Machine Learning-Enhanced Traffic Light Optimization System Prioritizing Emergency Vehicle Passage Using SVM and Random Forest Models

With the growing population, traffic congestion in cities is one of the most urgent concerns. Congestion not only causes additional delay and stress for the driver but also increases fuel consumption and pollution. The existing traffic management system does not offer priority when emergency vehicles are seen because it is a timer-based traffic control system. Ambulances, fire trucks, and other emergency vehicles are unable to arrive on time because of the traffic jams on the roadways. So, in order to reduce traffic congestion in daily life, our proposed methodology measures the density of vehicles at a 4-way junction. In the absence of emergency vehicles, the proposed system gives green light automatically based on the density of vehicles on the road. The traffic light changes according to the signal emitted by the sensor. Using an RF transmitter and receiver, the signal priority is switched to the lane in which an emergency vehicle is present. This system incorporates the entire traffic system and operates in emergency scenarios to ensure quick arrival at the desired location without any delay.

The paper describes the design of an intelligent auto traffic signal control system. Traffic congestion is the major issues that would be considered. At the junctions of the road, vehicular traffic intersects and it can be controlled by the traffic signals. One of the main need of the traffic signal is that good coordination and control among the vehicles. The traffic on the road is very high during the peak hours. This leads to the emergency vehicles to stick in the traffic jam. Dynamic control of traffic is needed during peak hours. Hence we propose an automatic traffic light control for emergency vehicles. The traffic light in the path of any emergency vehicles is controlled. It does not depend on the way of monitoring people to be manual which results in time delay. So, Human life is not affected due to the time delay in the arrival emergency vehicles. To control the traffic, the man power is not required in this method. The emergency vehicles find the shortest path to the location of the accident. If the train crosses the junction, the emergency vehicle gets alerted before five km. In front of the zebra line crossing, a divider can be created for safety crossing of people. The system uses AT mega 8micro controller, IR sensors. This system is used to control the traffic lights. And also save the time in emergency periods.

Traffic congestion has become a major problem in the cities where the population and the number of vehicles are continuously increasing. To ensure the safety of people, traffic light systems are incorporated at all necessary intersections of roads. Most of the traffic control systems used are now working based on fixed time for vehicular movement. So, a smart traffic control system is built which changes the waiting time of the vehicles based on situations, conditions, and priorities. Smart traffic system considers the vehicular density and special conditions such as the presence of an emergency vehicle at any of the roads and increases the waiting or clearance time accordingly. The system works such that, more the density of traffic at any side of the road, the longer would be the clearance time of that road with an increase in the duration of green light so as to allow more vehicles to pass through and hence reduce the traffic density. This avoids traffic congestion, wastage of time, and makes the system more efficient. A priority is given to the passage of emergency vehicles to prevent delays due to traffic congestion. So, the system is built such that during the presence of an emergency vehicle, the traffic light remains green till the emergency vehicle passes the signal and then returns to normal working. The system also considers the prevention of accidents and safety of the pedestrians during the night, when the traffic signals have only Amber lights, by use of sensors to detect any presence. The traffic lights along with alarms are used to indicate such presence. The system is built using Proteus software as a simulation tool for single-way and four ways traffic signals. Thus, the proposed work aims for a better and efficient traffic control system.

This project presents the Design of Emergency RFID Traffic Light Systems using the Ultra High-Frequency RFID reader as a detector to control the traffic light system. This project focused on emergency vehicles such as ambulances, firefighters, and police to get on smooth journey at a congested area with traffic light. The proposed way of detection is with RFID tags located at the emergency vehicles to generate emergency traffic lights system. The project established communication between traffic signals and emergency vehicles so that traffic signals can respond to the arrival of these emergency vehicles and respond accordingly. The findings shows that the emergency vehicles recommended speed of around 50km/h while approaching the traffic light. In addition, the distance during approaching the RFID reader does not exceed 7 meters to allow the RFID tag of emergency vehicles can be read clearly. When traffic signals change allowing emergency vehicles to move quickly past traffic with less hassle.

Traffic lights at crossroads help regulate the flow of vehicles so they can run smoothly and avoid congestion. One of the causes of traffic congestion is a traffic control light system that is not optimal because it still uses a fixed timer system, so the lights' duration is less efficient in its application. When the green light is on, the streets are deserted. But there is a traffic jam on another road. Therefore the concept of traffic light timing needs to be developed to get efficient timing. This study aims to create a traffic light control system that uses a PIR (Passive Infrared) motion sensor and an ultrasonic sensor based on the Arduino Mega2560 microcontroller based on the congestion level. The method used in this traffic control prototype is an experimental method of reading vehicle objects mounted with PIR sensors and ultrasonic sensors. This system can detect the movement of vehicles approaching a traffic light, measure the distance between the car and the traffic light, and set the timing of the light signal according to the level of congestion detected. This system has been tested using vehicle movement simulations brought closer to the PIR and ultrasonic sensors at different distances. The test results show the system can work properly and produce the light signal according to the detected traffic conditions. For its application to traffic lights in the future, it is feasible to help the traffic unit.

The current traffic light system uses a lot of fixed time signals. Fixed time signals cause traffic jams in one or several lanes due to traffic congestion. On the other hand, emergency vehicles cannot get their rights to the maximum due to the density of these vehicles. This study aims to build an intelligent traffic light with a vehicle density sensor device and a smartphone application to increase the accuracy of light timing and parse traffic density. Furthermore, in an emergency, they can still overcome and accelerate the speed of passing vehicles by manually intervening with the traffic light through a smartphone application connected wirelessly to the traffic light. The intelligent traffic light is made with Arduino Bluetooth Control (ABC), Bluetooth HC-05, Arduino Mega 2560, and infrared (IR) sensor E18-D80NK. The results show that the green light setting is based on the input from the IR sensor both near sensor (NS) and far sensor (FS) work well. When NS detects a vehicle with a green light, it increases Y seconds from the default X seconds. If FS detects a vehicle with a green light, it increases by Z seconds. Settings with the ABC application can randomly turn on the green light in four lanes according to the will of the smartphone operator.

The expansion of technology in metropolitan centers draws people to cities, which causes excessive traffic on the roadways during peak hours. This exacerbated the traffic situation, resulting in a delay, a loss of resources, and a waste of time. Like any other metropolitan metropolis, Riyadh, Saudi Arabia, has everyday traffic congestion during business hours. The current traffic management has made many attempts to ease traffic congestion in cities; despite these measures, the problem has not been solved adequately. To handle this road congestion, there is a need to appropriately store the big data collected by traffic sensors and utilize it for efficient traffic management employing cutting-edge technology. This study provides an architecture for a smart traffic management system that uses modern technologies such as the Internet of Things (IoT), cloud computing, 5G, and big data to aid conventional traffic management systems and efficiently handle the stated problem. The proposed technique has the potential to reduce traffic congestion significantly. Our proposed solution encourages mobility by using roadside messaging agents to offer real-time traffic information on traffic congestion and unexpected traffic incidents. Citizens will save time by getting these early warning messages, particularly during peak hours. As part of the suggested method, each signal dashboard gets traffic information. A case study is used in the research to evaluate alternative solutions to traffic congestion. The case study results show that the proposed strategy outperforms the present options.

Over the years, traffic lights have been used to manage traffic at road intersections. Though relatively effective, the vehicular queues that build up at each intersection being managed by a traffic light and the subsequent delay thereof, could have adverse effects on medical emergency vehicles (EVs). Reports have shown that queues at traffic intersection can increase travel times of medical EVs by an average of 20%. This in many instances could mean the difference between life and death. Prioritizing EVs could be a potential solution to this challenge. In this paper, an Internet of Things based priority preemption model for EVs in smart cities is proposed. It leverages on sensors to dynamically track the EV’s location and speed, and adaptively adjusts the timing sequence of all traffic lights on the EV’s path. This ensures that the EV experiences little or no delay to and from its destination. Experimental results show that the proposed model has the potential to reduce travel delays experienced by medical EVs by up to 35%.

Traffic congestion is a major concern in urban centers, as it can affect society, the environment, and the economy. There are many studies on the use of computational intelligence (CI) to improve mobility in urban centers. Some of these researches focus on developing strategies for traffic light programming, since traffic coordination is complex due to its many parameters, variables, and dynamic behavior, and also an inefficient traffic control plan can lead to increased delays and contribute to traffic congestion. Although there are many works in the literature on strategies for traffic control, there are still some contributions and gaps to be filled, especially because some studies do not consider the automatic optimization of traffic signals in real time, that is, according to the demand of vehicles on the roads, considering multiple objectives and the use of a network of intersections in their experiments. In addition, some of the proposed models are not independent of simulation to evaluate the solutions of CI algorithms, resulting in a more complex deployment in real situations. In this context, this paper presents a new method to optimize traffic light plan in a network of intersections and in real time, called Active Control of Traffic Signals (ACTS) associated with the Non-Dominated Sorting Genetic Algorithm, considering multiple objectives in the optimization process (minimizing the average delay time and the number of vehicles stops per cycle). To test the applicability of the model, a real dataset of vehicle demand collected by the Company of Transport and Traffic of Belo Horizonte (BHTrans) is loaded into the AIMSUN simulator, then the method is applied and compared with the current traffic control plan used by BHTrans. The results show that the ACTS method reduces the average vehicle delay by almost half compared to the results obtained with the current solution used by BHTrans. In real life, this means less time spent in traffic, which promotes faster traffic flow, reducing traffic congestions.

Accident rescue is an important topic for life saving and emergent handling. One issue of accident rescue is how to shorten the times for emergency vehicles (such as ambulances, fire engines, and police cars) to arrive at accident scenes so that the emergent events can be properly processed. For example, an ambulance should arrive at a traffic accident scene as fast as it can so that the wounded can be taken care of as soon as possible. However, in metropolitan areas traffic jams may make emergency vehicles difficult to arrive at the accident scenes. This is because cars on the roads may not have enough space to move themselves to empty a lane for the pass-through of emergency vehicles. In this condition, the valuable time for rescuing injured people or extinguishing fire will be wasted due to undesired traffic jams, which may result in unrecoverable tragedies. To solve this problem, in this thesis we propose a traffic control mechanism based on the IEEE 802.11p/1609 radio technology to control the traffic condition and traffic lights to shorten the time required by emergency vehicles to arrive at accident scenes. In the proposed mechanism, a traffic control center is deployed to monitor the traffic conditions on the roads and provide the traffic information for emergency vehicles. The traffic control center can dynamically adjust the traffic lights on the roads to help emergency vehicles arrive at accident scenes more quickly. Our simulation results show that the proposed mechanism can significantly reduce 30% to 50% arrival times required by emergency vehicles to arrive at accident scenes in our evaluated cases.

Traffic light control systems are widely used to monitor and control vehicles’ flow to provide a smooth and orderly flow of traffic by controlling which lane should be granted to pass through the intersection point without compromising on safety standards. However, a conventional traffic light system handles neither dynamic traffic flow nor the prioritization of emergency vehicles (EVs). Consequently leads to congestion as the conventional traffic light grants underutilized road lanes to have the equal cycle length as a congested lane and possibly causes an accident and delay when multiple EVs are approaching the intersection. This paper proposes an intelligent system that dynamically adjusts the cycle length for each of the lanes at an intersection based on the vehicular density and grants the different types of EVs to pass through the intersection point by assigning different priorities. The system consists of three modules, the traffic light control module, the emergency Radio-frequency identification (RFID) moduleandtheinternetmodule. Thetrafficlightcontrolmoduledetectsvehiculardensityusing ultrasonicsensorsandassignsadynamicsetofcyclelengthbasedontheindividuallanedensity condition. TheemergencyRFIDsareinstalledon differenttypesofEVsbasedonthepreset priority weights. The internet module allows the dynamic traffic light system to be controlled by authorized personnel in a real-time application.

In major cities throughout the world, traffic congestion is still a major problem that negatively affects the efficiency of transportation system. Traffic congestion creates several issues that require a creative and adaptable strategy to solve. This work tackles the problem by accurately forecasting vehicle density by merging state-of-the-art deep learning models, specifically YOLO - v8 for real-time vehicles identification and Stacked Long Short-Term Memory (LSTM) models for forecasting traffic density. These methods are combined to create a powerful vehicle density prediction system. The integration of YOLOv8 with LSTM provides a practical response to the growing issues brought on by traffic congestion in cities. The simulation results shows that accuracy of YOLOv8 is 95.36, while average RMSE value of Stacked LSTM models is 0.591. The proposed model is compared with RNN model for vehicle density forecasting and the proposed model performs better than RNN in terms of accuracy.

Disorganized city planning and a huge rise in use of automobiles on the road have caused massive traffic congestion in cities across the world. Pedestrian crossing designed to facilitate movement across the road network, have unfortunately become a hindrance to movements of traffic. Though the smart zebra lines had been introduced, it has not contributed much to reduce the time that holds vehicle lines under the traffic lights. Moreover, the establishment of transfer hubs and underground crossings remain silent in local context because of their cost. Even though there are plenty of pedestrian crossing mechanisms available, they are not secure and not ideal for the disabled, elderly, children, and the sick. Considerable numbers of police officers have to spend their time on traffic controlling duties though it’s inefficient and wastage of human resources. A number of studies have focused on automated vehicles and robots as tools to ease problems of congestion. This paper, it focuses on the design of an automated guided carriage system for pedestrian transportation in an efficient and secure manner.

Urban transformations resulting from technological and economic changes have contributed to the emergence of a pattern of urban dispersion. Rapid transportation based on private cars, along with investment in road networks and the decline in land values on the outskirts of cities, have helped to create the phenomenon of urban sprawl and expansion. This has led to the absence of connectivity between city areas and the separation of residential, industrial, office, retail, and recreational areas. In contrast, concerns have escalated about traffic congestion in cities, increased greenhouse gas emissions, and increased energy consumption allocated to transportation, which has enhanced interest in active mobility patterns as a sustainable solution. Therefore, the problem of our research is that the urban transportation planning process in the city of Kufa is characterized by randomness and lack of sustainability principles, with neglect of the vital role of urban transportation and its effects on the health and psychological state of the city's residents and its association with economic aspects. The research assumed that following the principles of the active city and applying them in the city's urban transportation plans contributes to improving the quality of life for residents and addressing the problems associated with urban transportation in the city of Kufa. The research aims to evaluate the current urban transportation system according to the principles of the active city. The study concluded that the horizontal extension of the city of Kufa, the abundance of infrastructure for private vehicles, and long travel distances led to a reduction in reliance on active transportation. The design of residential neighborhoods in the city of Kufa encourages horizontal extension. It lacks a strategy of urban compactness or compaction, which forced the residents of the city of Kufa to rely primarily on private motorized transportation in the process of transportation, and with a direct relationship that increased environmental impacts and run-over accidents. The absence of encouragement and education, along with social customs, made active transportation in the city of Kufa socially unpopular. Therefore, the planning of residential neighborhoods must be reconsidered, better communication must be provided, and infrastructure for walking and cycling must be provided according to the guidelines of sustainable urban planning. The wider spread of economic activities throughout the city may increase active travel and reduce the use of private motorized vehicles.

This chapter provides an in-depth overview of the state of the art on traffic light control and optimization. Several classical control systems, methods, concepts, tools, and strategies are described, and their related pros and cons are discussed. Four different types of control strategies are considered, pretimed, actuated, adaptive, and self-organized, and it is demonstrated that some strategies can be appropriate for local control, area control, or both (local and area). Further, the chapter develops a system of coupled nonlinear oscillators, that is used for traffic light control and optimization both at isolated junctions (i.e., local control) and in a network of coupled traffic junctions (i.e., area control). The case of an isolated traffic junction is modeled by coupled oscillators, each of which represents a specific phase group of the traffic light at the junction. The case of a network of coupled traffic junctions is also considered, and we show the possibility of modeling the traffic light at each junction by a single oscillator. The system developed is viewed as a modified version of the self-organized Kuramoto model for traffic light control due to some important features that are common to both systems (i.e., Kuramoto model and the system developed). The main advantage of the system developed is the possibility of dynamically monitoring the signals’ phases (delays), signal-splits, or signal timings according to the dynamic variation of the traffic demand in all conflicting approaches of the traffic junctions under investigation. The system of coupled nonlinear oscillators is considered a flexible platform, which is appropriate for modeling the four types of traffic light control strategies. Another advantage of the system developed is the possibility of an easy hardware implementation using electronic devices. This allows a straightforward possibility for designing appropriate electronic prototypes of traffic light controllers (appropriate for both local and area controls).