MODEL Model Klasifikasi Dengan Metode Earth Mover's Distance (EMD) Pada Citra Dipstick Urinalisis

Khairul Hafidh; Helfi Nasution; Alfian Abdul Jalid; Fauzan Asrin; Eka Ardiani Putri

doi:10.59061/jentik.v4i3.1566

Authors

Khairul Hafidh Universitas Tanjungpura
Helfi Nasution Informatika, Universitas Tanjungpura
Alfian Abdul Jalid Informatika, Universitas Tanjungpura
Fauzan Asrin Informatika, Universitas Tanjungpura
Eka Ardiani Putri Pendidikan Dokter, Universitas Tanjungpura

DOI:

https://doi.org/10.59061/jentik.v4i3.1566

Abstract

Pembacaan dipstick urinalisis secara visual rentan terhadap subjektivitas operator dan variasi pencahayaan lingkungan. Penelitian terdahulu yang memanfaatkan pengolahan citra digital umumnya membandingkan nilai RGB piksel lokal secara langsung, sehingga rentan terhadap gangguan intensitas cahaya dan ketidakrataan warna pada area reagen. Penelitian ini bertujuan mengimplementasikan metode Earth Mover's Distance (EMD) sebagai metrik kemiripan distribusi warna holistik pada embedded system berbasis Raspberry Pi dan Pi Cam. Sistem dilengkapi dengan kotak akuisisi pencahayaan terkontrol guna menjamin konsistensi citra. Sebanyak 79 sampel citra urine valid dipraproses melalui pemotongan Region of Interest (ROI) berukuran piksel serta ekstraksi nilai rata-rata komponen RGB untuk membangun basis pengetahuan tiap kelas parameter. Proses klasifikasi EMD mengevaluasi biaya transportasi minimum dalam mentransformasikan distribusi warna data uji terhadap basis pengetahuan tanpa memerlukan pelatihan deep learning yang rumit. Hasil evaluasi menunjukkan bahwa EMD memberikan performa optimal yang dipengaruhi oleh tingkat pemisahan (separability) warna antar-kategori. Parameter Protein mencapai kinerja tertinggi dengan akurasi 98,73% dan Macro F1-Score 99,12%, diikuti parameter pH dengan akurasi 91,14% dan Macro F1-Score 86,91%. Parameter Glukosa memperoleh akurasi 84,81% dan Macro F1-Score 83,38% akibat adanya tumpang tindih (overlapping) karakteristik warna pada kelas positif. Penelitian ini berhasil menjawab research gap penerapan EMD pada citra dipstick urinalisis dan membuktikan bahwa pendekatan berbasis distribusi warna jauh lebih robust terhadap noise pencahayaan. Kombinasi metode EMD dan embedded system menawarkan efisiensi komputasi yang tinggi, menjadikannya sangat potensial untuk diimplementasikan sebagai perangkat point-of-care testing (POCT) urinalisis yang mandiri, objektif, dan berbiaya rendah.

References

Balbach, S., Jiang, N., Moreddu, R., Dong, X., Kurz, W., Wang, C., … Yetisen, A. K. (2021). Smartphone-based colorimetric detection system for portable health tracking. Analytical Methods, 13(38), 4361–4369. https://doi.org/10.1039/d1ay01209f

Chambliss, A. B., & Van, T. T. (2022). Revisiting approaches to and considerations for urinalysis and urine culture reflexive testing. Critical Reviews in Clinical Laboratory Sciences, 59(2), 112–124. https://doi.org/10.1080/10408363.2021.1988048

Fazry, T. R., Furqan, M., & Rifki, M. I. (n.d.). Jurnal Manajemen Teknologi Informatika Implementasi Sistem Pakar Dengan Naive Bayes Dan Certainty Factor Untuk Diagnosis Stroke. Jl. Veteran No.26B, 25115.

Hafidh, K., & Asrin, F. (2023). Pemodelan Sistem Untuk Identifikasi Stadium Plasmodium Falciparum Pada Citra Mikroskopis Malaria Dengan Teknik Object Counting. Jaringan Sistem Informasi Robotik-JSR, 7(2), 153–157.

Hitzeman, N., Greer, D., & Carpio, E. (2022). Office-based urinalysis: A comprehensive review. American Family Physician, 1(106), 27-35B.

Hossain, M. S., Shahriar, G. M., Syeed, M. M. M., Uddin, M. F., Hasan, M., Shivam, S., & Advani, S. (2023). Region of interest (ROI) selection using vision transformer for automatic analysis using whole slide images. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-38109-6

Jang, E. C., Park, Y. M., Han, H. W., Lee, C. S., Kang, E. S., Lee, Y. H., & Nam, S. M. (2023). Machine-learning enhancement of urine dipstick tests for chronic kidney disease detection. Journal of the American Medical Informatics Association, 30(6), 1114–1124. https://doi.org/10.1093/jamia/ocad051

Jin, Z., Tang, Z., & Yan, J. (2022). An Modified Earth Mover’s Distance for Few-Shot Image Classification. https://doi.org/10.1109/PHM2022-London52454.2022.00077

Khamis, A., Tsuchida, R., Tarek, M., Rolland, V., & Petersson, L. (2024). Scalable Optimal Transport Methods in Machine Learning: A Contemporary Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1–20. https://doi.org/10.1109/TPAMI.2024.3379571

Kibria, I. E., Ali, H., & Khan, S. A. (2022). Smartphone-Based Point-of-Care Urinalysis Assessment. 2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC), 3374–3377. https://doi.org/10.1109/EMBC48229.2022.9870917

Kim, S. C., & Cho, Y. S. (2022). Predictive System Implementation to Improve the Accuracy of Urine Self-Diagnosis with Smartphones: Application of a Confusion Matrix-Based Learning Model through RGB Semiquantitative Analysis. Sensors, 22(14). https://doi.org/10.3390/s22145445

Lavi, E., Bourvine, A., Lin, Y.-W. E., & Talmon, R. (2025). Hyperbolic Distance Based on EMD and Diffusion for Hyperspectral Imaging. ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 1–5. https://doi.org/10.1109/ICASSP49660.2025.10889106

Meng, G., Zhou, R., Liu, L., Liang, P., Liu, F., Chen, D., … Hu, X. S. (2025). Efficient approximation of Earth Mover’s Distance Based on Nearest Neighbor Search. Retrieved from http://arxiv.org/abs/2401.07378

Montesuma, E. F., Mboula, F. N., & Souloumiac, A. (2025). Recent Advances in Optimal Transport for Machine Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 47(2), 1161–1180. https://doi.org/10.1109/TPAMI.2024.3489030

Pereira, L. M., & Hadi Amini, M. (2025). A Survey on Optimal Transport for Machine Learning: Theory and Applications. IEEE Access, 13, 26506–26526. https://doi.org/10.1109/ACCESS.2025.3539926

Pohanka, M., & Zakova, J. (2024). Urine Test Strip Quantitative Assay with a Smartphone Camera. International Journal of Analytical Chemistry, 2024. https://doi.org/10.1155/2024/6004970

Rosmawarni, N., Nurrahmi, H., Ladjamuddin, S. M., Fauziah, F., Putri, R. A., Nawangsih, I., … Rahmawati, W. M. (2025). Pemrosesan Citra (Image Processing). PT Penamuda Media.

Rubner, Y., Tomasi, C., & Guibas, L. J. (2000). The Earth Mover’s Distance as a Metric for Image Retrieval. International Journal of Computer Vision, 40(2), 99–121. https://doi.org/10.1023/A:1026543900054

Shi, L., Shen, Z., & Yan, J. (2024). Double-Bounded Optimal Transport for Advanced Clustering and Classification. Retrieved from www.aaai.org

Sun, M., Ma, W., & Liu, Y. (2022). Global and Local Feature Interaction with Vision Transformer for Few-shot Image Classification. International Conference on Information and Knowledge Management, Proceedings, 4530–4534. Association for Computing Machinery. https://doi.org/10.1145/3511808.3557604

Tan, Z., Zheng, K., & Huang, W. (2024). OTMatch: Improving Semi-Supervised Learning with Optimal Transport.

Utami, P. N., Arinal, V., & Mulyana, D. I. (2022). Klasifikasi dehidrasi tubuh manusia berdasarkan citra RGB pada warna urine menggunakan metode K-Nearest Neighbor. Jurnal Media Informatika Budidarma, 6(1), 18–26. https://doi.org/10.30865/mib.v6i1.3290

Wang, R., Zheng, H., Duan, X., Liu, J., Lu, Y., Wang, T., … Zhang, B. (2023). Few-Shot Learning with Visual Distribution Calibration and Cross-Modal Distribution Alignment. Retrieved from https://gitee.com/mindspore/models/tree/master/research/cv

Wardenaar, F., Armistead, S., Boeckman, K., Butterick, B., Youssefi, D., Thompsett, D., & Vento, K. (2022). Validity of Urine Color Scoring Using Different Light Conditions and Scoring Techniques to Assess Urine Concentration. Journal of Athletic Training, 57(2), 191–198. https://doi.org/10.4085/1062-6050-0389.21

Xu, Q., Yan, R., Gui, X., Song, R., & Wang, X. (2024). Machine learning-assisted image label-free smartphone platform for rapid segmentation and robust multi-urinalysis. Analytical and Bioanalytical Chemistry, 416(6), 1443–1455. https://doi.org/10.1007/s00216-024-05147-6

Zhang, C, Cai, Y., Lin, G., & Shen, C. (2023). DeepEMD: Differentiable Earth Mover’s Distance for Few-Shot Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5), 5632–5648. https://doi.org/10.1109/TPAMI.2022.3217373

Zhang, Chi, Cai, Y., Lin, G., & Shen, C. (2023). DeepEMD: Differentiable Earth Mover’s Distance for Few-Shot Learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5), 5632–5648. https://doi.org/10.1109/TPAMI.2022.3217373

Zhang, Z., Zhang, Y., Zhao, X., & Gao, Y. (2018). EMD Metric Learning. Retrieved from www.aaai.org

Zhou, Q., Wang, R., Zeng, G., Fan, H., & Zheng, G. (2022). Towards bridging the distribution gap: Instance to Prototype Earth Mover’s Distance for distribution alignment. Medical Image Analysis, 82. https://doi.org/10.1016/j.media.2022.102607