π-Conjugated Supramolecular Self-Assembled Fluorescent Sensor Array for Biogenic Amines: A Machine Learning Approach.

Area of Science:

• Supramolecular chemistry
• Analytical chemistry
• Sensor technology

Background:

• Biogenic amines are critical indicators of food spoilage and quality.
• Accurate detection of biogenic amines is essential for food safety.
• Existing detection methods can be time-consuming and require laboratory settings.

Purpose of the Study:

• To develop a novel π-conjugated supramolecular self-assembled fluorescence sensor array.
• To enable the detection and discrimination of biogenic amines in food samples.
• To apply machine learning for real-time, on-site food analysis.

Main Methods:

• Fabrication of π-conjugated supramolecular self-assembled fluorescence sensor arrays.
• Utilizing machine learning algorithms: Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA), and Hierarchical Cluster Analysis (HCA).
• Application of the sensor array system for real-time and on-site detection in food samples.

Main Results:

• Successful development of a fluorescence sensor array for biogenic amine detection.
• Demonstrated capability for real-time and on-site analysis of food samples.
• Achieved successful binary and ternary mixture analyses of biogenic amines.

Conclusions:

• The developed sensor array system offers a promising approach for rapid and reliable biogenic amine monitoring in food.
• Machine learning integration enhances the discrimination capabilities of the sensor array.
• This technology has significant potential for improving food safety and quality control.