Driver behavior profiling: An investigation with different smartphone sensors and machine learning

Ferreira, Jair; Carvalho, Eduardo Atem de; Ferreira, Bruno V.; Souza, Cleidson de; Suhara, Yoshihiko; Pentland, Alex; Pessin, Gustavo

doi:10.1371/journal.pone.0174959

Cited by 183 publications

(118 citation statements)

References 29 publications

Supporting

Mentioning

118

Contrasting

Order By: Relevance

“…Multi-day driving simulator research has shown how to calculate errors scores (based on, e.g., recorded lane keeping inaccuracies) and violations scores per driver [39] (e.g., based on speed, headway, and red light violations [40]). Various on-road studies have shown that it is possible to create a driver risk profile using sensors in smartphones (e.g., accelerometers, GPS) and vehicle sensors (e.g., [41][42][43][44]).…”

Section: Who Makes Errors and Violations?mentioning

confidence: 99%

Will vehicle data be shared to address the how, where, and who of traffic accidents?

et al. 2019

View full text Add to dashboard Cite

Vehicles are increasingly equipped with sensors that measure the state of the vehicle and surrounding road users. Although most of these sensor data currently remain local to the vehicle, the data could be shared with the aim to improve road safety. We postulate that there is a range of scenarios regarding data sharing, with two extremes: In scenario 1, the acquired shared data will be analysed regarding the how, where, and who of road traffic errors, violations, and accidents; actions can then be taken to improve automated driving systems, manage accident hotspots, and provide personalised feedback, rewards, or penalties to road users. In scenario 2, the recorded data will not be shared, because of privacy concerns. We conclude that there exists a tension between a position of utilitarian use of data and a position of privacy.

show abstract

Section: Who Makes Errors and Violations?mentioning

confidence: 99%

Will vehicle data be shared to address the how, where, and who of traffic accidents?

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In different studies, these windows could partially overlap or not overlap at all (Hokkanen et al, 2011;Lush et al, 2016;le Roux et al, 2017). An application example very similar to our approach is the assessment of car driver aggressiveness using continuous data by Ferreira et al (2017). However, to our knowledge, this approach has never been used on burst data in wildlife ecology.…”

Section: Moving Windowmentioning

confidence: 97%

Machine learning goes wild: Using data from captive individuals to infer wildlife behaviour

Rast

Kimmig

Giese

et al. 2019

Preprint

View full text Add to dashboard Cite

ABSTRACTRemotely tracking distinct behaviours of animals using acceleration data and machine learning has been carried out successfully in several species in captive settings. In order to study the ecology of animals in natural habitats, such behaviour classification models need to be transferred to wild individuals. However, at present the development of those models usually requires direct observation of the target animals.The goal of this study was to infer behaviour of wild, free roaming animals from acceleration data by training behaviour classification models on captive individuals, without the necessity to observe their wild conspecifics. We further sought to develop methods to validate the credibility of the resulting behaviour extrapolations.We trained two machine learning algorithms proposed by the literature, Random Forest (RF) and Support Vector Machine (SVM), on data from captive red foxes (Vulpes vulpes) and later applied them to data from wild foxes. We also tested a new advance for behaviour classification, by applying a moving window to an Artificial Neural Network (ANN). Finally, we investigated four strategies to validate our classification output.While all three machine learning algorithms performed well under training conditions, the established methods, RF and SVM, failed in classifying distinct behaviours when transferred from captive to wild foxes. Behaviour classification with the ANN and a moving window, in contrast, inferred distinct behaviours and showed consistent results for most individuals.Our approach is a substantial improvement over the methods previously proposed in the literature as it generated plausible results for wild fox behaviour. We were able to infer the behaviour of wild animals that have never been observed in the wild and to further illustrate the outputs credibility. This framework is not restricted to foxes but can be applied to infer the behaviour of many other species and thus empowers new advances in behavioural ecology.

show abstract

“…In [5] the authors proposed using different Android smartphone sensors and classification algorithms in order to profile driver behavior. Generally, user profiling is a task that includes a preliminary identification of the profiled subject.…”

Section: Introductionmentioning

confidence: 99%

“…Generally, user profiling is a task that includes a preliminary identification of the profiled subject. Moreover, in this survey, the authors analyzed several methods based on machine learning approaches, i.e., artificial neural networks (ANN), support vector machines (SVM), random forest (RF), and Bayesian network (BN) [5]. They confirmed that the gyroscope and the accelerometer are the best sensors to detect the driving behavior (although they confirmed that as general rule, using all sensor axes perform better than using a single one), whereas in terms of…”

Section: Introductionmentioning

confidence: 99%

Deep LSTM with Dynamic Time Warping Processing Framework: A Novel Advanced Algorithm with Biosensor System for an Efficient Car-Driver Recognition

Rundo

2020

Electronics

View full text Add to dashboard Cite

The latest generation of cars are increasingly equipped with driver assistance systems called ADAS (advanced driver assistance systems) which are able to assist the car driver in different driving scenarios, and in the most advanced automation levels, able to take over driving the car if required due to dangerous situations. Therefore, it is essential to adapt the ADAS specifically to the car-driver’s identity in order to better customize the driving assistance. To this end, algorithms that allow correct recognition of the vehicle driver are fundamental and preparatory. In this context, an algorithm for car-driver identity recognition is proposed which allows, with an accuracy close to 99%, recognition of the driver by means of a properly designed pipeline based on the analysis of the car driver PhotoPlethysmoGraphic (PPG) signal. The proposed approach makes use of deep long short-term memory (LSTM) architecture for learning such PPG signal features needed to discriminate one car driver from another. The extended validation and testing of the proposed system confirm the reliability of the proposed pipeline.

show abstract

Driver behavior profiling: An investigation with different smartphone sensors and machine learning

Cited by 183 publications

References 29 publications

Will vehicle data be shared to address the how, where, and who of traffic accidents?

Will vehicle data be shared to address the how, where, and who of traffic accidents?

Machine learning goes wild: Using data from captive individuals to infer wildlife behaviour

Deep LSTM with Dynamic Time Warping Processing Framework: A Novel Advanced Algorithm with Biosensor System for an Efficient Car-Driver Recognition

Contact Info

Product

Resources

About