Driving style analysis based on information from the vehicle
DOI: 10.19206/ce-2019-330
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study investigates the feasibility of using data from a vehicle’s On-Board Diagnostics (OBD) system to characterize and assess individual driving styles. The research is motivated by the significant impact driving behavior has on fuel consumption, pollutant emissions, and road safety. While previous studies have established that aggressive driving can increase fuel consumption by up to 20% and eco-driving can reduce it by 14%, there is a need for practical methods to quantify these styles using readily available vehicle data. The authors aim to determine which standard OBD parameters are most effective for distinguishing between different driving patterns. The experimental design involved real-world road tests conducted in urban (Warsaw) and extra-urban (Mazowieckie Voivodeship) traffic conditions. Two drivers, designated A and B, operated a 2011 Nissan Juke equipped with a spark-ignition engine. The drivers were instructed to maintain their habitual driving styles without adapting to the experiment. Data was recorded using a Texa OBDLog device connected to the vehicle’s Data Link Connector, capturing signals at a frequency of 1 Hz. The researchers selected specific standard OBD parameters for analysis, focusing primarily on vehicle velocity and the relative position of the accelerator pedal, as these were identified as particularly useful for assessing driving impact. From 494 total trip samples, data was filtered to exclude trips shorter than 180 seconds and those occurring in road congestion, resulting in a final dataset of urban and extra-urban trips for both drivers. The analysis focused on calculating zero-dimensional characteristics derived from the recorded signals, including average and maximum velocity, acceleration, deceleration, and various metrics related to accelerator pedal usage. These metrics were used to generate normalized histograms comparing the driving patterns of Driver A and Driver B across different traffic conditions. The results demonstrated distinct differences in the statistical distributions of these parameters between the two drivers. For instance, variations were observed in average velocity, maximum velocity, and the average relative position of the accelerator pedal, indicating that these OBD-derived metrics effectively capture the nuances of individual driving behaviors. The study concludes that information from the standard OBD system is suitable for assessing a driver’s style. By analyzing specific zero-dimensional characteristics of vehicle velocity and accelerator pedal position, it is possible to differentiate between drivers and characterize their habits. This finding supports the potential application of OBD data in optimizing driver assistance systems, improving fuel efficiency monitoring, and enhancing road safety research by providing a non-intrusive method for evaluating driving behavior.
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: tool software, validation psychometrics, dataset resource