Waste Classification for Sustainable Development Using Image Recognition with Deep Learning Neural Network Models

被引:38
作者
Malik, Meena [1 ]
Sharma, Sachin [2 ]
Uddin, Mueen [3 ]
Chen, Chin-Ling [4 ,5 ,6 ]
Wu, Chih-Ming [7 ]
Soni, Punit [8 ]
Chaudhary, Shikha [9 ]
机构
[1] Sagar Inst Sci & Technol, Dept CSE, Bhopal 462036, Madhya Pradesh, India
[2] Koneru Lakshmaiah Educ Fdn, Dept CSE, Vijaywada 522502, Andhra Pradesh, India
[3] Univ Doha Sci & Technol, Coll Comp & Informat Technol, Doha 24449, Qatar
[4] Changchun Sci Tech Univ, Sch Informat Engn, Changchun 130600, Peoples R China
[5] Xiamen Univ Technol, Sch Comp & Informat Engn, Xiamen 361024, Peoples R China
[6] Chaoyang Univ Technol, Dept Comp Sci & Informat Engn, Taichung 41349, Taiwan
[7] Xiamen Univ Technol, Sch Civil Engn & Architecture, Xiamen 361024, Peoples R China
[8] Chandigarh Univ, Dept CSE, Mohali 140413, Punjab, India
[9] Manipal Univ Jaipur, Sch Comp & IT, Jaipur 303007, Rajasthan, India
基金
中国国家自然科学基金;
关键词
litter classification; convolution neural networks; machine learning; EfficientNet-B0;
D O I
10.3390/su14127222
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
The proper handling of waste is one of the biggest challenges of modern society. Municipal Solid Waste (MSW) requires categorization into a number of types, including bio, plastic, glass, metal, paper, etc. The most efficient techniques proposed by researchers so far include neural networks. In this paper, a detailed summarization was made of the existing deep learning techniques that have been proposed to classify waste. This paper proposes an architecture for the classification of litter into the categories specified in the benchmark approaches. The architecture used for classification was EfficientNet-B0. These are compound-scaling based models proposed by Google that are pretrained on ImageNet and have an accuracy of 74% to 84% in top-1 over ImageNet. This research proposes EfficientNet-B0 model tuning for images specific to particular demographic regions for efficient classification. This type of model tuning over transfer learning provides a customized model for classification, highly optimized for a particular region. It was shown that such a model had comparable accuracy to that of EfficientNet-B3, however, with a significantly smaller number of parameters required by the B3 model. Thus, the proposed technique achieved efficiency on the order of 4X in terms of FLOPS. Moreover, it resulted in improvised classifications as a result of fine-tuning over region-wise specific litter images.
引用
收藏
页数:18
相关论文
共 26 条
[1]   Deep Reinforcement Learning Enabled Smart City Recycling Waste Object Classification [J].
Al Duhayyim, Mesfer ;
Eisa, Taiseer Abdalla Elfadil ;
Al-Wesabi, Fahd N. ;
Abdelmaboud, Abdelzahir ;
Hamza, Manar Ahmed ;
Zamani, Abu Sarwar ;
Rizwanullah, Mohammed ;
Marzouk, Radwa .
CMC-COMPUTERS MATERIALS & CONTINUA, 2022, 71 (03) :5699-5715
[2]  
Ceballos-Pinto Lorena, 1995, Revista Latinoamericana de Microbiologia, V37, P109
[3]  
Chaturvedi S., 2021, NAT ENVIRON POLLUT T, V20, P1515, DOI DOI 10.46488/NEPT.2021.v20i04.013
[4]   Litter Detection with Deep Learning: A Comparative Study [J].
Cordova, Manuel ;
Pinto, Allan ;
Hellevik, Christina Carrozzo ;
Alaliyat, Saleh Abdel-Afou ;
Hameed, Ibrahim A. ;
Pedrini, Helio ;
Torres, Ricardo da S. .
SENSORS, 2022, 22 (02)
[5]  
Devi R. S. S., 2018, INT J INNOV TECHNOL, V8, P401
[6]  
Dosovitskiy Alexey, 2016, Advances in Neural Information Processing Systems, V29
[7]   Household Waste Management System Using IoT and Machine Learning [J].
Dubey, Sonali ;
Singh, Pushpa ;
Yadav, Piyush ;
Singh, Krishna Kant .
INTERNATIONAL CONFERENCE ON COMPUTATIONAL INTELLIGENCE AND DATA SCIENCE, 2020, 167 :1950-1959
[8]   Deep Residual Learning for Image Recognition [J].
He, Kaiming ;
Zhang, Xiangyu ;
Ren, Shaoqing ;
Sun, Jian .
2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2016, :770-778
[9]  
Hu J, 2018, PROC CVPR IEEE, P7132, DOI [10.1109/CVPR.2018.00745, 10.1109/TPAMI.2019.2913372]
[10]   Recycling Waste Classification Using Vision Transformer on Portable Device [J].
Huang, Kai ;
Lei, Huan ;
Jiao, Zeyu ;
Zhong, Zhenyu .
SUSTAINABILITY, 2021, 13 (21)