Intelligent Evaluation and Dynamic Prediction of Oysters Freshness with Electronic Nose Non-Destructive Monitoring...

Area of Science:

• Food Science
• Sensory Science
• Analytical Chemistry

Background:

• Oyster quality deteriorates due to fluctuations in the cold chain, necessitating robust freshness monitoring.
• Assessing oyster freshness is crucial for preventing quality degradation and ensuring consumer safety.

Purpose of the Study:

• To develop and validate an electronic nose system for rapid oyster freshness assessment.
• To investigate oyster quality changes under various storage conditions using the electronic nose and traditional methods.

Main Methods:

• Development of an electronic nose with ten metal oxide gas sensors.
• Simultaneous quality assessments: GC-MS, TVBN, microbial counts, texture, and sensory analysis.
• Data analysis using Principal Component Analysis (PCA) and a GA-BP neural network model.

Main Results:

• Electronic nose measurements correlated with oyster spoilage levels across different storage temperatures.
• PCA effectively clustered oyster samples into fresh, sub-fresh, and decayed categories.
• The GA-BP neural network model achieved over 93% accuracy in predicting oyster freshness.

Conclusions:

• An electronic nose combined with quality indices provides an effective method for diagnosing oyster spoilage.
• This approach helps mitigate quality and safety risks within the oyster industry.
• Expert input enhanced the system's efficiency and practical applicability for real-time monitoring.