Driving style classification using long-term accelerometer information
The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
Driving style can be characteristically divided into normal and aggressive. Related researches show that useful information about driving style can be extracted using vehicle's inertial measurement signals with the help of GPS. However, for public transportation the GPS sensor isn't necessary because of repetition of the route. This assumption helps to create low-cost intelligent public transport monitoring system that is capable to classify aggressive and normal driver. In this paper, we propose pattern recognition approach to classify driving style into aggressive or normal automatically without expert evaluation and knowledge using accelerometer data when driving the same route in different driving styles. 3-axis accelerometer signal statistical features were used as classifier inputs. The results show that aggressive and normal driving style classification of 100% precision is achieved using collected data when driving the same route.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Driving style recognition using a smartphone as a sensor platform
Johnson, D. A., & Trivedi, M. M. (2011) · 2011 14th International IEEE Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2011.6083078 · Cited by 727 · cited 1×
“Trivedi [8] created the system called MIROAD that uses Dynamic Time Warping (DTW) and smartphone based sensor-fusion (accelerometer, gyroscope, magnetometer, GPS,”
MethodSafe Driving Using Mobile Phones
Fazeen, M., Gozick, B., Dantu, R., Bhukhiya, M., & González, M. C. (2012) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2012.2187640 · Cited by 341 · cited 1×
“[9] use the 3-axis accelerometer and GPS of an Android-based smartphone to record and analyze various driver behaviors and external road conditions.”
MethodDriver classification and driving style recognition using inertial sensors
Van Ly, M., Martin, S., & Trivedi, M. M. (2013) · 2013 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2013.6629603 · Cited by 306 · cited 1×
“[2] in experiment use driving event (turn, acceleration and braking) features for driver classification.”
MethodDriver's style classification using jerk analysis
Murphey, Y. L., Milton, R., & Kiliaris, L. (2009) · 2009 IEEE Workshop on Computational Intelligence in Vehicles and Vehicular Systems · doi:10.1109/civvs.2009.4938719 · Cited by 270 · cited 1×
“[12] present jerk analysis (first derivative of acceleration signal) that also could give good results for classification of driving style.”
Driving style recognition using fuzzy logic
Aljaafreh, A., Alshabatat, N., & Najim Al-Din, M. S. (2012) · 2012 IEEE International Conference on Vehicular Electronics and Safety (ICVES 2012) · doi:10.1109/icves.2012.6294318 · Cited by 152 · cited 1×
“[4] propose a driving performance inference system based on the signature of acceleration in two dimensions and speed.”
BackgroundDriving coach: A smartphone application to evaluate driving efficient patterns
Araújo, R. E., Igreja, A., de Castro, R. P., & Araújo, R. E. (2012) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2012.6232304 · Cited by 116 · cited 1×
“R. Araujo et al. [10] in experiment use smartphone to evaluate driving-efficient patterns to form a feedback as an eco-driving advice to the driver.”
MethodA Pattern-Recognition Approach for Driving Skill Characterization
Zhang, Y., Lin, W. C., & Chin, Y.-K. S. (2010) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2010.2055239 · Cited by 110 · cited 1×
“Pattern recognition approach is taken in Y. Zhang et al. [6] research study.”
MethodDriving style estimation via inertial measurements
Manzoni, V., Corti, A., De Luca, P., & Savaresi, S. M. (2010) · 13th International IEEE Conference on Intelligent Transportation Systems · doi:10.1109/itsc.2010.5625113 · Cited by 74 · cited 1×
“[5] evaluate driving style economy considering fuel consumption using mathematical modeling and information acquired from inertial signals and speed from GPS.”
MethodLeveraging sensor information from portable devices towards automatic driving maneuver recognition
Sathyanarayana, A., Sadjadi, S. O., & Hansen, J. H. L. (2012) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc.2012.6338717 · Cited by 67 · cited 1×
“[7] compare driving maneuver recognition results using both CAN-bus and tablet information and show that using smartphone sensor information one can obtain better results (about 15% classification accuracy increase) than CAN-bus sensor information.”
ResultDriver risk evaluation based on acceleration, deceleration, and steering behavior
Miyajima, C., Ukai, H., Naito, A., Amata, H., Kitaoka, N., & Takeda, K. (2011) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp.2011.5946860 · Cited by 44 · cited 1×
“[3] in their research use longitudinal, lateral acceleration and velocity signals captured in drive recorders for the driver risk analysis.”
Background
Cited by
Items 101–144 of 144
Expressway Rear-End Conflict Pattern Classification and Modeling
Ma, W., Miao, Y., He, Z., Wang, L., & Abdel-Aty, M. A. (2023) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981231171913 · Cited by 3
“Different terms and methods have been used to classify driving style based on individual, social, and technological factors ( 8 , 10 , 11 ).”
MethodAn unsupervised approach for automotive driver identification
Mainardi, N., Zanella, M., Reghenzani, F., Raspa, N., & Brandolese, C. (2018) · doi:10.1145/3285017.3285023 · Cited by 3
“, reading from the vehicle Electronic Computed Board or the CAN bus [2, 4, 7]) and they leverage supervised techniques [2, 7, 10] (e.”
MethodGuo, R., Chen, Y., Li, W., Qian, H., & Zhu, M. (2026) · Journal of Transportation Engineering Part A Systems · doi:10.1061/jtepbs.teeng-9284 · Cited by 2
Driving Style Identification Strategy Based on DS Evidence Theory
Wang, C.-T., He, R., & Zhu, B. (2023) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2023-01-0587 · Cited by 2
Accelerometer and Gyroscope Synthetic Data Calculation based on Driver Smartphone GPS
Shushkova, V., Kashevnik, A. M., & Bakeeva, L. (2024) · Conference of Open Innovations Association (FRUCT) · doi:10.23919/fruct64283.2024.10749939 · Cited by 5
“Another study [8] classifies driving styles for public transport.”
BackgroundPreliminary driving style classification of the professional drivers
Szumska, E., & Stańczyk, T. (2022) · The Archives of Automotive Engineering/ Archiwum Motoryzacji · doi:10.14669/am/157998 · Cited by 2
“Data on vehicle dynamic parameters from the CAN bus can be used to assess the driver’s behaviour in real conditions [12, 36, 38].”
BackgroundMethod(2017) · Elsevier eBooks · doi:10.1016/b978-0-12-812800-8.00009-6 · Cited by 2
Pérez, J., Olazagoitia, J. L., & Badea, F. (2022) · Journal of Sensors · doi:10.1155/2022/5719525 · Cited by 2
“In [7, 8], a classification of a driver’s driving style based on long-term accelerometer information is similarly performed.”
BackgroundTiny Machine Learning Techniques for Driving Behavior Scoring in a Connected Car Environment
Merenda, M., Mazzullo, V., Carotenuto, R., & Corte, F. G. D. (2021) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech52315.2021.9566333 · Cited by 2
KARABULUTER, B., Karaduman, Ö., Karabatak, M., & Eren, H. (2020) · European Journal of Science and Technology · doi:10.31590/ejosat.743076 · Cited by 1
Driving Style Classification and Dynamic Recognition Considering Traffic State
Xing, H., Wang, G., Liu, Y., & Zhang, H. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-3925-1_6 · Cited by 1
Driving Style Recognition at First Impression for Online Trajectory Prediction
Xu, T., Wu, K., Zhu, Y., & Ji, W. D. (2023) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2023.10.323 · Cited by 1
“, 2020), supervised machine learning algorithms such as k-nearest neighbors (kNN) (Vaitkus et al., 2014), support vector machine (SVM) (Xue et al.”
BackgroundHybrid ConvLSTM with Attention for Precise Driver Behavior Classification
Mustafa, G., Cho, S.-J., & Hwang, Y.-S. (2023) · IEEE International Conference on Artificial Intelligence and Knowledge Engineering (AIKE) · doi:10.1109/aike59827.2023.00008 · Cited by 1
“Recent research in the field has shown that utilizing smartphone sensor signals tends to yield better outcomes compared to CAN-bus sensor signals, mainly because smartphones offer a greater number of sensors than traditional CAN-bus connections [17].”
BackgroundHeadway regularity as an attribute for classifying bus drivers
Martínez-Estupiñán, Y., Delgado, F., & Muñoz, J. C. (2024) · Transportmetrica A Transport Science · doi:10.1080/23249935.2024.2337737 · Cited by 1
“Indices based on acceleration and speed are the most commonly used in the case of bus drivers and urban driving environments (Ellison, Greaves, and Bliemer 2013; Tavakoli Kashani et al. 2021; Vaitkus, Lengvenis, and Žylius 2014).”
Automotive Cockpit-Driving Integration for Human-Centric Autonomous Driving: A Survey
Zhu, Z., Zhao, S., Cai, M., Wang, C., & Du, A. (2025) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2025.3616947 · Cited by 2
Driving Habit Recognition and Shifting Correction Control of Vehicle Automatic Transmission
Xia, G., Zhang, Y., Wei, Z., Tang, X., & Wuwei, C. (2020) · Journal of Mechanical Engineering · doi:10.3901/jme.2020.20.120 · Cited by 1
“…等 [8] 介绍了在能源消 耗最低的情况下优化驾驶习惯的分类方法,以及根 据车辆的加速度、速度、刹车和车辆节气门的张开 关闭大小把驾驶者的个性分为了保守型、温和型和 激进型; QI 等 [9] 根据两汽车之间的间隔时间以及距 离,把驾驶者分为谨慎型、适中型和激进型; VAITKUS 等 [10] 基于加速度数据并采用 K 最邻近 (K-nearest neighbor , KNN) 算法,实现驾驶风格的 自动识别; ALJAAFREH 等 [11] 使用汽车在横移方向 以及纵移方向的加速度的范畴数目和车辆行驶速 度,建立了模糊推理为基础的驾驶者驾驶习惯分类 系统;许春卿 [12]…”
Design and Implementation of a New Intelligent Driving Habit Detection System
Zhu, J., Fan, M., & Xia, J. (2024) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac59436.2024.10503645 · Cited by 1
“Then convert the processed longitude and latitude into the form of coordinates ( x, y ) [18] .”
MethodPublic Transit Driver Behaviour Analysis Under Heterogeneous Road Traffic Conditions
Athapaththu, R., Ranasinghe, G., Pavithra, M. K., & Thayasivam, U. (2024) · Moratuwa Engineering Research Conference (MERCon) · doi:10.1109/mercon63886.2024.10689075 · Cited by 1
“When it comes to public transport bus driver behaviours, there are few studies exist that focus on driver behaviours in homogeneous traffic conditions [7], [13]–[15].”
BackgroundDriving heterogeneity identification using machine learning: A review and framework for analysis
Xue, Y., Calvert, S. C., & Hoogendoorn, S. P. (2025) · Transportation Research Interdisciplinary Perspectives · doi:10.1016/j.trip.2025.101511 · Cited by 9
Martínez, C. M., & Cao, D. (2018) · Elsevier eBooks · doi:10.1016/b978-0-12-815010-8.00003-x · Cited by 2
Incorporating Vertical Acceleration for Defining Driving Behaviour
Eboli, L., Mazzulla, G., & Pungillo, G. (2019) · International Journal of Information Retrieval Research · doi:10.4018/ijirr.2019040104 · Cited by 2
System Design of Driving Behavior Recognition Based on Semi-supervised Learning
Xu, C., Zhang, Y., Guo, D., Wang, W., & Liu, B. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-15127-0_54 · Cited by 1
Accelerating Automotive Analytics: The M2DC Appliance Approach
Agosta, G., Brandolese, C., Fornaciari, W., Mainardi, N., Pelosi, G., Reghenzani, F., Zanella, M., Courchamps, G. D., Ducrot, V., Juilly, K., et al. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-27562-4_33 · Cited by 1
“Nevertheless, there are two relevant limitations in most of the previous works: they rely on input data mainly retrieved with invasive methodologies [9,11,18] and they leverage supervised techniques [9,18,24] (e.”
BackgroundDriving Style Identification Model based on XGBoost
Liu, F., Liu, X., & Yan, H. (2021) · International Conference on Artificial Intelligence and Advanced Manufacture (AIAM) · doi:10.1145/3495018.3495033 · Cited by 2
“At the same time, machine learning methods such as random forest [7], k-nearest neighbor algorithm (KNN) [10], support vector machine (SVM) [11] had been used to construct driver’s driving style identification models, which had effectively reduced the influence of subjective factors to the result.”
MethodDriver Identification through Stochastic Multi-State Car-Following ModelingPreprint
Xu, D., Ding, Z., Tu, C., Zhao, H., Moze, M., Aioun, F., & Guillemard, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11077 · Cited by 1
“normal/aggressive [16][17], aggressive/cautious/super cautious [18], sporty/normal/comfortable [19], normal/vague/aggressive [20], low-/moderate-/high-risk [21] or cautious/average/expert/reckless [22] driving styles, and low/high [23] or experienced/average driving skills.”
A Review of Cockpit-driving Integration for Human-centric Autonomous DrivingPreprint
Zhu, Z., Zhao, S., Wang, C., & Du, A. (2023) · doi:10.36227/techrxiv.24428014.v1 · Cited by 2
A Review of Cockpit-driving Integration for Human-centric Autonomous DrivingPreprint
Zhu, Z., Zhao, S., Wang, C., & Du, A. (2023) · doi:10.36227/techrxiv.24428014 · Cited by 1
A Hybrid Classification of Driver’s Style and Skill Using Fully-Connected Deep Neural Networks
Liu, J., Hu, R., & Hu, H. (2021) · SAE technical papers on CD-ROM/SAE technical paper series · doi:10.4271/2020-01-5107
Vehicle Maneuvering-style Recognition in identifying the Culprit for a Road Accident
Siddiqui, M. S. (2019)
Feraud, I. S. (2020) · UPM Digital Archive (Technical University of Madrid) · doi:10.20868/upm.thesis.66065 · Cited by 2
Recognition of Driver Type in Complex Driving Environment
Liu, S., & Tan, D. (2021) · Automatic Control and Computer Sciences · doi:10.3103/s0146411621060055
Voloacă, Ş., & Toma, M. F. (2022) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/1220/1/012041
“With those low-cost systems, it is possible to study the passengers’ comfort according to driving style [2] and makes it possible to evaluate the dynamic movement factors that can influence a comfort index [3].”
Background(2018) · Elsevier eBooks · doi:10.1016/b978-0-12-815010-8.10000-6
Casati, J. P. B. (2021) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/t.18.2021.tde-27052022-103103
Recognition and Comparison of Driving Styles of Heavy-Duty Truck Drivers Under Different Scenarios
Yu, L., Ma, Y., Chen, S., Yao, H., & Zhou, M. (2022) · Lecture notes in electrical engineering · doi:10.1007/978-981-19-5615-7_52
Adaptive Personalized Steer-by-Wire System Design Based on Driving Style Identification
Gong, C., Zong, C., Dai, C., & Zhang, D. (2022) · IEEE International Conference on Intelligent Transportation Systems (ITSC) · doi:10.1109/itsc55140.2022.9921915
“Unsupervised helps to identify the input signal and determine the best classification strategy, supervised usually gives better classification results, and semi-supervised combines the advantages of both[15].”
BackgroundA Recursive Gaussian Process based Online Driving Style Analysis
Fink, D., Dues, T., Kortmann, K.-P., Blum, P., Schweers, C., & Trabelsi, A. (2023) · Proceedings of the ... American Control Conference/Proceedings of the American Control Conference · doi:10.23919/acc55779.2023.10156499 · Cited by 1
“In addition, further methods, such as Support-Vector-Machine [18], Support-Vector-Clustering [19] or Hidden-Markov-Model [20] can be applied for driving style classification.”
MethodZhang, Y., Li, J., Deng, L., Zang, Y., & Zhang, Y. (2023) · International Conference on Electromechanical Control Technology and Transportation (ICECTT) · doi:10.1117/12.2689655 · Cited by 1
Exploring Lane Change Style Recognition through Analysis of Latent Driving Behavior
Gu, S., & Yang, Y. (2024) · International Conference on Mechatronics, IoT and Industrial Informatics (ICMIII) · doi:10.1109/icmiii62623.2024.00040
“Vaitkus [12] presented a driving style classification method based on vehicle inertial measurement signals, utilizing accelerometer data for pattern recognition.”
MethodSTAGE: STyle-Controllable Action GEneration for Personalized Autonomous Driving
Liu, Z., Liu, X., Zhang, Y., & Huang, P. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3640974 · Cited by 1
“Mostexistingapproachescategorizedriving behaviorsintodistinctclasses[7],[8],suchasaggressive,cautious,andstandard.”
A Method Integrating K-Means++ and 1D-CNN for Driving Style Recognition
Lu, X., Xiong, R., Zhang, P., Chen, Y., Song, M., & Li, S. (2025) · CAA International Conference on Vehicular Control and Intelligence (CVCI) · doi:10.1109/cvci66304.2025.11348468
“Miyajima et al. [6] and Shi [7] applied Gaussian Mixture Models (GMM) to model driving behavior, while Vaitkus et al. [8] used K-Nearest Neighbors (KNN) for binary aggressive/normal classification.”
Feature Extraction and Online Identification of Driving Styles During Lane-Changing Maneuversuse
Wu, P., Zou, L., Wei, Y., & Hang, L. (2025) · International Conference on Image Processing, Multimedia Technology and Machine Learning (IPMML) · doi:10.1109/ipmml68499.2025.11406975
“Dörr et al. [3], Brombacher et al. [4], and Gomes et al. [5] respectively explored fuzzy logic, event-based analysis, and Interval Type-2 Fuzzy Inference Systems for driving style classification.”
Rethinking driving style recognition: A prediction error-based method
Hu, J., Gao, D., Hu, C., Lee, J. J., Zhou, H., & Abdel-Aty, M. A. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104790
Metadata
- Authors
- Vaitkus, V., Lengvenis, P., & Zylius, G.
- Affiliations
- Kaunas University of Technology (LT)
- ORCID
- Vaitkus, Vygandas
- Venue
- 2014 19th International Conference on Methods and Models in Automation and Robotics (MMAR)
- Publisher
- IEEE
- Published
- 2014-09
- Pages
- 641-644
- OpenAlex
- W2029809489
- Cited by
- 144
- References
- 12
- Citations by year
- 2026: 2 · 2025: 12 · 2024: 9 · 2023: 21 · 2022: 22 · 2021: 21 · 2020: 18 · 2019: 14 · 2018: 12 · 2017: 7 · 2016: 5 · 2015: 1
- FWCI
- 11.21
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Methods and Models in Automation and Robotics (publishedVersion)
- Topics
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Traffic and Road Safety
- Physical Sciences › Engineering › Automotive Engineering › IoT and GPS-based Vehicle Safety Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Keywords
- driving style classification, aggressive driving, accelerometer signals, public transport monitoring, statistical features, pattern recognition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.