuning. Results: The best was the native CNN, it was also the fastest among the three other models, taking only 20-30 ms per step for inference during runtime, though it requires 9000 ms time for training, the longest time among the models. It achieved an accuracy of 98%, and a validation accuracy of 97%. Conclusion: The system was able to determine when a wet granulation process has reached its endpoint based on live images from a camera after being trained on previously labeled data. The native CNN was the best model, offering the fastest runtime performance and the highest accuracy.

References

Amalia, R., Bustamam, A., & Sarwinda, D. (2021). Detection and description generation of diabetic retinopathy using convolutional neural network and long short-term memory. Journal of Physics: Conference Series, 1722(1). IOP Publishing Ltd. https://doi.org/10.1088/1742-6596/1722/1/012010

Bustamam, A., Sarwinda, D., Paradisa, R. H., Victor, A. A., Yudantha, A. R., & Siswantining, T. (2021). Evaluation of convolutional neural network variants for diagnosis of diabetic retinopathy. Commun. Math. Biol. Neurosci., 2021(0), Article ID 42. https://doi.org/10.28919/CMBN/5660

Farkas, D., Madarász, L., Nagy, Z. K., Antal, I., & Kállai-Szabó, N. (2021, May 1). Image analysis: A versatile tool in the manufacturing and quality control of pharmaceutical dosage forms. Pharmaceutics, Vol. 13. MDPI AG. https://doi.org/10.3390/pharmaceutics13050685

He, K., Zhang, X., Ren, S., & Sun, J. (2016a). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-December, 770–778. https://doi.org/10.1109/CVPR.2016.90

He, K., Zhang, X., Ren, S., & Sun, J. (2016b). Deep residual learning for image recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2016-December, 770–778. IEEE Computer Society. https://doi.org/10.1109/CVPR.2016.90

Li, X. (2024). Exploring the effect of depth and width of CNN models on binary classification of dogs and cats. Applied and Computational Engineering, 47(1), 147–158. https://doi.org/10.54254/2755-2721/47/20241274

Liu, B., Wang, J., Zeng, J., Zhao, L., Wang, Y., Feng, Y., & Du, R. (2021). A review of high shear wet granulation for better process understanding, control and product development. Powder Technology, 381, 204–223. https://doi.org/10.1016/J.POWTEC.2020.11.051

Liu, Z., Agu, E., Pedersen, P., Lindsay, C., Tulu, B., & Strong, D. (2021). Comprehensive Assessment of Fine-Grained Wound Images Using a Patch-Based CNN with Context-Preserving Attention. IEEE Open Journal of Engineering in Medicine and Biology, 2, 224–234. https://doi.org/10.1109/OJEMB.2021.3092207

Lou, H., Lian, B., & Hageman, M. J. (2021). Applications of Machine Learning in Solid Oral Dosage Form Development. Journal of Pharmaceutical Sciences, 110(9), 3150–3165. https://doi.org/10.1016/j.xphs.2021.04.013

Madarász, L., Mészáros, L. A., Köte, Á., Farkas, A., & Nagy, Z. K. (2023). AI-based analysis of in-line process endoscope images for real-time particle size measurement in a continuous pharmaceutical milling process. International Journal of Pharmaceutics, 641. https://doi.org/10.1016/j.ijpharm.2023.123060

Mahdi, F., Hassanpour, A., & Muller, F. (2018). An investigation on the evolution of granule formation by in-process sampling of a high shear granulator. Chemical Engineering Research and Design, 129, 403–411. https://doi.org/10.1016/j.cherd.2017.10.038

Mäki-Lohiluoma, E., Säkkinen, N., Palomäki, M., Winberg, O., Ta, H. X., Heikkinen, T., … Kauppinen, A. (2021). Use of machine learning in prediction of granule particle size distribution and tablet tensile strength in commercial pharmaceutical manufacturing. International Journal of Pharmaceutics, 609, 121146. https://doi.org/10.1016/J.IJPHARM.2021.121146

Millen, N., Kovačević, A., Djuriš, J., & Ibrić, S. (2020). Machine Learning Modeling of Wet Granulation Scale-up Using Particle Size Distribution Characterization Parameters. Journal of Pharmaceutical Innovation, 15(4), 535–546. https://doi.org/10.1007/s12247-019-09398-0

Razi, F. A., Bustamam, A., & Latifah, A. L. (2023). Development of Efficient Brain Tumor Classification on MRI Image Results Using EfficientNet. 2023 International Seminar on Intelligent Technology and Its Applications: Leveraging Intelligent Systems to Achieve Sustainable Development Goals, ISITIA 2023 - Proceeding, 575–580. https://doi.org/10.1109/ISITIA59021.2023.10221186

Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 4510–4520. IEEE Computer Society. https://doi.org/10.1109/CVPR.2018.00474

Sarwinda, D., Paradisa, R. H., Bustamam, A., & Anggia, P. (2021). Deep Learning in Image Classification using Residual Network (ResNet) Variants for Detection of Colorectal Cancer. Procedia Computer Science, 179, 423–431. Elsevier B.V. https://doi.org/10.1016/j.procs.2021.01.025

Singh, M., Shirazian, S., Ranade, V., Walker, G. M., & Kumar, A. (2022). Challenges and opportunities in modelling wet granulation in pharmaceutical industry – A critical review. Powder Technology, 403, 117380. https://doi.org/10.1016/J.POWTEC.2022.117380

Sudarsono, E., Bustamam, A., & Tampubolon, P. P. (2020). An optimized convolutional neural network using diffgrad for cataract image classification. AIP Conference Proceedings, 2296. American Institute of Physics Inc. https://doi.org/10.1063/5.0030746

Tan, M., & Le, Q. V. (2019). EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. Retrieved from http://arxiv.org/abs/1905.11946

Triyadi, A. B., Bustamam, A., & Anki, P. (2022). Deep Learning in Image Classification using VGG-19 and Residual Networks for Cataract Detection. Proceedings - 2022 2nd International Conference on Information Technology and Education, ICIT and E 2022, 293–297. https://doi.org/10.1109/ICITE54466.2022.9759886

Yu, H., Fu, J., Dang, L., Cheong, Y., Tan, H., & Wei, H. (2015). Prediction of the Particle Size Distribution Parameters in a High Shear Granulation Process Using a Key Parameter Definition Combined Artificial Neural Network Model. Industrial and Engineering Chemistry Research, 54(43), 10825–10834. https://doi.org/10.1021/acs.iecr.5b02679

Zhao, X., Liu, Z., Agu, E., Wagh, A., Jain, S., Lindsay, C., … Kan, J. (2019). Fine-Grained Diabetic Wound Depth and Granulation Tissue Amount Assessment Using Bilinear Convolutional Neural Network. IEEE Access, 7, 179151–179162. https://doi.org/10.1109/ACCESS.2019.2959027

Downloads

Published

2024-06-25

Similar Articles

1 2 > >> 

You may also start an advanced similarity search for this article.