Abstract: Traffic congestion is a critical issue in urban areas, leading to increased travel time, fuel consumption, and environmental pollution, while traditional traffic signal systems based on fixed timing fail to respond effectively to dynamic traffic conditions [4], [6]. This paper presents an AI-based smart traffic congestion control system that utilizes dataset-driven analysis to dynamically adjust traffic signal timings for improved efficiency [5], [10]. The proposed system uses a CSV-based dataset containing vehicle counts such as cars, bikes, buses, and trucks, and applies a weighted scoring mechanism to calculate traffic density and determine signal priority [7], [9]. Based on the computed priority score, the system dynamically allocates green signal duration to optimize traffic flow [5], [6]. Additionally, the system incorporates emergency vehicle detection and priority handling to ensure rapid response in critical situations [4], [5]. A graphical user interface (GUI) developed using Tkinter provides real-time visualization of traffic conditions and signal status. Experimental results demonstrate that the proposed system significantly improves traffic efficiency, achieving approximately 25–30% reduction in average waiting time under simulated conditions [5], [10].

Keywords: Smart Traffic System, AI Traffic Control, Dataset Analysis, Dynamic Signal Timing, Traffic Optimization

Downloads: | DOI: 10.17148/IARJSET.2026.134117