Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

An Adaptive System Architecture for Multimodal Intelligent Transportation Systems

Muhammad Farooq, Nima Afraz, Fatemeh Golpayegani

TL;DR

This work presents an adaptive, layered architecture for multimodal intelligent transportation systems (M-ITS) designed to tackle data integration, interoperability, scalability, and user experience challenges. It couples a seven-layer system architecture with a six-layer data architecture to enable seamless cross-modal services and robust data governance. The authors illustrate the approach with two use cases—traffic monitoring via magnetic sensors and traffic flow prediction—demonstrating how data and system architectures fuse to support real-time, data-driven decisions. The framework emphasizes modularity, standards-based interoperability (ITS standards), and a cloud-edge continuum to enable scalable, resilient, and user-centric multimodal transportation solutions with practical implications for urban mobility and disaster-response scenarios.

Abstract

Multimodal intelligent transportation systems (M-ITS) encompass a range of transportation services that utilise various modes of transport and incorporate intelligent technologies for enhanced efficiency and user experience. There are several challenges in M-ITS including data integration, Interoperability, scalability, user experience, etc. To address these challenges, such a system requires an adaptive system architecture that enables M-ITS to operate as an integrated ecosystem. In this paper, we provide an adaptive, user-centric, and layered architecture for multimodal transportation systems. The proposed architecture ensures scalability for seamless interactions of various subcomponents, that are often managed by different stakeholders. Concurrently, the data architecture is detailed, covering diverse data sources, advanced analytics, and stringent governance, providing a robust basis for intelligent decision-making. We provide two example use cases of the proposed architecture, showing how the data architecture and the system architecture can be fused and serve multimodal intelligent transport services.

An Adaptive System Architecture for Multimodal Intelligent Transportation Systems

TL;DR

This work presents an adaptive, layered architecture for multimodal intelligent transportation systems (M-ITS) designed to tackle data integration, interoperability, scalability, and user experience challenges. It couples a seven-layer system architecture with a six-layer data architecture to enable seamless cross-modal services and robust data governance. The authors illustrate the approach with two use cases—traffic monitoring via magnetic sensors and traffic flow prediction—demonstrating how data and system architectures fuse to support real-time, data-driven decisions. The framework emphasizes modularity, standards-based interoperability (ITS standards), and a cloud-edge continuum to enable scalable, resilient, and user-centric multimodal transportation solutions with practical implications for urban mobility and disaster-response scenarios.

Abstract

Multimodal intelligent transportation systems (M-ITS) encompass a range of transportation services that utilise various modes of transport and incorporate intelligent technologies for enhanced efficiency and user experience. There are several challenges in M-ITS including data integration, Interoperability, scalability, user experience, etc. To address these challenges, such a system requires an adaptive system architecture that enables M-ITS to operate as an integrated ecosystem. In this paper, we provide an adaptive, user-centric, and layered architecture for multimodal transportation systems. The proposed architecture ensures scalability for seamless interactions of various subcomponents, that are often managed by different stakeholders. Concurrently, the data architecture is detailed, covering diverse data sources, advanced analytics, and stringent governance, providing a robust basis for intelligent decision-making. We provide two example use cases of the proposed architecture, showing how the data architecture and the system architecture can be fused and serve multimodal intelligent transport services.
Paper Structure (53 sections, 5 figures)

This paper contains 53 sections, 5 figures.

Table of Contents

  1. Introduction
  2. Background of multimodal transportation system
  3. Actors and players in the system
  4. Benefits for actors and players
  5. Advantages of an adaptive multimodal transportation system
  6. A Case study: Seamless Urban Commutation
  7. Literature Review
  8. Contributions and paper organisation
  9. Adaptive multimodal transportation system Architecture
  10. Proposed System Architecture
  11. Proposed Data Architecture
  12. Aspects of the proposed adaptive multimodal architecture
  13. Data
  14. Data Sharing Protocols
  15. Data Storage
  16. ...and 38 more sections

Figures (5)

  • Figure 1: An example of an adaptive multimodal transportation system
  • Figure 2: Component level architecture for multimodal transport
  • Figure 3: Data level architecture for multimodal transport
  • Figure 4: Architecture for traffic monitoring system using magnetic sensor use case
  • Figure 5: Architecture for the traffic flow prediction use case