SavedAdd your journal

Journals / Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi / 2026 / Cilt: 16

A hybrid driving behavior classification approach based on multimodal data for intelligent transportation systems

Akıllı ulaşım sistemleri için çoklu veri türlerine dayalı hibrit sürücü davranışı sınıflandırma yaklaşımı

Ensar Arif Sağbaş(MUĞLA SITKI KOÇMAN ÜNİVERSİTESİ, TEKNOLOJİ FAKÜLTESİ, BİLİŞİM SİSTEMLERİ MÜHENDİSLİĞİ BÖLÜMÜ)0000-0002-7463-1150
Pages
—
Publication Date
2026-03-27
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

However, the study’s key novelty lies in the proposed hybrid subspace stacking method, which combines random subspace diversification and ensemble learning to surpass all baseline classifiers, achieving the highest accuracy of 95.69%.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:With the advancement of intelligent transportation systems, traffic safety remains a critical concern.
📊
Key Findings & Data:Support vector machine (SVM), Naïve Bayes (NB), and multilayer perceptron (MLP) models were compared, with the MLP yielding the best individual performance.
💡
Conclusion & Impact:However, the study’s key novelty lies in the proposed hybrid subspace stacking method, which combines random subspace diversification and ensemble learning to surpass all baseline classifiers, achieving the highest accuracy of 95.69%.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Sürücü davranışı · çoklu sensör füzyonu · OBD-II

Abstract

With the advancement of intelligent transportation systems, traffic safety remains a critical concern. This study classifies driver behaviors into calm, normal, and aggressive categories by integrating, for the first time in the literature, a multimodal dataset combining OBD-II, smartphone sensors, GPS, and environmental sound data. The newly created multi-source dataset encompasses engine parameters, motion sensors, road characteristics, and ambient sounds. The data were segmented using different window lengths, and statistical as well as time–frequency features were extracted to analyze the impact of window size on classification accuracy. Support vector machine (SVM), Naïve Bayes (NB), and multilayer perceptron (MLP) models were compared, with the MLP yielding the best individual performance. However, the study’s key novelty lies in the proposed hybrid subspace stacking method, which combines random subspace diversification and ensemble learning to surpass all baseline classifiers, achieving the highest accuracy of 95.69%.

Özet

Akıllı ulaşım sistemlerinin gelişimiyle birlikte trafik güvenliği hâlâ kritik bir sorun olarak önemini korumaktadır. Bu çalışma, literatürde ilk kez OBD-II, akıllı telefon sensörleri, GPS ve çevresel ses verilerini bütünleştiren çoklu (multimodal) bir veri kümesi kullanarak sürücü davranışlarını sakin, normal ve agresif kategorilerine ayırmaktadır. Yeni oluşturulan bu çok kaynaklı veri kümesi, motor parametreleri, hareket sensörleri, yol özellikleri ve ortam seslerini kapsamaktadır. Farklı pencere uzunluklarında bölünen verilerden istatistiksel ve zaman–frekans tabanlı öznitelikler çıkarılmış, pencere boyutunun sınıflandırma doğruluğuna etkisi analiz edilmiştir. Support vector machine (SVM), Naïve Bayes (NB) ve multilayer perceptron (MLP) modelleri karşılaştırılmış; MLP en iyi bireysel sonuçları vermiştir. Bununla birlikte, çalışmanın özgün katkısı olan hibrit alt-uzay istifleme (hybrid subspace stacking) yöntemi, rastgele alt-uzay çeşitlendirmesi ve topluluk öğrenmeyi birleştirerek tüm modelleri geride bırakmış ve %95.69 doğrulukla en yüksek başarıyı sağlamıştır.

🔖

Cite This Article

Sağbaş, E. A. (2026). A hybrid driving behavior classification approach based on multimodal data for intelligent transportation systems. Niğde Ömer Halisdemir Üniversitesi Mühendislik Bilimleri Dergisi, Cilt: 16. https://doi.org/10.28948/ngumuh.1818839

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (28)

  1. M. Malik and R. Nandal, A framework on driving behavior and pattern using On-Board diagnostics (OBD-II) tool, Materials Today: Proceedings, 80, 3762-3768, 2023. https://doi.org/10.1016/j.matpr. 2021.07.376
  2. M. Miyaji, M. Danno and K. Oguri, Analysis of driver behavior based on traffic incidents for driver monitor systems, In 2008 IEEE Intelligent Vehicles Symposium, pp. 930-935, Eindhoven, Netherlands, 5 September 2008.
  3. R. Aufrère, J. Gowdy, C. Mertz, C. Thorpe, C.C. Wang and T. Yata, Perception for collision avoidance and autonomous driving. Mechatronics, 13(10), 1149-1161, 2003. https://doi.org/10.1016/S0957-4158(03) 00047-3
  4. Y. Zou, L. Ding, H. Zhang, T. Zhu and L. Wu, Vehicle acceleration prediction based on machine learning models and driving behavior analysis. applied sciences, 12(10), 5259, 2022. https://doi.org/10.3390/ app12105259
  5. J.P. Bedretchuk, S. Arribas García, T. Nogiri Igarashi, R. Canal, A. Wedderhoff Spengler and G. Gracioli, Low-cost data acquisition system for automotive electronic control units. Sensors, 23(4), 2319, 2023. https://doi.org/10.3390/s23042319
  6. J. Claßen, S. Krysmon, F. Dorscheidt, S. Sterlepper and S. Pischinger, Real driving emission calibration—Review of current validation methods against the background of future emission legislation. Applied Sciences, 11(12), 5429, 2021. https://doi.org/10.3390/ app11125429
  7. R. Canal, F.K. Riffel and G. Gracioli, Machine learning for real-time fuel consumption prediction and driving profile classification based on ECU data. IEEE Access, 68586-68600, 2024. https://doi.org/10.1109/ACCESS. 2024.3400933
  8. G. Andria, F. Attivissimo, A. Di Nisio, A.M.L. Lanzolla and A. Pellegrino, Development of an automotive data acquisition platform for analysis of driving behavior. Measurement, 93, 278-287, 2016. https://doi.org/10.1016/j.measurement.2016.07.035
  9. H.A. Ameen, A.K. Mahamad, S. Saon, R.Q. Malik, Z.H. Kareem, M.A. Bin Ahmadon and S. Yamaguchi, Identification of driving safety profiles in vehicle to vehicle communication system based on vehicle OBD information. Information, 12(5), 194, 2021. https://doi.org/10.3390/info12050194
  10. K. Mohammed, M. Abdelhafid, K. Kamal, N. Ismail and A. Ilias, Intelligent driver monitoring system: An Internet of Things-based system for tracking and identifying the driving behavior, Computer Standards & Interfaces, 84, 103704, 2023. https://doi.org/10. 1016/j.csi.2022.103704
  11. A. Pirayre, P. Michel, S.S. Rodriguez and A. Chasse, Driving behavior identification and real-world fuel consumption estimation with crowdsensing data. IEEE Transactions on Intelligent Transportation Systems, 23(10), 18378-18391, 2022. https://doi.org/10.1109/ TITS.2022.3169534
  12. H.Y. Lin, J.Z. Zhang and C.C. Chang, Image Data Extraction and Driving Behavior Analysis Based on Geographic Information and Driving Data, Electronics, 12(13), 2989, 2023. https://doi.org/10.3390/ electronics12132989
  13. J.Z. Zhang and H.Y. Lin, Driving Behavior Analysis and Traffic Improvement using Onboard Sensor Data and Geographic Information. In VEHITS, pp. 284-291, 28-30 April 2021.
  14. S.K. Singh and A.K. Singh, Driving pattern analysis to determine driver behaviors for local authority based on cloud using OBD II, International journal of electrical and computer engineering systems, 13(10), 937-944, 2022. https://doi.org/10.32985/ijeces.13.10.14
  15. I. Aris, M.F. Zakaria, S.M. Abdullah and R.M. Sidek, Development of OBD-II driver information system, International Journal of Engineering and Technology, 4(2), 253-259, 2007.
  16. A.A. Süzen and K. Kayaalp, Web based tracking of vehicle fault and performance data on OBD II, Scientific Journal of Mehmet Akif Ersoy University, 1(1), 13-16, 2018.
  17. M. Carignani, S. Ferrini, M. Petracca, M. Falcitelli, and P. Pagano, A prototype bridge between automotive and the IoT, In 2015 IEEE 2nd World Forum on Internet of Things (WF-IoT), sayfa 12-17, Milan, Italy, 21 January 2016.
  18. R. Kumar and A. Jain, Driving behavior analysis and classification by vehicle OBD data using machine learning, The Journal of Supercomputing, 79(16), 18800-18819, 2023. https://doi.org/10.1007/s11227-023-05364-3
  19. E.A. Sağbaş, S. Korukoglu and S. Balli, Stress Detection via Keyboard Typing Behaviors by Using Smartphone Sensors and Machine Learning Techniques, Journal of Medical Systems, 44(4):1-12, 2020. https://doi.org/10. 1007/s10916-020-1530-z
  20. S. Ballı, E.A. Sağbaş and M. Peker, Human activity recognition from smart watch sensor data using a hybrid of principal component analysis and random forest algorithm, Measurement and Control, 52(1-2), 37-45, 2019. https://doi.org/10.1177/ 0020294018813692
  21. R. Olbricht, Overpass API. Anwenderkonferenz für Freie und Open Source Software für Geoinformationssysteme, 2011.
  22. E.A. Sağbaş, Driving Helper: Araç motor operasyonlarının izlenmesi ve veri toplanması için gerçek zamanlı bir Android uygulama, 3rd International Conference on Recent Academic Studies, sayfa 441-446, Konya, Türkiye, 3-4 December 2024.
  23. E.A. Sağbaş, M. Peker and S. Balli, A novel approach for transportation mode detection: Combining t-SNE manifold learning and support vector machines, International Artificial Intelligence and Data Processing Symposium, sayfa 1-5, Malatya, 16-17 September 2017.
  24. M. Peker and İ. Kırbaş, Myoelectric Control of Hand Movements Using Data Mining Process Model, The Journal of Graduate School of Natural and Applied Sciences of Mehmet Akif Ersoy University, 7(1):84-93, 2016.
  25. T. Feng and H.J.P. Timmermans, Comparative Evaluation of Algorithms for GPS Data Imputation, 13th WCTR, Rio de Janerio, sayfa 1-11, Rio de Janerio, Brazil, 15 July 2016.
  26. B. Chandra and M. Gupta, Robust approach for estimating probabilities in Naïve–Bayes Classifier for gene expression data, Expert Systems with Applications, 38(3), 1293-1298, 2011. https://doi.org/10.1016/j. eswa.2010.06.076
  27. D.H. Wolpert, Stacked generalization. Neural networks, 5(2), 241-259, 1992. https://doi.org/10.1016/ S0893-6080(05)80023-1
  28. E. Frank, M.A. Hall and I.H. Witten, The WEKA Workbench. Online Appendix for Data Mining: Practical Machine Learning Tools and Techniques, Morgan Kaufmann, Fourth Edition, 2016.