Intelligent Evaluation and Dynamic Prediction of Oyster Freshness with Electronic Nose Based on the Distribution of...

Area of Science:

• Food Science
• Analytical Chemistry
• Sensory Science

Background:

• Oyster quality and flavor are significantly influenced by volatile organic compounds.
• Rapid and accurate assessment of oyster freshness is crucial for the seafood industry.
• Understanding flavor changes during storage requires detailed analysis of volatile profiles.

Purpose of the Study:

• To rapidly assess oyster freshness and monitor flavor changes during storage.
• To identify key volatile compounds associated with oyster rancidity.
• To develop and validate an electronic nose system for oyster quality evaluation.

Main Methods:

• Gas Chromatography-Mass Spectrometry (GC-MS) for volatile compound identification.
• Electronic nose technology for rapid sensory analysis.
• Machine learning algorithms including Linear Discriminant Analysis (LDA), Principal Component Analysis (PCA), Support Vector Machine (SVM), and Random Forest (RF) for data interpretation.

Main Results:

• Alcohols, acids, and aldehydes were identified as primary contributors to oyster rancidity.
• Specific heterocyclic compounds, like Cis-2-(2-Pentenyl) furan, increased with storage time.
• The electronic nose system, coupled with LDA, SVM, and RF models, achieved over 90-95% accuracy in classifying oyster freshness at various temperatures.
• Pearson correlation confirmed a strong alignment between sensor responses and specific volatile compounds.

Conclusions:

• The electronic nose system provides a viable and rapid alternative to GC-MS for evaluating oyster freshness.
• Key volatile compounds, particularly heterocyclic ones, can serve as markers for oyster quality.
• Machine learning models effectively predict oyster freshness based on electronic nose data.