Parrot optimizer: Algorithm and applications to medical problems

Area of Science:

• Computational intelligence
• Metaheuristic optimization
• Bio-inspired algorithms

Background:

• Stochastic optimization is crucial for complex research challenges.
• Existing methods require enhanced exploration and exploitation capabilities.

Purpose of the Study:

• Introduce the Parrot Optimizer (PO), a novel bio-inspired algorithm.
• Evaluate PO's performance against established algorithms on diverse benchmark functions.
• Assess PO's applicability to engineering and medical domains.

Main Methods:

• Developed the Parrot Optimizer (PO) based on Pyrrhura Molinae parrot behaviors.
• Benchmarked PO on 35 functions, including IEEE CEC 2022 test sets.
• Conducted parameter sensitivity analysis and applied PO to engineering and medical problems.

Main Results:

• PO demonstrated competitive exploratory and exploitative traits.
• PO outperformed several popular algorithms in benchmark tests.
• PO proved effective and superior in engineering design, disease diagnosis, and medical image segmentation.

Conclusions:

• The Parrot Optimizer (PO) is a promising and competitive stochastic optimization algorithm.
• PO offers significant advantages over existing methods in various applications.
• Open-source code and supplementary materials are available for the PO algorithm.