Small intelligent gas sensing detection system based on double-branch convolutional neural network and high-precision quantitative analysis method of aflatoxin
By analyzing the temporal dynamics and spatial characteristics of fungal metabolic VOCs data using a dual-branch convolutional neural network (DB-CNN), a compact intelligent gas sensing and detection system for AFB1 was designed. This system solves the problem of inaccurate detection of AFB1 in existing technologies and enables high-precision quantitative analysis of aflatoxin and real-time monitoring of the food supply chain.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- JIANGNAN UNIV
- Filing Date
- 2025-12-04
- Publication Date
- 2026-07-17
AI Technical Summary
Existing volatile organic compound (VOC)-based detection systems are mainly used to determine whether grains and foods are contaminated or to accurately detect the amount of fungi, but there is a lack of methods for accurately detecting aflatoxin B1 (AFB1) through VOCs.
A compact intelligent gas sensing and detection system for AFB1 was designed by using a dual-branch convolutional neural network (DB-CNN) to analyze the temporal dynamics and spatial characteristics of fungal metabolic VOCs data. The system extracts gas fingerprints through parallel convolutional channels, enabling high-precision quantitative analysis of AFB1.
It enables accurate differentiation between corn, peanuts, wheat and other grains infected with Aspergillus flavus and high-precision quantitative analysis of AFB1. It supports wireless transmission and is suitable for dynamic real-time monitoring of fungal contamination in the food supply chain, providing early warning and quality control.
Smart Images
Figure CN122409764A_ABST