Decoupling and Collaboration: An Intelligent Gateway-Based Internet of Things System Architecture for Meat Processing

Jun Liu (), Chenggang Zhou, Haoyuan Wei, Jie Pi and Daoying Wang
Additional contact information
Jun Liu: College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210031, China
Chenggang Zhou: College of Artificial Intelligence, Nanjing Agricultural University, Nanjing 210031, China
Haoyuan Wei: Guangxi Key Laboratory of Digital Infrastructure, Guangxi Zhuang Autonomous Region Information Center, Nanning 530000, China
Jie Pi: Institute of Agricultural Facilities and Equipment, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China
Daoying Wang: Institute of Agricultural Products Processing, Jiangsu Academy of Agricultural Sciences, Nanjing 210014, China

Agriculture, 2025, vol. 15, issue 2, 1-17

Abstract: The complex multi-stage process of meat processing encompasses critical phases, including slaughtering, cooling, cutting, packaging, warehousing, and logistics. The quality and nutritional value of the final meat product are significantly influenced by each processing link. To address the major challenges in the meat processing industry, including device heterogeneity, model deficiencies, rapidly increasing demands for data analysis, and limitations of cloud computing, this study proposes an Internet of Things (IoT) architecture. This architecture is centered around an intelligently decoupled gateway design and edge-cloud collaborative intelligent meat inspection. Pork freshness detection is used as an example. In this paper, a high-precision and lightweight pork freshness detection model is developed by optimizing the MobileNetV3 model with Efficient Channel Attention (ECA). The experimental results indicate that the model’s accuracy on the test set is 99.8%, with a loss function value of 0.019. Building upon these results, this paper presents an experimental platform for real-time pork freshness detection, implemented by deploying the model on an intelligent gateway. The platform demonstrates stable performance with peak model memory usage under 600 MB, average CPU utilization below 20%, and gateway internal response times not exceeding 100 ms.

Keywords: meat processing; intelligent gateways; Internet of Things; edge computing; decoupling collaborative design (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: 2025
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2077-0472/15/2/179/pdf (application/pdf)
https://www.mdpi.com/2077-0472/15/2/179/ (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:15:y:2025:i:2:p:179-:d:1567626

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 ().