THE ROLE OF ARTIFICIAL INTELLIGENCE IN TRAFFIC FLOW MANAGEMENT

Аннотация

This paper explores the role of Artificial Intelligence (AI) in optimizing traffic flow management within urban environments. It examines how AI technologies, including machine learning, computer vision, and predictive analytics, contribute to real-time traffic monitoring, congestion reduction, and adaptive signal control systems. The study highlights the integration of AI with smart city infrastructure to enhance efficiency, safety, and environmental sustainability. Case studies and current implementations are analyzed to demonstrate AI's effectiveness in reducing delays and improving traffic conditions. The annotation emphasizes the transformative potential of AI in reshaping traffic systems and supporting the development ofintelligent transportation networks. Key words:AI, transport, passenger transport, publictransport sector, education, system. Introduction. The current period is characterized by the rapid development of cities, the improvement of improvement works and the sharp increase in the number of city residents. In such conditions, provision of high-quality transport services to city residents requires further development of city passenger transport, development of new and more efficient ways of transportation [1]. The organization of road transport in the city transport network has its own characteristics. It should be noted that the main complexity of the management of passenger transportation processes in cities is the uncertainties in the formation of transportation flows [2,3]. The impact of most factors affecting the size of the passenger flow is changing over time andhas aprobabilisticcharacter. Result and discussion. The multi-phase study was based on individual in-depth interviews with 50 senior local passenger transport operators, government officials, lobbyists and experts from New Zealand and around the world; and four validation workshops with 28 sector stakeholders [4]. The data was analysed using mostly pre-determined themes from which four scenarios were constructed and then validated. The implications are that the local passenger transport system is about to transitionto a system of ‘shared mobility; publictransport will need to evolve to stay relevant but will remain important in any scenario; and therole of Government will be vital in overseeing the transition to the shared mobility era. These lessons are now being used to inform transport and broader policy decisions across New Zealand [5]. Overall, the study is the first to apply such a global and qualitatively rich dataset to view the long-term futurelocal passenger transport system as a whole[6]. 282 INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE ISSN:2692-5206,ImpactFactor:12,23 AmericanAcademicpublishers,volume05,issue08,2025 Journal: https://www.academicpublishers.org/journals/index.php/ijai Fig 1.AI inTrafficManagement Much has been written about the accelerating pace of societal and technological change, but, until recently, such statements have not typically been applied to the public transport sector. Indeed, the operational concept underlying the bus for instance (i.e. large vehicles on fixed routes and operating on fixed timetables) has not fundamentally changed as a concept since its introductionalmost 200years ago. The formation of passenger flows is also influenced by the time of day, days of the week and seasons ofthe year. Although there are currently many methods of monitoring and analyzing passenger flows, the followingtwo disadvantages are common toall ofthem: 1) the study of passenger flows is carried out in a certain area of the city at a certain time interval, however, the results obtained in this case are generalized to thewhole city and used for alltimeintervals; 2) the studied situation belongs to the past, but its results are used for future solutions. In other words, the studied passenger flow is the result of the actual fulfillment of the demand for transport in thepast, and theexpected flowinthefuture maybedifferent from it; 3) the study and analysis of flows is a very labor-intensive activity (thousands of man-hours), which requires very large costs. The problem can be solved through mathematical models that reflect the connection between the volume of transportation expected in the future and the factors that cause the movement of the city's population[18,19,20,21,22]. It is important to take into account the factors of the following three groups that shape the transport mobility of the populationwhen determining thefuture sizesof passenger flows (Figure 1): Based on theperformance of the above steps, the necessary levels of the indicators of passenger transportation service impact ontrafficsafety will bedetermined. Thefollowing can beindicated as such indicators: 1)walking distance to thestopsofthepassenger transport route; 2)operational qualitiesof thepassenger transport vehicle (capacity, ease ofwalking, etc.). 283 INTERNATIONAL JOURNAL OF ARTIFICIAL INTELLIGENCE ISSN:2692-5206,ImpactFact