Electronic records of undesirable driving events

Musicant, Oren; Bar-Gera, Hillel; Schechtman, Edna

doi:10.1016/j.trf.2009.11.001

Cited by 32 publications

(23 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Musicant et al [12] acknowledge the vast amounts of data that IVDRs generate, and use this argument to motivate why much of the research is directed towards identifying only extreme events from the raw data. The result is much less information to process in evaluating a particular driver.…”

Section: Literaturementioning

confidence: 99%

“…Musicant et al [12] note that temporal factors influence the number of harsh driving events. They identified both the time of day, and day of week as playing a significant role in predicting the number of harsh driving events.…”

Section: Researchmentioning

confidence: 99%

“…Unfortunately accidents are primarily attributed to driver behaviour. To study safety, Musicant et al [12] argue that we can use extreme driving events such as harsh braking and acceleration, improper turning and swerving as surrogates for safety: a high frequency of undesirable events is a direct indication of risky and unsafe driving.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Combining accelerometer data and contextual variables to evaluate the risk of driver behaviour

Joubert

Beer²,

Koker

2016

Transportation Research Part F: Traffic Psychology and Behaviou

View full text Add to dashboard Cite

Telemetry devices are generating and transferring increasingly more data, with notable potential for decision makers. In this paper we consider the accelerometer and speed data produced by in-vehicle data recorders as a proxy for driver behaviour. Instead of extracting harsh events to cope with the large volumes of data, we discretise the data into a tractable and finite risk space. This novel methodology allows us to track both acceptable and non-acceptable driving behaviour, and calculate a more comprehensive risk model using the envelope of the data, and not a priori thresholds. We show how thresholds suggested in literature can characterise some driving behaviour as good, even though our empirical evidence has not even registered such extreme driving behaviour.We demonstrate the model using accelerometer data from 124 vehicles over a one month period. Three rules, each a combination of accelerometer and/or speed data, are applied to the risk space to derive person-specific scores that are comparable among the individuals. The results show that the scoring is useful to identify specific risk groups. The proposed model is also dynamic in that it dynamically adjusts to the observed records, instead of data having to abide by a limited model specification.

show abstract

Section: Literaturementioning

confidence: 99%

Section: Researchmentioning

confidence: 99%

See 1 more Smart Citation

Combining accelerometer data and contextual variables to evaluate the risk of driver behaviour

Joubert

Beer²,

Koker

2016

Transportation Research Part F: Traffic Psychology and Behaviou

View full text Add to dashboard Cite

show abstract

“…CloudThink is an unbiased data broker that ensures customers' data is securely transferred to application clients who process the data to produce benefits for drivers. In doing so, it highly emphasizes user privacy, an important yet often neglected issue particularly in telematics (Duri et al, 2004(Duri et al, , 2002Iqbal and Lim, 2010;Musicant et al, 2010). The strategy guiding the research and development of CloudThink is modelled after the highly successful approach taken by Sanjay Sarma to standardize RFID technology in founding the Auto-ID labs and its corresponding industry organization EPCglobal which provided a much-needed link between research and industrial commercialization (Sarma, 2004).…”

Section: Introductionmentioning

confidence: 99%

Cloudthink: A Scalable Secure Platform for Mirroring Transportation Systems in the Cloud

et al. 2015

View full text Add to dashboard Cite

Abstract. We present a novel approach to developing a vehicle communication platform consisting of a low-cost, open-source hardware for moving vehicle data to a secure server, a Web Application Programming Interface (API) for the provision of third-party services, and an intuitive user dashboard for access control and service distribution. The CloudThink infrastructure promotes the commoditization of vehicle telematics data by facilitating easier, flexible, and more secure access. It enables drivers to confidently share their vehicle information across multiple applications to improve the transportation experience for all stakeholders, as well as to potentially monetize their data. The foundations for an application ecosystem have been developed which, taken together with the fair value for driving data and low barriers to entry, will drive adoption of CloudThink as the standard method for projecting physical vehicles into the cloud. The application space initially consists of a few fundamental and important applications (vehicle tethering and remote diagnostics, road-safety monitoring, and fuel economy analysis) but as CloudThink begins to gain widespread adoption, the multiplexing of applications on the same data structure and set will accelerate its adoption.

show abstract

“…Researchers have also found the information logged by them helpful in discovering new information about behavior. For example, the rate of undesirable driving events was found to be higher at the beginning and end of trips (Musicant, Bar-Gera and Schechtman, 2010) and for young drivers with sensationseeking tendencies (Prato, Lotan and Toledo, 2010). Parental behavior was linked to novice driver behavior, and parental involvement was linked to a reduction in the events rate (McGehee, et al, 2007, Prato, Lotan andToledo, 2009).…”

Section: Introductionmentioning

confidence: 99%

Integrating Kinematic- and Vision-Based Information to Better Understand Driving Behaviour

Musicant

Toledo

Lotan³

et al. 2011

Proceedings of the 6th International Driving Symposium on Human Factors in Driver Assessment, Training, and Vehicle Design : Dr

Self Cite

View full text Add to dashboard Cite

Summary:This study explored the use of two types of advanced driver assistance systems (ADAS) as tools for observing driving behavior. The first was a kinematic-based ADAS that uses speed and acceleration data to detect driving events such as hard braking, speeding and sharp turning. The second was a visionbased ADAS that uses video data to provide lane departure warnings (LDW), headway warnings (HW) and forward collision warnings (FCW). Data was collected for more than 4,500 trips and 2,200 driving hours during a period of 70 days. The sample consisted of 10 drivers that used both types of ADAS simultaneously. The information collected also included more than 17,000 records of various types of driving events. First, the events rates were estimated by the Poisson and the Poisson-lognormal models. Then, Pearson correlation and factor analysis were implemented to study the relationships among the events and to evaluate whether different types of events converged to describe the same behaviors. Significant correlations were observed between the braking and turning kinematic-based events and the FCW vision-based event, which converged under the same factor. High rates of these events may indicate that the person is driving in an urban style. The LDW, HW and speeding events converged to the second factor, which is more relevant in inter-urban areas. These findings, although based on a small-scale study, point to a potential for the use of commercial ADAS for driving behavior analysis. The integration of kinematic-based and vision-based information can provide deeper understanding of the measured behavior.

show abstract

Electronic records of undesirable driving events

Cited by 32 publications

References 11 publications

Combining accelerometer data and contextual variables to evaluate the risk of driver behaviour

Combining accelerometer data and contextual variables to evaluate the risk of driver behaviour

Cloudthink: A Scalable Secure Platform for Mirroring Transportation Systems in the Cloud

Integrating Kinematic- and Vision-Based Information to Better Understand Driving Behaviour

Contact Info

Product

Resources

About