Artificial intelligence for waste sorting using applied deep learning models

Authors

  • Tanachod Pholsripim Faculty of Science, Buriram Rajabhat University, Buriram Province
  • Sunisa Sukhophan Faculty of Science, Buriram Rajabhat University, Buriram Province
  • Prem Enkvetchakul Faculty of Science, Buriram Rajabhat University, Buriram Province

Keywords:

Artificial Intelligence, Deep Learning, Waste Sorting, Neural Networks

Abstract

This research aimed to develop and apply an artificial intelligence system for waste classification by utilizing deep learning technology to analyze and categorize various types of waste. Specifically, it employed Convolutional Neural Networks (CNN), a highly efficient technique for image processing, through a no-code deep learning platform, which facilitates easier development of deep learning models. The research process was divided into three main stages: data collection, model training, and model testing. A total of 2,000 waste images were collected, categorized into four main types: general waste, organic or wet waste, recyclable waste, and hazardous waste. These images were used to train and test the waste classification model. The experimental results demonstrated that the system could classify waste types with an average accuracy as high as 91.5%. The system achieved the highest efficiency in classifying general and recyclable waste with an accuracy of up to 100%, and the lowest efficiency in classifying hazardous waste with an accuracy of 86%.

References

Baojun, G., Wei, Z., Zhebin, S., Qiucheng, H., & Dongping, Z. (2022). AI-based detection system of resident’s behaviors in automatic trash sorting booths: A background computing-based solution. Proceedings of the China Automation Congress (CAC), 756–1760. https://doi.org/10.1109/CAC57257.2022.10055608

Bozic, D., Runje, B., Lisjak, D., & Kolar, D. (2023). Metrics related to confusion matrix as tools for conformity assessment decisions. Applied Sciences, 13(14), 8187. https://doi.org/10.3390/app13148187

Charan, P. V. S., Anand, P. M., Shukla, S. K., Selvan, N., & Chunduri, H. (2022). DOTMUG: A threat model for target specific APT attacks–Misusing Google Teachable Machine. Proceedings of the 10th International Symposium on Digital Forensics and Security (ISDFS), 1–8. https://doi.org/ 10.1109/ISDFS55398.2022.9800780

Chorakhe, T., & Noppitak, S. (2023). Comparison of deep learning approach for water bottle waste classification. Kalasin University Journal of Science Technology and Innovation, 2(2), 53–65. https://doi.org/10.14456/ksti.2023.10. [In Thai].

Fahmi, F., & Lubis, B. P. (2022). Identification and sorting of waste using artificial intelligence based on convolutional neural network. Proceedings of the 6th International Conference on Electrical, Telecommunication and Computer Engineering (ELTICOM), 222–226. https://doi.org/10.1109/ELTICOM57747.2022.10038044

Fang, B., Liu, Y., Chen, Z., Wei, X., Li, J., Zou, D., Chen, C., Xue, S., Chen, S., Liu, J., Wu, L., Wang, B., Han, Z., Zhai, Y., Zhu, J., Yi, Z., Wang, Y., & Wu, J. (2023). Artificial intelligence for waste management in smart cities: A review. Environmental Chemistry Letters, 21(4), 1959–1989.

Jaratwichakorn, N. (2019). Increasing management capacity to provide garbage services in the Bangkok metropolitan markets. UMT Poly Journal, 16(1), 361–370. [In Thai].

Phachanai, T., Panngoen, C., Khonngam, K., Srisamoodkham, W., & Wongsa, W. (2022). Recyclable waste sorting machine with image processing. PSRU Journal of Industrial Technology and Engineering, 4(2), 242–253. [In Thai].

Zheng, X., Zhu, Z., Xiao, Z., Huang, D., Yang, C., He, F., Zhou, X., & Zhao, T. (2023). CNN-based transfer learning in intelligent recognition of scrap bundles. ISIJ International, 63(8), 1383–1393. https://doi.org/10.2355/isijinternational.ISIJINT-2023-064.

Zulhusni, M., Sari, C. A., & Rachmawanto, E. H. (2024). Implementation of DENSeNET121 architecture for waste type classification. Advance Sustainable Science, Engineering and Technology, 6(3), 1–9. https://doi.org/10.26877/asset.v6i3.673

Downloads

Published

2025-08-29

How to Cite

Pholsripim, T., Sukhophan, S., & Enkvetchakul, P. (2025). Artificial intelligence for waste sorting using applied deep learning models. Agriculture & Technology RMUTI Journal, 6(2), 34–42. retrieved from https://li01.tci-thaijo.org/index.php/atj/article/view/263096

Issue

Vol. 6 No. 2 (2025): Agriculture & Technology RMUTI Journal

Section

Articles

License

Copyright (c) 2025 Agriculture & Technology RMUTI Journal

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

เนื้อหาและข้อมูลในบทความที่ลงตีพิมพ์ในวารสารทดสอบระบบ ThaiJo2 ถือเป็นข้อคิดเห็นและความรับผิดชอบของผู้เขียนบทความโดยตรงซึ่งกองบรรณาธิการวารสาร ไม่จำเป็นต้องเห็นด้วย หรือร่วมรับผิดชอบใดๆ

บทความ ข้อมูล เนื่อหา รูปภาพ ฯลฯ ที่ได้รับการดีพิมพ์ในวารสารทดสอบระบบ ThaiJo2 ถือเป็นลิขสิทธิ์ของวารสารทดสอบระบบ ThaiJo2 หากบุคคลหรือหน่วยงานใดต้องการนำทั้งหมดหรือส่วนหนึ่งส่วนใดไปเผยแพร่หรือเพื่อกระทำการใดๆ จะต้องได้รับอนุญาตเป็นลายลักอักษรณ์จากวารสารทดสอบระบบ ThaiJo2 ก่อนเท่านั้น