An Intelligent Waste-Sorting and Recycling Device Based on Improved EfficientNet

Zhicheng Feng; Jie Yang; Lifang Chen; Zhichao Chen; Linhong Li

doi:10.3390/ijerph192315987

An Intelligent Waste-Sorting and Recycling Device Based on Improved EfficientNet

Int J Environ Res Public Health. 2022 Nov 30;19(23):15987. doi: 10.3390/ijerph192315987.

Authors

Zhicheng Feng^{1

2}, Jie Yang^{1

3}, Lifang Chen⁴, Zhichao Chen^{1

2}, Linhong Li^{1

2}

Affiliations

¹ Department of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou 341000, China.
² Jiangxi Provincial Key Laboratory of Maglev Technology, Ganzhou 341000, China.
³ Ganjiang Innovation Academy, Chinese Academy of Sciences, Ganzhou 341000, China.
⁴ Department of Science, Jiangxi University of Science and Technology, Ganzhou 341000, China.

Abstract

The main source of urban waste is the daily life activities of residents, and the waste sorting of residents' waste is important for promoting economic recycling, reducing labor costs, and protecting the environment. However, most residents are unable to make accurate judgments about the categories of household waste, which severely limits the efficiency of waste sorting. We have designed an intelligent waste bin that enables automatic waste sorting and recycling, avoiding the extensive knowledge required for waste sorting. To ensure that the waste-classification model is high accuracy and works in real time, GECM-EfficientNet is proposed based on EfficientNet by streamlining the mobile inverted bottleneck convolution (MBConv) module, introducing the efficient channel attention (ECA) module and coordinate attention (CA) module, and transfer learning. The accuracy of GECM-EfficientNet reaches 94.54% and 94.23% on the self-built household waste dataset and TrashNet dataset, with parameters of only 1.23 M. The time of one recognition on the intelligent waste bin is only 146 ms, which satisfies the real-time classification requirement. Our method improves the computational efficiency of the waste-classification model and simplifies the hardware requirements, which contributes to the residents' waste classification based on intelligent devices.

Keywords: EfficientNet; artificial intelligence; image classification; sustainable development; waste sorting and recycling.

MeSH terms

Intelligence
Learning
Recycling
Refuse Disposal*
Waste Management*

Grants and funding

This work was supported by a grant from the Research Projects of Ganjiang Innovation Academy, Chinese Academy of Sciences (No. E255J001), the National Natural Science Foundation of China (No. 62063009), and the Jiangxi Postgraduate Innovation Special Fund Project (YC2022-S648).