Waste Segregation through AI

  • Ravikumar B Chawhan Department of Information Science and Engineering Smt. Kamala and Sri. Venkappa M. Agadi College of Engineering & Technology
  • Basavaraj M Shirahatti Department of Information Science and Engineering Smt. Kamala and Sri. Venkappa M. Agadi College of Engineering & Technology
  • Ganesh B Halakeri Department of Information Science and Engineering Smt. Kamala and Sri. Venkappa M. Agadi College of Engineering & Technology
  • Prajwal Kadadi Department of Information Science and Engineering Smt. Kamala and Sri. Venkappa M. Agadi College of Engineering & Technology
  • Rahul A Kumbar Department of Information Science and Engineering Smt. Kamala and Sri. Venkappa M. Agadi College of Engineering & Technology
Keywords: Waste Sorting, Artificial Intelligence, TensorFlow.js, Image Recognition, Transfer Learning, Google Teachable Machine, Browser-Based Inference, Smart Waste Management, Environmental Sustainability, Computer Vision

Abstract

Growing volumes of municipal solid waste, driven by rapid urbanization, have intensified demands for scalable and intelligent material classification tools. This paper introduces a purely browser-based waste sorting application that leverages Artificial Intelligence to categorize discarded items into three groups: Biodegradable/Wet, Recyclable/Dry, and Hazardous. The system deploys a TensorFlow.js inference model trained via Google Teachable Machine, executing all predictions locally within the user’s browser without transmitting any data to an external server. The front-end stack, built with HTML5, CSS3, Tailwind CSS, and Daisy UI, supports live webcam capture and static image uploads, delivering results within two to five seconds accompanied by color-coded disposal advisories. An embedded feedback channel enables users to flag incorrect predictions, supporting iterative model improvement. Testing across multiple browsers and device categories confirmed reliable classification performance, with plastic materials achieving confidence levels approaching 97.6%. The application is lightweight, privacy-conscious, and deployable without backend infrastructure, making it suitable for municipal, educational, and community-level waste management programs.

References

[1] P. Gupta and M. Sahu, “Automatic Waste Segregation Using Convolutional Neural Networks,” Int. J. Comput. Appl., vol. 175, no. 12, pp. 1–6, 2020.
[2] A. Mohammed and M. Shaib, “Artificial Intelligence and Machine Learning Frameworks for Smart Waste Management,” IEEE Access, vol. 9, pp. 45231–45245, 2021.
[3] M. S. Rad, A. von Kaenel, A. Droux, F. Ghioldi, N. Ouerhani, and P. Dugerdil, “A Computer Vision System for Waste Sorting and Recycling,” in Proc. IEEE CSIT, 2017, pp. 1–5.
[4] World Bank, What a Waste 2.0: A Global Snapshot of Solid Waste Management to 2050. Washington D.C.: World Bank Publications, 2018.
[5] F. Zhang, X. Zhu, and M. Ye, “Fast Specialization for Zero-Shot Classification Applied to Smart Waste Management,” Sensors, vol. 20, no. 14, p. 3816, 2020.
[6] United Nations Environment Programme, Solid Waste Management: Global Trends and Regional Guidelines. Nairobi: UNEP, 2019.
Published
2026-04-19
How to Cite
Chawhan, R., Shirahatti, B., Halakeri, G., Kadadi, P., & Kumbar, R. (2026). Waste Segregation through AI. Asian Journal For Convergence In Technology (AJCT) ISSN -2350-1146, 12(1), 145-147. Retrieved from https://asianssr.org/index.php/ajct/article/view/1533

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.