RFID-Assisted Priority Traffic Management System with Real-Time Vehicle Density Sensing

RFID-Assisted Priority Traffic Management System with Real-Time Vehicle Density Sensing

Rajeshwaran S

Faculty, Electronics and Communication Engineering Department, Sri Ramakrishna Engineering College, Coimbatore, India.

Kowshik Balaji V

UG Scholar, Electronics and Communication Engineering Department, Sri Ramakrishna Engineering College, Coimbatore, India.

Elakkiya R

UG Scholar, Electronics and Instrumenatation Engineering Department, Sri Ramakrishna Engineering College, Coimbatore, India.

Abstract – In this work, we present a smart traffic control system based on RFID technology for emergency vehicle prioritization and real-time sensing of vehicle density for traffic light control optimization. Emergency vehicles are fitted with RFID tags, and these are picked up by RFID readers installed at intersections so that the system can dynamically override default signal patterns to generate a green route. Concurrently, sensors like ultrasonic or IR modules track vehicle counts at different lanes to make adaptive signal timing possible in accordance with current traffic conditions. The decision-making is coordinated by a control unit that is microcontroller-based. This system enhances emergency response time and minimizes traffic jams and offers a scalable solution for today's smart city scenarios.

Keywords – Smart Traffic System, RFID,Emergency Vehicle Priority,Traffic Density Sensors,Intelligent Transportation System (ITS),Adaptive Traffic Control,IoT-based Traffic Management,Real-time Signal Control

I.INTRODUCTION

The geometric rise in the number of cars and the increasing urbanization have made traffic congestion a recurring problem in metropolitan areas. Due to the fixed-timing algorithms that support conventional traffic management systems' inability to adjust to shifting road conditions, travel times, fuel consumption, and vehicle emissions all rise. Most significantly, these technologies delay the deployment of emergency services, such as police vehicles, fire engines, and ambulances, in instances where seconds matter. Their ability to monitor, assess, and respond to traffic conditions in real time has made intelligent transportation systems (ITS) a popular way to overcome these limitations. Among the many ITS systems, sensor-based traffic observation and radio frequency identification (RFID) have been regarded as efficient and cost- effective technologies. Traffic lights can yield to emergency cars since RFID makes it possible for them to be automatically recognized. At the same time, sensors such as magnetic, infrared (IR), or ultrasonic detectors provide real-time traffic density data that may be used to adaptively modify signal timings in response to actual vehicle flow rather than strict timetables.

The design and implementation of a smart traffic control system that combines real-time traffic density monitoring with RFID-based emergency vehicle recognition is described in this study. RFID tags are attached to emergency vehicles, and RFID

readers are placed at intersections to detect when these vehicles are approaching. When the system detects it, it automatically interrupts the regular signal flow to create a "green corridor" that allows the emergency vehicle to pass through immediately.

In order to improve overall traffic

flow and reduce congestion, density sensors simultaneously measure the number of automobiles on each road section and dynamically modify signal timing.

The basic processing system consists of a microcontroller- based control unit that applies decision algorithms, receives inputs from RFID and density sensors, and regulates traffic lights accordingly. The system is suitable for integration into current urban transportation infrastructures because of its scalability, cost-effectiveness, and energy efficiency.

By introducing a hybrid method, this study contributes to the ongoing smartening of smart city infrastructure, enhancing both general traffic flow efficiency and emergency response. A prototype that simulates and tests the new system demonstrates that it is successful in improving traffic signal performance in a variety of scenarios and reducing emergency response times.

1. LITERATURE REVIEW

   The goal of recent advancements in intelligent traffic control is to overcome the drawbacks of fixed-time signal systems, which cause delays and congestion because they are unable to react to real-time situations. Although they offer dynamic signal management, adaptive systems like SCOOT and SCATS are costly and infrastructure-dependent. Although they are sensitive to environmental factors, sensor-based systems that use infrared, ultrasonic, or inductive loop detectors have been proposed as a way to evaluate vehicle density and adjust signals accordingly. As demonstrated by Jain et al., RFID scanners detect tagged ambulances and trigger green lights to make room for emergency vehicles, demonstrating the growing usage of RFID technology for this purpose

   1.1 A brief review on RFID based prioritizing in urban traffic system

   Urban traffic congestion has become a recurring issue in modern cities, particularly when it comes to allowing emergency vehicles to travel quickly and unhindered. The intelligence required to dynamically adjust to the presence of high-priority vehicles is not present in conventional traffic light

   systems. Because of this drawback, researchers and urban planners are looking more closely at RFID (Radio Frequency Identification) as a reliable and affordable way to prioritize emergency vehicles.

   The capacity of RFID technology to identify tagged vehicles in real-time and notify a traffic control unit is used by RFID- based priority traffic systems. Strategically positioned RFID readers detect the signal from an emergency vehicle, such as a police car, fire truck, or ambulance, that has an implanted RFID tag when it approaches an intersection.

   Following confirmation, the traffic light is overridden or preempted to allow for swift and safe vehicle movement. This method lowers the likelihood of accidents at junctions, improves emergency response times, and significantly cuts down on delay times.

   RFID-based systems have disadvantages despite their advantages, such as a narrow detection range, potential signal interference, and the need for calibration and maintenance. However, RFID systems continue to be the preferred method for short-range, low-latency vehicle priority in dense urban traffic due to its low cost, simplicity of installation, and passive nature.

   In conclusion, RFID-based traffic priority has shown to be a highly promising option for smart city infrastructure.

2. PROPOSED DESIGN

   According to the current vehicle density, the suggested traffic management system will automatically regulate traffic flow and utilize RFID technology to ensure that emergency vehicles are given priority. Every crossing has sensors, such as infrared or ultrasonic modules, that count how many cars are in each lane as it approaches. A microcontroller receives this data and uses it to calculate, based on traffic intensity, the optimal green light duration for each approach. In parallel, RFID scanners positioned at a set distance from the intersection continuously search for RFID tags on emergency vehicles, such as police cars, fire trucks, and ambulances.

   After identifying a valid tag, the system compares it to a list of approved emergency vehicles and momentarily interrupts the regular traffic signal cycle, giving the approaching emergency vehicle's lane a green light while stopping the others. The system returns to density-based traffic control when the emergency vehicle has gone through. A microcontroller, usually an Arduino or Raspberry Pi, serves as the core processing unit for all of these operations. Adequate delays also guard against hazardous switching. To enable remote monitoring or traffic official overrides, wireless communication units or graphical interface modules can be incorporated as optional extras.

   Hardware and software components must be combined to build a functional prototype in order to install the proposed traffic

   control system. To identify vehicle concentration, IR sensors or ultrasonic modules are positioned on each lane as part of the hardware setup. In order to analyze the incoming sensor inputs and calculate the intensity of traffic flow in real time, the sensors are connected to an Arduino Uno microcontroller. The same microcontroller is simultaneously interfaced with an

   RFID module (such as the MFRC522) that is configured to search for RFID tags within a range of roughly three to five meters. Emergency vehicles are equipped with passive RFID tags, each of which is programmed with a unique ID that is kept in the microcontroller's memory for authentication.

3. PROPOSED METHODOLOGY

   1. Sensor Setup for Detecting Vehicle Density

      Infrared or ultrasonic sensors were installed on each lane to detect the presence of automobiles. The microcontroller was interfaced with these sensors to enable real-time vehicle counts. The data gathered was used to dynamically optimize the timing of the signals.

   2. Integration of RFID Modules

   Special passive RFID tags were installed in emergency vehicles. In order to read approaching tagged automobiles, RFID readers were installed near intersections. The purpose of the system was to identify and confirm emergency vehicle is present with tags.

   1. Development of Signal Control Algorithms

      To regulate traffic signals based on the number of vehicles on the road, an algorithm was put into place. Automatic signal priority was started by emergency vehicle detection. In order to prevent signal conflicts, safe transition delays were implemented.

   2. Hardware Assembly and Interfacing

      Every component had a modular interface with the microcontroller. Traffic lights (LED-based) were managed using digital pins or relays. Circuits for power supplies were made to operate steadily.

   3. Programming Microcontrollers

      Decision logic and sensor data gathering were programmed using the Arduino IDE. Traffic signal switching and RFID tag authentication were programmed. Reliability and real- time responsiveness were prioritized in the code.

   4. Simulation and Testing

   There were several emergency scenarios and traffic flow simulations.Timing behavior, tag detection accuracy, and system responsiveness were evaluated.The effectiveness of the prioritization mechanism was validated by testing.

4. METHODOLOGY

serial monitor, which provides real-time feedback on the mode switches and sensor readings. Because of its accessibility and ease of use, the Arduino IDE is ideal for rapid prototyping and system testing, allowing for quick optimization and changes throughout the

1. Hardware Description

   Because of its many I/O pins and many serial interfaces, the Arduino Mega 2560 is used as the primary controller in the suggested system. This allows it to handle RFID data, read sensor values, and control traffic lights simultaneously. In order to accomplish certain tasks, such as counting cars using

   infrared or ultrasonic sensors, an Arduino Nano is used as a subordinate unit. I²C is used to communicate with the Mega. To detect passive RFID tags installed on emergency vehicles, the Mega interfaces with the MFRC522 RFID module via SPI. The Mega prioritizes the related channel over standard signal operations when it reads a valid tag. Emergency vehicles are equipped with battery-free passive RFID tags that operate at

   13.56 MHz for identifying purposes. High-brightness red, yellow, and green LEDs are used to simulate traffic lights. These LEDs are powered by transistor-based drivers or current- limiting resistors and are connected to the Mega's digital ports. A 9V12V DC regulated power supply ensures the peripheral modules and microcontrollers operate steadily. A dependable, scalable smart traffic system with dynamic control and emergency response capabilities is made possible by this hardware configuration.

2. Software Description

   1. Arduino Development Environment

      The Arduino Development Environment is an open- source development platform for creating embedded systems and applications based on microcontrollers. Because of its adaptability, user-friendliness, and strong community support, the Arduino platform was selected for the Enhanced Fuel and Electric Mode Transition System (EFEMTS). The development environment's hardware (Arduino boards) and software (Arduino IDE) make it simple to write, compile, and load code into the microcontroller. The Arduino Integrated Development Environment (IDE) is a cross- platform tool that makes programming Arduino boards in the C/C++ language simple and is specifically made to be user-friendly for beginners. The IDE boasts an easy-to-use interface with key features like code suggestions, syntax highlighting, and built-in serial monitoring for debugging. The Arduino board, in particular, was chosen for our project because of its many I/O ports, which are crucial for handling input from a variety of sensors (such as accelerometers, GPS modules for measuring slope, and battery sensors). The microprocessor serves as the central control unit, handling sensor input and controlling the changes in fuel and electric power modes based on preset parameters. The IDE speeds up development by making it easy to add libraries for specific components (such sensors or actuators). Real-time system performance monitoring is also made possible by the development process.

   2. RFID module

      A reader and an electronic tag attached to an object exchange data using radio waves in Radio Frequency Identification (RFID), a contactless identification technology. The RFID tag (or transponder), RFID reader (or interrogator), and antenna are the three main parts of an RFID system. There are two types of tags: passive, which run on the reader's signal without a battery, and active, which have an internal power source for increased range and functionality. RFID operates over various frequency bands, such as low frequency (LF), high frequency (HF), and ultra-high frequency (UHF), each designed for different uses, from inventory tracking and supply chain management to security access control and asset tracking. RFID's advantages include speed of data reading, non-line-of- sight, and the ability to read multiple tags at once, making it a very useful tool in

      automation and real- time identification systems.

3. BLOCK DIAGRAM OF THE PROPOSED SYSTEM

   In order to address these issues, the proposed project uses a combination of infrared or ultrasonic sensors and RFID modules, which are controlled by microcontrollers. Vehicle density is tracked through sensors installed at every road segment that leads to an intersection, counting the number of vehicles and feeding the information to a central microcontroller Arduino Megafor processing. The project aims to implement a smart traffic control system that dynamically adjusts traffic lights according to real-time vehicle concentration and automatically gives priority to emergency vehicles with te aid of RFID technology. At the same time, emergency vehicles are equipped with passive RFID tags with individual identifiers, and an RFID reader, placed ahead of the intersection, continuously scans for tags. When a registered emergency tag is detected, normal traffic flow is overridden, and a green signal is given to the relevant lane, allowing for quick and uninterrupted travel. The Arduino Nano is optionally used for localized tasks like sensor data acquisition, and digital pins and driver circuits drive red, yellow, and green LEDs to simulate traffic lights. The microcontroller dynamically modifies the duration of the signal based on the density, maximizing the flow efficiency. A regulated DC supply powers the whole system, and wireless modules for remote monitoring are optional. The Arduino IDE is used to create logic, offering modular expandability and real-time responsiveness. [image] To test this system's dependability and efficiency, it is put through a variety of simulated traffic and emergency situations. According to the results, the method maximizes regular traffic flow while significantly reducing emergency vehicle response times. It is deployable, scalable, and reasonably priced in emerging cities where emergency delays and traffic congestion are major problems. Overall, the project shows how to integrate intelligent automation into urban traffic management systems in a practical and efficient way.

4. FLOW CHART

Start

The system comes online following a power-up. The hardware components are initialized.

Initialize System (Arduino Mega, Sensors, RFID)

The Arduino Mega initializes all peripherals such as IR/ultrasonic sensors (for density) and traffic LEDs, and the RFID module. Initial configurations and default signal states are stored.

Check for Emergency Vehicle (RFID Reader Scans)

The RFID reader continuously scans for any incoming RFID tags within the vicinity of the intersection.

If a tag is identified, the system then checks if it is for an emergency vehicle.

If affirmative, it moves to the emergency prioritization phase.

If no tag is identified, the system advances to monitor vehicle density

Match with Emergency ID

The tag UID is matched with pre-stored IDs of certified emergency vehicles (ambulance, police, fire truck).

Prioritize Lane (Green Signal for Emergency Vehicle)

In case a valid emergency ID is identified, the system interrupts the regular traffic cycle and automatically turns the light green for the relevant lane immediately.

Wait Until Emergency Vehicle Passes

The system holds the green indication until the emergency vehicle has traveled through the intersection (can be timed or sensor-based).

Resume Normal Operation

After the emergency vehicle clears, the system resumes its normal density-based signal control.

Measure Vehicle Density (Using IR/Ultrasonic Sensors)

In the absence of an emergency, IR or ultrasonic sensors count the number of vehicles queued in each lane.

Calculate Density per Lane

Vehicle sensors (IR or ultrasonic) positioned in each lane measure real-time vehicle count.The data is processed by the microcontroller in order to analyze traffic congestion by direction.Density data are retained and provided as input to assign signal priority.

Set Signal Timing Based on Density

The optimal duration for green light by lane is determined by an algorithm based on vehicle density.Busy lanes receive longer green lights to cut down on waiting times and congestion.Fairness is guaranteed by cyclic rotation of green time to every lane within certain bounds.

Display & Execute Signal Control

Depending on calculated delays, the Arduino controls LEDs as symbols for traffic lights in each lane.Red, yellow, and green LEDs are sequentially fired to mimic real-life traffic lights.Signal statuses are shown live, and motorists are directed appropriately.

Repeat Loop

Upon the end of a signal cycle, the system resets and reassesses the sensor and RFID inputs.In case there is no detected emergency vehicle, the density- based logic is executed again for the subsequent cycle.This cyclical loop secures dynamic adjustment to traffic dynamics. The proposed traffic control system uses intelligent and automated methods to address major municipal issues including traffic congestion and emergency vehicle response delays. Conventional traffic lights operate according to a preset schedule, which leads to less- than-ideal traffic flow and unnecessary waiting. With the use of microcontrollers, Arduino, IR/ultrasonic, and RFID modules, this project offers dynamic traffic light management. Every intersection's vehicle density is measured in real time, and signal timing is dynamically adjusted to provide lanes with more traffic a proportionately longer green light. At the same time, emergency cars are prioritized using RFID technology. Authorized vehicles, such fire engines and ambulances, are equipped with RFID tags that are detected by RFID scanners placed in front of junctions. Following detection, the system assumes management of regular traffic and grants immediate green access to the emergency lane; once the vehicle has passed, normal traffic control resumes. LEDs are used to simulate traffic lights in the real world, and the system uses an Arduino Mega as the primary controller and an Arduino Nano for local sensor inputs. Testing revealed that the setup responded appropriately to various traffic loads and emergency situations, timing signals optimally and promptly resolving emergencies.

Over extended periods of operation, the entire system remained steady, as did the sensor data. Most significantly, there was a significant improvement in emergency vehicle response time, and overall traffic flow became more equal and efficient. Because of its affordability, scalability, and ease of maintenance, the solution may be widely implemented in crowded cities, especially in developing nations. The feasibility and benefits of combining priority with real-time vehicle identification in an emergency are demonstrated by this experiment. It suggests that with minimal human intervention, such technology can automate traffic infrastructure, improve road safety, and reduce delays. Future advancements may include AI-based prediction models or wireless monitoring compatibility to maintain improved performance and robustness.

CONCLUTION

In order to alleviate municipal traffic congestion and improve emergency vehicle response times, a smart traffic management system was successfully created and deployed in this project. Without the need for human intervention, the system dynamically modifies traffic signal timings and prioritizes certified emergency vehicles by utilizing vehicle density sensors and RFID-based emergency vehicle detection. Arduino microcontrollers enabled dependable test-case operations and real-time response. The results demonstrated improved traffic flow efficiency and reduced emergency vehicle waits. The technology is scalable, affordable, and suitable for contemporary cities, especially those in developing nations. All things considered, the initiative is a useful step toward intelligent transportation systems that support public safety and mobility.

Future scope

The traffic control system under discussion provides a solid foundation for managing emergencies and reducing urban traffic patterns. However, there are plenty of opportunities for future improvement and scaling up. Future solutions should include the system into city-level traffic management systems to provide a hub-and-spoke monitoring mechanism and allow the system for multi- lane crossings.Predictive control based on previous occurrences, current data, or the time of day or night may be made possible using machine learning-driven algorithms. Furthermore, a better level of dependability may be achieved by combining RFID and camera-based vehicle identification, such as detecting emergency vehicles without RFID tags or illicit vehicle entry. Remote connections, system alerts, and interaction with the smart city platform would all be made possible by the addition of GSM or IoT modules. In remote or off-grid locations, solar units and power-conscious components can also be used for greenfield rollout.

Finally, the

to emergency vehicles with the aid of RFID technology. At the same time, emergency vehicles are equipped with passive RFID tags with individual identifiers, and an RFID reader, placed ahead of the intersection, continuously scans for tags. When a registered emergency tag is detected, normal traffic flow is overridden, and a green signal is given to the relevant lane, allowing for quick and uninterrupted travel. The Arduino Nano is optionally used for localized tasks like sensor data acquisition, and digital pins and driver circuits drive red, yellow, and green LEDs to simulate traffic lights. The microcontroller dynamically modifies the duration of the signal based on the density, maximizing the flow efficiency. A regulated DC supply powers the whole system, and wireless modules for remote monitoring are optional. The Arduino IDE is used to create logic, offering modular expandability and real- time responsiveness. [image] To test this system's dependability and efficiency, it is put through a variety of simulated traffic and emergency situations. According to the results, the method maximizes regular traffic flow while significantly reducing emergency vehicle response times. It is deployable, scalable, and reasonably priced in emerging cities where emergency delays and traffic congestion are major problems. Overall, the project shows how to integrate intelligent automation into urban traffic management systems in a practical and efficient way.

1. FLOW CHART

Start

The system comes online following a power-up. The hardware components are initialized.

Initialize System (Arduino Mega, Sensors, RFID)

The Arduino Mega initializes all peripherals such as IR/ultrasonic sensors (for density) and traffic LEDs, and the RFID module. Initial configurations and default signal states are stored.

Check for Emergency Vehicle (RFID Reader Scans)

The RFID reader continuously scans for any incoming RFID tags within the vicinity of the intersection.

If a tag is identified, the system then checks if it is for an emergency vehicle.

If affirmative, it moves to the emergency prioritization phase.

If no tag is identified, the system advances to monitor vehicle density

Match with Emergency ID

The tag UID is matched with pre-stored IDs of certified emergency vehicles (ambulance, police, fire truck).

Prioritize Lane (Green Signal for Emergency Vehicle)

In case a valid emergency ID is identified, the system interrupts the regular traffic cycle and automatically turns the light green for the relevant lane immediately.

Wait Until Emergency Vehicle Passes

The system holds the green indication until the emergency vehicle has traveled through the intersection (can be timed or sensor-based).

Resume Normal Operation

After the emergency vehicle clears, the system resumes its normal density-based signal control.

Measure Vehicle Density (Using IR/Ultrasonic Sensors)

In the absence of an emergency, IR or ultrasonic sensors count the number of vehicles queued in each lane.

Calculate Density per Lane

Vehicle sensors (IR or ultrasonic) positioned in each lane measure real-time vehicle count.The data is processed by the microcontroller in order to analyze traffic congestion by direction.Density data are retained and provided as input to assign signal priority.

Set Signal Timing Based on Density

The optimal duration for green light by lane is determined by an algorithm based on vehicle density.Busy lanes receive longer green lights to cut down on waiting times and congestion.Fairness is guaranteed by cyclic rotation of green time to every lane within certain bounds.

Display & Execute Signal Control

Depending on calculated delays, the Arduino controls LEDs as symbols for traffic lights in each lane.Red, yellow, and green LEDs are sequentially fired to mimic real-life traffic lights.Signal statuses are shown live, and motorists are directed appropriately.

Repeat Loop

Upon the end of a signal cycle, the system resets and reassesses the sensor and RFID inputs.In case there is no detected emergency vehicle, the density- based logic is executed again for the subsequent cycle.This cyclical loop secures dynamic adjustment to traffic dynamics.

The proposed traffic control system uses intelligent and automated methods to address

major municipal issues including traffic congestion and emergency vehicle response delays. Conventional traffic lights operate according to a preset schedule, which leads to less- than-ideal traffic flow and unnecessary waiting. With the use of microcontrollers, Arduino,

IR/ultrasonic, and RFID modules, this project offers dynamic traffic light management. Every intersection's vehicle density is measured in real time, and signal timing is dynamically adjusted to provide lanes with more traffic a proportionately longer green light. At the same time, emergency cars are prioritized using RFID technology. Authorized vehicles, such fire engines and ambulances, are equipped with RFID tags that are detected by RFID scanners placed in front of junctions. Following detection, the system assumes management of regular traffic and grants immediate green access to the emergency lane; once the vehicle has passed, normal traffic control resumes. LEDs are used to simulate traffic lights in the

real world, and the system uses an Arduino Mega as the primary controller and an Arduino Nano for local sensor inputs. Testing

Testing revealed that the setup responded appropriately to various traffic loads and emergency situations, timing signals optimally and promptly resolving emergencies. Over

extended periods of operation, the entire system remained steady, as did the sensor data. Most significantly, there was a significant improvement in emergency vehicle response time, and overall traffic flow became more equal and efficient. Because of its affordability, scalability, and ease of maintenance, the solution may be widely implemented in crowded cities, especially in developing nations. The feasibility and benefits of combining priority with real-time vehicle identification in an emergency are demonstrated by this experiment. It suggests that with minimal human intervention, such technology can automate traffic infrastructure, improve road safety, and reduce delays. Future advancements may include AI-based prediction models or wireless monitoring compatibility to maintain improved performance and robustness.

CONCLUTION

In order to alleviate municipal traffic congestion and improve emergency vehicle response times, a smart traffic management system was successfully created and deployed in this project. Without the need for human intervention, the system dynamically modifies traffic signal timings and prioritizes certified emergency vehicles by utilizing vehicle density sensors and RFID-based emergency vehicle detection. Arduino microcontrollers enabled dependable test-case operations and real-time response. The results demonstrated improved traffic flow efficiency and reduced emergency vehicle waits. The technology is scalable, affordable, and suitable for contemporary cities, especially those in developing nations. All things considered, the initiative is a useful step toward intelligent transportation systems that support public safety and mobility.

FUTURE SCOPE

The traffic control system under discussion provides a solid foundation for managing emergencies and reducing urban traffic patterns. However, there are plenty of opportunities for future improvement and scaling up. Future solutions should include the system into city-level traffic management systems to provide a hub-and-spoke monitoring mechanism and allow the system for multi- lane crossings.Predictive control based on previous occurrences, current data, or the time of day or night may be made possible using machine learning-driven algorithms. Furthermore, a better level of dependability may be achieved by combining RFID and camera-based vehicle identification, such as detecting emergency vehicles without RFID tags or illicit vehicle entry. Remote connections, system alerts, and interaction with the smart city platform would all be made possible by the addition of GSM or IoT modules. In remote or off-grid locations, solar units and power-conscious components can also be used for greenfield rollout.

Finally, the

emergency response strategy may be further defined by interaction with local emergency services and law enforcement, which enables the system to autonomously reroute traffic across the city as needed.

REFERENCES

1. Dingding Rong, Yuqi Pang, Peijun Ye, Qingyuan Ji An Agent-Based Traffic Recommendation System: Revisiting and Revising Urban Traffic Management Strategies IEEE access- 2024

2. Aewodros syum gebre AI-Integrated Traffic Information System:A SynergisticApproach of Physics Informed Neural Network and Traffic Estimation and Real-Time Assistance, IEEE access – 2024

3. Hongyan Dui , Songru Zhang IoT-Enabled Real- Time Traffic Monitoring and Control Management for Intelligent Transportation Systems., IEEE Access 2024

4. MY DRISS LAANAOUI1 Enhancing Urban Traffic Management Through Real-Time Anomaly Detection and Load Balancing, IEEE Access – 2023

5. ZUPING CAO, LILI LU Modeling and Simulating Urban Traffic Flow Mixed With Regular and Connected Vehicles, IEEE Access – 2021