.png){kind=icon}
.png){kind=icon}
Return
Knowledge-guided hybrid deep learning framework for robust early warning of food temperature deviations in dynamic urban delivery
.png){kind=icon}
OA
AI
F
Y
Y
X
X
J
J
DOI：10.1016/j.jfoodeng.2026.113147.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A knowledge-guided deep learning framework enables early warning of food temperature deviations in urban delivery • Thermodynamic insights and multi-source operational data improve prediction reliability beyond ambient temperature monitoring • High accuracy is achieved (RMSE = 0.31 °C, 30-min horizon) using only two low-cost sensors • Cumulative door open time is identified as a key driver of food temperature instability during unloading • Lightweight architecture supports real-time edge deployment for proactive food quality preservation
Keywords:
Cold chain
Temperature management
Food quality
Food loss
Deep learning
Early warning
Smart monitoring
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
5.8
Papers:
1.0W
Citations:
3.3W
Organization
Cited Papers