OPTIMALISASI AKURASI MODEL DEEP LEARNING PADA KLASIFIKASI SAMPAH PLASTIK MENGGUNAKAN STRATEGI FINE-TUNING MOBILENETV2

Difilal Syaban Rizkiyan; Dian Ade Kurnia; Yudhistira Arie Wijaya; Nining Rahaningsih; Willy Prihartono

Authors

Difilal Syaban Rizkiyan STMIK IKMI Cirebon, Indonesia
Dian Ade Kurnia STMIK IKMI Cirebon, Indonesia
Yudhistira Arie Wijaya STMIK IKMI Cirebon, Indonesia
Nining Rahaningsih STMIK IKMI Cirebon, Indonesia
Willy Prihartono STMIK IKMI Cirebon, Indonesia

Keywords:

sampah plastik, MobileNetV2, fine-tuning, klasifikasi citra, deep learning.

Abstract

Pengelolaan sampah plastik yang efektif memerlukan sistem pemilahan otomatis yang andal, terutama pada skenario multi-kelas dengan kemiripan visual tinggi antar jenis plastik. Penelitian ini bertujuan menganalisis pengaruh strategi fine-tuning parsial MobileNetV2 terhadap kinerja klasifikasi tujuh kelas sampah plastik, dengan membandingkannya terhadap model baseline yang hanya melatih classification head pada fitur pra-latih ImageNet. Dataset yang digunakan terdiri atas 3.500 citra sampah plastik yang terbagi seimbang ke dalam tujuh kelas dan dipisahkan menjadi data latih, validasi, dan uji dengan proporsi 70% : 15% : 15%. Seluruh citra di-resize menjadi 256×256 piksel dan diproses melalui augmentasi standar. Model baseline menggunakan MobileNetV2 pra-latih (base dibekukan), global average pooling, dropout, dan lapisan dense 7 kelas, dilatih dengan optimizer Adam (learning rate 1e-3) dan loss sparse categorical cross-entropy. Pada skenario fine-tuning, sekitar 40 lapisan terakhir MobileNetV2 di-unfreeze dan dilatih ulang dengan Adam (learning rate 1e-4) menggunakan konfigurasi data yang sama. Hasil pengujian menunjukkan bahwa model baseline mencapai akurasi 91,62% dan macro F1-score 0,9164, sedangkan model fine-tuning meningkat menjadi akurasi 93,71% dan macro F1-score 0,9370. Temuan ini menunjukkan bahwa fine-tuning parsial MobileNetV2 memberikan peningkatan kinerja yang konsisten tanpa menambah kompleksitas arsitektur inferensi, sehingga relevan untuk diterapkan pada sistem pemilahan sampah plastik otomatis berbasis visi komputer.

References

Abbasian Ardakani, G., & al., et. (2024). Interpretation of Artificial Intelligence Models in Healthcare: Evaluation metrics, pitfalls and recommendations. Journal of Ultrasound in Medicine. https://doi.org/10.1002/jum.16524

Alfano, P. D., Pastore, V. P., Rosasco, L., & Odone, F. (2024). Top-tuning: A study on transfer learning for an efficient alternative to fine tuning for image classification with fast kernel methods. Image and Vision Computing, 142. https://doi.org/10.1016/j.imavis.2023.104894

Alzubaidi, L., Bai, J., Al-Sabaawi, A., Santamaría, J., Albahri, A. S., Al-dabbagh, B. S. N., Fadhel, M. A., Manoufali, M., Zhang, J., Al-Timemy, A. H., Duan, Y., Abdullah, A., Farhan, L., Lu, Y., Gupta, A., Albu, F., Abbosh, A., & Gu, Y. (2023). A survey on deep learning tools dealing with data scarcity: definitions, challenges, solutions, tips, and applications. Journal of Big Data, 10(1). https://doi.org/10.1186/s40537-023-00727-2

Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021). Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8(1). https://doi.org/10.1186/s40537-021-00444-8

Bobulski, J., & Kubanek, M. (2021). Deep Learning for Plastic Waste Classification System. Applied Computational Intelligence and Soft Computing, 2021. https://doi.org/10.1155/2021/6626948

Davila, A., Colan, J., & Hasegawa, Y. (2024). Comparison of fine-tuning strategies for transfer learning in medical image classification. Image and Vision Computing, 146, 105012. https://doi.org/10.1016/j.imavis.2024.105012

Fan, Z., Yan, Z., & Wen, S. (2023). Deep Learning and Artificial Intelligence in Sustainability: A Review of SDGs, Renewable Energy, and Environmental Health. Sustainability (Switzerland), 15(18). https://doi.org/10.3390/su151813493

Hosna, A., Merry, E., Gyalmo, J., Alom, Z., Aung, Z., & Azim, M. A. (2022). Transfer learning: a friendly introduction. Journal of Big Data, 9(1). https://doi.org/10.1186/s40537-022-00652-w

Kim, H. E., Cosa-Linan, A., Santhanam, N., Jannesari, M., Maros, M. E., & Ganslandt, T. (2022). Transfer learning for medical image classification: a literature review. In BMC Medical Imaging (Vol. 22, Issue 1). BioMed Central Ltd. https://doi.org/10.1186/s12880-022-00793-7

Liang, H., & Seo, S. (2022). Lightweight Deep Learning for Road Environment Recognition. Applied Sciences (Switzerland), 12(6). https://doi.org/10.3390/app12063168

Lu, W., & Chen, J. (2022). Computer vision for solid waste sorting: A critical review of academic research. Waste Management, 142, 29–43. https://doi.org/10.1016/j.wasman.2022.02.009

Maeda-Gutiérrez, V., Galván-Tejada, C. E., Zanella-Calzada, L. A., Celaya-Padilla, J. M., Galván-Tejada, J. I., Gamboa-Rosales, H., Luna-García, H., Magallanes-Quintanar, R., Guerrero Méndez, C. A., & Olvera-Olvera, C. A. (2020). Comparison of convolutional neural network architectures for classification of tomato plant diseases. Applied Sciences (Switzerland), 10(4). https://doi.org/10.3390/app10041245

Malik, M., Sharma, S., Uddin, M., Chen, C. L., Wu, C. M., Soni, P., & Chaudhary, S. (2022). Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models. Sustainability (Switzerland), 14(12). https://doi.org/10.3390/su14127222

Mohammad, A. S., Jarullah, T. G., Al-Kaltakchi, M. T. S., Alshehabi Al-Ani, J., & Dey, S. (2024). IoT-MFaceNet: Internet-of-Things-Based Face Recognition Using MobileNetV2 and FaceNet Deep-Learning Implementations on a Raspberry Pi-400. Journal of Low Power Electronics and Applications, 14(3). https://doi.org/10.3390/jlpea14030046

Nayanathara Thathsarani Pilapitiya, P. G. C., & Ratnayake, A. S. (2024). The world of plastic waste: A review. In Cleaner Materials (Vol. 11). Elsevier Ltd. https://doi.org/10.1016/j.clema.2024.100220

Pučnik, R., Dokl, M., Fan, Y. Van, Vujanović, A., Novak Pintarič, Z., Aviso, K. B., Tan, R. R., Pahor, B., Kravanja, Z., & Čuček, L. (2024). A waste separation system based on sensor technology and deep learning: A simple approach applied to a case study of plastic packaging waste. Journal of Cleaner Production, 450. https://doi.org/10.1016/j.jclepro.2024.141762

Rahman, M. W., Islam, R., Hasan, A., Bithi, N. I., Hasan, M. M., & Rahman, M. M. (2022). Intelligent waste management system using deep learning with IoT. Journal of King Saud University - Computer and Information Sciences, 34(5), 2072–2087. https://doi.org/10.1016/j.jksuci.2020.08.016

Rayhan, Y., & Rifai, A. P. (2024). Multi-class Waste Classification Using Convolutional Neural Network. Applied Environmental Research, 46(2). https://doi.org/10.35762/AER.2024021

Sarker, I. H. (2021). Deep learning: A comprehensive overview on techniques, taxonomy, applications and research directions. SN Computer Science, 2, 420. https://doi.org/10.1007/s42979-021-00815-1

Single, S., Iranmanesh, S., & Raad, R. (2023). RealWaste: A Novel Real-Life Data Set for Landfill Waste Classification Using Deep Learning. Information (Switzerland), 14(12). https://doi.org/10.3390/info14120633

Yang, Z., Xia, Z., Yang, G., & Lv, Y. (2022). A Garbage Classification Method Based on a Small Convolution Neural Network. Sustainability (Switzerland), 14(22). https://doi.org/10.3390/su142214735

Yong, L., Ma, L., Sun, D., & Du, L. (2023). Application of MobileNetV2 to waste classification. PLoS ONE, 18(3 March). https://doi.org/10.1371/journal.pone.0282336