Paper Contents
Abstract
This study introduces a practical, AI-driven solution for sorting bulky industrial waste in real time. By analyzing video footage, a supervised artificial neural network (ANN) classifies each item and routes it to either a guillotine-type shredder or a dual-shaft crusher. In this research training is done on 500 labeled images, the ANN reached an accuracy of 84.2%, supported by safety protocols and manual oversight. The systems modular design allows for gradual deployment, with early trials of convolutional neural networks (CNNs) showing convincing improvements. This ANN-phase marks a meaningful step toward smarter, safer, and scalable industrial waste automation.
Copyright
Copyright © 2025 wasantha samarathunga. This is an open access article distributed under the Creative Commons Attribution License.
