Driver identification using driving behavior signals

Wakita, Toshihiro; Ozawa, Kyoko; Miyajima, Chiyomi; Igarashi, Ken; Itou, Katunobu; Itakura, Fumitada

doi:10.1109/itsc.2005.1520171

Cited by 36 publications

(26 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Two other related efforts which investigated the potential to identify drivers in simulated virtual environments were performed by Zhang et al and by Wakita et al [29,31]. Wakita et al reached 73% driver identification among a set of 30 drivers which were instructed to follow a guide vehicle.…”

Section: Related Workmentioning

confidence: 99%

Automobile Driver Fingerprinting

Enev

Takakuwa

Koscher

et al. 2015

Proceedings on Privacy Enhancing Technologies

210

130

View full text Add to dashboard Cite

Today's automobiles leverage powerful sensors and embedded computers to optimize efficiency, safety, and driver engagement. However the complexity of possible inferences using in-car sensor data is not well understood. While we do not know of attempts by automotive manufacturers or makers of after-market components (like insurance dongles) to violate privacy, a key question we ask is: could they (or their collection and later accidental leaks of data) violate a driver's privacy? In the present study, we experimentally investigate the potential to identify individuals using sensor data snippets of their natural driving behavior. More specifically we record the in-vehicle sensor data on the controllerarea-network (CAN) of a typical modern vehicle (popular 2009 sedan) as each of 15 participants (a) performed a series of maneuvers in an isolated parking lot, and (b) drove the vehicle in traffic along a defined ∼ 50 mile loop through the Seattle metropolitan area. We then split the data into training and testing sets, train an ensemble of classifiers, and evaluate identification accuracy of test data queries by looking at the highest voted candidate when considering all possible one-vs-one comparisons. Our results indicate that, at least among small sets, drivers are indeed distinguishable using only incar sensors. In particular, we find that it is possible to differentiate our 15 drivers with 100% accuracy when training with all of the available sensors using 90% of driving data from each person. Furthermore, it is possible to reach high identification rates using less than 8 minutes of training data. When more training data is available it is possible to reach very high identification using only a single sensor (e.g., the brake pedal). As an extension, we also demonstrate the feasibility of performing driver identification across multiple days of data collection.

show abstract

Section: Related Workmentioning

confidence: 99%

Automobile Driver Fingerprinting

Enev

Takakuwa

Koscher

et al. 2015

Proceedings on Privacy Enhancing Technologies

210

130

View full text Add to dashboard Cite

show abstract

“…Related studies revealed that researchers focusing on driver behaviour are divided into two main categories: driver identification and driver action prediction. The first category concentrates on identifying individual drivers or grouping a set of drivers through a suitable set of inputs [8], [9]. Erzin et al [10] presented a system that can detect if the driver is drunk, distracted or fatigued through the user behaviour, in order for assistive action to be taken.…”

Section: A Driver Behaviour For Prediction and Identificationmentioning

confidence: 99%

Predicting car states through learned models of vehicle dynamics and user behaviours

Georgiou

Demiris

2015

2015 IEEE Intelligent Vehicles Symposium (IV)

View full text Add to dashboard Cite

Abstract-The ability to predict forthcoming car states is crucial for the development of smart assistance systems. Forthcoming car states do not only depend on vehicle dynamics but also on user behaviour. In this paper, we describe a novel prediction methodology by combining information from both sources -vehicle and user -using Gaussian Processes. We then apply this method in the context of high speed car racing. Results show that the forthcoming position and speed of the car can be predicted with low Root Mean Square Error through the trained model.

show abstract

“…Modeling, recognition, and classification of driving behaviors have been studied using various statistical and computing methods [7,8]. With the rise of sensor technologies embedded in smartphones, driving behavior signals can be collected and assessed more readily and conveniently.…”

Section: Introductionmentioning

confidence: 99%

“…Thus, developing algorithms for these input signals would widen the deployment of driver identification capability itself. This paper proposes a driver identification algorithm designed to use driving behavior and geolocation signals for real-time applications (e.g., for instantaneous traffic safety purpose [8]). First, an anomaly detection is performed to preliminarily assess if the current driving behavior signals deviate from the expected patterns.…”

Section: Introductionmentioning

confidence: 99%

“…(2) Identifying drivers based on low-level signals using neural network with feature extraction and model construction: the proposed algorithms focus on using low-level signals from inertial sensors found in offthe-shelf devices (e.g., smartphones) unlike previous algorithms which require specialized sensors and/or driving simulators [7,8,[11][12][13][14]. The challenge is that, before being effectively deployed in real-world scenarios, driver identification algorithms will have to learn many distinct behaviors.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Combining Unsupervised Anomaly Detection and Neural Networks for Driver Identification

Tanprasert

Saiprasert

Thajchayapong

2017

Journal of Advanced Transportation

View full text Add to dashboard Cite

This paper proposes an algorithm for real-time driver identification using the combination of unsupervised anomaly detection and neural networks. The proposed algorithm uses nonphysiological signals as input, namely, driving behavior signals from inertial sensors (e.g., accelerometers) and geolocation signals from GPS sensors. First anomaly detection is performed to assess if the current driver is whom he/she claims to be. If an anomaly is detected, the algorithm proceeds to find relevant features in the input signals and use neural networks to identify drivers. To assess the proposed algorithm, real-world data are collected from ten drivers who drive different vehicles on several routes in real-world traffic conditions. Driver identification is performed on each of the sevensecond-long driving behavior signals and geolocation signals in a streaming manner. It is shown that the proposed algorithm can achieve relatively high accuracy and identify drivers within 13 seconds. The proposed algorithm also outperforms the previously proposed driver identification algorithms. Furthermore, to demonstrate how the proposed algorithm can be deployed in real-world applications, results from real-world data associated with each operation of the proposed algorithm are shown step-by-step.

show abstract

Driver identification using driving behavior signals

Cited by 36 publications

References 7 publications

Automobile Driver Fingerprinting

Automobile Driver Fingerprinting

Predicting car states through learned models of vehicle dynamics and user behaviours

Combining Unsupervised Anomaly Detection and Neural Networks for Driver Identification

Contact Info

Product

Resources

About