KLASIFIKASI SAMPAH DAUR ULANG MENGGUNAKAN CONVOLUTIONAL NEURAL NETWORK DAN GRAY LEVEL CO-OCCURRENCE MATRIX

Moh Rifqi Abdan; Mutaqin Akbar

doi:10.51401/jinteks.v7i3.5903

Authors

Moh Rifqi Abdan Universitas Mercu Buana Yogyakarta
Mutaqin Akbar Universitas Mercu Buana Yogyakarta

DOI:

https://doi.org/10.51401/jinteks.v7i3.5903

Keywords:

convolutional neural network, glcm, multi-input, tekstur, klasifikasi sampah

Abstract

Pengelolaan sampah di Indonesia menghadapi tantangan serius dengan produksi mencapai 34 juta ton per tahun dan 40% tidak terkelola dengan baik. Pemilahan sampah yang akurat menjadi kunci keberhasilan proses daur ulang, namun metode manual masih tidak efisien dan inkonsisten. Penelitian ini bertujuan mengembangkan model multi-input yang menggabungkan Convolutional Neural Network (CNN) dengan fitur tekstur Gray Level Co-occurrence Matrix (GLCM) untuk klasifikasi sampah daur ulang kategori kardus, kaca, logam, kertas, plastik, dan sampah umum. Dataset terdiri dari 2527 citra yang dibagi dengan rasio 80:20 untuk pelatihan dan pengujian. Fitur GLCM diekstraksi menggunakan 24 parameter tekstur dari empat arah sudut berbeda, kemudian digabungkan dengan representasi visual CNN melalui arsitektur multi-input. Model dilatih menggunakan optimizer Adam dengan Focal Loss untuk mengatasi ketidakseimbangan kelas. Hasil evaluasi menunjukkan akurasi testing sebesar 75,35% dengan macro F1-score 0,7394 dan weighted F1-score 0,7496. Performa terbaik dicapai pada kategori kardus (91,2% recall) dan kertas (87,3% recall). Penggabungan CNN-GLCM terbukti efektif dalam membedakan material dengan karakteristik visual serupa namun tekstur berbeda, memberikan solusi potensial untuk sistem pemilahan sampah otomatis yang lebih akurat dan efisien.

References

Kementerian Lingkungan Hidup dan Kehutanan, “Capaian Kinerja Pengelolaan Sampah,” istem Informasi Pengelolaan Sampah Nasional. [Online]. Available: https://sipsn.menlhk.go.id/sipsn/

N. Ferronato and V. Torretta, “Waste mismanagement in developing countries: A review of global issues,” Int. J. Environ. Res. Public Health, vol. 16, no. 6, 2019, doi: 10.3390/ijerph16061060.

M. I. B. Ahmed et al., “Deep Learning Approach to Recyclable Products Classification: Towards Sustainable Waste Management,” Sustain., vol. 15, no. 14, pp. 1–16, 2023, doi: 10.3390/su151411138.

A. Fadlil, R. Umar, Sunardi, and A. S. Nugroho, “Comparison of Machine Learning Approach for Waste Bottle Classification,” Emerg. Sci. J., vol. 6, no. 5, pp. 1075–1085, 2022, doi: 10.28991/ESJ-2022-06-05-011.

M. Kowsher et al., “LSTM-ANN & BiLSTM-ANN: Hybrid deep learning models for enhanced classification accuracy,” Procedia Comput. Sci., vol. 193, pp. 131–140, 2021, doi: 10.1016/j.procs.2021.10.013.

R. G. Hefron, B. J. Borghetti, J. C. Christensen, and C. M. S. Kabban, “Deep long short-term memory structures model temporal dependencies improving cognitive workload estimation,” Pattern Recognit. Lett., vol. 94, pp. 96–104, 2017, doi: 10.1016/j.patrec.2017.05.020.

Y. M. Leiyu Chen, Shaobo Li, Q. Bai, Jing Yang, Sanlong Jiang, “Review of Image Classification Algorithms Based on Convolutional Neural Networks,” 2021.

F. Liu, H. Xu, M. Qi, D. Liu, J. Wang, and J. Kong, “Depth-Wise Separable Convolution Attention Module for Garbage Image Classification,” Sustain., vol. 14, no. 5, 2022, doi: 10.3390/su14053099.

X. Zhang, J. Cui, W. Wang, and C. Lin, “A study for texture feature extraction of high-resolution satellite images based on a direction measure and gray level co-occurrence matrix fusion algorithm,” Sensors (Switzerland), vol. 17, no. 7, 2017, doi: 10.3390/s17071474.

L. Meilong, Chen and Xiehua, Yu and Shaojun, Su and Daqing, “Image Texture Analysis Based on Gray Level Co-Occurrence Matrix,” Int. Conf. Inf. Technol. Med. Educ., pp. 451–455, 2023, doi: doi: 10.1109/ITME60234.2023.00096.

M. and A. Y. Z. H. N. Carlo, K. Andreas, “Comparative Analysis of Fungal Infections Classification in Apple Leaves Using CNN and CNN with GLCM Features,” Int. Conf. Cybern. Intell. Syst., pp. 1–5, 2024, doi: 10.1109/ICORIS63540.2024.10903820.

D. L. Maíla Claro, Rodrigo Veras, André Santana, Flávio Araújo, Romuere Silva, João Almeida, “An hybrid feature space from texture information and transfer learning for glaucoma classification,” An hybrid Featur. Sp. from texture Inf. Transf. Learn. glaucoma Classif., vol. 64, no. 102597, pp. 1047–3203, 2019, doi: https://doi.org/10.1016/j.jvcir.2019.102597.

S. Poudel and P. Poudyal, “Classification of Waste Materials using CNN Based on Transfer Learning,” ACM Int. Conf. Proceeding Ser., pp. 29–33, 2022, doi: 10.1145/3574318.3574345.

M. W. Rahman, R. Islam, A. Hasan, N. I. Bithi, M. M. Hasan, and M. M. Rahman, “Intelligent waste management system using deep learning with IoT,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 5, pp. 2072–2087, 2022, doi: 10.1016/j.jksuci.2020.08.016.

Y. Ding, C. Liu, H. Zhu, and Q. Chen, “A supervised data augmentation strategy based on random combinations of key features,” Inf. Sci. (Ny)., vol. 632, no. January, pp. 678–697, 2023, doi: 10.1016/j.ins.2023.03.038.

A. R. A. Jyoti Pandey, “Implementasi arsitektur jaringan saraf konvolusional ringan menggunakan TensorFlow lite,” J. Int. Teknol. Inf., vol. 15, pp. 2489–2498, 2023, doi: 10.1007/s41870-023-01320-9.

Kementerian Lingkungan Hidup., Undang-Undang No. 18 Tahun 2008 tentang Pengelolaan Sampah. 2008.

Cvmwa, “Recycling and Energy.” [Online]. Available: https://cvwma.com/cvwma-education/recycling-and-energy/

Rippleglass, “How Does Glass Recycling Work?” [Online]. Available: https://www.rippleglass.com/how-does-glass-recycling-work/

K. M. Bataineh, “Advances in Civil Engineering - 2020 - Bataineh - Life?Cycle Assessment of Recycling Postconsumer High?Density Polyethylene.pdf.”

P. Lecun, Y. and Bottou, L. and Bengio, Y. and Haffner, “Gradient-based learning applied to document recognition,” Proc. IEEE, vol. 86, no. 11, pp. 2278–2324, 1998, doi: 10.1109/5.726791.

G. E. Krizhevsky, A., Sutskever, I., & Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Adv. Neural Inf. Process. Syst., vol. 25, 2012.

M. Akbar, A. S. Purnomo, and S. Supatman, “Multi-Scale Convolutional Networks untuk Pengenalan Rambu Lalu Lintas di Indonesia,” J. Sisfokom (Sistem Inf. dan Komputer), vol. 11, no. 3, pp. 310–315, 2022, doi: 10.32736/sisfokom.v11i3.1452.

M. Akbar, “Pengenalan Rambu Lalu Lintas Menggunakan Convolutional Neural Networks,” J. Teknol. dan Sist. Komput., vol. 9, pp. 120--125, 2021, doi: 10.14710/jtsiskom.2021.13959.

I. Haralick, Robert M. and Shanmugam, K. and Dinstein, “Textural Features for Image Classification,” IEEE Trans. Syst. Man. Cybern., vol. SMC-3, no. 6, pp. 610–621, 1973, doi: 10.1109/TSMC.1973.4309314.

F. Nekouei, “Garbage Image Dataset,” Platform Kaggle. [Online]. Available: https://www.kaggle.com/datasets/farzadnekouei/trash-type-image-dataset/data

T. Y. Lin, P. Goyal, R. Girshick, K. He, and P. Dollar, “Focal Loss for Dense Object Detection,” IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 2, pp. 318–327, 2020, doi: 10.1109/TPAMI.2018.2858826.

S. Barburiceanu, R. Terebes, and S. Meza, “3D Texture Feature Extraction and Classification Using Glcm and Lbp-Based Descriptors,” Appl. Sci., vol. 11, no. 5, pp. 1–26, 2021, doi: 10.3390/app11052332.

M. Buda, A. Maki, and M. A. Mazurowski, “A systematic study of the class imbalance problem in convolutional neural networks,” Neural Networks, vol. 106, pp. 249–259, 2018, doi: 10.1016/j.neunet.2018.07.011.

S. Ioffe and C. Szegedy, “Batch normalization: Accelerating deep network training by reducing internal covariate shift,” 32nd Int. Conf. Mach. Learn. ICML 2015, vol. 1, pp. 448–456, 2015.

V7labs, “F1 Score in Machine Learning: Intro & Calculation.” [Online]. Available: https://www.v7labs.com/blog/f1-score-guide

F. Nekouei, “Imbalanced Garbage Classification | ResNet50,” Platform Kaggle. [Online]. Available: https://www.kaggle.com/code/farzadnekouei/imbalanced-garbage-classification-resnet50