Related Experiment Video
Updated: Aug 7, 2025
08:47
Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation
Published on: February 9, 2024
1.5K
An optimal model for municipal solid waste management using hybrid dual faster R-CNN
1Department of Computer Science and Engineering, Sathyabama Institute of Science and Technology, Chennai, India. jithinajose@gmail.com.
Environmental Monitoring and Assessment
|March 13, 2023
Summary
Global waste generation is rising due to urbanization and population growth. This study introduces a novel waste classification system using optimized dual Faster R-CNN to improve municipal solid waste management and pollution control strategies.
Area of Science:
- Environmental Science
- Computer Science
- Artificial Intelligence
Background:
- Increasing global waste generation driven by economic development, population growth, and urbanization presents significant management challenges.
- Current municipal solid waste (MSW) levels are substantial (2.1 million tons in 2016), with projections indicating a rise to 3.4 million tons by 2050.
- Complex waste management systems struggle to maintain pollution control due to the escalating volume and changing composition of MSW.
Purpose of the Study:
- To develop an accurate waste classification system for effective municipal solid waste management.
- To address the need for precise waste composition prediction to enable suitable decomposition techniques.
- To enhance pollution control strategies by improving the accuracy of waste classification.
Main Methods:
- Proposed a novel waste management system integrating dual Faster R-CNN architecture.
- Employed the Complex-valued encoding Multi-chain Seeker Optimization Algorithm (CMSOA) to optimize the dual Faster R-CNN model.
- Evaluated the system's performance using metrics such as accuracy, precision, recall, F-measure, RMSE, MAE, and MAPE.
Main Results:
- The proposed CMSOA-optimized dual Faster R-CNN system demonstrated superior waste classification accuracy compared to existing methods.
- Case study analysis on five major cities in Maharashtra validated the effectiveness of the developed system.
- Comparative analysis confirmed the enhanced performance of the proposed hybrid approach in classifying waste composition.
Conclusions:
- The developed system offers a significant advancement in accurately classifying municipal solid waste composition.
- Accurate waste classification is crucial for optimizing waste management strategies and improving pollution control.
- The hybrid CMSOA-optimized dual Faster R-CNN approach provides a robust solution for complex waste management challenges.
