775 research outputs found
IOT-Driven accident detection and notification system with smart speed cameras for traffic signal optimization in vehicular environments
No full textIn our rapidly urbanizing world, the movement of goods, people, and services is greatly facilitated by transportation infrastructure. Each year, lost resources, higher fuel consumption, and increased pollution result in billion-dollar costs associated with traffic congestion, accidents on the roads, and inefficiencies in the transportation systems.
The road network is under pressure due to the increase in the urban population, and innovative solutions are needed to increase road safety. To improve road safety but also to increase the smooth flow of traffic, automatic accident detection systems as well as the traffic light optimization system must be implemented.
Both systems use the latest technology, artificial intelligence (AI), machine learning, as well as the Internet of Things (IoT). The automatic accident detection system focuses on real-time accident detection to inform emergency services as quickly as possible to minimize injuries and deaths, while the traffic light optimization system focuses on improving traffic flow, so that there is unimpeded passage of emergency vehicles, which are directed to the incident location. This technology not only saves lives but also helps the overall performance of urban and intercity transportation systems.
This thesis studies how these two systems can be implemented in the future to increase road safety and reduce emergency response times, as so far, the times are quite high.
In this way, this thesis offers several contributions to the field of traffic management as well as the management of a traffic accident. The research presented in this thesis tries to highlight the problem using real evidence from the Aegean Motorway and focuses on creating a system that will try to close various gaps from previous attempts to create a similar system.
The research highlights the importance of integrating emerging technologies such as IoT, AI, and ML into traffic control systems in a bid to mitigate growing issues such as traffic congestion, accidents, and ineffective transit. Automatic Accident Detection System (AADS) utilizes sensors, cameras, and intelligent algorithms to detect accidents in real time and alert rescue teams in a timely fashion. By making accurate accident data available to first responders, this rapid response can also minimize the severity of injuries and fatalities. The Traffic Light Optimization System (TLOS), on the other hand, optimizes the timing of traffic lights according to traffic flow to minimize congestion and maximize the overall efficiency of the city's transportation networks.
Although AADS and TLOS can and do provide many advantages, there are some challenges associated with their adoption, as highlighted by the study. High cost, privacy and data concerns, and the need for robust communication infrastructure are significant drawbacks that must be overcome. Public acceptance is also a key factor in the implementation of these technologies. While people know the possible benefits of AADS and TLOS in reducing traffic congestion and improving road safety, they also have concerns regarding the efficiency, cost, and privacy of the systems. Public education and resolution of these concerns are very important steps towards gaining more acceptance of the technologies.
The study also highlights the environmental benefits of TLOS as it can be utilized for the reduction of car emissions and fuel usage as well as traffic flow optimization. The study includes an analysis at the Agia interchange, which illustrates how the application of TLOS can reduce travel time and waiting time in traffic. For AADS and TLOS to be effective, several stakeholders, including city or state citizens, policymakers, and industry professionals, must be involved in the implementation of the systems to address the challenges and build trust. By continuously improving such systems, it is possible to move towards more sustainable, efficient, and safe transportation solutions.
First, in this specific research, a literature review was conducted so that we could understand exactly how these systems work, as well as find implementations of systems around the world. It was also very important to highlight the pros and cons of these systems.
Then, a microscopic analysis was carried out through the VISSIM, in a specific area of the highway, to determine the problems that may be created by the existence of traffic lights, such as e.g. the increased travel times as well as the increased queues that can also lead to traffic accidents.
This specific analysis could not be missing from a survey that aimed to understand how familiar drivers are with these systems, as well as their perception of them. Finaly, to complete this specific research, we tried to create an application as well as a system that would have the ability to inform all parties involved in the event of an accident and would have the ability to provide information that was previously unknown and was a deterrent in dealing with traffic accidents.
Regarding the results, this specific research came to fill the gaps that had been found during the literature review. The existence of an application that contains all the necessary information for the most appropriate response to a traffic accident is now a fact. This system can in the future become a "car black box" which, with the appropriate connection to the car, can even provide information about the weather
Autonomous Driving and Connected Mobility Modelling: Smart Dynamic Traffic Monitoring and Enforcement System for Connected and Intelligent Mobility
No full textAutonomous Driving and Connected Mobility Modelling: Smart Dynamic Traffic Monitoring and Enforcement System for Connected and Intelligent Mobility
No full textThe Importance of Implementation of Traffic Light Optimization System: Greece Case Study
No full textIn recent years, vehicle traffic has become a major issue, with a significant increase in the number of vehicles leading to congestion on urban roads and motorways. This has resulted in an increase in accidents, causing more injuries and fatalities. In particular the cases with seriously injured road users who may not survive due to traffic congestion delaying emergency services. This paper tries to analyse the importance of the response time of the emergency services during road accidents, using real data from a hybrid environment (motorway and urban road). The presented model in this research aims to identifying the traffic problems, where the traffic lights are found to cause congestion issues and high travel times, even with low traffic volumes. The implementation of a traffic lights optimization system can be a crucial element in survival chances. The study also shows that an increase in traffic volume leads to drastic traffic congestion, highlighting further the importance of the traffic light optimization system
Automatic Accident Detection System Using IoT Compared to the Systems that a Traffic Centre Uses for Accident Detection
No full textIn recent years, vehicle traffic has become a major issue with a significant increase in the number of vehicles, leading to congestion on urban roads and motorways. This has resulted in an increase in accidents, causing more injuries and fatalities. There are many steps in managing an accident, it can be said assuring that one of the most important steps is the rapid detection of the incident and its exact location. Quick and accurate information enables emergency services to act quickly at the incident location and reduce their response times. This paper tries to compare the automatic accident detection system with traditional traffic center systems and analyze the importance of implementing this system to reduce accident detection times and accurately detect their location. The detection of the accident time and its location are crucial links in the accident management chain
The Importance of Implementation of Traffic Light Optimization System: A Greece Case Study
No full textThe Importance of Implementation of Traffic Light Optimization System: A Greece Case Study
No full textCloud Computing Security and Deep Learning: An ANN approach ScienceDirect Cloud Computing Security and Deep Learning: An ANN approach
No full textDeep learning techniques have shown significant impact in enhancing security across various domains by leveraging artificial neural networks models. When applied to cloud computing security, deep learning offers cost-effective solutions by automating threat detection, reducing manual monitoring, and improving overall security effectiveness. Deep learning models using neural networks play crucial role in tasks like intrusion detection, malware detection, anomaly detection, and log analysis. Integration of deep learning into cloud security requires careful evaluation of existing systems, defining objectives, dataset selection and preparation, model tuning, and eventual modifications for compatibility. Furthermore, implementing deep learning techniques in cloud security entails considering factors such as computational resources, data collection and preparation costs, model development, integration efforts, and ongoing monitoring and maintenance. This paper proposes a feed-forward propagation Artificial Neural Network (ANN) model in cloud security and investigates the key steps for integrating such models into cloud security strategies. Considering that the effectiveness of the ANN model depends on factors such as training data quality, network architecture, and weight adjustment algorithms, the study utilizes a dataset from Kaggle.com for validation and demonstrates steps involved in training and evaluation of the ANN model. Abstract Deep learning techniques have shown significant impact in enhancing security across various domains by leveraging artificial neural networks models. When applied to cloud computing security, deep learning offers cost-effective solutions by automating threat detection, reducing manual monitoring, and improving overall security effectiveness. Deep learning models using neural networks play crucial role in tasks like intrusion detection, malware detection, anomaly detection, and log analysis. Integration of deep learning into cloud security requires careful evaluation of existing systems, defining objectives, dataset selection and preparation, model tuning, and eventual modifications for compatibility. Furthermore, implementing deep learning techniques in cloud security entails considering factors such as computational resources, data collection and preparation costs, model development, integration efforts, and ongoing monitoring and maintenance. This paper proposes a feed-forward propagation Artificial Neural Network (ANN) model in cloud security and investigates the key steps for integrating such models into cloud security strategies. Considering that the effectiveness of the ANN model depends on factors such as training data quality, network architecture, and weight adjustment algorithms, the study utilizes a dataset from Kaggle.com for validation and demonstrates steps involved in training and evaluation of the ANN model
Artificial Intelligence based Smart Traffic Enforcement and Management System in urban areas
No full textIn the urban environment, traffic congestion has become a significant concern. Congestion negatively influences the economy, the environment, and the quality of life in general. Unfortunately, traditional traffic control systems fail to control traffic discipline due to inadequate human resource management and limited extension of current infrastructure, resulting in increased traffic congestion and road infractions. This paper aims to create an intelligent system dashboard to make judgments on its own, detect congested areas and actual congestion locations, and plan alternative routes. The system should collect all available data from different cities and create forecasts based on the previous year's data. The designing Artificial Intelligence traffic controllers in our proposal can adapt to current data from sensors to perform constant optimizations on the signal timing plan for intersections in a network to minimize traffic congestions by using real-time traffic data, which is the main issue in traffic flow control today. A new technology known as Radio Frequency Identification (RFID) has been introduced , which can be used in conjunction with the existing signalling system to provide real-time smart traffic control. Traffic congestion will be decreased as a result of the use of this innovative technology. In addition, bottlenecks and traffic violations will be spotted early, allowing for early preventative actions to be implemented, saving the motorist time and money. Long-term decision-making is aided by traffic monitoring, mainly when designing transportation plans and budgets. It also helps law enforcement agencies identify the different types of traffic and take appropriate precautions, such as installing security cameras and other control mechanisms
Evaluating the Impacts of Autonomous Vehicles’ Market Penetration on a Complex Urban Freeway during Autonomous Vehicles’ Transition Period
No full textAutonomous vehicles (AVs) have been a rapidly emerging phenomenon in recent years, with some automated features already available in vehicles. AVs are expected to potentially revolutionize the existing inefficient state of urban transportation and be a step closer to environmental sustainability. This study focuses on simulation modeling in assessing the potential effects of autonomous vehicles (AVs) and on mobility and safety by developing a framework model based on traffic microsimulation for a real network located in Al-Madinah, Saudi Arabia. The market penetration rates (MPRs) will not reach 100% in the near future; instead, penetration will progressively increase. As a result, in our study, we investigated the potential effect of AV technology in five different AV market penetration rates: 0% (baseline), 25%, 50%, 75%, and 100%. The results suggest that Avs significantly improve the network’s safety and operational performance at high penetration rates. Specifically, estimated vehicle delays decreased by 26%, 34.4%, 63.7%, and 74.2% for 25%, 50%, 75%, and 100% AV penetration rates, respectively. Finally, we think this study will help decisionmakers over in the long-term in their attempts to achieve sustainable development through the optimal integration of innovative and novel technologies
- …
