TY - JOUR
T1 - How Smartphone Accelerometers Reveal Aggressive Driving Behavior? - The Key is the Representation
AU - Carlos, Manuel Ricardo
AU - Gonzalez, Luis C.
AU - Wahlstrom, Johan
AU - Ramirez, Graciela
AU - Martinez, Fernando
AU - Runger, George
N1 - Funding Information:
Manuscript received August 25, 2018; revised April 17, 2019; accepted June 21, 2019. Date of publication July 16, 2019; date of current version July 29, 2020. The work of M. R. Carlos and L. C. González was supported by Google Inc., under a Latin American Research Award. The Associate Editor for this paper was L. Li. (Corresponding author: Luis C. González.) M. R. Carlos, L. C. González, G. Ramírez, and F. Martínez are with the Facultad de Ingeniería, Universidad Autónoma de Chihuahua, Chihuahua 31125, Mexico (e-mail: lcgonzalez@uach.mx).
Publisher Copyright:
© 2000-2011 IEEE.
PY - 2020/8
Y1 - 2020/8
N2 - Aggressive driving behavior is one of the leading causes of road accidents worldwide. One way to ameliorate this situation is to collect and analyze driving patterns with the intention of promoting driving awareness, a task that has been called driving analytics (DA). DA employing the driver's smartphone has attracted attention from the community given its good capabilities to capture, via its integrated sensors, data that could be exploited to infer driving style. Most works in the related literature have represented this sensor information either as statistical scores or in raw format that are later fed into threshold-based heuristics or machine learning (ML) approaches. Based on the hypothesis that better data representations do exist, in this paper, we propose a second-order representation, based on the bag-of-words' strategy, to model accelerometer timestamps associated with aggressive driving maneuvers. We evaluate this representation in two scenarios and three data sets against the best reported work in each of them. In the first scenario, we classify accelerometer samples as either belonging to aggressive or safe driving style. In the second scenario, we approach a multi-class problem, where we are now interested in identifying the exact aggressive maneuver that the accelerometer sample represents. The results show that this novel representation outperforms both state-of-the-art works with 6% and 15% in F-measure for each scenario, respectively. To further investigate the strength of our representation, we make a comparison against similar second-order strategies that have also proved to be successful. Overall, this analysis suggests that this representation constitutes an attractive method for driving behavior classification, boosting discriminative performance of ML approaches.
AB - Aggressive driving behavior is one of the leading causes of road accidents worldwide. One way to ameliorate this situation is to collect and analyze driving patterns with the intention of promoting driving awareness, a task that has been called driving analytics (DA). DA employing the driver's smartphone has attracted attention from the community given its good capabilities to capture, via its integrated sensors, data that could be exploited to infer driving style. Most works in the related literature have represented this sensor information either as statistical scores or in raw format that are later fed into threshold-based heuristics or machine learning (ML) approaches. Based on the hypothesis that better data representations do exist, in this paper, we propose a second-order representation, based on the bag-of-words' strategy, to model accelerometer timestamps associated with aggressive driving maneuvers. We evaluate this representation in two scenarios and three data sets against the best reported work in each of them. In the first scenario, we classify accelerometer samples as either belonging to aggressive or safe driving style. In the second scenario, we approach a multi-class problem, where we are now interested in identifying the exact aggressive maneuver that the accelerometer sample represents. The results show that this novel representation outperforms both state-of-the-art works with 6% and 15% in F-measure for each scenario, respectively. To further investigate the strength of our representation, we make a comparison against similar second-order strategies that have also proved to be successful. Overall, this analysis suggests that this representation constitutes an attractive method for driving behavior classification, boosting discriminative performance of ML approaches.
KW - Driving analytics
KW - aggressive driving
KW - bag of words
KW - driving behavior
KW - insurance telematics
UR - http://www.scopus.com/inward/record.url?scp=85079147957&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85079147957&partnerID=8YFLogxK
U2 - 10.1109/TITS.2019.2926639
DO - 10.1109/TITS.2019.2926639
M3 - Article
AN - SCOPUS:85079147957
SN - 1524-9050
VL - 21
SP - 3377
EP - 3387
JO - IEEE Transactions on Intelligent Transportation Systems
JF - IEEE Transactions on Intelligent Transportation Systems
IS - 8
M1 - 8764567
ER -