Blindfolded Spider-man Optimization: A Single-Point Metaheuristics Suitable for Continuous and Discrete Spaces

TL;DR

This paper introduces Blindfolded Spiderman Optimization, a novel single-point metaheuristic algorithm effective for both continuous and discrete optimization problems, demonstrating superior performance over existing methods.

Contribution

The paper presents a new metaheuristic algorithm that combines a piecewise linear search with a blindfolded jumping strategy, applicable to diverse optimization domains.

Findings

Outperforms state-of-the-art metaheuristics on benchmark functions

Effective on both continuous and discrete optimization problems

Shows superior results compared to Buggy Pinball and other algorithms

Abstract

In this study, we introduce a new single point metaheuristic optimization approach suitable for both continuous and discrete domains. The proposed algorithm, entitled Blindfolded Spiderman Optimization, follows a piecewise linear search trajectory where each line segment considers a move to an improved solution point. The trajectory resembles spiderman jumping from one building to the highest neighbor building in a blindfolded manner. Blindfolded Spiderman Optimization builds on top of the Buggy Pinball Optimization algorithm. Blindfolded Spiderman Optimization is tested on 16 mathematical optimization functions and one discrete problem of Unbounded Knapsack. We perform a thorough evaluation of Blindfolded Spiderman Optimization against established and state-of-the-art metaheuristic optimization methods, including Whale Optimization, Grey Wolf Optimization, Particle Swarm Optimization, Simulated Annealing, Threshold Accepting, and Buggy Pinball Optimization considering various optimization domains and dimensions. We show that Blindfolded Spiderman Optimization achieves great performance on both continuous and discrete spaces, and superior performance compared to all single-point metaheuristic approaches considered.