A fresh-cut papaya freshness prediction model based on partial least squares regression and support vector machine...

Area of Science:

• Food Science
• Sensory Analysis
• Statistical Modeling

Background:

• Fresh-cut fruits, like papaya, are susceptible to quality degradation during storage.
• Objective assessment of freshness in fresh-cut produce is crucial for quality control and consumer satisfaction.

Purpose of the Study:

• To investigate physicochemical and flavor quality changes in fresh-cut papaya stored at 4°C.
• To develop and compare multivariate statistical models for predicting the freshness of fresh-cut papaya.

Main Methods:

• Fresh-cut papaya was stored at 4°C, and its physicochemical and flavor qualities were analyzed.
• Aerobic plate counts were used as a freshness indicator.
• Partial Least Squares Regression (PLSR) and Support Vector Machine Regression (SVMR) algorithms were employed to build prediction models.

Main Results:

• Freshness of fresh-cut papaya could be distinguished using physicochemical and flavor quality data.
• Aerobic plate counts showed a significant correlation with storage time.
• The SVMR model demonstrated higher prediction accuracy compared to the PLSR model.

Conclusions:

• Combining flavor quality analysis with multivariate statistical methods effectively evaluates fresh-cut papaya freshness.
• SVMR offers a robust approach for predicting the shelf-life and quality of fresh-cut papaya.
• Aerobic plate counts serve as a reliable predictor for assessing the freshness of stored fresh-cut papaya.