Traffic Monitoring and Control System for Smart City Pollution Regulation Using IoT and Correlated Capsule Networks

Organizational vehicle density management and automated interventions without humans are gaining traction with traffic monitoring and control systems based on the Internet of Things (IoT). Regarding controlling pollution and regulating vehicle density, the current traffic control technologies are ineffective regarding real-time adaptability, efficient classification techniques, and scalable infrastructure. Therefore, a system that uses the IoT is necessary for the real-time identification and regulation of automobiles that release excessive pollution. As a result, the study suggests a TCSP-PC, or Traffic Control System Process for Pollution Control, to manage waste in smart cities. This control system incorporates capsule networks for vehicle categorization based on emission behaviour and employs IoT sensors for data collecting. This system primarily seeks automobiles that cause much pollution during their travels by monitoring their emission infractions. To initiate initial pollution control, such vehicle data is used to detect infractions at any interval. The IoT paradigm aids this process through traffic control regulations. Additionally, capsule networks are used to learn the emission behaviours of both environmentally good and polluting automobiles on the roadside. Through capsule networks that categorize vehicles according to their emission behaviour on the roadside, traffic control systems can monitor and control autos. The vehicles may be categorized as either environmentally friendly or polluting. The system finds polluting vehicles, organizes them using capsule networks, and then suggests pollution restrictions based on the IoT. Utilizing pre-existing smart city resource data, this novel approach combines technological concerns with rules about traffic control and environmental impacts. Comparative analysis with existing models (VEQM, MPTC-PRP, MWIS, and CONV-BI-LSTM) demonstrates significant improvements in impact verification (+12.48%), classification rate (+15.36%), and traffic control efficiency (+121.5 vehicles/km). Additionally, the system achieves an average 9.77% enhancement in data analysis rate and a notable reduction in processing time (-2.06s), ensuring real-time responsiveness. These findings highlight the potential of TCSP-PC to optimize urban traffic flow, reduce emissions, and improve decision-making in smart city infrastructure.

Перевод пока недоступен