Improved Lightweight Mango Sorting Model Based on Visualization

Hongyu Wei, Wenyue Chen, Lixue Zhu, Xuan Chu, Hongli Liu, Yinghui Mu and Zhiyu Ma ()
Additional contact information
Hongyu Wei: College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Wenyue Chen: College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Lixue Zhu: College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Xuan Chu: College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Hongli Liu: College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China
Yinghui Mu: College of Agriculture, South China Agricultural University, Guangzhou 510642, China
Zhiyu Ma: College of Mechanical and Electrical Engineering, Zhongkai University of Agriculture and Engineering, Guangzhou 510225, China

Agriculture, 2022, vol. 12, issue 9, 1-13

Abstract: Neural networks are widely used in fruit sorting and have achieved some success. However, due to the limitations of storage space and power consumption, the storage and computing of a neural network model on embedded devices remain a massive challenge. Aiming at realizing a lightweight mango sorting model, the feature-extraction characteristics of the shallow and deep networks of the SqueezeNet model were analyzed by a visualization method, and then eight lightweight models were constructed by removing redundant layers or modifying the convolution kernel. It was found that the model designated Model 4 performed well after training and testing. The class activation mapping method was used to explain the basis of the classification decision, and the model was compared with ten classical classification models. The results showed that the calculation performance of the model was significantly improved without reducing accuracy. The parameter storage requirement is 0.87 MB, and the calculation amount is 181 MFLOPS, while the average classification accuracy can still be maintained at 95.64%. This model has a high-cost performance and can be widely used in embedded devices.

Keywords: deep learning; lightweight convolutional neural network; visualization; mango sorting (search for similar items in EconPapers)
JEL-codes: Q1 Q10 Q11 Q12 Q13 Q14 Q15 Q16 Q17 Q18 (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/12/9/1467/pdf (application/pdf)
https://www.mdpi.com/2077-0472/12/9/1467/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jagris:v:12:y:2022:i:9:p:1467-:d:914562

Access Statistics for this article

Agriculture is currently edited by Ms. Leda Xuan

More articles in Agriculture from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().