Innovative Bacterial Colony Detection: Leveraging Multi-Feature Selection with the Improved Salp Swarm Algorithm.

Area of Science:

• Bioinformatics
• Computational Biology
• Machine Learning

Background:

• Accurate bacterial classification is crucial for diagnostics and research.
• Traditional methods often struggle with complex, high-dimensional datasets.
• Feature selection is key to improving classification model performance.

Purpose of the Study:

• To develop an advanced multi-feature selection method for bacterial classification.
• To enhance the salp swarm algorithm (SSA) for improved performance.
• To automate bacterial categorization based on unique characteristics.

Main Methods:

• Introduced an improved salp swarm algorithm (ISSA) incorporating opposition-based learning (OBL) and a local search algorithm (LSA).
• The ISSA optimizes multi-feature selection by increasing selected features and classification accuracy.
• The method involves three automated stages for bacterial categorization.

Main Results:

• The ISSA achieved 73.75% classification accuracy on three datasets with 19 features, outperforming other algorithms.
• Demonstrated superior performance in determining the optimal number of features.
• Achieved a classification error rate of 0.249, indicating a better fit value.

Conclusions:

• The ISSA method significantly enhances bacterial classification accuracy through optimized multi-feature selection.
• The integration of OBL and LSA improves SSA's ability to handle local optimization and diversity.
• This approach offers a promising contribution to solving feature selection challenges in bacterial analysis.