Identification of Beef Odors under Different Storage Day and Processing Temperature Conditions Using an Odor Sensing...

Area of Science:

• Food Science
• Analytical Chemistry
• Sensor Technology

Background:

• Beef quality and safety are critical concerns for consumers.
• Traditional methods for assessing beef quality can be time-consuming and destructive.
• Developing rapid, non-destructive methods for monitoring beef is essential.

Purpose of the Study:

• To evaluate an odor sensing system for distinguishing beef odors based on storage duration and processing temperatures.
• To assess the effectiveness of dimensionality reduction techniques like Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP) for odor data.
• To improve the accuracy of beef quality classification using supervised machine learning models.

Main Methods:

• Utilized a 16-channel electrochemical sensor array to capture beef odors under various storage days (D0-D8) and temperatures (room temp, 100°C, 180°C).
• Employed Gas Chromatography-Mass Spectrometry (GC-MS) to identify key odorant compounds.
• Applied Principal Component Analysis (PCA) and Uniform Manifold Approximation and Projection (UMAP) for data visualization and dimensionality reduction, including supervised UMAP.
• Performed machine learning classification using six algorithms on reduced datasets.

Main Results:

• Odor profiles varied significantly with storage days and processing temperatures.
• PCA and unsupervised UMAP effectively clustered data by storage days but not temperatures.
• Supervised UMAP demonstrated high accuracy in clustering both storage days and temperatures.
• Machine learning models achieved over 99.5% accuracy with supervised UMAP and reduced dimensionality.

Conclusions:

• The odor sensing system, coupled with supervised UMAP, offers a highly accurate, non-destructive method for monitoring beef quality and safety.
• This research highlights the potential of electronic noses and data downscaling techniques in food industry applications.
• Findings provide a foundation for future advancements in electronic nose technology for food quality assessment.