An automated waste management system using artificial intelligence and robotics

被引:4
作者
Thao, Le Quang [1 ,2 ]
机构
[1] VNU Univ Sci, Fac Phys, Hanoi 100000, Vietnam
[2] Vietnam Natl Univ, Hanoi 100000, Vietnam
关键词
Waste classification; Artificial intelligence; Wireless network; Robotic arm; Convolutional neural network; CLASSIFICATION;
D O I
10.1007/s10163-023-01796-4
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The challenge of pollution in the twenty-first century is a significant obstacle on the path to sustainability. With the growth of human populations, an increase in waste production is observed, resulting in negative impacts on the environment and human health. This issue is addressed by our project, which presents a solution for waste management through precise waste sorting. A camera and a Convolutional Neural Network (CNN) are employed by our system to accurately classify waste with a 99% success rate. A robotic arm is also incorporated to physically sort the waste into designated bins. All hardware components are connected through a wireless network, which provides numerous advantages such as enhanced worker health, improved efficiency, and reduced human labor, ultimately contributing to sustainable development. The proposed waste management framework includes a developed hardware prototype, providing a comprehensive solution for efficient waste management. An interesting aspect of the project is its potential application on embedded systems with limited configuration, paving the way for a waste management industry that utilizes Internet of Things (IoT) devices at the source. This approach can aid in achieving the goal of establishing clean and pollution-free cities.
引用
收藏
页码:3791 / 3800
页数:10
相关论文
共 34 条
  • [1] Intelligent Waste Classification System Using Deep Learning Convolutional Neural Network
    Adedeji, Olugboja
    Wang, Zenghui
    [J]. 2ND INTERNATIONAL CONFERENCE ON SUSTAINABLE MATERIALS PROCESSING AND MANUFACTURING (SMPM 2019), 2019, 35 : 607 - 612
  • [2] Biron M., 2020, A Practical Guide to Plastics Sustainability: Concept, Solutions, and Implementation, DOI 10.1016/B978-0-12-821539-5.00009-4
  • [3] Deep Learning for Plastic Waste Classification System
    Bobulski, Janusz
    Kubanek, Mariusz
    [J]. APPLIED COMPUTATIONAL INTELLIGENCE AND SOFT COMPUTING, 2021, 2021
  • [4] An explainable artificial intelligence approach for unsupervised fault detection and diagnosis in rotating machinery
    Brito, Lucas C.
    Susto, Gian Antonio
    Brito, Jorge N.
    Duarte, Marcus A., V
    [J]. MECHANICAL SYSTEMS AND SIGNAL PROCESSING, 2022, 163
  • [5] Cross-validatory selection of test and validation sets in multivariate calibration and neural networks as applied to spectroscopy
    Burden, FR
    Brereton, RG
    Walsh, PT
    [J]. ANALYST, 1997, 122 (10) : 1015 - 1022
  • [6] Automatic Classification and Identification of Road Garbage Images and Evaluation of Environmental Health Based on UNet plus
    Chen, Wei
    Zheng, Xuan
    Zhou, Haijun
    Li, Zhe
    [J]. TRAITEMENT DU SIGNAL, 2022, 39 (02) : 701 - 710
  • [7] Multilayer Hybrid Deep-Learning Method for Waste Classification and Recycling
    Chu, Yinghao
    Huang, Chen
    Xie, Xiaodan
    Tan, Bohai
    Kamal, Shyam
    Xiong, Xiaogang
    [J]. COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2018, 2018
  • [8] Applying machine learning approach in recycling
    Erkinay Ozdemir, Merve
    Ali, Zaara
    Subeshan, Balakrishnan
    Asmatulu, Eylem
    [J]. JOURNAL OF MATERIAL CYCLES AND WASTE MANAGEMENT, 2021, 23 (03) : 855 - 871
  • [9] Waste Mismanagement in Developing Countries: A Review of Global Issues
    Ferronato, Navarro
    Torretta, Vincenzo
    [J]. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH, 2019, 16 (06)
  • [10] Franciscone Carlo, EEZYBOTARM MK2