Dr. Santos Gracia Villar, researcher at the Universidad Europea del Atlántico (European University of the Atlantic, UNEATLANTICO), is participating in a study that presents an innovative approach to detect anomalies on roads in real time with parallel data processing, proposing a solution to manage urban traffic.
Intelligent Transportation Systems (ITS) are essential to effectively manage road traffic, facilitating optimization and information sharing. These systems not only improve the user experience, but are also crucial to the efficient operation of the transportation network. However, with the ever-changing transportation landscape, a significant challenge has arisen in data exchange. The growth of big data and the increase of players in the ITS ecosystem have exposed limitations that make it difficult to effectively address road congestion.
The diversity of vehicles and the increase in their number complicate this communication network. Communication problems are amplified by the variety and quantity of data, while real-time systems become indispensable to improve ITS efficiency. These multifaceted challenges generate concerns about congestion, poorly designed intersections, and transportation incidents, negatively affecting the road infrastructure.
To address these challenges, the emergence of effective traffic management presents itself as a key solution, highlighting the prediction of traffic density on roads and highways. To this end, the study has investigated the different units in ITS and VANET networks, introducing an innovative system to predict high-risk areas. It implements the Lamda architecture in the system to adapt it to real time through continuous data processing. This architecture ensures the system’s ability to respond quickly to changes in traffic, maintaining operational continuity even in the face of failures.
In addition, SUMO, a flexible, open-source urban mobility simulation tool, was used to recreate complex urban traffic scenarios. This tool encapsulates the dynamic interactions between vehicles, pedestrians and urban infrastructure. To ensure the realism of the simulation, a traffic flow pattern consistent with peak and off-peak hours was implemented and meticulously calibrated with real traffic data to improve the reliability and relevance of the results. Also, real-time performance was tested through simulation involving four vehicles with similar origin and destination points.
Experimental results and analysis showed that this system excels in providing users with safe routes to their destinations. It does not rely on predictions of accidents or congestion, but rather provides real-time information on current traffic conditions based on vehicle density and travel time. When it detects high density or anomalies in a particular section, the system reroutes subsequent vehicles to less congested roads, thus ensuring efficient traffic flow.
In addition to its enormous capacity for real-time data processing in intelligent transportation systems, thanks to the integration of advanced Big Data technologies, the main strength of this system lies in its primary focus on road safety. That is, it prioritizes safety over mere travel time reduction, thus significantly improving the safety of road users.
In conclusion, the study contributes a real-time anomaly detection system that works efficiently with parallel data processing. In this way, it offers users safer routes to reach their destinations, making the system a robust tool for effective traffic management on roads and highways.
If you want to learn more about this study, click here.
To read more research, consult the UNEATLANTICO repository.
The Ibero-American University Foundation (FUNIBER) promotes several study programs in the area of technology, such as the Master’s Degree in Strategic Management in Software Engineering. This program is oriented to train dynamic, creative and leading professionals capable of leading business projects focused on the development of software systems.