CCFS: A cooperating coevolution technique for large scale feature selection on microarray datasets.

Area of Science:

• Bioinformatics
• Machine Learning
• Computational Biology

Background:

• Microarray datasets present challenges due to high dimensionality and small sample sizes.
• Effective feature selection is crucial for machine learning on such data.
• Existing methods struggle with the complexity of these datasets.

Purpose of the Study:

• To propose a novel feature selection method called CCFS.
• To address the limitations of current feature selection techniques for high-dimensional microarray data.
• To enhance the performance of machine learning models using selected features.

Main Methods:

• CCFS employs a global search strategy using divide and conquer principles.
• The algorithm randomly divides features and uses cooperative co-evolution.
• A binary gravitational search algorithm optimizes feature selection with a filter criterion.

Main Results:

• Experiments on seven binary microarray datasets demonstrate CCFS's effectiveness.
• CCFS performance was compared against nine state-of-the-art algorithms.
• Statistical analysis confirmed CCFS significantly improved accuracy, sensitivity, specificity, and reduced feature count.

Conclusions:

• The proposed CCFS method offers a significant advancement in feature selection for high-dimensional microarray data.
• CCFS outperforms existing methods in key performance metrics.
• This approach provides a more effective solution for analyzing complex biological datasets.