The expanded invasive weed optimization metaheuristic for solving continuous and discrete optimization problems.

Area of Science:

• Computational Intelligence
• Optimization Algorithms
• Metaheuristics

Background:

• Invasive Weed Optimization (IWO) is a nature-inspired metaheuristic algorithm.
• Existing IWO algorithms face challenges in search space exploration.
• Hybrid strategies are crucial for enhancing optimization algorithm performance.

Purpose of the Study:

• To introduce an expanded Invasive Weed Optimization (exIWO) algorithm.
• To evaluate the exIWO algorithm's effectiveness using a hybrid search space exploration strategy.
• To compare the exIWO algorithm's performance against other optimization methods.

Main Methods:

• The study proposes a novel hybrid strategy for search space exploration within the IWO framework.
• The expanded Invasive Weed Optimization (exIWO) algorithm is developed based on this hybrid strategy.
• The exIWO algorithm is applied to three distinct optimization problems: numerical function minimization, feature selection, and the Traveling Salesman Problem (TSP).

Main Results:

• The exIWO algorithm achieved competitive results in minimizing numerical functions.
• The exIWO algorithm demonstrated effectiveness in feature selection tasks.
• The exIWO algorithm provided comparable solutions for the Mona Lisa TSP Challenge.

Conclusions:

• The proposed hybrid strategy enhances the Invasive Weed Optimization algorithm's performance.
• The exIWO algorithm is a viable and effective tool for various optimization tasks.
• The exIWO algorithm shows promise compared to existing optimization techniques.