Integrated Smart Waste Management System Based on Artificial Intelligence and IoT

Abstract

This study presents an innovative smart waste management system developed through the integrated use of artificial intelligence, IoT and mobile technologies. The system features a multi-layered architecture that combines sensor-based data collection, real-time monitoring via a cloud infrastructure, AI-assisted waste classification and user interaction. Container occupancy rates were measured using an ESP32 microcontroller and ultrasonic sensors, and the data was transferred to the Firebase infrastructure. In the image classification process, the CNN model achieved 94.5% accuracy, while the Gemini model, which requires no additional training, demonstrated superior performance with 97.1% accuracy. The mobile application increased users' recycling awareness, while the web-based panel provided occupancy tracking and route optimization for managers. The results demonstrate that the hybrid CNN-Gemini approach increases waste classification accuracy and system efficiency. This holistic structure is considered a low-cost, scalable and environmentally friendly solution for sustainable smart city applications.

Keywords

• Artificial intelligence
• Deep learning
• IoT sensor
• Smart Waste Management
• Sustainability

Yapay Zeka ve IoT Tabanlı Entegre Akıllı Atık Yönetim Sistemi

Abstract

Bu çalışmada yapay zekâ, IoT ve mobil teknolojilerin entegre kullanımıyla geliştirilen yenilikçi bir akıllı atık yönetim sistemi sunulmaktadır. Sistem, sensör tabanlı veri toplama, bulut altyapısı üzerinden gerçek zamanlı izleme, yapay zekâ destekli atık sınıflandırması ve kullanıcı etkileşimini birleştiren çok katmanlı bir mimariye sahiptir. Konteyner doluluk oranları bir ESP32 mikrodenetleyici ve ultrasonik sensörler kullanılarak ölçülmüş ve veriler Firebase altyapısına aktarılmıştır. Görüntü sınıflandırma sürecinde CNN modeli %94,5 doğruluk elde ederken, ek eğitim gerektirmeyen Gemini modeli %97,1 doğrulukla üstün bir performans göstermiştir. Mobil uygulama kullanıcıların geri dönüşüm farkındalığını artırırken, web tabanlı panel yöneticiler için doluluk takibi ve rota optimizasyonu sağlamıştır. Sonuçlar, hibrit CNN-Gemini yaklaşımının atık sınıflandırma doğruluğunu ve sistem verimliliğini artırdığını göstermektedir. Bu bütünsel yapı, sürdürülebilir akıllı şehir uygulamaları için düşük maliyetli, ölçeklenebilir ve çevre dostu bir çözüm olarak kabul edilmektedir.

Keywords

• Yapay zeka
• Derin öğrenme
• IoT sensörü
• Akıllı Atık Yönetimi
• Sürdürülebilirlik

References

1. Dawson, Ian GJ, and Danni Zhang, "The 8 billion milestone: Risk perceptions of global population growth among UK and US residents." Risk Analysis, vol.44, no. 8, pp. 1809-1827, 2024.
2. World Bank, What a Waste 2.0: A Global Snapshot of Solid Waste Management to 2050, 2nd ed., Washington, DC: World Bank Group, 2019. [Online]. https://documents1.worldbank.org/curated/en/697271544470229584/pdf/What-a-Waste-2-0-A-Global-Snapshot-of-Solid-Waste-Management-to-2050.pdf. [Accessed: Nov. 7, 2025]
3. M. Kolukısaoğlu, K. E. Maçin, and İ. Demir, “Katı atık toplama sıklığının toplama-taşıma maliyetine etkisi,” Artıbilim: Adana Bilim ve Teknoloji Üniversitesi Fen Bilimleri Dergisi, vol. 1, no. 1, pp. 46–56, 2018.
4. O. Rızvanoğlu, Katı atık toplama güzergâh optimizasyonu: Haliliye (Şanlıurfa) İlçesi örneği [Ph.D. dissertation], Harran University, 2018.
5. Republic of Türkiye Ministry of Environment, Urbanization and Climate Change, “Geri kazanım oranımızı %36.08’e çıkardık,” Sıfır Atık Vakfı Resmî Duyurusu, 30 Mar. 2025. [Online]. Available: https://sifiratik.gov.tr/kutuphane/haberler/geri-kazanim-oranimizi-yuzde-36-08-e-cikardik. [Accessed: Nov. 7, 2025]
6. United Nations Environment Programme (UNEP), Global Waste Management Outlook 2018, UNEP Publication, 2018. [Online]. https://zoinet.org/wp-content/uploads/2018/02/GWMO-at-a-glance.pdf. [Accessed: Nov. 7, 2025]
7. Republic of Türkiye Ministry of Environment, Urbanization and Climate Change, Türkiye Çevre Durum Raporu 2022, Ankara: ÇŞB Yayınları, 2022. [Online]. Available: https://ced.csb.gov.tr/2022-yili-il-cevre-durum-raporlari-i-109391. [Accessed: Nov. 7, 2025]
8. Birleşmiş Milletler Kalkınma Programı (UNDP), Sürdürülebilir Kalkınma Amaçları Raporu 2021, UNDP Türkiye, 2021. [Online]. Available: https://www.undp.org/tr/turkiye/publications/undp-turkiye-2021-yillik-raporu. [Accessed: Nov. 7, 2025]

9. United Nations Development Programme (UNDP), “Human Development Data Center – Human Development Index (HDI) for Turkey (1990–2022),” 2024. [Online]. Available: https://hdr.undp.org/data-center/specific-country-data#/countries/TUR. [Accessed: Nov. 7, 2025]
10. European Environment Agency (EEA), “Municipal and Packaging Waste Management Country Profiles – Turkey (2010–2022),” EEA, 2025. [Online]. Available: https://www.eea.europa.eu/en/topics/in-depth/waste-and-recycling/. [Accessed: Nov. 7, 2025]
11. A. Addas, M. N. Khan, F. Nasser, “Waste management 2.0 leveraging Internet of Things for an efficient and eco-friendly smart city solution,” Plos one, vol. 19, 2024,
12. M. F. Kuzhin, A. Joshi, V. Mittal, M. Khatkar, and U. Guven, “Optimizing waste management through IoT and analytics: A case study using the waste management optimization test,” BIO Web of Conferences, vol. 86, Art. 01090, 2024.
13. A. Lakhouit, “Revolutionizing urban solid waste management with AI and IoT: a review of smart solutions for waste collection, sorting, and recycling,” Results in Engineering, vol. 25, 2025.
14. Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, no. 7553, pp. 436–444, May 2015.
15. W. Rawat and Z. Wang, “Deep convolutional neural networks for image classification: A comprehensive review,” Neural Computation, vol. 29, no. 9, pp. 2352–2449, 2017.
16. A. Krizhevsky, I. Sutskever, and G. E. Hinton, “ImageNet classification with deep convolutional neural networks,” in Proc. Advances in Neural Information Processing Systems 25 (NIPS 2012), Lake Tahoe, NV, Dec. 2012, pp. 1097–1105.
17. I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, Cambridge, MA: MIT Press, 2016.
18. Kaggle, “Garbage classification dataset,” 2022. [Online]. Available: https://www.kaggle.com/datasets/feyzazkefe/trashnet. [Accessed: Nov. 7, 2025]
19. Flutter, “Flutter documentation – build apps for mobile, web and desktop,” 2025. [Online]. Available: https://flutter.dev/. [Accessed: Nov. 7, 2025]
20. Google Firebase, “Firebase documentation and SDKs,” 2025. [Online]. Available: https://firebase.google.com/. [Accessed: Nov. 7, 2025]
21. Gemini Team, R. Anil, S. Borgeaud, J.-B. Alayrac, J. Yu, R. Soricut, et al., “Gemini: A family of highly capable multimodal models,” arXiv preprint arXiv:2312.11805, Dec. 2023.
22. Google AI Research, “Google Gemini model overview,” 2024. [Online]. Available: https://ai.google.dev/. [Accessed: Nov. 7, 2025]
23. M. Babiuch, P. Foltýnek, and P. Smutný, “Using the ESP32 microcontroller for data processing,” in Proc. 20th Int. Carpathian Control Conf. (ICCC), Krakow, Poland, May 2019, pp. 1–6.
24. J. Majchrzak, M. Michalski, and G. Wiczynski, “Distance estimation with a long-range ultrasonic sensor system,” IEEE Sensors Journal, vol. 9, no. 7, pp. 767–773, Jul. 2009. doi: 10.1109/JSEN.2009.2014213.
25. T. Aydoğan, K. Gül, and E. Dönmez, “Ultrasonik sensör ile iki boyutlu haritalandırma sistemi,” SDU International Journal of Technological Sciences, vol. 1, no. 1, 2009. [Online]. Available: https://dergipark.org.tr/tr/pub/sdujts/issue/37631/430174
26. N. Cameron, ESP32 Microcontroller: Application of Communication Protocols with ESP32 Microcontroller, Berkeley, CA: Apress, 2023.
27. Espressif Systems, “ESP32 microcontroller datasheet,” Rev. 3.3, 2024. [Online]. Available: https://www.alldatasheet.com/view.jsp?Searchword=Esp32. [Accessed: Nov. 7, 2025]
28. A. S. A. Afrena and A. S. Ab Ghafar, “Poultry farming abnormality detection using ESP32-CAM and OpenCV,” Progress in Engineering Application and Technology, vol. 5, no. 2, pp. 307–311, 2024.
29. K. S. Sunil, A. K. B., P. A. Diljith, H. M. T. K., and M. Nirmal, “Rubbish Revolution: A smart solution for effective plastic waste management and collaborative user engagement in responsible disposal,” in Proc. 3rd Int. Conf. for Innovation in Technology (INOCON), Mar. 2024, pp. 1–7.
30. S. Yin, C. Fu, S. Zhao, K. Li, X. Sun, T. Xu, and E. Chen, “A survey on multimodal large language models,” National Science Review, vol. 11, no. 12, Art. nwae403, 2024. doi: 10.1093/nsr/nwae403.
31. A. Radford, J. W. Kim, C. Hallacy, A. Ramesh, G. Goh, S. Agarwal, et al., “Learning transferable visual models from natural language supervision,” in Proc. Int. Conf. on Machine Learning (ICML), Jul. 2021, pp. 8748–8763.
32. S. Poudel and P. Poudyal, “Classification of waste materials using CNN based on transfer learning,” in Proc. 14th Annual Meeting of the Forum for Information Retrieval Evaluation, Dec. 2022, pp. 29–33.
33. A. Sevinç and F. Özyurt, “Classification of recyclable waste using deep learning architectures,” Fırat University Journal of Experimental and Computational Engineering, vol. 1, no. 3, pp. 122–128, 2022.
34. R. Wu, X. Liu, T. Zhang, J. Xia, J. Li, M. Zhu, and G. Gu, “An efficient multi-label classification-based municipal waste image identification,” Processes, vol. 12, no. 6, Art. 1075, 2024.
35. H. M. Fadhil, A. J. Oribe, M. K. Jwaid, and M. M. J. Hussain, “EcoSavvy: Revolutionizing waste management in smart cities,” in IET Conference Proceedings CP870, Vol. 2023, No. 39, pp. 518–535, Stevenage, UK: The Institution of Engineering and Technology, Dec. 2023.
36. K. K. de Wildt and M. H. Meijers, “Time spent on separating waste is never wasted: Fostering people’s recycling behavior through the use of a mobile application,” Computers in Human Behavior, vol. 139, Art. 107541, 2023.
37. C. S. de Morais, D. R. Ramos Jorge, A. R. Aguiar, A. P. Barbosa-Póvoa, A. P. Antunes, and T. R. P. Ramos, “A solution methodology for a smart waste collection routing problem with workload concerns: Computational and managerial insights from a real case study,” International Journal of Systems Science: Operations & Logistics, vol. 10, no. 1, pp. 1–20, 2023.
38. S. E. Bibri, J. Krogstie, A. Kaboli, and A. Alahi, “Smarter eco-cities and their leading-edge artificial intelligence of things solutions for environmental sustainability: A comprehensive systematic review,” Environmental Science and Ecotechnology, vol. 19, Art. 100330, 2024.