Vehicular Data Space: The Data Point of View
DOI: 10.1109/comst.2019.2911906
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper addresses the critical role of data in Intelligent Transportation Systems (ITS), motivated by the growing economic and environmental costs of traffic congestion and the increasing complexity of vehicular sensor networks. While existing literature often focuses on communication challenges, this work shifts the perspective to the data itself, introducing the concept of the Vehicular Data Space (VDS). The authors aim to provide a holistic survey of ITS services and applications by categorizing the data sources that feed them, thereby highlighting the importance of data availability, quality, and heterogeneous fusion for robust application design. The study employs a comprehensive literature review to construct a taxonomy of the VDS and define a five-stage data cycle: Data Creation, Acquisition, Preparation, Processing, and Use. The authors categorize data sources into two primary groups: Intra-Vehicular Sensors (IVS) and Extra-Vehicular Sensors (EVS). IVS includes data from the Engine Control Unit (ECU) via the On-Board Diagnostic (OBD) port and devices embedded in vehicles, such as probe vehicles and smartphones. EVS encompasses infrastructure sensors (inductive loops, cameras, radars), transit authority data (government statistics on accidents and traffic), publicity data (commercial services like OnStar or Audi Connect), and media sources (social media platforms like Twitter and Waze, as well as radio broadcasts). The paper analyzes how these diverse sources contribute to the VDS, noting that while physical sensors provide operational states, virtual sensors like social media offer real-time, large-coverage information that complements physical infrastructure. Key findings include the identification of specific data types utilized by various ITS applications, such as using ECU data for driver behavior analysis and fuel monitoring, and leveraging social media for incident reporting in areas lacking physical sensors. The authors demonstrate that the VDS encompasses both raw data and contextualized information, with the data cycle serving as a guideline for developing new solutions. The review highlights that while intra-vehicle sensor counts are rising significantly (up to 200 sensors per vehicle by 2020), the integration of heterogeneous data from infrastructure, government entities, and media remains underexplored. The paper also notes specific challenges in data creation and preparation, such as the need for filters and corrections to make raw sensor data usable for processing algorithms. The significance of this work lies in its establishment of the VDS as a unifying framework for understanding the vehicular scenario from a data-centric viewpoint. By outlining the taxonomy and data cycle, the authors provide a structured approach for researchers to identify gaps in data utilization and address open issues related to data creation, processing, and use. The paper concludes that effective ITS development depends not just on communication technologies, but on the careful management and fusion of diverse data sources. This perspective encourages future research to focus on the entire data lifecycle, ensuring that data quality and availability are prioritized to enhance decision-making, safety, and mobility in transportation systems.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | OpenAlex-citations | — | — | 1 | 2026-06-20 |
| archive | success | unpaywall | — | — | 2 | 2026-06-26 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-20 |
| chunk | success | chunk | — | — | 1 | 2026-06-20 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-20 |
| promote | success | — | — | — | 1 | 2026-06-20 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-20 |
| verify | success | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; verification: verified.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Methodological Resource: dataset resource