We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Indonesian Waste Database: Smart Mechatronics System
Summary
This study developed a mechatronic waste sorting robot paired with a smart database of Indonesian waste types, covering six categories including plastics. Automated waste classification technology can improve recycling rates and reduce the plastic that ends up in environments where it breaks down into microplastics.
Waste management is an essential component of urban management. As a waste solution, waste management is critical. The goal of this research is to develop a waste management database that is coupled with a mechatronic robot system. Compiling and gathering data on the sorts of garbage found in Indonesia is the starting point for this research. Indonesian waste is classified into six groups: cardboard, paper, metal, plastic, medical, and organic. The total images of the six groups are estimated at 1880 pictures. According to this picture database, Artificial Intelligence (AI) training was used to create the classification system. In the final AI process, the test method was performed using DenseNet121, DenseNet169, and DenseNet201. Testing using artificial intelligence DenseNet201 across 40 epochs yields the best 92,7% accuracy rate. Simultaneously with Artificial Intelligence testing, a mechatronic system is created as a direct implementation of the Artificial Intelligence output model. A four-servo arm robot with dc motor wheel mobility is included in the mechatronic system. According to these findings, the Indonesian waste database can be categorized correctly using Artificial Intelligence and the mechatronics system. This higher accuracy of the artificial intelligence model may be used to create a waste-sorting robot prototype.
Sign in to start a discussion.
More Papers Like This
A Smart Garbage Classification based on Deep Learning
Researchers developed an AI-powered garbage classification system using deep learning to automatically sort waste categories. Accurate automated waste sorting could improve plastic recycling rates, reducing the amount of plastic that eventually breaks down into environmental microplastics.
Design and Development of Smart Beach Debris Collection and Segregation System
Researchers designed and built a smart automated system for collecting and segregating beach debris, using sensors and robotics to identify and sort plastic waste from natural material on shorelines. The system demonstrated effective separation of plastic debris in field tests.
Artificial Intelligence-Based Robotic Technique for Reusable Waste Materials
This paper describes an AI-based robotic arm system that uses a customized deep learning model to classify and sort waste materials including plastics and cartons by material type for automated recycling. The integrated system combines gripping, motion control, and AI-driven material classification into a full-automation architecture for waste recovery.
Application of AI-Enabled Computer Vision Technology for Segregation of Industrial Plastic Wastes
Researchers developed an AI-powered computer vision system to segregate mixed industrial plastic wastes by polymer type, addressing a key barrier to effective plastic recycling. The system achieved high classification accuracy across common plastic categories, demonstrating that machine vision can improve sorting efficiency and recycled plastic quality.
Mechatronic system to classify plastic and metal bottles using capacitive and inductive sensors
This study designed a mechatronic system using capacitive and inductive sensors to classify plastic and metal bottles, developing an automated sorting approach that achieves high classification accuracy relevant to recycling operations.