Type Deep Learning Model for Multi-Label Waste Classification in Canal Environments: A Comparative Study with CNN Architectures

Najirah Umar, Billy Eden William Asrul, Yuyun Yuyun
Pages 261-276
Abstract Views 881
PDF Downloads 2213
Crossref Citations -
DOI https://doi.org/10.47738/jads.v7i1.1066

Abstract


The escalating environmental degradation caused by waste underscores the necessity of developing intelligent and sustainable management systems. This study introduces a deep learning–based framework with proposed a modified ConvNeXt architecture enhanced by a two-layer non-linear MLP classification, specifically designed for multi-object waste classification in canal environments. Specifically, ConvNeXt-CNN is introduced as the primary backbone for extracting visual features from waste images. Then, a modified Multi-Layer Perceptron (MLP) is employed to transform these features into multi-label predictions. To optimize the model’s generalization capability in recognizing the complexity of waste images, a hybrid data augmentation technique combining SMOTE and MixUp was applied during training. The proposed approach was then compared with ten fine-tuned Convolutional Neural Network (CNN) architectures, ResNet18, ResNet50, VGG16, VGG19, DenseNet121, MobileNet_v2, and EfficientNet (B0, B1, B2, and B3), and evaluated using accuracy, precision, recall, and F1-score metrics. The experimental dataset comprises 855 waste images containing a total of 2,662 annotated objects across 18 categories, including Bamboo, Beverage Carton, Cardboard, Fabric, Glass Bottle, Inorganic Waste, Kite, Leaf, Metal, Organic Waste, Paper, Plastic, Plastic Bottle, Plastic Cup, Residual Waste, Rubber, Small E-waste, Styrofoam, and Wood. The results show that the fine-tuned ConvNeXt achieved the best performance with an F1-score of 0.99, surpassing DenseNet121 (0.95), ResNet18 (0.91), and VGG16 (0.94). The ConvNeXt model demonstrated its robust capability by achieving consistently high identification scores across majority 18 waste categories. When it came to training efficiency, the fine-tuned MobileNetV2 model proved to be the top performer, outclassing ten other pretrained models, with a training time of 13.35s per epoch.  Results exhibit that finetuned ConvNext outperforms in terms of accuracy, recall, precision, and F1-score. In conclusion, Integrating ConvNeXt and MLP for multi-object waste classification effectively supports intelligent waste management, enabling practical real-world deployment in smart bins, Material Recovery Facilities, and IoT-integrated urban waste systems.

Keywords


CNN; ConvNeXt-Tiny; Deep Learning; Multi-label; Waste Classification

Full Text:

PDF

References


G. Salvia et al., “The wicked problem of waste management: An attention-based analysis of stakeholder behaviours,” J. Clean. Prod., vol. 326, no. December 2020, p. 129200, 2021, doi: 10.1016/j.jclepro.2021.129200.

E. A. M. A. J. Löhr;, “WIREs Water - 2023 - MacAfee - Multi‐scalar interactions between mismanaged plastic waste and urban flooding in an era of.pdf,” 2023, Wiley Periodicals LLC.

V. Owatsakul, P. Panput, P. Jaisuda, and D. Rinchumphu, “Impacts of Wastewater Management and Enhancing the Landscape of the Mae Kha Canal: A Quasi-Experimental Study,” Water (Switzerland), vol. 17, no. 7, 2025, doi: 10.3390/w17071105.

L. J. J. Meijer, T. van Emmerik, R. van der Ent, C. Schmidt, and L. Lebreton, “More than 1000 rivers account for 80% of global riverine plastic emissions into the ocean,” Sci. Adv., vol. 7, no. 18, pp. 1–13, 2021, doi: 10.1126/sciadv.aaz5803.

D. Honingh, T. van Emmerik, W. Uijttewaal, H. Kardhana, O. Hoes, and N. van de Giesen, “Urban River Water Level Increase Through Plastic Waste Accumulation at a Rack Structure,” Front. Earth Sci., vol. 8, no. February, pp. 1–8, 2020, doi: 10.3389/feart.2020.00028.

D. A. Abo-Sreeaa, N. M. AboulAtta, and D. A. El-Molla, “The impact of blockage on the performance of canal coverage structures,” J. Eng. Appl. Sci., vol. 70, no. 1, pp. 1–21, 2023, doi: 10.1186/s44147-023-00246-0.

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.

T. H. Yan, S. N. M. Azam, Z. M. Sani, and A. Azizan, “Accuracy study of image classification for reverse vending machine waste segregation using convolutional neural network,” Int. J. Electr. Comput. Eng., vol. 14, no. 1, pp. 366–374, 2024, doi: 10.11591/ijece.v14i1.pp366-374.

H. Zheng and Y. Gu, “Encnn-upmws: Waste classification by a CNN ensemble using the UPM weighting strategy,” Electron., vol. 10, no. 4, pp. 1–21, 2021, doi: 10.3390/electronics10040427.

D. Hogan Itam, E. Chimeme Martin, and I. Taiwo Horsfall, “Enhanced convolutional neural network methodology for solid waste classification utilizing data augmentation techniques,” Waste Manag. Bull., vol. 2, no. 4, pp. 184–193, 2024, doi: 10.1016/j.wmb.2024.11.002.

M. Nahiduzzaman et al., “An automated waste classification system using deep learning techniques: Toward efficient waste recycling and environmental sustainability,” Knowledge-Based Syst., vol. 310, no. January, p. 113028, 2025, doi: 10.1016/j.knosys.2025.113028.

R. Chauhan, S. Shighra, H. Madkhali, L. Nguyen, and M. Prasad, “Efficient Future Waste Management: A Learning-Based Approach with Deep Neural Networks for Smart System (LADS),” Appl. Sci., vol. 13, no. 7, 2023, doi: 10.3390/app13074140.

Z. Kang, J. Yang, G. Li, and Z. Zhang, “An Automatic Garbage Classification System Based on Deep Learning,” IEEE Access, vol. 8, pp. 140019–140029, 2020, doi: 10.1109/ACCESS.2020.3010496.

M. Kaya, S. Ulutürk, Y. Ç. Kaya, and O. Altıntaş, “Optimization of Several Deep CNN Models,” Sak. Univ. J. Comput. Inf. Sci., vol. 6, no. 2, pp. 91–104, 2023.

M. Chhabra, B. Sharan, M. Elbarachi, and M. Kumar, “Intelligent waste classification approach based on improved multi-layered convolutional neural network,” Multimed. Tools Appl., vol. 83, no. 36, pp. 84095–84120, 2024, doi: 10.1007/s11042-024-18939-w.

M. S. Bin Islam et al., “ECCDN-Net: A deep learning-based technique for efficient organic and recyclable waste classification,” Waste Manag., vol. 193, no. November 2024, pp. 363–375, 2025, doi: 10.1016/j.wasman.2024.12.023.

M. M. Abo-Zahhad and M. Abo-Zahhad, “Real time intelligent garbage monitoring and efficient collection using Yolov8 and Yolov5 deep learning models for environmental sustainability,” Sci. Rep., vol. 15, no. 1, pp. 1–26, 2025, doi: 10.1038/s41598-025-99885-x.

R. Wu et al., “An Efficient Multi-Label Classification-Based Municipal Waste Image Identification,” Processes, vol. 12, no. 6, pp. 1–14, 2024, doi: 10.3390/pr12061075.

Q. Zhang et al., “A multi-label waste detection model based on transfer learning,” Resour. Conserv. Recycl., vol. 181, no. December 2021, p. 106235, 2022, doi: 10.1016/j.resconrec.2022.106235.

G. Celik, “Multi-layer feature fusion for high-accuracy solid waste classification using a hybrid deep learning model,” Vis. Comput., 2025, doi: 10.1007/s00371-025-04031-3.

Z. Liu, H. Mao, C. Y. Wu, C. Feichtenhofer, T. Darrell, and S. Xie, “A ConvNet for the 2020s,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2022-June, pp. 11966–11976, 2022, doi: 10.1109/CVPR52688.2022.01167.

B. Madhavi et al., “SwinConvNeXt: a fused deep learning architecture for Real-time garbage image classification,” Sci. Rep., vol. 15, no. 1, pp. 1–16, 2025, doi: 10.1038/s41598-025-91302-7.

D. Ghosh and A. Goswami, “Enhanced deep learning framework for efficient garbage classification in smart waste management systems,” Inf. Sci. (Ny)., vol. 719, no. April, p. 122462, 2025, doi: 10.1016/j.ins.2025.122462.

W. Qiu, C. Xie, and J. Huang, “An Improved EfficientNetV2 for Garbage Classification,” Lect. Notes Comput. Sci., vol. 15864 LNAI, pp. 79–90, 2025, doi: 10.1007/978-981-96-9901-8_7.

D. Hendrycks and K. Gimpel, “Gaussian Error Linear Units (GELUs),” pp. 1–10, 2023, [Online]. Available: http://arxiv.org/abs/1606.08415

T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, “A simple framework for contrastive learning of visual representations,” 37th Int. Conf. Mach. Learn. ICML 2020, vol. PartF16814, no. Figure 1, pp. 1575–1585, 2020.

J. B. Grill et al., “Bootstrap your own latent a new approach to self-supervised learning,” Adv. Neural Inf. Process. Syst., vol. 2020-Decem, 2020.

E. With, “S Patiotemporal R Epresentation L Earning,” vol. 3, no. 1, pp. 1–19, 2022.

Q. Guo, C. Wang, D. Xiao, and Q. Huang, “A novel multi-label pest image classifier using the modified Swin Transformer and soft binary cross entropy loss,” Eng. Appl. Artif. Intell., vol. 126, no. PC, p. 107060, 2023, doi: 10.1016/j.engappai.2023.107060.

G. Polat, Ü. M. Çağlar, and A. Temizel, “Class distance weighted cross entropy loss for classification of disease severity,” Expert Syst. Appl., vol. 269, no. December 2024, p. 126372, 2025, doi: 10.1016/j.eswa.2024.126372.

C. Qin, Y. Cao, and L. Meng, “L1-Smooth SVM with Distributed Adaptive Proximal Stochastic Gradient Descent with Momentum for Fast Brain Tumor Detection,” Comput. Mater. Contin., vol. 79, no. 2, pp. 1975–1994, 2024, doi: 10.32604/cmc.2024.049228.

J. Zhu et al., “Feature-targeted deep learning framework for pulmonary tumorous Cone-beam CT (CBCT) enhancement with multi-task customized perceptual loss and feature-guided CycleGAN,” Comput. Med. Imaging Graph., vol. 121, no. December 2024, p. 102487, 2025, doi: 10.1016/j.compmedimag.2024.102487.

R. Wang, L. Jiao, C. Xie, P. Chen, J. Du, and R. Li, “S-RPN: Sampling-balanced region proposal network for small crop pest detection,” Comput. Electron. Agric., vol. 187, no. June, p. 106290, 2021, doi: 10.1016/j.compag.2021.106290.

A. Bakhtiarnia, Q. Zhang, and A. Iosifidis, “Efficient High-Resolution Deep Learning: A Survey,” ACM Comput. Surv., vol. 56, no. 7, pp. 1–19, 2024, doi: 10.1145/3645107.

A. M. L. De Alwis, M. Bazli, and M. Arashpour, “Automated recognition of contaminated construction and demolition wood waste using deep learning,” Resour. Conserv. Recycl., vol. 219, no. December 2024, p. 108278, 2025, doi: 10.1016/j.resconrec.2025.108278.

C. Shorten and T. M. Khoshgoftaar, “A survey on Image Data Augmentation for Deep Learning,” J. Big Data, vol. 6, no. 1, 2019, doi: 10.1186/s40537-019-0197-0.

J. L. Leevy, T. M. Khoshgoftaar, R. A. Bauder, and N. Seliya, “A survey on addressing high-class imbalance in big data,” J. Big Data, vol. 5, no. 1, 2018, doi: 10.1186/s40537-018-0151-6.

M. Xu, S. Yoon, A. Fuentes, and D. S. Park, “A Comprehensive Survey of Image Augmentation Techniques for Deep Learning,” Pattern Recognit., vol. 137, p. 109347, 2023, doi: 10.1016/j.patcog.2023.109347.

Y. X. Zhao and Y. Lee, “Bird Species Classification Using Image Background Removal for Data Augmentation,” Comput. Mater. Contin., vol. 84, no. 1, pp. 791–810, 2025, doi: 10.32604/cmc.2025.065048.

K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” 3rd Int. Conf. Learn. Represent. ICLR 2015 - Conf. Track Proc., pp. 1–14, 2015.

K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., vol. 2016-Decem, pp. 770–778, 2016, doi: 10.1109/CVPR.2016.90.

G. Huang, Z. Liu, L. Van Der Maaten, and K. Q. Weinberger, “Densely connected convolutional networks,” Proc. - 30th IEEE Conf. Comput. Vis. Pattern Recognition, CVPR 2017, vol. 2017-Janua, pp. 2261–2269, 2017, doi: 10.1109/CVPR.2017.243.

M. Sandler, A. Howard, M. Zhu, A. Zhmoginov, and L. C. Chen, “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit., pp. 4510–4520, 2018, doi: 10.1109/CVPR.2018.00474.

M. Tan and Q. V. Le, “EfficientNet: Rethinking model scaling for convolutional neural networks,” 36th Int. Conf. Mach. Learn. ICML 2019, vol. 2019-June, pp. 10691–10700, 2019.




DOI: https://doi.org/10.47738/jads.v7i1.1066

Refbacks

  • There are currently no refbacks.


Barcode

Journal of Applied Data Sciences

ISSN:2723-6471 (Online)
Publisher:Bright Publisher
Website:http://bright-journal.org/JADS
Email:taqwa@amikompurwokerto.ac.id (principal contact)
  support@bright-journal.org (technical issues)

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0