https://aistudies.org/index.php/ais/issue/feed 2024-07-11T11:39:26+00:00 Editorial Office editorial@aistudies.org Open Journal Systems <p>Artificial Intelligence Studies (AIS) is an International Refereed Journal published in any field releated to Artificial Intelligence.The objective of AIS is to be able to hear scientific studies both at&nbsp; international academic and industrial organizations.</p> https://aistudies.org/index.php/ais/article/view/71 2024-07-10T14:43:54+00:00 Safa Dörterler safa.dorterler@dpu.edu.tr Durmuş Özdemir durmus.ozdemir@dpu.edu.tr Hasan Temurtaş hasan.temurtas@dpu.edu.tr

<p>This paper presents new models of the Battle Royale Optimization (BRO) algorithm that are improved by integrating it with chaotic maps. The paper aims to optimize the BRO algorithm using chaotic maps, addressing the challenge of balancing exploration and exploitation, a common challenge in optimization problems. Five different chaotic maps are integrated into BRO to create Bernoulli-BRO, Cubic-BRO, Duffing-BRO, Intermittency-BRO and Liebovtech-BRO models. The chaotic BRO models developed in the study are tested on the Tubular Column Design Problem, one of the engineering problems. The results show that the Intermittency-BRO algorithm performs the best and achieves the lowest optimum costs compared to the other models. It is also observed that chaotic BRO algorithms give more consistent results with lower average cost than classical BRO. In conclusion, this study shows that chaotic maps can be successfully used in optimization problems and chaotic BRO algorithms exhibit superior performance compared to classical BRO. Especially the Intermittency-BRO algorithm gives the best results in terms of both cost and statistical data. The results of the paper emphasize that chaotic maps offer a more effective approach to optimization problems by improving the balance between the exploration and exploitation capabilities of the BRO algorithm.</p>

2024-07-10T00:00:00+00:00 ##submission.copyrightStatement## https://aistudies.org/index.php/ais/article/view/69 2024-07-11T11:39:26+00:00 Alamou Shola Mouhsine Daouda ashola.daouda@gazi.edu.tr Ümit Atila umitatila@gazi.edu.tr

<p>This paper explores the use of metaheuristic algorithms for the Multi-Depot Vehicle Routing Problem (MDVRP), a complex form of the Vehicle Routing Problem (VRP) crucial in logistics. The study contributes to operational research, offering strategies for effective logistics management and underscores the significance of metaheuristic algorithms in tackling intricate optimization problems. The study focuses on optimizing vehicle routes from multiple depots, using a k-clustering technique for initial grouping. It examines algorithms like Particle Swarm Optimization (PSO), Artificial Bee Colony (ABC), Ant Colony Optimization (ACO), and a hybrid of PSO with Tabu Search (PSO-TS). These algorithms are vital for efficient route planning in varied environments, with practical implications demonstrated in real-world logistics scenarios. The findings revealed the limitations of the PSO algorithm and showed the improvement with Tabu Search. While, the resulting hybrid, PSO-TS, demonstrated remarkable improvements and stands out for its efficiency and reliability in MDVRP, it underscored the potential of metaheuristic algorithms in solving NP-hard combinatorial problems.</p>

2024-07-10T00:00:00+00:00 ##submission.copyrightStatement##