Identification of Drug Material Melting Conditions from Hot-Stage Microscopy Images Using Active Contour and Support Vector Machine Methods

Julia Mega  Reski; Muhammad  Ramadhani

doi:10.59395/ijadis.v7i1.1513

Authors

Julia Mega Reski Institut Teknologi Statistika dan Bisnis Muhammadiyah Semarang
Muhammad Ramadhani Department of Department of Electrical Engineering, Universitas Ahmad Dahlan, Yogyakarta, Indonesia

DOI:

https://doi.org/10.59395/ijadis.v7i1.1513

Keywords:

Smart Hot-Stage Microscopy , Image Processing , Melting Analysis , Pharmaceutical Material

Abstract

The hospital pharmacy installation plays an essential role in ensuring the quality of pharmaceutical supplies. One important stage in drug production is raw material analysis, particularly melting point determination as a purity indicator. Conventional methods, such as capillary tubes, are limited in accuracy and prone to subjectivity. This study aims to develop an automated image-based monitoring system integrated with Hot Stage Microscopy (HSM) to objectively detect real-time morphological changes in pharmaceutical materials. The system was designed using digital image processing stages consisting of image acquisition, processing, and output. Images were captured using a binocular microscope and processed on an Odroid XU4 mini-computer. Phase boundaries were identified using the Active Contour segmentation method, while texture features were extracted using the Gray Level Co-occurrence Matrix (GLCM) at four orientation angles. Classification was performed using a Support Vector Machine (SVM) with a Radial Basis Function (RBF) kernel. The results showed that the Active Contour method effectively detected melting phases, and the SVM achieved an accuracy of 91.67%, precision of 91.89%, sensitivity of 91.67%, and an F1-score of 91.66%. The system successfully distinguished pure Paracetamol from mixtures with Gallic Acid and Ferulic Acid.

846 481

Downloads

Download data is not yet available.

References

[1] I. Conference and L. Science, Improving Health For Better Future Life: Strengthening From Basic Science To Clinical Research.

[2] S. F. Lumbangaol, Implementasi Manajemen Pengelolaan Logistik Obat di Instalasi Farmasi Rumah Sakit Surya Insani Pasir Pangaraian Kabupaten Rokan Hulu Implementation of Drug Logistics Management in The Pharmacy Installation of Surya Insani Hospital Pasir Pangaraian Rokan Hulu Regency, no. c, pp. 103110, 2024. DOI: https://doi.org/10.35451/jfm.v7i1.2256

[3] F. Sipayung et al., Analisis Pengelolaan Sediaan Farmasi di Instalasi Farmasi Rumah Sakit di Kota Medan Tahun 2023 menjadi tanggung jawab pemerintah pusat , akan tetapi menjadi tanggung jawab pemerintah, no. 6, 2024. DOI: https://doi.org/10.61132/obat.v2i6.883

[4] I. Darsaklis, Identification of an Unknown Organic Compound by Determination of its Melting Point, vol. 12, no. February, pp. 2832, 2025. DOI: https://doi.org/10.26438/ijsrcs.v12i1.184

[5] M. Wesolowski and E. Leyk, Coupled and Simultaneous Thermal Analysis Techniques in the Study of Pharmaceuticals, Pharmaceutics, vol. 15, no. 6, 2023, doi: 10.3390/pharmaceutics15061596. DOI: https://doi.org/10.3390/pharmaceutics15061596

[6] A. F. Irabin et al., Synthesis of immunomodulatory biomimetic lipid polymer hybrid nanoparticles and application of zebrafish larvae in immunomodulation screening, Eur. J. Pharm. Sci., vol. 207, no. February, p. 107037, 2025, doi: 10.1016/j.ejps.2025.107037. DOI: https://doi.org/10.1016/j.ejps.2025.107037

[7] J. M. Reski, A. Yudhana, and A. Info, Classification of Crystallization Images of Pharmaceutical Raw Materials Using Convolutional Neural Network Algorithm, vol. 6, no. 3, pp. 705715, 2025, doi: 10.59395/ijadis.v6i3.1440. DOI: https://doi.org/10.59395/ijadis.v6i3.1440

[8] J. Chen, C. Liang, J. Chen, and Q. Zhou, Modeling Analysis of Melting and Crystallization Process of Mold Flux Based on the Image Processing Technology, Crystals, vol. 13, no. 4, 2023, doi: 10.3390/cryst13040594. DOI: https://doi.org/10.3390/cryst13040594

[9] C. Jiang et al., Automated Growth Rate Measurement of the Facet Surfaces of Single Crystals of the -Form of l-Glutamic Acid Using Machine Learning Image Processing, Cryst. Growth Des., vol. 24, no. 8, pp. 32773288, 2024, doi: 10.1021/acs.cgd.3c01548. DOI: https://doi.org/10.1021/acs.cgd.3c01548

[10] D. Wang, X. Dang, W. Liu, and Y. Wang, Image segmentation using active contours with image structure adaptive gradient vector flow external force, Front. Appl. Math. Stat., vol. 9, 2023, doi: 10.3389/fams.2023.1271296. DOI: https://doi.org/10.3389/fams.2023.1271296

[11] Y. Sari, A. R. Baskara, P. B. Prakoso, and M. A. Rahman, Application of Active Contour Model on Image Processing for Detection of Road Damage, J. Jalan Jemb., vol. 38, no. 2, pp. 138147, 2021.

[12] R. Guido, S. Ferrisi, D. Lofaro, and D. Conforti, An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review, Inf., vol. 15, no. 4, 2024, doi: 10.3390/info15040235. DOI: https://doi.org/10.3390/info15040235

[13] A. Kar, N. Nath, U. Kemprai, and Aman, Performance Analysis of Support Vector Machine (SVM) on Challenging Datasets for Forest Fire Detection, Int. J. Commun. Netw. Syst. Sci., vol. 17, no. 02, pp. 1129, 2024, doi: 10.4236/ijcns.2024.172002. DOI: https://doi.org/10.4236/ijcns.2024.172002

[14] W. Sun and M. H. Shahrajabian, Therapeutic Potential of Phenolic Compounds in Medicinal PlantsNatural Health Products for Human Health, Molecules, vol. 28, no. 4, 2023, doi: 10.3390/molecules28041845. DOI: https://doi.org/10.3390/molecules28041845

[15] R. E. N. Rongcai, W. U. Guoxiong, and C. A. I. Ming, Recent Advances in Pharmaceutical Sciences.vol. 14.New Delhi, India: AkiNik Publications, 2024.

[16] K. Pyrzynska, Ferulic AcidA Brief Review of Its Extraction, Bioavailability and Biological Activity, Separations, vol. 11, no. 7, 2024, doi: 10.3390/separations11070204. DOI: https://doi.org/10.3390/separations11070204

[17] P. Chen, F. Zou, and W. Liu, Recent advancement in prevention against hepatotoxicity, molecular mechanisms, and bioavailability of gallic acid, a natural phenolic compound: challenges and perspectives, Front. Pharmacol., vol. 16, no. March, pp. 116, 2025, doi: 10.3389/fphar.2025.1549526. DOI: https://doi.org/10.3389/fphar.2025.1549526

[18] M. Hadidi, R. Lin-Atero, M. Tarahi, M. C. Christodoulou, and F. Aghababaei, The Potential Health Benefits of Gallic Acid: Therapeutic and Food Applications, vol. 13, no. 8. 2024. doi: 10.3390/antiox13081001. DOI: https://doi.org/10.3390/antiox13081001

[19] A. J. Dyba, E. Wicek, M. Nowak, J. Janczak, K. P. Nartowski, and D. E. Braun, Metronidazole Cocrystal Polymorphs with Gallic and Gentisic Acid Accessed through Slurry, Atomization Techniques, and Thermal Methods, Cryst. Growth Des., vol. 23, no. 11, pp. 82418260, 2023, doi: 10.1021/acs.cgd.3c00951. DOI: https://doi.org/10.1021/acs.cgd.3c00951

[20] A Comprehensive Study on Image Preprocessing Techniques for Enhanced Image Analysis Noise Reduction.

[21] Y. Chen, P. Ge, G. Wang, G. Weng, and H. Chen, An overview of intelligent image segmentation using active contour models, Intell. Robot., vol. 3, no. 1, pp. 2355, 2023, doi: 10.20517/ir.2023.02. DOI: https://doi.org/10.20517/ir.2023.02

[22] M. I. Alhafiz, W. Wirasno, and A. Solichin, Segmentasi Dengan Metode Active Contour Untuk Peningkatan Akurasi Klasifikasi Citra Usg Kanker Payudara Menggunakan K-Nearest Neighbor (Knn), JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 10, no. 1, pp. 3448, 2025, doi: 10.29100/jipi.v10i1.5681. DOI: https://doi.org/10.29100/jipi.v10i1.5681

[23] N. M. Sani, A. Setyawan, and R. Gernowo, Journal of Physics and Its Applications, J. Phys. Its Appl., vol. 3, no. 2, pp. 142147, 2021. DOI: https://doi.org/10.14710/jpa.v3i2.10674

[24] S. Hallur and A. Gavade, Image feature extraction techniques: A comprehensive review, Franklin Open, vol. 12, no. September, p. 100366, 2025, doi: 10.1016/j.fraope.2025.100366. DOI: https://doi.org/10.1016/j.fraope.2025.100366

[25] W. Tang, Review of Image Classification Algorithms Based on Graph Convolutional Networks, EAI Endorsed Trans. AI Robot., vol. 2, pp. 151, 2023, doi: 10.4108/airo.3462. DOI: https://doi.org/10.4108/airo.3462

[26] S. A. R. Srg, Irhamna, M. F. Aldi, M. Ramadhan, and N. L. Siregar, Ekstraksi Fitur Citra Berdasarkan Tekstur Dengan Glcm (Gray Level Co-Occurrence), JUTISAL (Jurnal Tek. Inform. Komput. Universal), vol. 3, no. 1, pp. 4451, 2023.

[27] J. Jumadi and D. Sartika, Pengolahan Citra Digital Untuk Identifikasi Objek Menggunakan Metode Hierarchical Agglomerative Clustering, Jurnal Sains dan Teknologi, Vol.10, No 2, Tahun 2021, vol. 10, no. 2, pp. 148156, 2021. DOI: https://doi.org/10.23887/jst-undiksha.v10i2.33636

[28] T. Nadu et al., Support vector machine for image classification, vol. 97, no. 4, pp. 111.

[29] P. A. Azli, M. Minarni, A. Syahrani, G. Y. Swara, and A. Anisya, Segmentasi Citra Daun Tomat untuk Klasifikasi Penyakit Tanaman Menggunakan Support Vector Machine (SVM), J. Inform. J. Pengemb. IT, vol. 10, no. 4, pp. 9971008, 2025, doi: 10.30591/jpit.v10i4.9404. DOI: https://doi.org/10.30591/jpit.v10i4.9404

[30] E. Winarno, W. Hadikurniawati, A. Septiarini, and H. Hamdani, Analysis of color features performance using support vector machine with multi-kernel for batik classification, Int. J. Adv. Intell. Informatics, vol. 8, no. 2, pp. 151164, 2022, doi: 10.26555/ijain.v8i2.821. DOI: https://doi.org/10.26555/ijain.v8i2.821

[31] S. W. Iriananda, R. W. Budiawan, A. Y. Rahman, and I. Istiadi, Optimasi Klasifikasi Sentimen Komentar Pengguna Game Bergerak Menggunakan Svm, Grid Search Dan Kombinasi N-Gram, J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 4, pp. 743752, 2024, doi: 10.25126/jtiik.1148244. DOI: https://doi.org/10.25126/jtiik.1148244

[32] M. Fajri and A. Primajaya, Komparasi Teknik Hyperparameter Optimization pada SVM untuk Permasalahan Klasifikasi dengan Menggunakan Grid Search dan Random Search, J. Appl. Informatics Comput., vol. 7, no. 1, pp. 1419, 2023, doi: 10.30871/jaic.v7i1.5004. DOI: https://doi.org/10.30871/jaic.v7i1.5004

[33] S. Ernawati and R. Wati, Evaluasi Performa Kernel SVM dalam Analisis Sentimen Review Aplikasi ChatGPT Menggunakan Hyperparameter dan VADER Lexicon, J. Buana Inform., vol. 15, no. 01, pp. 4049, 2024, doi: 10.24002/jbi.v15i1.7925. DOI: https://doi.org/10.24002/jbi.v15i1.7925

[34] F. Dewi, N. Cahyo, H. Wibowo, M. R. Handayani, and K. Umam, Hyperparamter tuning, vol. 10, no. 3, pp. 25842593, 2025. DOI: https://doi.org/10.29100/jipi.v10i3.7774