Traffic Light Control using Sensors and Microcontroller

Traffic Light Control using Sensors and Microcontroller

Shantheeveeran S T

Dept. Robotics and Automation PSG College of Technology Coimbatore, India

Suryah R L

Dept. Robotics and Automation PSG College of Technology Coimbatore, India

Anbarasi M P

Dept. Robotics and Automation PSG College of Technology Coimbatore, India

Abstract Traffic management has become more important nowadays due to rapid urban growth and the rising number of vehicles on roads. Traditional traffic light systems usually operate on fixed time intervals, not considering real-time traffic flow. This often leads to longer wait times, congestion, and fuel wastage. To fix this, sensor-based traffic control systems using microcontrollers provide a smarter and real-time solution. The system monitors traffic situations through sensors and adjusts the signal timings accordingly. Microcontrollers act as the brain, receiving sensor input and managing the signal logic to improve traffic flow. this paper reviews the components, working principle, types, significance, and future scope of traffic light control systems using sensors and microcotrollers.

Keywords Traffic Signal System, Microcontroller, Smart Cities, IR Sensors, Arduino, Dynamic Traffic Management, Real- time Control, Intelligent Transport System (ITS).

1. INTRODUCTION

   In recent years, rapid urbanization and a surge in private vehicle ownership have placed an enormous strain on urban traffic systems. The unplanned expansion of road networks, combined with outdated traffic management strategies, has made congestion one of the most pressing challenges in modern cities. Traffic delays not only lead to increased fuel consumption and air pollution but also cause economic losses and impact emergency services, logistics, and daily commutes. With urban populations expected to grow significantly in the coming decades, cities must transition toward more intelligent, adaptive, and sustainable traffic management systems. Traditional traffic light systems operate on fixed-time intervals that are manually configured based on historical data or empirical assumptions. While these systems may work in low-traffic or predictable environments, they are inherently inefficient in dynamic and high-density urban settings. Fixed cycles often cause unnecessary waiting times on empty roads while failing to provide sufficient green light time where traffic volume is high. This rigid structure results in idling vehicles, longer commute times, higher fuel costs, and elevated levels of greenhouse gas emissions.

   The limitations of conventional traffic systems have led to the growing interest in **Intelligent Traffic Signal Systems (ITSS)** that adapt in real time to current road conditions. These systems leverage embedded electronics, real-time sensors, microcontrollers, and decision-making algorithms to optimize the timing of traffic signals. By continuously monitoring traffic flow and vehicle density, sensor-based systems can assign signal phases more efficiently, reduce idle

   time at intersections, and enhance the throughput of vehicles across busy junctions.

   Microcontrollers play a vital role in modern traffic control systems. They serve as the processing unit that reads input from various sensors, runs algorithms to determine traffic priority, and controls the timing of red, yellow, and green lights. Microcontrollers such as Arduino Uno, Raspberry Pi, and PIC offer cost-effective, programmable solutions that can be scaled for intersections of varying complexity. Their ability to run real-time code makes them suitable for applications requiring fast decision-making and adaptability. Sensors form the backbone of real-time traffic detection. Infrared (IR) sensors are commonly used for short-range vehicle presence detection, especially in low-cost or prototype systems. Ultrasonic sensors offer slightly more range and can detect motion or measure distance to approaching vehicles. Inductive loop detectors, embedded in road surfaces, detect vehicles through electromagnetic signals and are widely used in commercial-grade systems. These sensors continuously feed data to the microcontroller, enabling dynamic adjustment of signal timing. The integration of communication technologies such as Internet of Things (IoT) and Vehicle-to-Infrastructure (V2I) further enhances the effectiveness of adaptive traffic control systems. IoT allows the traffic signal network to share data with centralized servers, enabling predictive analytics, remote control, and integration with smart city platforms. V2I communication allows vehicles and traffic lights to exchange information, potentially giving emergency vehicles priority or guiding drivers through optimized routes.

   In this paper, we propose a smart traffic light control system using IR sensors and an Arduino microcontroller. The system is designed to detect real-time traffic flow in each direction at a four-way intersection and adjust the signal phases accordingly. It dynamically calculates the duration of green lights based on vehicle density, implements a transition phase with yellow lights, and ensures fairness across all directions through a priority-based logic. A prototype is implemented using LED indicators to simulate traffic lights, and the system architecture is designed for modular scalability.

   The rest of the paper is structured as follows: Section II discusses the hardware components and system architecture. Section III outlines the working principle and control logic. Section IV presents the practical significance and benefits of the system. Section V explores the future scope including AI integration and V2X communication. Finally, Section VI provides conclusions and reflections on real-world

   implementation challenges and prospects. This structured approach ensures a logical flow of information from technical.

   1. Valvano, J. W. Embedded Systems: Introduction to the MSP432 Microcontroller

      This foundational text provides a deep understanding of embedded system design using the MSP432 microcontroller, forming the basis for implementing real-time control systems such as traffic signal automation using microcontrollers.

   2. Ramon, M. C. Introduction to Embedded Systems: Using Microcontrollers and the MSP430 This resource complements Valvanos work by focusing on the MSP430 microcontroller, offering insights into sensor interfacing and decision-making logicboth crucial for dynamic traffic signal control.

   3. Rafiquzzaman, M. Microcontroller Theory and Applications with the PIC18F The book explores the architecture and applications of PIC microcontrollers, influencing the design choices and programming logic of microcontroller-based traffic control systems in the study.

   4. Dimitrakopoulos & Zarkesh-Ha Smart Transportation Systems: Vehicular Networks and Applications This reference discusses the integration of vehicular networks into intelligent transport systems, helping frame the importance of sensor communication and real-time data processing in traffic control.

   5. Sigua, R. G. Fundamentals of Traffic Engineering By explaining traditional traffic flow concepts and control mechanisms, this book provides a comparative foundation against which the benefits of sensor-based adaptive traffic systems are evaluated.

   6. Buyya & Dastjerdi Internet of Things: Principles and Paradigms

      The principles of IoT discussed here inform the potental of integrating cloud and networked communication into sensor- driven traffic systems, enabling smart city compatibility and predictive control.

   7. Pallàs-Areny & Webster Sensors and Signal Conditioning

      A technical guide to sensor behavior and signal processing, this book supports the practical design of real-time vehicle detection systems using IR and ultrasonic sensors for accurate traffic input.

   8. Dorf & Bishop Modern Control Systems This control engineering text provides mathematical and system-based insight into automated control logic, which is foundational for creating efficient, responsive traffic signal algorithms.

   9. Forouzan, B. A. Data Communications and Networking

      The networking concepts from this reference assist in understanding how sensor data can be transmitted across connected systems and integrated into broader ITS networks.

   10. Roy & Sinha Machine Learning for Intelligent Transportation Systems

       This work introduces the potential of AI and machine learning in adapting traffic signal behavior based on historical patterns, which aligns with future directions discussed in your paper.

   11. Ahmed & Kanhere Smart Traffic Lights Control Using Vehicular Networks

       This IEEE conference paper demonstrates the effectiveness of vehicle-to-infrastructure (V2I) communication in traffic systems, inspiring ideas for emergency vehicle prioritization and signal forecasting.

   12. Aly, El-Bendary & Hassanien Intelligent Traffic Light Control System Using Fuzzy Logic Their use of fuzzy logic models showcases alternative AI- based decision-making approaches to manage signal timing adaptively, contributing to the algorithmic discussion in your paper.

   13. Rout, Sahoo & Majhi Real-Time Traffic Signal Control System Using Wireless Sensor Networks This study emphasizes low-cost implementation using wireless sensor networks, supporting the feasibility and scalability of microcontroller-based traffic light prototypes in resource-constrained environments.

   14. Sahu & Shakshuki Dynamic Traffic Management Using Vehicular Ad Hoc Networks The research validates the role of VANETs in real-time traffic optimization, offering technical support for dynamic, decentralized traffic light coordination discussed in the system architecture.

2. COMPONENTS AND ARCHITECTURE

   This section outlines the essential hardware components and the system-level architecture used to implement the sensor- based traffic light control system. The design aims for low- cost deployment, modular scalability, and real-time responsiveness suitable for educational applications.

   Arduino Uno

   The Arduino Uno serves as the microcontroller unit (MCU) responsible for reading sensor data, processing traffic logic, and controlling the output signals to the LEDs or actual traffic lights. It is selected for its simplicity, widespread community support, and compatibility with various sensors.

   IR Sensors

   Infrared (IR) sensors are used to detect the presence of vehicles in each lane. These sensors consist of an IR LED and a photodiode that detect reflected light from nearby objects. When a vehicle is detected, the sensor sends a HIGH signal to the Arduino. Each lane is equipped with one IR sensor, and continuous data is sent to the microcontroller for decision- making.

   Figure 1: Basic connection diagram of Arduino-based traffic

   light using LEDs and IR sensor module

   This diagram displays the overall system configuration of the smart traffic light controller. It shows how IR sensors are positioned at each intersection approach, with all sensors connected to an Arduino UNO microcontroller. The Arduino processes input from the sensors and controls the timing logic for each traffic signal. Relay modules interface between the Arduino and the LED indicators representing traffic lights, enabling dynamic light switching as per detected vehicular density.

   LED Traffic Signals

   In the prototype, red, yellow, and green LEDs are used to simulate traffic lights for each lane. These LEDs are controlled by the Arduino via digital output pins. In real- world applications, these outputs would drive relays or high- voltage drivers to operate actual traffic lights.

   Relay Module

   The relay module allows the low-power signals from the Arduino to control higher power circuits, including 12V or 220V traffic light systems. In this setup, relays act as electrical switches that isolate the control circuit from the power supply.

   Power Supply

   A regulated 5V or 12V DC power supply is used to power the entire circuit. The microcontroller and sensors operate on 5V, while external loads such as relay modules and signal lights can be configured to run on higher voltage if needed.

   System Architecture

   The architecture of the system is designed around a four-way intersection. Each direction has its own IR sensor for vehicle detection and a corresponding traffic signal represented by three LEDs. The Arduino receives sensor data in real time, executes a dynamic control algorithm to determine the priority lane, and activates the green light for that lane. Once the countdown timer expires, the system transitions to the next lane in priority order. The core control logic operates in an infinite loop and checks the sensor status every few milliseconds. If no vehicle is detected in a particular direction, that lane is skipped or assigned minimal green time to avoid unnecessary delays. Yellow lights are turned

3. WORKING OF THE COMPONENTS

   The sensor-based traffic light control system works by linking together inputs, processing, and outputs. Sensors placed on different lanes of a junction keep detecting the presence or number of vehicles. these signals are sent to a Microcontroller, which runs a decision-making algorithm to manage the signal timings. The goal is to cut down extra waiting time, use green lights smartly, and keep traffic moving smoothly. Signal Detection and Processing: Each lane has sensorsusually Infrared (IR), Ultrasonic, or Inductive Loop sensors. these sensors either check if a vehicle is there (yes/no) or count how many there are. here's how the detection works: When a vehicle comes close, the sensor sends info to the Microcontroller. The Microcontroller checks all the sensor

   data every short while (like every 100 ms). It compares the traffic in all directions.Then it decides how long each green light should stay on, based on the data. Microcontroller Logic Execution: The Microcontroller runs a real-time control process that usually follows these steps:Initialization Phase all input/output pins are set, sensors are turned on, and timers reset. Data Collection reads sensor inputs to find out where vehicles are and how many. Priority Calculation the lane with the most vehicles gets green first. If the traffic is about the same on two or more lanes, it uses round-robin or some weight- based logic. Signal Switching: green light turns on for the chosen lane. red lights go on for the rest. a countdown timer runs for the green light. Transition Phase before switching, yellow light shows up for 35 seconds to warn drivers. Next Cycle once the timer ends, control moves to the next lane in priority.

   Traffic Adaptation Logic: This system supports dynamic timing. For example: If Lane A has 10 vehicles and Lane B has 2 vehicles: Lane A might get 30 seconds of green light.Lane B gets only 10 seconds. If no vehicles are detected on a lane, it is skipped or given minimal green time to maintain the cycle. Emergency Vehicle Detection (Optional Feature): Some advanced versions use sound sensors or RF modules to detect emergency sirens or signals from ambulances, fire trucs, or police vehicles. Upon detection, the Microcontroller overrides the normal sequence. The signal is instantly switched to green for the emergency lane. Once the vehicle passes, normal operation resumes.Pedestrian Crossing Integration: Push buttons are used for pedestrian crossings. When a pedestrian presses the button: The Microcontroller checks if its safe to allow pedestrian crossing. If yes, all vehicle signals are turned red, and a pedestrian green signal is activated. A countdown timer is displayed to alert pedestrians of remaining time. The system reverts to vehicle signals after the crossing window ends. System Responsiveness and Speed: One of the key advantages of using Microcontrollers is their ability to respond quickly. The cycle of reading sensor input, decision-making, and output switching happens within microseconds to milliseconds, depending on the processor clock speed. this rapid response is essential in managing real- time traffic conditions.

   Figure 2: Prototype of a Traffic Signal Control System

   This schematic depicts the wiring details for connecting IR sensors, relay modules, and LEDs to the Arduino platform. Each IR sensor is wired to a dedicated digital input pin, while each relay is controlled via output pins. The figure helps illustrate the clear separation and coordination of signal detection and actuation in the prototype.

4. IMPORTANCE OF SENSOR BASED TRAFFIC LIGHT SYSTEM

   The implementation of sensor-based traffic light systems marks a significant advancement over traditional fixed-timing systems by introducing intelligent, adaptive control into traffic management. These systems are designed to respond to real- time traffic conditions using sensor inputs to dynamically manage the duration of signal phases. Unlike conventional systems that run on static intervals, smart traffic lights detect the presence or density of vehicles in each lane and allocate green light time accordingly. This adaptive behavior reduces unnecessary waiting times and optimizes the movement of vehicles through intersections. As a result, vehicle idle times decrease, the average speed across junctions improves, and driver frustration caused by inefficient signals is significantly reduced. By minimizing stop-and-go scenarios, such systems contribute to better traffic flow and urban mobility, especially during peak hours or unpredictable surges in traffic volume. In addition to improving efficiency, sensor-based traffic systems play a crucial role in reducing environmental impact and enhancing public safety. Vehicles idling at intersections consume excess fuel and emit harmful gases such as carbon dioxide (CO) and nitrogen oxides (NO), which contribute to air pollution and global warming. By streamlining traffic flow and eliminating unnecessary stops, intelligent signals directly help in lowering fuel consumption and greenhouse gas emissions. Moreover, these systems can be equipped with special modules to detect emergency vehicles such as ambulances or fire trucks. Upon detection, the system overrides the normal signal pattern to grant immediate right- of-way, allowing emergency responders to reach their destinations faster. This ability to prioritize emergency traffic not only reduces response times but can also be life-saving in critical situations. Additionally, pedestrian safety is improved through features like push-button crossings, visual and audible countdown timers, and adaptive signal extensions for individuals with mobility challenges, making intersections safer and more inclusive.

   These systems are also designed to operate efficiently during nighttime and off-peak hours when traffic volume is low. Traditional systems continue to cycle signals regardless of vehicle presence, but sensor-based systems can skip or shorten green time for empty lanes, reducing energy waste and preventing late-night accidents. Their compatibility with smart city frameworks and the Internet of Things (IoT) ecosystem further enhances their value. They can share data with centralized traffic management servers, work in tandem with surveillance cameras and pollution monitors, and feed

   real-time traffic information to AI systems for predictive analytics. While the initial deployment cost of such intelligent systems may be higher than that of static counterparts, the long-term economic and environmental benefits are considerable. These include reduced congestion-related losses, lower fuel subsidies, and fewer health costs due to improved air quality. In academic and technological domains, these systems serve as rich platforms for education and innovation, offering hands-on opportunities in microcontrollers, embedded systems, automation, AI, and data analytics.

5. REAL TIME IMPLEMENTATION

   The real-time prototype of the intelligent traffic light control system was constructed using low-cost components, including IR sensors, an Arduino Uno microcontroller, and LED indicators to simulate traffic lights. Each IR sensor was positioned to monitor a separate lane of a four-way intersection, detecting vehicle presence in real time. The Arduino continuously read sensor data and processed it using a priority-based control algorithm. When a vehicle was detected in a lane, the system dynamically adjusted the signal duration to minimize idle time and ensure smoother vehicle movement. The entire system was powered by a 5V regulated power supply, and the logic was coded using the Arduino IDE. A transition phase using yellow LEDs was introduced between green and red phases to mimic real-world signaling behavior. The control loop executed every 100 milliseconds, ensuring rapid response to changing traffic patterns. During testing, the prototype demonstrated clear improvements over fixed-time cycles by reducing unnecessary green-light durations and eliminating idle red-light periods when no vehicles were present. The modular design allows for easy scaling and integration of additional features such as pedestrian buttons, emergency vehicle prioritization, or IoT connectivity. The real-time responsiveness and adaptability of the system validate its applicability in urban intersections with fluctuating traffic volumes.

   Figure 3: Overhead ultrasonic traffic sensors detecting vehicle presence and density in multiple lanes

   This image shows the assembled hardware prototype on a breadboard. The setup includes an Arduino UNO board, several IR sensors positioned at the mock intersection, relay modules, and LED traffic lights for each direction. The physical arrangement demonstrates a scaled-down but functional system for real-time traffic flow detection and signal management.

6. APPLICATIONS

   Sensor-based traffic light control systems have a diverse and expanding range of applications across urban, semi-urban, and rural areas, where traffic flow exhibits significant variability throughout the day. These intelligent systems leverage real-time data collected from various sensors, such as infrared, ultrasonic, or inductive loop detectors, to dynamically adjust signal timings and optimize traffic management. In smart cities, these systems form an integral part of intelligent transport infrastructure. Rapid urbanization and increasing vehicle ownership have led to congested road networks that demand efficient solutions. By deploying sensor-based traffic lights at key intersections, cities can significantly reduce traffic jams, shorten travel times, and improve overall commuter experience. These adaptive systems help decrease fuel consumption and carbon emissions by minimizing unnecessary idling and stop-and-go driving patterns, contributing directly to environmental sustainability goals. In the realm of emergency management, sensor-based traffic light control plays a vital role in facilitating the swift movement of emergency vehicles. Integrating specialized detection modulessuch as sound sensors capable of picking up sirens or RF transceivers linked to ambulance and fire truck transmittersenables the ystem to recognize the approach of emergency responders. The traffic lights then prioritize these vehicles by granting immediate right-of-way, thereby reducing response times and potentially saving lives.

   For pedestrian safety, sensor-based systems can incorporate interactive features such as push-button crossing controls and countdown timers. These enhancements ensure that pedestrians, especially vulnerable groups like children, the elderly, and individuals with disabilities, can cross streets safely and confidently. The system can also detect pedestrian presence through infrared or pressure sensors, activating crossing signals only when necessary to balance vehicle flow and pedestrian movement. During off-peak hours or nighttime, when traffic volumes are low or uneven, sensor- based traffic lights intelligently adjust green phases or even skip them for empty lanes. This dynamic adjustment not only conserves electrical energy but also reduces the risk of accidents caused by inappropriate signal timing in low-traffic conditions.

   Beyond traffic control, these systems can integrate with broader urban management frameworks. By interfacing with urban planning software, municipal authorities can analyze traffic patterns to inform infrastructure development and policy decisions. When connected to surveillance cameras, these systems enhance security and can monitor compliance with traffic rules. Integration with pollution monitoring devices allows cities to correlate traffic flow with air quality data, facilitating targeted actions to reduce emissions and

   promote sustainable urban living. From simple educational kits to complex municipal installations, microcontroller- driven adaptive traffic light systems represent a transformative step in intelligent transportation systems, paving the way for safer, more efficient, and environmentally friendly urban mobility.

   Figure 4: Visualization of sensor-based traffic monitoring at an intersection

   The flowchart represents the logical steps of the dynamic traffic light control algorithm, including sensor data acquisition, priority determination, timer countdown, and lane switching. The flowchart outlines the logic sequence implemented in the Arduinos programming. Beginning with continuous sensor monitoring, the algorithm determines traffic densities, assigns green light priorities, manages timing cycles for each approach, and controls transition to yellow and red phases. The chart provides a visual summary of the adaptive decision-making process of the smart controller.As cities continue to urbanize and vehicle density increases, sensor-based and intelligent traffic control systems are expected to play a central role in shaping the future of mobility. The integration of advanced technologies such as artificial intelligence (AI), Internet of Things (IoT), cloud computing, and 5G connectivity is opening new horizons for traffic management. The future scope of sensor-based traffic light control systems includes the following transformative directions: Integration with Smart Cities and IoT: Future traffic lights will become key components in smart city networks, interconnected through IoT. These systems will: Communicate with central traffic servers. Share real-time traffic flow data for city-wide optimization. Enable predictive analysis using historical data trends. AI and Machine Learning-Based Optimization: With the help of machine learning algorithms, traffic lights can learn from: Past traffic patterns. Time-of-day and seasonal variations.These ai- powered systems will be able to self-adjust dynamically, making data-driven decisions without needing manual reprogramming. In the long run, they may even evolve to forecast traffic congestion before it happens. vehicle-to- infrastructure (V2I) communication: With the development of connected vehicles and autonomous driving systems, future

   traffic lights will: Communicate directly with vehicles (V2I). Send signal status and timing information to vehicle dashboards. Receive data about approaching traffic directly from cars. Prioritize high-occupancy or electric vehicles based on policy. This two-way communication will result in smoother navigation, reduced accidents, and improved energy efficiency. adaptive traffic control systems (ATCS): ATCS will allow traffic lights to be completely flexible and decentralized. Each junction will: Operate independently based on local data. Coordinate with neighboring intersections for synchronization. This will be especially useful in metropolitan cities where traffic behavior can be highly unpredictable. Integration with cloud and edge computing: Sensor data from multiple intersections will be collected and analyzed using: Cloud computing for large-scale traffic data analysis. Edge computing at the intersection level for real-time decision- making. This hybrid setup ensures both speed and long-term insight generation. enhanced emergency and disaster response: In the future, traffic systems may: Automatically reconfigure routes in case of accidents, fire, or natural disasters. Communicate with drones and rescue robots. Enable dynamic evacuation routes during large-scale emergencies. Renewable energy and sustainable design: Future traffic control systems may be: Powered by solar panels with battery backup. Designed with low-power electronics to reduce energy footprint.

   Figure 5: Smart Traffic Signal System Using Vehicle Detection and Microcontroller Integration

   This figure presents graphical or simulated results of the traffic light operation under varying input conditions. It may show timing charts for green lights based on detected traffic volume or snapshots from simulation software. The visualization confirms the systems ability to dynamically adjust signal timings and demonstrates its efficiency versus traditional fixed-cycle controllers.

7. CONCLUSION

   Traffic light control using sensors and microcontrollers represents a significant breakthrough in modern urban traffic management. Traditional traffic light systems, which operate on fixed timers and predetermined cycles, often fail to respond effectively to real-time traffic conditions. In contrast, sensor-based traffic control systems utilize a variety of data inputssuch as vehicle presence, traffic density, and pedestrian movementto dynamically adjust signal timings. This adaptive approach not only optimizes traffic flow but also significantly reduces unnecessary delays and congestion at intersections.

   The integration of microcontrollers as the core processing units allows for precise, real-time decision-making and seamless communication between sensors and traffic signals. These compact embedded systems offer high reliability, low power consumption, and flexibility in programming, making them ideal for deployment in diverse traffic environments. Advancements in sensor technologies, such as infrared sensors, ultrasonic detectors, and camera-based vision systems, have enhanced the accuracy and scope of traffic monitoring. Combined with the growing capabilities of artificial intelligence and machine learning algorithms, modern traffic light control systems can predict traffic patterns, adapt to sudden changes, and even prioritize emergency vehicles or public transport, thereby improving overall road safety.

   As urban populations continue to grow and cities strive to become smarter and more sustainable, sensor and microcontroller-based traffic control systems are poised to become indispensable components of smart city infrastructure. By enabling more efficient traffic management, these technologies contribute to reduced fuel consumption, lower emissions, and enhanced quality of life for city residents. The future of urban mobility is increasingly dependent on such intelligent, responsive traffic solutions that keep pace with the evolving demands of modern transportation networks.

8. REFERENCES

1. J. W. Valvano, Embedded Systems: Introduction to the MSP432 Microconroller, 1st ed., Jones & Bartlett Learning, pp. 1620, 2017.

2. M. C. Ramon, Introduction to Embedded Systems: Using Microcontrollers and the MSP430, Newnes Press, pp. 1450, 2012.

3. M. Rafiquzzaman, Microcontroller Theory and Applications with the PIC18F, Wiley-IEEE Press, vol. 1, pp. 1576, 2011.

4. G. Dimitrakopoulos and P. Zarkesh-Ha, Smart Transportation Systems: Vehicular Networks and Applications, Springer, Smart City Series, pp. 23198, 2021.

5. R. G. Sigua, Fundamentals of Traffic Engineering, 2nd ed., Univ. of the Philippines Press, Dept. of Civil Engineering, pp. 12325, 2008.

6. R. Buyya and A. V. Dastjerdi, Internet of Things: Principles and Paradigms, Morgan Kaufmann Publishers, Computer Science Series,

   pp. 5420, 2016.

7. R. Pallàs-Areny and J. G. Webster, Sensors and Signal Conditioning, 3rd ed., Wiley-Interscience, IEEE Instrumentation Series, pp. 9638, 2012.

8. R. C. Dorf and R. H. Bishop, Modern Control Systems, Pearson Education, 13th ed., Control Engineering Series, pp. 331102, 2016.

9. B. A. Forouzan, Data Communications and Networking, 5th ed., McGraw-Hill, Network Communications Series, pp. 11262, 2012.

10. P. K. Roy and G. R. Sinha, Machine Learning for Intelligent Transportation Systems, Springer, Lecture Notes in Electrical Engineering, vol. 750, pp. 15272, 2020.

11. M. A. Ahmed and S. S. Kanhere, Smart traffic lights control using vehicular networks, Proc. 2016 IEEE 84th Vehicular Technology Conf. (VTC-Fall), Montreal, Canada, pp. 15, 2016.

12. N. M. Aly, M. M. El-Bendary, and A. E. Hassanien, Intelligent traffic light control system using fuzzy logic, Proc. 13th Int. Conf. Intelligent Systems Design and Applications (ISDA), pp. 153158, 2013.

13. S. K. Rout, A. K. Sahoo, and B. Majhi, Design and implementation of a real-time traffic signal control system based on wireless sensor networks, Proc. Int. Conf. Information Technology (ICIT), pp. 16, 2014.

14. P. K. Sahu and E. H. M. Shakshuki, A dynamic traffic management system based on vehicular ad hoc networks, IEEE Trans. Intelligent Transportation Systems, vol. 16, no. 5, pp. 25572569, Oct. 2015.

15. T. D. Nguyen, T. V. Pham, and H. V. Pham, An IoT-based adaptive traffic signal control system using reinforcement learning, Proc. 2020 6th Int. Conf. Green Technology and Sustainable Development (GTSD),

pp. 100105, 2020.