Hybrid model based on Genetic Algorithms and SVM applied to variable selection within fruit juice classification

Area of Science:

• Machine Learning
• Data Science
• Agricultural Science

Background:

• Neural Networks are currently used for apple juice classification.
• A need exists for advanced machine learning methods in food quality assessment.

Purpose of the Study:

• To implement a novel hybrid model combining Genetic Algorithms (GA) and Support Vector Machines (SVM) for apple juice classification.
• To enhance variable selection for improved classification accuracy.

Main Methods:

• A hybrid model integrating GA and SVM was developed.
• SVM was utilized as the fitness function within the GA framework.
• This approach facilitates the selection of the most representative variables for classification.

Main Results:

• The hybrid GA-SVM model demonstrated effectiveness in identifying crucial variables for apple juice classification.
• This method offers a new approach to feature selection in machine learning applications.

Conclusions:

• The proposed hybrid GA-SVM model provides a robust framework for apple juice classification.
• This study highlights the potential of combining evolutionary algorithms with SVM for optimizing classification tasks in food science.