Proposition of a new fitness function: Hadj-said fitness function

Abstract

In the dynamic field of artificial intelligence, genetic algorithms (GAs) offer a powerful approach to solving complex problems by mimicking biological mechanisms such as mutation, crossover, and natural selection. Their efficiency relies primarily on the fitness function, which evaluates the quality of candidate solutions and guides the evolutionary process toward an optimal outcome. A well-designed fitness function not only enhances convergence speed but also reduces the risk of stagnation and improves algorithmic accuracy. This paper explores the fundamental role of fitness functions in optimization, machine learning, multi-objective optimization, and cryptography, highlighting their impact on the performance of GAs. We propose a novel fitness function that incorporates the influence of crossover, mutation, and inversion rates on solution quality. This approach, which diverges from conventional models, demonstrates improved convergence behavior and adaptability across different problem domains. The proposed method enhances GA performance not only in secure data encryption but also in general optimization and learning tasks, making it a valuable contribution for both researchers and practitioners, which can open new avenues for research in the development of more robust evolutionary strategies that can adapt effectively to the specific characteristics and challenges of each problem domain.