Performance Evaluation of Major Classification Algorithms for Aggressive Driving Detection using CAN-bus Data

Year 2020, Issue: 20, 774 - 782, 31.12.2020

Berat Karabuluter , Özgür Karaduman , Murat Karabatak , Haluk Eren

https://doi.org/10.31590/ejosat.743076

Abstract

Advanced Driving Assistants Systems (ADAS) have an important milestone for unmanned vehicles. The main goal of this study is to compare the performances of major classification algorithms for aggressive driving detection, which is one of the fundamental problems of ADAS, through CAN (Control Area Network) bus sensor data. Supervised Learning based Classification Algorithms (SLCAs) are employed by this study, which are Artificial Neural Networks (ANN), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), C4.5 Algorithm (J48), and Naïve Bayesian Classifier. These algorithms utilize CAN bus (Controller Area Network Bus) data acquired by OBDII (On-board Diagnostics) socket of the vehicle to detect driver mood associated with driving style. With the aim of ground truth, aggressive and calm drive were tried by different subject drivers, and acquired CAN bus sensor data in question is labeled as "aggressive" and "calm”, in our experiments. Afterwards, these are normalized for proper modality in mentioned classification algorithms. In the end of the process, combining latter and former steps are transformed into training data to assess performances of SLCAs for driver mood detection. Resultant performance evaluation for the algorithms suggest that the Naïve Bayes Classifier is more successful than the others.

Keywords

CAN-bus, driving safety, aggressive driving, intelligent vehicles, classification algorithms

CAN-bus Verileri kullanarak Agresif Sürüş Tespiti için Temel Sınıflandırma Algoritmalarının Performans Değerlendirmesi

Abstract

İleri Sürücü Destek Sistemleri (İSDS) insansız araçlar için bir kilometre taşıdır. Bu çalışmanın temel amacı, CAN-bus sensör verilerini kullanarak İSDS’ nin temel problemlerinden birisi olan agresif sürüş tespiti yapmak için temel sınıflandırma algoritmalarının performanslarını karşılaştırmaktır. Yapay Sinir Ağları, Destek Vektör Makineleri, K-Enyakın Komşular, C4.5 Algoritması ve Naïve Bayes Sınıflandırıcısının yer aldığı bu çalışmada Eğiticili Öğrenme Tabanlı Sınıflandırma Algoritmaları (EÖSAs) kullanılmıştır. Bu algoritmalar, sürücünün ruh halini belirlemek amacıyla aracın OBDII soketinden elde edilen CAN-bus verilerini kullanır. Deneylerimizde, referans olacak ham verileri elde etmek için, farklı denekler tarafından agresif ve sakin sürüş gerçekleştirilerek elde edilen CAN-bus sensör verileri "agresif" ve "sakin" olarak etiketlenmiştir. Daha sonra bu veriler, sözkonusu sınıflandırma algoritmalarının yapısına uygun hale gelmesi için normalize edilmiştir. İşlemin sonunda, sonraki ve önceki adımlar birleştirilerek, sürücü ruh halini tespit etmek için EÖSA’ ların performansını değerlendirmek üzere eğitim verilerine dönüştürülmüştür. Belirtilen algoritmalar için yapılan performans değerlendirmesi sonucunda, Naïve Bayes sınıflandırıcısının diğerlerinden daha başarılı olduğu görülmüştür.

Keywords

CAN veriyolu, sürüş güvenliği, agresif sürüş, akıllı araçlar, sınıflandırma algoritmaları

References

• https://www.safemotorist.com/articles/road_rage.aspx (21.05.2020)
• https://www.iii.org/fact-statistic/facts-statistics-aggressive-driving (19.05.2020)
• https://aaafoundation.org/2015-traffic-safety-culture-index/ (21.05.2020)
• http://www.tuik.gov.tr/ (21.05.2020)
• Kumtepe, Ö., Akar, G. B. and Yüncü, E., 2015. “On Vehicle Aggressive Driving Behavior Detection Using Visual Information”, Signal Processing and Communications Applications Conference (SIU), Malatya, Turkey, pp: 795-798.
• Kumtepe, Ö., Yüncü, E. and Akar, G. B., 2016. “A Multimodal Approach for Aggressive Driving Detection”, Signal Processing and Communication Application Conference, Zonguldak, Turkey, pp: 729-732.
• Johnson, D. A. and Trivedi, M. M., 2011. “Driving Style Recognition Using a Smartphone as A Sensor Platform”, Conference on Intelligent Transportation Systems (ITSC), IEEE, Washington, DC, USA, pp. 1609-1615.
• Eren, H., Makinist, S, Akın, E. and Yilmaz, A. 2012. “Estimating Driving Behavior by A Smartphone”, Intelligent Vehicles Symposium (IV), IEEE, Alcala de Henares, Spain, pp. 234-239.
• Bergasa, L. M., Almería, D., Almazán, J., Yebes, J. J. and Arroyo, R., 2014. “Drivesafe: An App for Alerting Inattentive Drivers and Scoring Driving Behaviors”, Intelligent Vehicles Symposium, IEEE, Dearborn, MI, USA, pp. 240-245.
• Koh, D. W. and Kang, H. B., 2015. “Smartphone-Based Modeling and Detection of Aggressiveness Reactions in Senior Drivers”, Intelligent Vehicles Symposium, IEEE, Seoul, South Korea, pp. 12-17.
• Li, F., Zhang, H., Che, H., and Qiu, X., 2016. “Dangerous Driving Behavior Detection using Smartphone Sensors”, 19th International Conference on Intelligent Transportation Systems (ITSC), IEEE, Rio de Janeiro, Brazil, pp. 1902-1907.
• Oliver, R., Wegener, S., Stark, J., Judmaier, P., Michelberger, F., and Barberi, A., 2019. “Merging Virtual World with Real-Life Behavior: A Concept for a Smartphone App to Influence Young People’s Travel Behavior”, Transportation Research Record (TRR), SAGE, 2673.4, pp. 241-250.
• Imkamon, T, Saensom, P., Tangamchit, P. and Pongpaibool, P., 2008. “Detection of Hazardous Driving Behavior Using Fuzzy Logic”, International Conference on Electrical Engineering Electronics, Computer, Telecommunications and Information Technology, Krabi, Thailand, pp. 657-660.
• Wu B. F., Chen Y. H. and Yeh, C. H., 2012. “Fuzzy Logic Based Driving Behavior Monitoring Using Hidden Markov Models”, International Conference on ITS Telecommunications, Taipei, Taiwan, pp. 447-451.
• Songkroh, A., Fooprateepsiri, R. and Lilakiataskun, W., 2014. “An Intelligent Risk Detection from Driving Behavior Based On Bpnn and Fuzzy Logic Combination”, 13th International Conference on Computer and Information Science (ICIS), IEEE/ACIS, Taiyuan, China, pp. 105-110.
• Fazio, P., Santamaria, A. F., De Rango, F, Tropea, M., Serianni A., 2016. “New Application for Analyzing Driving Behaviour and Environment Characterization in Transportation Systems Based On a Fuzzy Logic Approach”, Unmanned Systems Technology XVIII, Baltimore, Maryland, United States, 13 pages.
• Arefnezhad, S., Samiee, S., Eichberger, A. and Nahvi, A., 2019. “Driver Drowsiness Detection Based On Steering Wheel Data Applying Adaptive Neuro-Fuzzy Feature Selection”, Sensors, 19(4), 943.
• Vesselenyi, T., Rus, A., Mitran, T., Moca, S., and Lehel, C., 2019. “Fuzzy Decision Algorithm for Driver Drowsiness Detection”, In SIAR International Congress of Automotive and Transport Engineering: Science and Management of Automotive and Transportation Engineering, Springer, Cham, pp. 458-467.
• Vaitkus, V., Lengvenis, P. and Žylius, G., 2014. “Driving Style Classification Using Long-Term Accelerometer Information” International Conference on Methods and Models in Automation and Robotics, Miedzyzdroje, Poland, pp. 641-644.
• Li, Y., Miyajima, C, Kitaoka, N., and Takeda, K., 2014. “Measuring Aggressive Driving Behavior Using Signals from Drive Recorders”, International Conference on Intelligent Transportation Systems (ITSC), IEEE, Qingdao, China, pp. 1886-1887.
• Vignali, V., Bichicchi, A., Simone, A., Lantieri, C., Dondi, G. and Costa, M., 2019. “Road sign vision and driver behaviour in work zones”, Transportation Research Part F: Traffic Psychology and Behaviour, 60, 474-484.
• de Naurois, C. J., Bourdin, C., Stratulat, A., Diaz, E. and Vercher, J. L., 2019. “Detection and prediction of driver drowsiness using artificial neural network models”, Accident Analysis & Prevention, 126, 95-104.
• Doshi, A. and Trivedi, M. M., 2010. “Examining The Impact of Driving Style On the Predictability and Responsiveness of the Driver: Real-World and Simulator Analysis” Intelligent Vehicles Symposium, IEEE, San Diego, CA, USA, pp. 232-237.
• Gregoriades, A. and Pampaka, M., 2013. “Driver Behaviour Analysis Through Simulation”, International Conference on Systems, Man, and Cybernetics, IEEE, Manchester, UK, pp. 3681-3686.
• Shirazi, M. M. and Rad, A. B., 2014. “Detection of Intoxicated Drivers Using Online System Identification of Steering Behavior”, Transactions on Intelligent Transportation Systems, IEEE, pp. 1738-1747.
• Keklikoglou, A., Fitzpatrick, C. D. and Knodler, M. A., 2018. “Investigation of time and speed perception using a driving simulator,” Transportation Research Record (TRR), SAGE, 2672(37), pp. 132-140.
• Dia, H., and Panwai, S., 2015. “Impact of Driving Behavior On Emissions and Road Network Performance”, International Conference on Data Science and Data Intensive Systems, IEEE, Sydney, NSW, Australia, pp. 355-361.
• Sun, J., Zhen, A., Li, C., Zhang M., Hu, X., 2016. “A Vehicles’ CO2 Emission Monitoring Platform Combined with Driver’s Driving Behavior”, International Conference on Consumer Electronics-Asia (ICCE-Asia), IEEE, Seoul, South Korea, pp. 1-2.
• Stogios, C., Kasraian, D., Roorda, M. J. and Hatzopoulou, M., 2019. “Simulating Impacts of Automated Driving Behavior and Traffic Conditions on Vehicle Emissions”, Transportation Research Part D: Transport and Environment, Elsevier, 76, 176-192.
• Faria, M. V., Duarte, G. O., Varella, R. A., Farias, T. L. and Baptista, P. C., 2019. “Driving for decarbonization: Assessing the energy, environmental, and economic benefits of less aggressive driving in Lisbon, Portugal”, Energy Research & Social Science, 47, 113-127.
• Karaduman, O., Eren, H., Kurum, H. and Celenk, M., 2013. “An Effective Variable Selection Algorithm for Aggressive/Calm Driving Detection Via CAN Bus”, International Conference on Connected Vehicles and Expo (ICCVE), IEEE, Vienna, Austria, pp. 586-591.
• Taylor, A., Japkowicz, N. and Leblanc, S., 2015. “Frequency-Based Anomaly Detection for the Automotive CAN Bus”, World Congress on Industrial Control Systems Security (WCICSS), IEEE, pp. 45-49.
• Fugiglando, U., Massaro, E., Santi, P., Milardo, S., Abida, K., Stahlmann, R., ... and Ratti, C., 2018. “Driving Behavior Analysis Through CAN Bus Data in an Uncontrolled Environment”, Transactions on Intelligent Transportation Systems, IEEE, 20(2), 737-748.
• Lokman, S. F., Othman, A. T., Bakar, M. H. A. and Musa, S., 2019. “The Impact of Different Feature Scaling Methods on Intrusion Detection for in-Vehicle Controller Area Network (CAN)”, In International Conference on Advances in Cyber Security, Springer, Singapore, pp. 195-205.
• Le, Q., Jiang, K. and Zhang, F., 2020. “Design of Automatic Detection System for Vehicle Networking Communication Abnormal Data Based On CAN Bus”, International Journal of Information and Communication Technology, 16(2), 123-139.
• Sokolova, M., Japkowicz, N, Szpakowicz, S., 2006. “Beyond Accuracy, F-Score and ROC: A Family of Discriminant Measures for Performance Evaluation”, Springer Australasian Joint Conference on Artificial Intelligence, Heidelberg, Berlin, Germany, pp. 1015-1021.