Driver identification and impostor detection based on driving behavior signals

Martínez, María Victoria Luna; Echanobe, Javier; Campo, I. del

doi:10.1109/itsc.2016.7795582

Cited by 44 publications

(27 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Moreira-Matias and Farah [23] also develop a generic machine learning methodology and feature reduction process. Martínez et al [24] give accuracy above 80% with multisensor data on 11 drivers. A comparative analysis of our work with others is given in Table 12.…”

Section: Discussionmentioning

confidence: 96%

Investigations on Driver Unique Identification from Smartphone’s GPS Data Alone

Chowdhury

Chakravarty

Ghose

et al. 2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

Driver identification is an emerging area of interest in vehicle telematics, automobile control, and insurance. Recent body of works indicates that it may be possible to uniquely identify a driver using multiple dedicated sensors. In this paper, we present an approach for driver identification using smartphone GPS data alone. For our experiments, we collected data from 38 drivers for two months. We quantified the driver's natural style by extracting a set of 137 statistical features from data generated for each completed trip. The analysis shows that, for the "driver identification" problem, an average accuracy of 82.3% is achieved for driver groups of 4-5 drivers. This is comparable to the state of the arts where mostly a multisensor approach has been taken. Further, it is shown that certain behavioral attributes like high driving skill impact identification accuracy. We observe that Random Forest classifier offers the best results. These results have great implications for various stakeholders since the proposed method can identify a driver based on his/her naturalistic driving style which is quantified in terms of statistical parameters extracted from only GPS data.

show abstract

Section: Discussionmentioning

confidence: 96%

Investigations on Driver Unique Identification from Smartphone’s GPS Data Alone

Chowdhury

Chakravarty

Ghose

et al. 2018

Journal of Advanced Transportation

View full text Add to dashboard Cite

show abstract

“…The OBD-II standard has been mandatory for all cars and light trucks sold in the United States since 1996, and the EOBD standard has been mandatory for all petrol vehicles sold in the European Union since 2001 and all diesel vehicles since 2004 [ 19 , 20 ]. A lot of recent research focuses on the analysis of sensor data from the CAN bus system [ 5 , 21 , 22 , 23 , 24 , 25 , 26 , 27 , 28 ].…”

Section: Related Workmentioning

confidence: 99%

Complementary Deep and Shallow Learning with Boosting for Public Transportation Safety

Luo

Leung

Qiu

et al. 2020

Sensors

View full text Add to dashboard Cite

To monitor road safety, billions of records can be generated by Controller Area Network bus each day on public transportation. Automation to determine whether certain driving behaviour of drivers on public transportation can be considered safe on the road using artificial intelligence or machine learning techniques for big data analytics has become a possibility recently. Due to the high false classification rates of the current methods, our goal is to build a practical and accurate method for road safety predictions that automatically determine if the driving behaviour is safe on public transportation. In this paper, our main contributions include (1) a novel feature extraction method because of the lack of informative features in raw CAN bus data, (2) a novel boosting method for driving behaviour classification (safe or unsafe) to combine advantages of deep learning and shallow learning methods with much improved performance, and (3) an evaluation of our method using a real-world data to provide accurate labels from domain experts in the public transportation industry for the first time. The experiments show that the proposed boosting method with our proposed features outperforms seven other popular methods on the real-world dataset by 5.9% and 5.5%.

show abstract

“…The results achieved an accuracy of about 76.9% for a two-driver classification and 50.1% for a five-driver classification. Martinez et al [52] proposed a nonintrusive method for identifying impostor drivers. They relied on a dataset [53] that allowed access to a variety of sensor data.…”

Section: A Intra-vehicular Sensormentioning

confidence: 99%

“…Several studies have focused on driving style and driving maneuvers recognition [39], [41], [42], [43], [46], [49], [51], [52], [54], [56], [79], [81], [82], [84], [88], [91]. Some of these studies identify who the driver is whereas others classify the driver's behavior as aggressive or normal, and driving maneuvers.…”

Section: A Safetymentioning

confidence: 99%

Vehicular Data Space: The Data Point of View

Rettore

Maia

Villas

et al. 2019

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

Over the years, governments and automakers launched initiatives to improve road traffic efficiency, safety, and people mobility. They have been working on various aspects of intelligent transportation systems (ITSs), which aim to improve decision-making, availability of information, and communication technologies to provide applications and services to boost the transportation systems. The development of new applications and services for ITS depends on the availability of different data sources, what it is not the current case. Many studies focus on the communication issues of applications and their associated challenges. To reveal the recent vehicular data use, we examined the most remarkable studies of the last few years, which describe services and applications for ITS, however with a focus on the data employed by them. We introduce the concept of vehicular data space (VDS), which is then used to describe the vehicular scenario from the perspective of data. Moreover, we outline a taxonomy, according to the different data sources. We also categorize the applications, highlighting the data each one used in their approach. Finally, we present some challenges and open issues related to the process for data creation, data preparation, data processing, and data use. In a nutshell, this paper constitutes one of the first holistic surveys on services and applications for ITSs, focusing on the data used by them, as well as their future challenges. Index Terms-Vehicular data space (VDS), vehicular sensor data, connected vehicles, intelligent transportation system (ITS), heterogeneous data, vehicular ad-hoc network (VANET). I. INTRODUCTIONM ORE and more cities will have to deal with significant issues related to transportation and traffic because people and goods are in constant need for quicker and safer mobility modes. The number of fatalities and injuries on the road has achieved an alarming scenario. Globally, 1.3 million people die every year, and up to 50 million suffer severe injuries. These facts have a direct impact on the economics of nations, leading to costs in the order of about 2% to 5% of the Gross Domestic Product (GDP) in many countries [1]. It is also reported that traffic congestion results in critical economic and environmental costs. In 2011, 498 U.S. urban areas were

show abstract

Driver identification and impostor detection based on driving behavior signals

Cited by 44 publications

References 12 publications

Investigations on Driver Unique Identification from Smartphone’s GPS Data Alone

Investigations on Driver Unique Identification from Smartphone’s GPS Data Alone

Complementary Deep and Shallow Learning with Boosting for Public Transportation Safety

Vehicular Data Space: The Data Point of View

Contact Info

Product

Resources

About