Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal JURNAL PETERNAKAN Pharmaceutical Sciences and Research (PSR) Eduvest - Journal of Universal Studies
Sutriyo Sutriyo, Sutriyo
Departemen Farmasi FMIPA-UI Depok
Aerospace Engineering Agriculture, Biological Sciences & Forestry Computer Science & IT Health Professions Neuroscience Social Sciences

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Evaluation And Selection Of Optimal Deep Learning Architecture For Predicting The Endpoint In High Shear Wet Granulation For Antacid Tablet Production Maulana, Irvan; Yanuar, Arry; Sutriyo, Sutriyo; Bustamam, Alhadi
Eduvest - Journal of Universal Studies Vol. 4 No. 6 (2024): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v4i5.1274

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.
Utilization of Near-Infrared Spectroscopy Combined with PLS-2 Regression Learner to Predict Metformin HCL Tablet Dissolution Profile Zakaria, Mohamad Rahmatullah; Sutriyo, Sutriyo; Hayun, Hayun; Rukmana, Taufiq Indra
Eduvest - Journal of Universal Studies Vol. 5 No. 1 (2025): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v5i1.1566

Abstract

One of the assurances of pharmaceutical tablet's quality, effectivity, and safety is the dissolution test, which is commonly known by pharmaceutical manufacturers. Conventionally, this test is performed by simulating the release rate of a drug using a Dissolution Tester, which mimics the human gastrointestinal condition. As stated by the current compendial for tablet dosage form, the dissolution rate is mandatory, with no exception for Metformin HCl tablets. This laboratory method is often time-consuming, unsafe for organic reagent exposure, and produces waste. This problem requires rapid, simple, and nondestructive technologies, hence having powerful analytical performance. One of the technologies that is widely used is Near Infrared (NIR) spectroscopy. This study utilized the NIR spectrum as a predictor to generate a mathematical model using Partial Least Square Regression (PLS-2) to build a dissolution rate model for the Metformin HCl tablet, which uses the Farmakope Indonesia IV <1231> (FI-IV) dissolution method as the compendial reference method. The PLS-2 model was built, which shows the low difference between SEC and SECV in each sampling point and a good correlation in the coefficient of determination (R2) of each point's time of dissolution within 0.900 to 0.953. The challenge test was performed to prove the predictability of the PLS-2 model with NIR against the actual reference FI-IV method using differential and similarity Factors (f2 & f1), enabling real-time release testing (RTRT).
Co-Authors . Iskandarsyah Adilla Novitasari, Adilla Arry Yanuar Bustamam, Alhadi Dian Hayati Febrian Hevike Filosane, Febrian Hevike Hasan Rachmat, Hasan Hayun Hayun Indah, Rosari Joshita Djajadisastra, Joshita Khairunnisya, Khairunnisya Maulana, Irvan Mega Suryani, Mega Mita Rosalina, Mita Mun’im, Abdul Rarah Ratih Adjie Maheswari Rosmala Dewi Rukmana, Taufiq Indra Siti Nur Aeni, Siti Nur Sundarsih, Sundarsih Wieda Nurwidada Haritsa Zain Zakaria, Mohamad Rahmatullah Zuraida Syafara Dzuhro, Zuraida Syafara