Work

Research on Deep Prediction of Agricultural Product Quality Based on Multi Model Fusion: A Case Study of Eel

Year: 2025

Type: conference-paper

Abstract: This study focuses on the prediction of eel meat quality storage. Given the urgent need for quality control of agricultural products in the agricultural industry, key indicators such as water content, malondialdehyde content, carboxyl content, and colony index were covered using the 1-120 day eel meat quality data provided by A. After a rigorous data cleaning process and removal of outliers, the advantages of CNN-LSTM Transformer model fusion are utilized. CNN extracts local features, LSTM captures long-term dependencies, and Transformer processes global dependencies, effectively improving prediction accuracy. Through in-depth analysis of 1-120 day data, key indicators of eel meat quality changes from 121-180 days were successfully predicted. This study provides a powerful tool for the quality control of eel meat, promotes sustainable development of the agricultural industry, and is of great significance for ensuring the quality of agricultural product market supply and reducing losses.

Source: International Conference on Generative Artificial Intelligence and Information Security (GAIIS)

DOI: 10.1145/3728725.3728776

Authors: Jiamin Zheng, Qilin Zhang, Shaoyi Song, Xuan Zhao, Yipeng Zhou

Institution: Beijing Technology and Business University

Language: English

Topic: Meat and Animal Product Quality

Subfield: Animal Science and Zoology

Field: Agricultural and Biological Sciences

Domain: Life Sciences

SDG: Zero hunger

Open Access status: hybrid

Funder: Beijing Technology and Business University