How hospitals response to disasters; a conceptual deep reinforcement learning approach

Mirbakhsh, Ardeshir

doi:10.21203/rs.3.rs-2715241/v1

Cited by 2 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Lee et al developed a multi agent control system based on classic physics model know as spring-mass-damper model. This study revealed that multi agent approach suits well not only for advanced machine learning based models, but also in dealing with conventional and classic models [23].…”

Section: Multi-agent Systemmentioning

confidence: 90%

Artificial Intelligence-Based Real-Time Traffic Management

2023

J Electrical Electron Eng

View full text Add to dashboard Cite

The paper proposes applying the ant colony optimization algorithm within a distributed multi-agent architecture, leveraging IoT technology, to address path routing challenges in urban traffic. The study emphasizes the potential of advanced AI techniques and multi-agent systems in revolutionizing traffic management for efficient and sustainable urban transportation systems. Our study addresses the challenging issue of traffic congestion in modern urban areas and the limitations of traditional solutions like road expansion and network indicators. To effectively tackle traffic congestion, the study explores various strategies that analyze traffic elements, falling into the Macroscopic and Microscopic Models. However, conventional traffic modeling faces significant challenges in dealing with complex traffic systems. The rise of the Internet of Things (IoT) offers opportunities for effective traffic analysis by collecting vast and uncertain data. Nevertheless, most existing systems focus on local events, leaving a gap in their effectiveness. To address this, multi-agent systems become a novel strategy, deploying distributed agents across road intersections for comprehensive traffic management. Artificial Intelligence (AI) techniques, including fuzzy logic, evolutionary algorithms, neural networks, and reinforcement learning, emerge as promising solutions for traffic control. For instance, artificial neural networks accurately predict urban traffic flow, and meta-heuristic AI approaches like the artificial bee colony algorithm optimize signal timings.

show abstract

Section: Multi-agent Systemmentioning

confidence: 90%

Artificial Intelligence-Based Real-Time Traffic Management

2023

J Electrical Electron Eng

View full text Add to dashboard Cite

show abstract

“…A combination of Transportation Engineering-based policies with conceptual deep reinforcement learning has been used by Mirbakhsh et al to optimize ambulance dispatch in a pandemic or natural disaster circumstances [2]. Dresner et al divided the intersection area into an n×n grid of reservation tiles.…”

Section: Literature Reviewmentioning

confidence: 99%

Enhanced Automated Intersection Control for Platooning AVs: A Fusion Model with Significant Traffic, Safety, and Environmental Improvements

2023

J Electrical Electron Eng

View full text Add to dashboard Cite

An automated intersection control system for platooning AVs is developed by combining an existing AVs platooning model and a known intersection control system for AVs. The proposed model remarkably improves traffic and safety measures, specifically in extreme volume regimes compared to the regular DSCLS model. This model outperformed the other AV-based intersection control systems in traffic measures with a 9% delay reduction and 18% maximum throughput increment. The safety and environmental measures were also remarkably improved by the proposed model.

show abstract

How hospitals response to disasters; a conceptual deep reinforcement learning approach

Cited by 2 publications

References 7 publications

Artificial Intelligence-Based Real-Time Traffic Management

Artificial Intelligence-Based Real-Time Traffic Management

Enhanced Automated Intersection Control for Platooning AVs: A Fusion Model with Significant Traffic, Safety, and Environmental Improvements

Contact Info

Product

Resources

About