Smartphone sensing for understanding driving behavior: Current practice and challenges (original) (raw)
Related papers
Driving behavior analysis with smartphones: insights from a controlled field study
2012
We evaluate a mobile application that assesses driving behavior based on in-vehicle acceleration measurements and gives corresponding feedback to drivers. In the insurance business, such applications have recently gained traction as a viable alternative to the monitoring of drivers via "black boxes" installed in vehicles, which lacks interaction opportunities and is perceived as privacy intrusive by policyholders. However, pose uncertainty and other noise-inducing factors make smartphones potentially less reliable as sensor platforms. We therefore compare critical driving events generated by a smartphone with reference measurements from a vehicle-fixed IMU in a controlled field study. The study was designed to capture driver variability under real-world conditions, while minimizing the influence of external factors. We find that the mobile measurements tend to overestimate critical driving events, possibly due to deviation from the calibrated initial device pose. While weather and daytime do not appear to influence event counts, road type is a significant factor that is not considered in most current state-of-the-art implementations.
Driving behavior analysis with smartphones
Proceedings of the 11th International Conference on Mobile and Ubiquitous Multimedia - MUM '12, 2012
We evaluate a mobile application that assesses driving behavior based on in-vehicle acceleration measurements and gives corresponding feedback to drivers. In the insurance business, such applications have recently gained traction as a viable alternative to the monitoring of drivers via "black boxes" installed in vehicles, which lacks interaction opportunities and is perceived as privacy intrusive by policyholders. However, pose uncertainty and other noise-inducing factors make smartphones potentially less reliable as sensor platforms. We therefore compare critical driving events generated by a smartphone with reference measurements from a vehicle-fixed IMU in a controlled field study. The study was designed to capture driver variability under real-world conditions, while minimizing the influence of external factors. We find that the mobile measurements tend to overestimate critical driving events, possibly due to deviation from the calibrated initial device pose. While weather and daytime do not appear to influence event counts, road type is a significant factor that is not considered in most current state-of-the-art implementations.
Estimating Driving Behavior by a Smartphone
—In this paper, we propose an approach to understand the driver behavior using smartphone sensors. The aim for analyzing the sensory data acquired using a smartphone is to design a car-independent system which does not need vehicle mounted sensors measuring turn rates, gas consumption or tire pressure. The sensory data utilized in this paper includes the accelerometer, gyroscope and the magnetometer. Using these sensors we obtain position, speed, acceleration, deceleration and deflection angle sensory information and estimate commuting safety by statistically analyzing driver behavior. In contrast to state of the art, this work uses no external sensors, resulting in a cost efficient, simplistic and user-friendly system.
Classification of Driving Characteristics Using Smartphone Sensor Data
Human factors and driving characteristics have become a key consideration and design factor for all kinds of transportation systems and infrastructure elements. Classification of driving behaviors allows a finer perception of real traffic, as it helps distinguish and interpret the way that drivers react to different traffic states and situations. Until recently, obtaining detailed traffic information on individual vehicles required expensive and hard-to-operate, specialized equipment that had to be installed on the vehicle of study (thus making it clear to the driver that s/he was under observation and thus potentially affecting his driving behavior). During the past several years, a new type of phones has been prevalent, so called smartphones. These devices incorporate several powerful sensors that collect much of the same information, as those specialized devices. Of course, the accuracy and performance of these devices are not necessarily in par with their more elaborate and expe...
Smartphones, Suitable Tool for Driver Behavior Recognition. A Systematic Review
Communications in Computer and Information Science, 2020
A current reality is the increase in the number of road traffic accidents caused mainly by incorrect driving habits. For this reason, the development of different approaches that can help reduce accidents on the road is imperative. A strategy is the use of smartphones as a tool to identify driving behaviors, which is documented in the state of the art. This paper presents a systematic review focused on the strategies used to recognizing driving behaviors with sensors that are part of smartphones. The review was carried out on the Scopus database, included studies published in the last 4 years (2017-2020) that allowed identifying a total of 222222 relevant results. This paper presents a report of the most used sensors, algorithms, driving events and driving patterns. It includes result discussion and considerations of future work on this topic, additional to the bibliometric report.
Safety Science, 2020
Naturalistic driving studies (NDS) are increasingly being used to investigate driver on-road behavior. In parallel, smartphones are gaining interest as data acquisition systems (DAS) in NDS instead of costly in-vehicle DAS. However, smartphone and in-vehicle DAS differ across several attributes and no current document outlines the implications of using smartphones as DAS in NDS. In this document, we present a comparative review of the advantages and disadvantages of using smartphone and in-vehicle DAS in NDS and discuss their implications. In addition, we present a brief account on prospective technological developments that might have further implications for using smartphones for studying and advancing road safety. Researchers and practitioners can use this review as a general guide to decide which DAS (smartphone or in-vehicle) to use in their NDS. For example, smartphones would be a cost-effective alternative for studying driving style (e.g., braking and speeding), but an inferior alternative to in-vehicle DAS for reconstructing crashes or near crashes and for studying short-term relationships between events (e.g., smartphone usage and hard braking). Researchers and practitioners can also use this review as an aid for the design of NDS with smartphones. For example, we show that it would be advisable to use beacons to know if participants were driving their vehicle or riding the bus, and that data completeness and accuracy would depend on battery charge and using a cradle. Prospective technologies might mitigate the shortcomings that we have outlined and might even dim the distinction between the different types of DAS.
DrivingStyles: A smartphone application to assess driver behavior
2013 IEEE Symposium on Computers and Communications (ISCC), 2013
The DrivingStyles architecture integrates both data mining techniques and neural networks to generate a classification of driving styles by analyzing the driver behavior along each route. In particular, based on parameters such as speed, acceleration, and revolutions per minute of the engine (rpm), we have implemented a neural network based algorithm that is able to characterize the type of road on which the vehicle is moving, as well as the degree of aggressiveness of each driver. The final goal is to assist drivers at correcting the bad habits in their driving behavior, while offering helpful tips to improve fuel economy. In this work we take advantage of two key-points: the evolution of mobile terminals and the availability of a standard interface to access car data. Our DrivingStyles platform to achieve a symbiosis between smartphones and vehicles able to make the former operate as an onboard unit. Results show that neural networks were able to achieve a high degree of exactitude at classifying both road and driver types based on user traces. DrivingStyles is currently available on the Google Play Store platform for free download, and has achieved more than 1550 downloads from different countries in just a few months. Index Terms-Driving styles; Android smartphone; OBD-II; neural networks; eco-driving.
Driving Style Recognition Using a Smartphone as a Sensor Platform
Driving style can characteristically be divided into two categories: "typical" (non-aggressive) and aggressive. Understanding and recognizing driving events that fall into these categories can aid in vehicle safety systems. Potentiallyaggressive driving behavior is currently a leading cause of traffic fatalities in the United States. More often than not, drivers are unaware that they commit potentially-aggressive actions daily. To increase awareness and promote driver safety, we are proposing a novel system that uses Dynamic Time Warping (DTW) and smartphone based sensor-fusion (accelerometer, gyroscope, magnetometer, GPS, video) to detect, recognize and record these actions without external processing. Our system differs from past driving pattern recognition research by fusing related inter-axial data from multiple sensors into a single classifier. It also utilizes Euler representation of device attitude (also based on fused data) to aid in classification. All processing is done completely on the smartphone.
Driver Rating: a mobile application to evaluate driver behavior
South Florida Journal of Development, 2021
The combination of data from sensors embedded in vehicles and smartphones promises to generate great innovations in intelligent transportation systems. This article presents Driver Rating, a mobile application to evaluate the behavior of drivers based on the data gathered from vehicles´ and smartphones´ sensors. The Driver Rating application analyzes five variables (fuel consumption, carbon dioxide emission, speed, longitudinal acceleration, and transverse acceleration) to evaluate driver´s behaviors while driving. To test the Driver Rating application and identify its potentialities, an experiment was carried out on an urban environment, showing promising results regarding the classification of drivers’ behavior.
Driving style recognition using machine learning and smartphones
F1000Research, 2022
Background: The lack of real-time monitoring is one of the reasons for the lack of awareness among drivers of their dangerous driving behavior. This work aims to develop a driver profiling system where a smartphone’s built-in sensors are used alongside machine learning algorithms to classify different driving behaviors. Methods: We attempt to determine the optimal combination of smartphone sensors such as accelerometer, gyroscope, and GPS in order to develop an accurate machine learning algorithm capable of identifying different driving events (e.g. turning, accelerating, or braking). Results: In our preliminary studies, we encountered some difficulties in obtaining consistent driving events, which had the potential to add “noise” to the observations, thus reducing the accuracy of the classification. However, after some pre-processing, which included manual elimination of extraneous and erroneous events, and with the use of the Convolutional Neural Networks (CNN), we have been able ...