The Traveling Salesman Problem (TSP), a prominent combinatorial optimization issue, is the subject of this study's evaluation of the performance of new and old optimization techniques. This paper seeks to expand knowledge of optimization techniques and how they might be applied to solve TSP challenges. The goal of the research is to compare various algorithms' scalability, convergence, and computation times on benchmark instances of several sizes. To achieve this goal, this paper carried out extensive testing using the Artificial Bee Colony (ABC), Grey Wolf Optimization (GWO), and Salp Swarm Algorithm (SSA) as new optimization algorithms and the Genetic Algorithm (GA), Ant Colony Optimization (ACO), and Simulated Annealing (SA) as old optimization algorithms. On small, medium, and large-scale benchmark cases, these algorithms were examined. The findings of this investigation show that the new optimization techniques are more convergent and scalable than the old ones, especially for medium-scale scenarios. They perform better performance in terms of solution quality by applying objective function values. The new methods also exhibit improved scalability, successfully adjusting to medium-scale instances. However, there were no discernible changes between the smaller and larger instances. This study makes an impact by offering insightful information about how well optimization methods perform while solving the TSP. Each algorithm's strengths and downsides have been reported, and these details offer useful guidance for choosing an algorithm for a certain scenario. The results also show the practical ramifications of applying novel optimization techniques, especially in medium-scale instances..
24 December 2025 in Sinop Üniversitesi Fen Bilimleri Dergisi
Traffic accidents represent a major challenge to public safety and urban development. In recent years, the number of road traffic accidents has been increasing due to the rising global population and the growing number of vehicles, leading to numerous fatalities and injuries. This study examines traffic accidents in five major cities of Türkiye from 2021 to 2024, aiming to identify trends and predict future accidents using linear regression and random forest regressor models. Data for this analysis were obtained from the Gendarmerie General Command of the Ministry of Internal Affairs, Republic of Türkiye. To evaluate model performance, key metrics such as Mean Absolute Error, Mean Squared Error, and R-squared were utilized. The results indicate significant variations in accident patterns across cities, months, and years. Furthermore, findings highlight the effectiveness of machine learning models in predicting traffic incidents with high accuracy. Among the two models, the random forest regressor outperforms linear regression in terms of evaluation metrics. Moreover, the analytical results indicate an upward trend in accidents, fatalities, and injuries across the five cities, particularly in Ankara and İzmir. These predictive and analytical insights can provide valuable guidance for policymakers and researchers in formulating effective strategies to mitigate traffic accidents and enhance road safety.