Using AI to Solve Traffic Issues in Saudi Arabia - A Reflection on the ReachInnovation Hackathon
The reaction between water and acids/bases
Figure 1: google meet of the participants and organizing team
Participants: Abdullah Alsubaie, Noura Albaker, Noor Alzayer, Reema Ashour, Murad AlGhamdi
Organizing team: Fatimah Ashour (Director), Jenan Almadeh (Co-Director), Naif Mubarak (ReachInnovation Coordinator)
Proofreader: Hussein A. Yousif (ReachSci Hubs Senior Director)
The hackathon focused on promoting innovation and research translation in Saudi Arabia. Teams worked to develop solutions for pressing issues leveraging available research.
Two teams participated in the hackathon. Team 1 focused on utilizing AI and machine learning to optimize traffic flow and reduce congestion. Team 2 proposed enhancing existing traffic management strategies using real-time data and optimized signage.
The first team's innovation centered on the implementation of AI-Driven Traffic Management (Figure 2). This solution aimed to leverage Artificial Intelligence (AI) to optimize traffic signal control in real-time, with the goal of reducing congestion and enhancing overall traffic management efficiency (Figure 3).
A key citation supporting this approach is the research paper “Application of Artificial Intelligence for Development of Intelligent Transport System in Smart Cities“, which inspired the innovation, highlighting the potential of AI algorithms to dynamically adapt to changing traffic conditions and significantly reduce congestion (1).
Figure 2: Time Plan for Implementing the Innovation
Figure 3: Image Created by the Group to Present Their Innovation
The second team's innovation revolved around the integration of Hard Shoulder Running (HSR) and queue warning systems, particularly relevant for managing traffic during and after accidents. This innovative approach sought to improve energy efficiency by replacing existing fiber optic warning lights with energy-saving LED lights (Figure 4).
Figure 4: LED Warning Lights Concept
Additionally, the team proposed the use of Google Maps data to provide advanced traffic notifications to users, enhancing their overall commuting experience (Chart 1). A significant benefit of this innovation was the potential to minimize traffic accidents and improve safety on Saudi Arabia's roads. This proposed solution was an addition to the research paper titled “Simulation of hard shoulder running combined with queue warning during traffic accident with CTM model” published by one the Institute of Engineering and Technology’s Journals “Intelligent Transport Systems” (2).
Chart 1: Percentage Benefit of Team Innovation Implementation
Reflecting on the potential benefits to Saudi society, both innovations hold the promise of significantly improving the daily lives of commuters. The AI-Driven Traffic Management system could lead to a substantial reduction in journey times, vehicle emissions, and wait times at intersections. This would not only enhance the overall commuting experience but also contribute to a reduction in environmental pollution and stress associated with traffic congestion. The integration of HSR and queue warning systems, combined with the use of Google Maps data, could lead to safer and more efficient traffic management. The reduction in accidents and delays in reaching destinations would not only benefit drivers but also improve overall road safety and reduce societal costs associated with accidents.
In conclusion, these innovative solutions have the potential to bring tangible improvements to the traffic management landscape in Saudi Arabia. While each innovation addresses specific challenges, they collectively contribute to a safer, more efficient, and environmentally friendly transportation system. If implemented, these innovations could pave the way for a brighter and more convenient future for Saudi society, aligning with the country's vision for 2030.
References:
1- Gurjar, J. (2015). Application of artificial intelligence for development of intelligent transport system in smart cities. www.academia.edu. https://www.academia.edu/14424763/Application_of_Artificial_Intelligence_for_Development_of_Intelligent_Transport_System_in_Smart_Cities
2- Li, R., Ye, Z., Li, B., & Zhan, X. (2017). Simulation of hard shoulder running combined with queue warning during traffic accident with CTM model. Iet Intelligent Transport Systems, 11(9), 553–560. https://doi.org/10.1049/iet-its.2016.0345