pith. sign in

arxiv: 2604.15216 · v1 · submitted 2026-04-16 · 💻 cs.HC · cs.CY· cs.LG

Low-Cost System for Automatic Recognition of Driving Pattern in Assessing Interurban Mobility using Geo-Information

Oscar Romero , Aika Silveira Miura , Lorena Parra , Jaime Lloret This is my paper

Pith reviewed 2026-05-10 10:09 UTC · model grok-4.3

classification 💻 cs.HC cs.CYcs.LG
keywords driving style recognitionartificial neural networkgeo-informationinterurban mobilitylow-cost sensorsdriving pattern classificationvehicle safety system
0
0 comments X

The pith

Adding location and time data to sensor inputs raises driving style classification accuracy by 13 percent.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper describes a low-cost hardware setup with GPS and accelerometer sensors feeding an artificial neural network that classifies a driver's behavior as normal, aggressive, or distracted while traveling on interurban roads. When the network detects an abnormal pattern it triggers an audio warning through a speaker on the device node. The authors report that including latitude, longitude, and time alongside velocity and turning rates produces 83 percent average accuracy across three styles and 92 percent accuracy when only normal versus aggressive styles are distinguished. A reader would care because most cars on the road lack any driver-assessment system, so such a retrofit could give real-time safety feedback without relying on expensive factory-installed equipment.

Core claim

The central claim is that an artificial neural network trained on velocity, latitude, longitude, time, and three-axis turning speed collected from a conventional interurban road achieves 83 percent average accuracy classifying three driving styles, with the addition of geo-information and time data contributing a 13 percent accuracy gain over versions that omit those inputs.

What carries the argument

An artificial neural network inside a low-cost node that ingests velocity, position, time, and three-axis turning speed from connected sensors to classify driving style in real time.

If this is right

  • The system can issue immediate spoken warnings when it detects aggressive or distracted patterns.
  • Accuracy improves to 92 percent when the task is simplified to only normal versus aggressive styles.
  • The approach works with inexpensive sensors and can be added to vehicles that lack factory driver-monitoring systems.
  • Combining position, time, and motion data yields measurably better classification than motion data alone.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Retraining the same network on data from urban roads or different vehicle types could extend the same accuracy gains to city driving.
  • The 13 percent lift from geo-information suggests that location context helps the model separate styles that produce similar speed profiles.
  • Logging classified driving events across many users could generate aggregate maps of risky road segments without needing additional infrastructure.

Load-bearing premise

The neural network trained on data from one conventional interurban road and three specific driving styles will continue to perform well when deployed on other roads, with other drivers, and under varied real-world conditions.

What would settle it

Deploying the trained system on a different interurban road or with a new group of drivers and observing whether accuracy drops below 70 percent would directly test whether the reported performance holds.

Figures

Figures reproduced from arXiv: 2604.15216 by Aika Silveira Miura, Jaime Lloret, Lorena Parra, Oscar Romero.

Figure 1
Figure 1. Figure 1: Identified areas and their characteristics affecting driver’s patterns. [PITH_FULL_IMAGE:figures/full_fig_p005_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Sensors included in the system: Global Positioning System (GPS) sensor (a), and G [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Selected node: Raspberry Pi 3. As an overview, [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Summary or proposed system [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Assembled system [PITH_FULL_IMAGE:figures/full_fig_p006_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: ANN design for the automatic recognition of driving parameters (a) using ten parameters and (b) using seven [PITH_FULL_IMAGE:figures/full_fig_p007_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Variation of velocity along the route for the three driving patterns. [PITH_FULL_IMAGE:figures/full_fig_p009_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Variation of fgx along the route for the three driving patterns. [PITH_FULL_IMAGE:figures/full_fig_p010_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Variation of fax along the route for the three driving patterns. [PITH_FULL_IMAGE:figures/full_fig_p011_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Summary of correctly classified data and the different sizes of training datasets when the different [PITH_FULL_IMAGE:figures/full_fig_p012_10.png] view at source ↗
read the original abstract

Mobility in urban and interurban areas, mainly by cars, is a day-to-day activity of many people. However, some of its main drawbacks are traffic jams and accidents. Newly made vehicles have pre-installed driving evaluation systems, which can prevent accidents. However, most cars on our roads do not have driver assessment systems. In this paper, we propose an approach for recognising driving styles and enabling drivers to reach safer and more efficient driving. The system consists of two physical sensors connected to a device node with a display and a speaker. An artificial neural network (ANN) is included in the node, which analyses the data from the sensors, and then recognises the driving style. When an abnormal driving pattern is detected, the speaker will play a warning message. The prototype was assembled and tested using an interurban road, in particular on a conventional road with three driving styles. The gathered data were used to train and validate the ANN. Results, in terms of accuracy, indicate that better accuracy is obtained when the velocity, position (latitude and longitude), time, and turning speed for the 3-axis are used, offering an average accuracy of 83%. If the classification is performed considering just two driving styles, normal and aggressive, then the accuracy reaches 92%. When the geo-information and time data are included, the main novelty of this paper, the classification accuracy is improved by 13%.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 1 minor

Summary. The manuscript presents a low-cost prototype system with two physical sensors feeding an embedded ANN on a device node to classify driving styles during interurban travel. It reports that inputs combining velocity, latitude/longitude position, time, and 3-axis turning speed yield 83% average accuracy on data collected from one conventional interurban road using three driving styles, with a claimed 13% improvement from the addition of geo-information and time; binary normal-vs-aggressive classification reaches 92%. The system issues real-time audio warnings for abnormal patterns.

Significance. If the accuracy figures and 13% geo/time improvement hold under broader testing, the work has moderate significance for accessible driver-monitoring technology in legacy vehicles, potentially supporting safer interurban mobility through low-cost hardware and real-time feedback. The physical prototype assembly and on-road data collection are strengths that demonstrate implementation feasibility. The explicit benchmarking of feature sets (with and without geo/time) is a positive aspect of the empirical evaluation.

major comments (2)
  1. [Abstract] Abstract: the central performance claims (83% average accuracy, 92% binary accuracy, and 13% improvement from geo-information and time) are stated without any mention of dataset size, number of samples or trials per style, train/test split, cross-validation procedure, or error analysis. This is load-bearing for the main claim because the statistical reliability of the reported improvement cannot be assessed or reproduced from the given information.
  2. [Prototype testing description] Prototype testing description: evaluation is confined to data gathered from a single conventional interurban road with three specific driving styles. No cross-road, cross-driver, or cross-condition results are provided, so the claimed benefit of including geo-information and time cannot be separated from possible overfitting to that road's geometry, traffic patterns, and driver cohort.
minor comments (1)
  1. [Abstract] The phrase 'turning speed for the 3-axis' is ambiguous; clarify whether this denotes gyroscope angular velocity, accelerometer-derived values, or another quantity, and specify the sensor model.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the detailed and constructive review of our manuscript. We have addressed each of the major comments in the point-by-point responses below. We will update the manuscript to enhance the transparency of our experimental methodology and to better contextualize the scope of our prototype evaluation.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the central performance claims (83% average accuracy, 92% binary accuracy, and 13% improvement from geo-information and time) are stated without any mention of dataset size, number of samples or trials per style, train/test split, cross-validation procedure, or error analysis. This is load-bearing for the main claim because the statistical reliability of the reported improvement cannot be assessed or reproduced from the given information.

    Authors: We agree with the referee that the abstract would benefit from additional details regarding the experimental setup to allow for better assessment of the results' reliability. In the revised version of the manuscript, we will modify the abstract to include the dataset size, the number of samples per driving style, the train/test split ratio, the cross-validation method used (e.g., k-fold), and a brief note on the error analysis. This revision will be made without changing the reported accuracy figures. revision: yes

  2. Referee: [Prototype testing description] Prototype testing description: evaluation is confined to data gathered from a single conventional interurban road with three specific driving styles. No cross-road, cross-driver, or cross-condition results are provided, so the claimed benefit of including geo-information and time cannot be separated from possible overfitting to that road's geometry, traffic patterns, and driver cohort.

    Authors: The referee correctly identifies a limitation in our current evaluation, which was performed on data from a single interurban road. This is typical for an initial prototype demonstration focused on hardware feasibility and the impact of specific features like geo-information and time. We will revise the manuscript to include an explicit discussion of this limitation in a new 'Limitations and Future Work' section. There, we will note the potential for the observed improvements to be influenced by the specific road characteristics and outline our plans for future studies involving multiple roads, drivers, and conditions to further validate the generalizability. We do not currently have data from additional roads to perform such cross-validation. revision: partial

Circularity Check

0 steps flagged

No circularity: standard empirical ML evaluation on held-out sensor data

full rationale

The paper collects raw sensor data (velocity, position, time, 3-axis turning speed) from one interurban road under three driving styles, feeds the features into an ANN, trains the network, and reports accuracy on validation data (83% average, 92% for binary normal/aggressive, +13% when geo/time features are added). No equations, parameters, or claims reduce to their own inputs by construction. The accuracy figures are obtained from standard train/validate splits on external measurements rather than any self-definitional loop, fitted-input-as-prediction, or self-citation chain. The central claim therefore rests on observable data and conventional ML practice, not on renaming or re-deriving the inputs.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on standard empirical ML assumptions for training an ANN on sensor data; no free parameters, invented entities, or non-standard axioms are introduced beyond typical neural network classification.

axioms (1)
  • domain assumption Artificial neural networks can learn to classify driving patterns from sensor data when trained on representative examples
    Invoked to justify using ANN for style recognition and reporting accuracy on test data.

pith-pipeline@v0.9.0 · 5570 in / 1206 out tokens · 52948 ms · 2026-05-10T10:09:04.540430+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

43 extracted references · 43 canonical work pages

  1. [1]

    Global Status Report on Road Safety 2018; World Health Organization: Geneva, Switzerland, 2018; p

    World Health Organization. Global Status Report on Road Safety 2018; World Health Organization: Geneva, Switzerland, 2018; p. 94

    work page 2018

  2. [2]

    Traffic safety effects of new speed limits in Sweden

    Vadeby, A.; Forsman, Å. Traffic safety effects of new speed limits in Sweden. Accid. Anal. Prev. 2018, 114, 34 –39. [CrossRef] [PubMed]

    work page 2018

  3. [3]

    -N.; Nguyen, H

    Nguyen, T.-H.; Lu, D.- N.; Nguyen, D. -N.; Nguyen, H. -N. Dynamic Basic Activity Sequence Matching Method in Abnormal Driving Pattern Detection Using Smartphone Sensors. Electronics 2020, 9, 217. [CrossRef]

    work page 2020

  4. [4]

    Driving Style Recognition Using a Smartphone as a Sensor Platform

    Johnson, D.A.; Trivedi, M.M. Driving Style Recognition Using a Smartphone as a Sensor Platform. In Proceedings of the 14th International IEEE Conference on Intelligent Transportation Systems (ITSC), Washington, DC, USA, 5–7 October 2011

    work page 2011

  5. [5]

    Detection of Driving Events using Sensory Data on Smartphone

    Saiprasert, C.; Pholprasit, T.; Thajchayapong, S. Detection of Driving Events using Sensory Data on Smartphone. Int. J. ITS Res. 2017, 15, 17–28. [CrossRef]

    work page 2017

  6. [6]

    Assessing safety critical driving patterns of heavy passenger vehicle drivers using instrumented vehicle data—An unsupervised approach

    Yarlagadda, J.; Jain, P.; Pawar, D.S. Assessing safety critical driving patterns of heavy passenger vehicle drivers using instrumented vehicle data—An unsupervised approach. Accid. Anal. Prev. 2021, 163, 106464. [CrossRef]

    work page 2021

  7. [7]

    Personalized Driving Behavior Monitoring and Analysis for Emerging Hybrid Vehicles

    Li, K.; Lu, M.; Lu, F.; Lv, Q.; Shang, L.; Maksimovic, D. Personalized Driving Behavior Monitoring and Analysis for Emerging Hybrid Vehicles. In Pervasive Computing. Pervasive 2012, 1st ed.; Kay, J., Lukowicz, P., Tokuda, H., Olivier, P., Krüger, A., Eds.; Springer: Berlin, Germany, 2012; Volume 7319, pp. 1–19

    work page 2012

  8. [8]

    Modeling the Driving Behavior of Electric Vehicles Using Smartphones and Neural Networks

    Alvarez, A.D.; Garcia, F.S.; Naranjo, J.E.; Anaya, J.J.; Jimenez, J. Modeling the Driving Behavior of Electric Vehicles Using Smartphones and Neural Networks. IEEE Intell. Transp. Syst. Mag. 2014, 6, 44–53. [CrossRef]

    work page 2014

  9. [9]

    Detection of driver health condition by monitoring driving behavior through machine learning from observation

    Gonzalez, A.J.; Wong, J.M.; Thomas, E.M.; Kerrigan, A.; Hastings, L.; Posadas, A.; Negy, K.; Wu, A.S.; Ontañon, S.; Lee, Y.; et al. Detection of driver health condition by monitoring driving behavior through machine learning from observation. Expert Syst. Appl. 2022, 199, 117167. [CrossRef]

    work page 2022

  10. [10]

    Design of an Improved Fuzzy Logic -Based Model for Prediction of Car Following Behavior

    Khodayari, A.; Kazemi, R.; Ghaffari, A.; Braunstingl, R. Design of an Improved Fuzzy Logic -Based Model for Prediction of Car Following Behavior. In Proceedings of the 2011 IEEE International Conference on Mechatronics, Istanbul, Turkey, 13–15 April 2011; pp. 200–205

    work page 2011

  11. [11]

    Available online: https://seeingmachines.com/ (accessed on 5 August 2022)

    SeeingMachines. Available online: https://seeingmachines.com/ (accessed on 5 August 2022)

    work page 2022

  12. [12]

    Available online: https://www.lytx.com/en-us (accessed on 5 August 2022)

    Lytx. Available online: https://www.lytx.com/en-us (accessed on 5 August 2022)

    work page 2022

  13. [13]

    Available online: https://www.progressive.com/manage-policy/ (accessed on 5 August 2022)

    Progressive. Available online: https://www.progressive.com/manage-policy/ (accessed on 5 August 2022)

    work page 2022

  14. [14]

    DrivingStyles: A smartphone application to assess driver behavior

    Meseguer, J.E.; Calafate, C.T.; Cano, J.C.; Manzoni, P. DrivingStyles: A smartphone application to assess driver behavior. In Proceedings of the 2013 IEEE Symposium on Computers and Communications (ISCC), Split, Croatia, 7– 10 July 2013; pp. 000535–000540

    work page 2013

  15. [15]

    Sensing Vehicle Dynamics for Determining Driver Phone Use

    Wang, Y.; Yang, J.; Liu, H.; Chen, Y.; Gruteser, M.; Martin, R.P. Sensing Vehicle Dynamics for Determining Driver Phone Use. In Proceedings of the 11th Annual International Conference on Mobile Systems, Applications, and Services (MobiSys’ 13), New York, NY, USA, 25–28 June 2013

    work page 2013

  16. [16]

    Senspeed: Sensing Driving Conditions to Estimate Vehicle Speed in Urban Environments

    Han, H.; Yu, J.; Zhu, H.; Chen, Y.; Yang, J.; Zhu, Y.; Xue, G.; Li, M. Senspeed: Sensing Driving Conditions to Estimate Vehicle Speed in Urban Environments. In Proceedings of the IEEE Conference on Computer Communications, Toronto, ON, Canada, 27 April 2014

    work page 2014

  17. [17]

    Using mobile phones to determine transportation modes

    Reddy, S.; Mun, M.; Burke, J.; Estrin, D.; Hansen, M.; Srivastava, M. Using mobile phones to determine transportation modes. ACM Trans. Sens. Netw. 2010, 6, 1–27. [CrossRef]

    work page 2010

  18. [18]

    D3: Abnormal Driving Behaviors Detection and Identification Using Smartphone Sensors

    Chen, Z.; Yu, J.; Zhu, Y.; Chen, Y.; Li, M. D3: Abnormal Driving Behaviors Detection and Identification Using Smartphone Sensors. In Proceedings of the 12th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON), Seattle, WA, USA, 22–25 June 2015

    work page 2015

  19. [19]

    Modeling the impact of latent driving patterns on traffic safety using mobile sensor data

    Paleti, R.; Sahin, O.; Cetin, M. Modeling the impact of latent driving patterns on traffic safety using mobile sensor data. Accid. Anal. Prev. 2017, 107, 92–101. [CrossRef]

    work page 2017

  20. [20]

    Using Mobile Phone Sensors to Detect Driving Behavior

    Singh, P.; Juneja, N.; Kapoor, S. Using Mobile Phone Sensors to Detect Driving Behavior. In Proceedings of the 3rd ACM Symposium on Computing for Development (ACM DEV’ 13), New York, NY, USA, 11–12 January 2013

    work page 2013

  21. [21]

    Detecting Aggressive Driving Behavior Using Mobile Smartphone

    Chhabra, R.; Verma, S.; Rama, K.C. Detecting Aggressive Driving Behavior Using Mobile Smartphone. In Proceedings of 2nd International Conference on Communication, Computing and Networking, 1st ed.; Krishna, C., Dutta, M., Kumar, R., Eds.; Springer: Singapore, 2019; Volume 46

    work page 2019

  22. [22]

    Using Neural Networks to Identify Driving Style And Headway Control Behavior of Drivers

    MacAdam, C.; Bareket, Z.; Fancher, P.; Ervin, R. Using Neural Networks to Identify Driving Style And Headway Control Behavior of Drivers. Veh. Syst. Dyn. 2007, 29, 143–160. [CrossRef]

    work page 2007

  23. [23]

    Unobtrusive Drowsiness Detection by Neural Network Learning of Driver Steering

    Sayed, R.; Eskandarian, A. Unobtrusive Drowsiness Detection by Neural Network Learning of Driver Steering. J. Automob. Eng. 2001, 215, 969–975. [CrossRef]

    work page 2001

  24. [24]

    Look -ahead control for heavy trucks to minimise trip time and fuel consumption

    Hellström, E.; Ivarsson, M.; Åslund, J.; Nielsen, L. Look -ahead control for heavy trucks to minimise trip time and fuel consumption. Control Eng. Pract. 2009, 17, 245–254. [CrossRef]

    work page 2009

  25. [25]

    Analysis of Recurrent Neural Networks for Probabilistic Modeling of Driver Behavior

    Morton, J.; Wheeler, T.A.; Kochenderfer, M.J. Analysis of Recurrent Neural Networks for Probabilistic Modeling of Driver Behavior. IEEE Trans. Intell. Transp. Syst. 2017, 18, 1289–1298. [CrossRef]

    work page 2017

  26. [26]

    VHC de Albuquerque, Deep learning for safe autonomous driving: Current challenges and future directions

    Muhammad, K.; Ullah, A.; Lloret, J.; Del Ser, J. VHC de Albuquerque, Deep learning for safe autonomous driving: Current challenges and future directions. IEEE Trans. Intell. Transp. Syst. 2020, 22, 4316–4336. [CrossRef]

    work page 2020

  27. [27]

    Driving Style Classification Using a Semisupervised Support Vector Machine

    Wang, W.; Xi, J.; Chong, A.; Li, L. Driving Style Classification Using a Semisupervised Support Vector Machine. IEEE Trans. Hum. Mach. Syst. 2017, 47, 650–660. [CrossRef]

    work page 2017

  28. [28]

    Facial -Expression Analysis for Predicting Unsafe Driving Behavior

    Jabon, M.; Bailenson, J.; Pontikakis, E.; Takayama, L.; Nass, C. Facial -Expression Analysis for Predicting Unsafe Driving Behavior. IEE Pervasive Comput. 2011, 10, 84–95. [CrossRef]

    work page 2011

  29. [29]

    Brief Report: Examining Driving Behavior in Young Adults with High Functioning Autism Spectrum Disorders: A Pilot Study Using a Driving Simulation Paradigm

    Reimer, B.; Fried, R.; Mehler, B.; Joshi, G.; Bolfek, A.; Godfrey, A.; Zhao, N.; Goldin, R.; Biederman, J. Brief Report: Examining Driving Behavior in Young Adults with High Functioning Autism Spectrum Disorders: A Pilot Study Using a Driving Simulation Paradigm. J. Autism Dev. Disord. 2013, 43, 2211–2217. [CrossRef] [PubMed]

    work page 2013

  30. [30]

    Deviated state detection method in driving around curves based on naturalistic driving behavior database for driver assistance systems

    Shino, M.; Yoshitake, H.; Hiramatsu, M.; Sunda, T.; Kamata, M. Deviated state detection method in driving around curves based on naturalistic driving behavior database for driver assistance systems. Int. J Automot. Technol. 2014, 15, 749–755. [CrossRef]

    work page 2014

  31. [31]

    Available online: https://invensense.tdk.com/wp- content/uploads/2015/02/MPU- 6000 -Datasheet1.pdf (accessed on 1 August 2022)

    GY-521 MPU -6050 Datasheet. Available online: https://invensense.tdk.com/wp- content/uploads/2015/02/MPU- 6000 -Datasheet1.pdf (accessed on 1 August 2022)

    work page 2015

  32. [32]

    Available online: https://www.openimpulse.com/blog/wp -content/uploads/wpsc/ downloadables/GY-NEO6MV2-GPS-Module-Datasheet.pdf (accessed on 1 August 2022)

    PS GY -NEO6MV2 Datasheet. Available online: https://www.openimpulse.com/blog/wp -content/uploads/wpsc/ downloadables/GY-NEO6MV2-GPS-Module-Datasheet.pdf (accessed on 1 August 2022)

    work page 2022

  33. [33]

    Available online: https://static.raspberrypi.org/files/product- briefs/Raspberry-Pi-Model- BplusProduct-Brief.pdf (accessed on 1 August 2022)

    Raspberry Pi 3 Datasheet. Available online: https://static.raspberrypi.org/files/product- briefs/Raspberry-Pi-Model- BplusProduct-Brief.pdf (accessed on 1 August 2022)

    work page 2022

  34. [34]

    Driver behavior detection and classification using deep convolutional neural networks

    Shahverdy, M.; Fathy, M.; Berangi, R.; Sabokrou, M. Driver behavior detection and classification using deep convolutional neural networks. Expert Syst. Appl. 2020, 149, 113240. [CrossRef]

    work page 2020

  35. [35]

    Research on classification and recognition of driving styles based on feature engineering

    Liu, Y.; Wang, J.; Zhao, P.; Qin, D.; Chen, Z. Research on classification and recognition of driving styles based on feature engineering. IEEE Access 2019, 7, 89245–89255. [CrossRef]

    work page 2019

  36. [36]

    Improving Machine Learning Identification of Unsafe Driver Behavior by Means of Sensor Fusion

    Lattanzi, E.; Castellucci, G.; Freschi, V. Improving Machine Learning Identification of Unsafe Driver Behavior by Means of Sensor Fusion. Appl. Sci. 2020, 10, 6417. [CrossRef]

    work page 2020

  37. [37]

    A Smartphone- Based Sensing Platform to Model Aggressive Driving Behaviors

    Hong, J.H.; Margines, B.; Dey, A.K. A Smartphone- Based Sensing Platform to Model Aggressive Driving Behaviors. In Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Toronto, ON, Canada, 26 April–1 May 2014; pp. 4047–4056

    work page 2014

  38. [38]

    and Ghatee, M

    Bejani, M.M. and Ghatee, M. A context aware system for driving style evaluation by an ensemble learning on smartphone sensors data. Transp. Res. Part C Emerg. Technol. 2018, 89, 303–320. [CrossRef]

    work page 2018

  39. [39]

    Hidden Markov model based driving event detection and driver profiling from mobile inertial sensor data

    Daptardar, S.; Lakshminarayanan, V.; Reddy, S.; Nair, S.; Sahoo, S.; Sinha, P. Hidden Markov model based driving event detection and driver profiling from mobile inertial sensor data. In Proceedings of the 2015 IEEE Sensors, Busan, Korea, 1–4 November 2015; pp. 1–4

    work page 2015

  40. [40]

    A smartphone based technique to monitor driving behavior using DTW and crowdsensing

    Singh, G.; Bansal, D.; Sofat, S. A smartphone based technique to monitor driving behavior using DTW and crowdsensing. Pervasive Mob. Comput. 2017, 40, 56–70. [CrossRef]

    work page 2017

  41. [41]

    Drivingstyles: A mobile platform for driving styles and fuel consumption characterization

    Meseguer, J.E.; Toh, C.K.; Calafate, C.T.; Cano, J.C.; Manzoni, P. Drivingstyles: A mobile platform for driving styles and fuel consumption characterization. J. Commun. Netw. 2017, 19, 162–168. [CrossRef]

    work page 2017

  42. [42]

    Distributed database management techniques for wireless sensor networks

    Diallo, O.; Rodrigues, J.J.P.C.; Sene, M.; Lloret, J. Distributed database management techniques for wireless sensor networks. IEEE Trans. Parallel Distrib. Syst. 2013, 26, 604–620. [CrossRef]

    work page 2013

  43. [43]

    Intelligent beaconless geographical forwarding for urban vehicular environments

    Ghafoor, K.Z.; Abu Bakar, K.; Lloret, J.; Khokhar, R.H.; Lee, K.C. Intelligent beaconless geographical forwarding for urban vehicular environments. Wirel. Netw. 2013, 19, 345–362. [CrossRef]

    work page 2013