Driver Identification Based on Spectral Analysis of Driving Behavioral Signals

Nishiwaki, Yoshihiro; Ozawa, Kyoko; Wakita, Toshihiro; Miyajima, Chiyomi; Itou, Katunobu; Takeda, Kazuya

doi:10.1007/978-0-387-45976-9_3

Cited by 27 publications

(24 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They studied their performance on learning a good representation of driving styles from the transformed data inputs. For driver identification, the authors of [6][7][8] have proposed several signal processing approaches using Gaussian Mixture Model (GMM) and different feature selection strategies. To handle the car theft problem, Meng et al [9] have proposed a Hidden Markov Models (HMM) method, coupled with an HMM-based similarity measure, using mainly three features: acceleration, brake, and steering wheel data.…”

Section: Background and Related Workmentioning

confidence: 99%

Who is behind the wheel? Driver identification and fingerprinting

2018

View full text Add to dashboard Cite

In the era of the Internet of Things (IoT), every object can be made smart with embedded sensors, and connected to the internet through wireless technologies. The term "smart" was introduced first for the mobile phone, and the term smartphone was used for the first time in 1999. After 2012, smart watches and other wearable devices became popular. The massive data collected with smart phones and wearable devices offer unprecedented opportunities for human behavior modeling, real-time health monitoring, and personalised services. When people think of IoT, phones, watches, and other small devices often spring to mind. However, automobile manufacturers are now embedding into their vehicles Wi-Fi, global positioning system (GPS) and a bunch of sensors that collect data about the vehicle and the driving behavior. Soon, every car will be connected to its manufacturer, to service companies, to insurance carriers, to its drivers, and to the world around it. Gartner predicts that there will be a quarter of a billion connected vehicles by 2020 [1]. Most cars now have over 400 sensors built into them, capturing data every few milliseconds about steering wheel movement, tire pressure, driver actions, speed, GPS position, car wear and tear, and more. Autonomous cars generate dozens of operational data

show abstract

Section: Background and Related Workmentioning

confidence: 99%

Who is behind the wheel? Driver identification and fingerprinting

2018

View full text Add to dashboard Cite

show abstract

“…Authors in [15,16] represent gas and brake pedal operation patterns with the Gaussian mixture model (GMM). They obtain an identification rate equal to 89.6% using data extracted by a driving simulator and equal to 76.8% for a field test with 276 drivers, resulting in 61% and 55% error reduction, respectively, over a driver model based on raw pedal operation signals without spectral analysis.…”

Section: Related Workmentioning

confidence: 99%

Driver and Path Detection through Time-Series Classification

Bernardi

Cimitile

Martinelli

et al. 2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

Driver identification and path kind identification are becoming very critical topics given the increasing interest of automobile industry to improve driver experience and safety and given the necessity to reduce the global environmental problems. Since in the last years a high number of always more sophisticated and accurate car sensors and monitoring systems are produced, several proposed approaches are based on the analysis of a huge amount of real-time data describing driving experience. In this work, a set of behavioral features extracted by a car monitoring system is proposed to realize driver identification and path kind identification and to evaluate driver’s familiarity with a given vehicle. The proposed feature model is exploited using a time-series classification approach based on a multilayer perceptron (MLP) network to evaluate their effectiveness for the goals listed above. The experiment is done on a real dataset composed of totally 292 observations (each observation consists of a given person driving a given car on a predefined path) and shows that the proposed features have a very good driver and path identification and profiling ability.

show abstract

“…Miyajima et al and Nishiwaki et al [23,24] developed an identification method based on frequency analysis (ceptstrum based) of sensor data collected from two independent experiments; the first experiment used data collected from a driving virtual simulator (86% identification accuracy among 11 subjects), and the second experiment leveraged data previously collected from the CAIR dataset (76.8% identification accuracy among 274 subjects). The CAIR dataset recorded multimedia data such as audio, video and vehicle sensor information as drivers responded to prompted dialogue questions; the main objective of this dataset was to study the humanmachine speech interface during driving behavior [22].…”

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

Driver Identification Based on Spectral Analysis of Driving Behavioral Signals

Cited by 27 publications

References 7 publications

Who is behind the wheel? Driver identification and fingerprinting

Who is behind the wheel? Driver identification and fingerprinting

Driver and Path Detection through Time-Series Classification

Automobile Driver Fingerprinting

Contact Info

Product

Resources

About