Edge AI-Assisted IoV Application for Aggressive Driver Monitoring: A Case Study on Public Transport Buses

Abstract

With increasing adoption of digital technologies to automotive industry, the revo-lution of the vehicles opens new doors for many advanced applications to improve the driver safety and comfort. Thanks to Advanced Driver Assistance Systems (ADAS), no doubt that the future driving experience will be safer than today. De-spite the emergence of new trends, road accidents caused by aggressive driving are still a major problem in many countries. This study presents an edge AI-assisted ag-gressive driver monitoring system based on Internet of Vehicles (IoV) model. In the proposed system, the kNN algorithm and dynamic time warping method are used to recognize the signal patterns of aggressive drivers. The hardware platform is built on the RP2040 microcontroller-based Raspberry Pi Pico board and the Waveshare Quad Expander used for sensor extensions. The MPU-9250 9-axis motion tracking sensor is used as an inertial measurement unit (IMU) to identify the patterns of driv-ers who did sudden lane changes, heavy acceleration, and harsh braking on the roads. Besides, the required software is created using the MicroPython scripting language via Thonny IDE. The proposed method is tested on public transport vehi-cles to determine the drivers engaging in dangerous driving behavior for passengers. The obtained results show that the proposed method can provide satisfactory success to support for recognizing the aggressive behavior of drivers.

Keywords

• aggressive driving
• machine learning
• IMU
• accelerometer
• gyroscope
• edge AI

References

1. [1] Koesdwiady A, Soua R, Karray F, Kamel MS. Recent trends in driver safety monitoring systems: State of the Art and challeng-es. IEEE Transactions on Vehicular Technology. 2017; 66(6): 4550-4563. doi: 10.1109/TVT.2016.2631604
2. [2] Schroten A, Van Grinsven A, Tol E, Leestemaker L, Schack-mann PP, Vonk-Noordegraaf D, Van Meijeren J, Kalisvaart S. Research for TRAN Committee - The impact of emerging tech-nologies on the transport system. European Parliament, Policy Department for Structural and Cohesion Policies. Brussels. 2020
3. [3] López C, Ruíz-Benítez R, Vargas-Machuca C. On the environ-mental and social sustainability of technological innovations in Urban Bus Transport: The EU Case. Sustainability. 2019; 11(5): 1413. doi: 10.3390/su11051413
4. [4] Holnicki P, Nahorski Z, Kałuszko A. Impact of vehicle fleet modernization on the traffic-originated air pollution in an urban area: A case study. Atmosphere. 2021; 12(12): 1581. doi: 10.3390/atmos12121581
5. [5] Retallack AE, Ostendorf B. Current understanding of the ef-fects of congestion on traffic accidents. International Journal of Environmental Research and Public Health. 2019; 16(18): 3400. doi: 10.3390/ijerph16183400
6. [6] Iyer LS. AI-enabled applications towards intelligent transporta-tion. Transportation Engineering. 2021; 5: 1-11. doi: 10.1016/j.treng.2021.100083
7. [7] Nguyen HP, Nguyen PQP, Bui VD. Applications of big data analytics in traffic management in intelligent transportation sys-tems. International Journal on Informatics Visualization. 2022; 6(1-2): 177-187. doi: 10.30630/joiv.6.1-2.882
8. [8] Wang D, Xu W, Jia X. Analysis of intelligent transportation system application based on internet of things and big data technology under the background of information society. Ad-vances in Multimedia. 2022; 6001355. doi: 10.1155/2022/6001355

9. [9] Sethi P, Sarangi SR. Internet of things: Architectures, protocols, and applications. Journal of Electrical and Computer Engineer-ing. 2017; 9324035. doi: 10.1155/2017/9324035
10. [10] Sobin, CC. A Survey on architecture, protocols and chal-lenges in IoT. Wireless Personal Communications. 2020; 112: 1383-1429. doi: 10.1007/s11277-020-07108-5
11. [11] Yang F, Wang S, Li J, Liu Z, Sun Q. An overview of internet of vehicles. China Communications. 2014; 11(10): 1-15. doi: 10.1109/CC.2014.6969789 [12] Ji B, Zhang X, Mumtaz S, Han C, Li C, Wen H, Wang D. Survey on the internet of vehicles: Network architectures and applications. IEEE Communications Standards Magazine. 2020; 4(1): 34-41. doi: 10.1109/MCOMSTD.001.1900053
12. [13] Kaiwartya O, Abdullah AH, Cao Y, Altameem A, Prasad M, Lin C-T, Liu X. Internet of vehicles: Motivation, layered ar-chitecture, network model, challenges, and future aspects. IEEE Access. 2016; 4: 5356-5373. doi: 10.1109/ACCESS.2016.2603219
13. [14] Kalsoom N, Ahmad I, Alroobaea R, Raza MA, Khalid S, Ahmed Z, Ali I. Architecture for Resource allocation in the in-ternet of vehicles for cooperating driving system. Journal of Advanced Transportation. 2021; 6637568. doi: 10.1155/2021/6637568
14. [15] Jameel F, Chang Z, Huang J, Ristaniemi T. Internet of autonomous vehicles: Architecture, features, and socio-technological challenges. IEEE Wireless Communications. 2019; 26(4): 21-29. doi: 10.1109/MWC.2019.1800522
15. [16] Abbas MT, Muhammad A, Song W-C. Road-Aware es-timation model for path duration in internet of vehicles (IoV). Wireless Personal Communications. 2019; 109: 715-738. doi: 10.1007/s11277-019-06587-5
16. [17] Sahbi R, Ghanemi S, Djouani R. A network model for internet of vehicles based on SDN and cloud computing. 6th International Conference on Wireless Networks and Mobile Communications, Marrakesh. 2018; 1-4, doi: 10.1109/WINCOM.2018.8629610
17. [18] Chu W, Wuniri Q, Du X, Xiong Q, Huang T, Li K. Cloud control system architectures, technologies and applications on intelligent and connected vehicles: a Review. Chinese Journal of Mechanical Engineering. 2021; 34, 139. doi: 10.1186/s10033-021-00638-4
18. [19] Kumar S, Sharma H, Singh G, Neetu, Chugh H. Internet of vehicles (IoV): A 5G connected car. Advances and Applica-tions in Mathematical Sciences. 2020; 19(5): 363-370.
19. [20] Mahmood Z. Connected vehicles in the IoV: Concepts, technologies and architectures. InConnected vehicles in the in-ternet of things: concepts, technologies and frameworks for the IoV 2020 Jan 14 (pp. 3-18). Cham: Springer International Pub-lishing. https://doi.org/10.1007/978-3-030-36167-9_1
20. [21] Lv Z, Chen D, Wang Q. Diversified technologies in in-ternet of vehicles under intelligent edge computing. IEEE Transactions on Intelligent Transportation Systems. 2021; 22(4): 2048-2059. doi: 10.1109/TITS.2020.3019756
21. [22] Chang Z, Liu S, Xiong X, Cai Z, Tu G. A Survey of re-cent advances in edge-computing-powered artificial intelligence of things. IEEE Internet of Things Journal. 2021; 8(18): 13849-13875. doi: 10.1109/JIOT.2021.3088875.
22. [23] Merenda M, Porcaro C, Iero D. Edge machine learning for AI-enabled IoT Devices: A review. Sensors. 2020; 20(9), 2533. doi: 10.3390/s20092533
23. [24] Sakr F, Bellotti F, Berta R, De Gloria A. Machine learn-ing on mainstream microcontrollers. Sensors. 2020; 20(9), 2638. doi: 10.3390/s20092638
24. [25] Mendez J, Bierzynski K, Cuéllar MP, Morales DP. Edge intelligence: concepts, architectures, applications, and future di-rections. ACM Transactions on Embedded Computing Systems. 2022; 21(5): 1-41. doi: 10.1145/3486674
25. [26] Li Y, Xue F, Feng L, Qu Z. A driving behavior detection system based on a smartphone’s built-in sensor. International Journal of Communication Systems. 2016; 30: 1-13. doi: 10.1002/dac.3178
26. [27] Zylius G. Investigation of route-independent aggressive and safe driving features obtained from accelerometer signals. IEEE Intelligent Transportation Systems Magazine. 2017; 9(2): 103-113. doi: 10.1109/MITS.2017.2666583
27. [28] Martinez CM, Heucke M, Wang F-Y, Gao B, Cao D. Driving style recognition for intelligent vehicle control and ad-vanced driver assistance: A survey. IEEE Transactions on Intel-ligent Transportation Systems. 2018; 19(3): 666-676. Doi: 10.1109/TITS.2017.2706978
28. [29] Chhabra R, Verma Seema, Krishna CR. Detecting ag-gressive driving behavior using mobile smartphone. 2nd Inter-national Conference on Communication, Computing and Net-working, India. 2018; 513–521. doi: 10.1007/978-981-13-1217-5_49
29. [30] Moukafih Y, Hafidi H, Ghogho M. Aggressive driving detection using deep learning-based time series classification. Proceedings of the International Symposium on INnovations in Intelligent SysTems and Applications (INISTA), Sofia, Bulgaria. 2019; 1-5. doi: 10.1109/INISTA.2019.8778416
30. [31] Azadani MN, Boukerche A. Performance evaluation of driving behavior identification models through CAN-BUS data. Proceedings of the IEEE Wireless Communications and Net-working Conference (WCNC), Seoul, Korea (South). 2020; 1-6. doi: 10.1109/WCNC45663.2020.9120734
31. [32] Schlegel K, Mirus F, Neubert P, Protzel P. Multivariate time series analysis for driving style classification using neural networks and hyperdimensional computing. Proceedings of the IEEE Intelligent Vehicles Symposium (IV), Nagoya, Japan. 2021; 602-609. doi: 10.1109/IV48863.2021.9576028
32. [33] Abdulwahid SN, Mahmoud MA, Ibrahim N, Zaidan BB, Ameen HA. Modeling motorcyclists’ aggressive driving behav-ior using computational and statistical analysis of real-time driving data to improve road safety and reduce accidents. In-ternational Journal of Environmental Research and Public Health. 2022; 19(13): 1-20. doi: 10.3390/ijerph19137704
33. [34] Monselise M, Yang CC. Detecting aggressive driving patterns in drivers using vehicle sensor data. Transportation Re-search Interdisciplinary Perspectives. 2022; 14:1-11. doi: 10.1016/j.trip.2022.100625
34. [35] Romero O, Miura AS, Parra L, Lloret J. Low-cost system for automatic recognition of driving pattern in assessing inter-urban mobility using geo-information. ISPRS International Journal of Geo-Information. 2022; 11(12): 1-18. doi:10.3390/ijgi11120597
35. [36] Gao Y, Zhu J. Characteristics, Impacts and trends of urban transportation. Encyclopedia. 2022; 2: 1168-1182. doi: 10.3390/encyclopedia2020078
36. [37] Bauer M, Dźwigoń W, Okraszewska R. Analysis of rea-sons of accidents between cyclists and public transport vehicles in cities. 5th International Conference on Road and Rail Infra-structure (CETRA), Zadar. 2018; 1409-1415. doi: 10.5592/CO/cetra.2018.92
37. [38] Bhattacharya S, Jha H, Nanda RP. Application of IoT and artificial intelligence in road safety. International Confer-ence on Interdisciplinary Research in Technology and Man-agement (IRTM), Kolkata. 2022; 1-4. doi: 10.1109/IRTM54583.2022.9791529
38. [39] Torbaghan ME, Sasidharan M, Reardon L, Muchanga-Hvelplund LCW. Understanding the potential of emerging digi-tal technologies for improving road safety. Accident Analysis & Prevention. 2022; 166, 106543. doi: 10.1016/j.aap.2021.106543
39. [40] Smith AP. A UK survey of driving behaviour, fatigue, risk taking and road traffic accidents. BMJ Open. 2016; 6(8): 1-6. doi: 10.1136/bmjopen-2016-011461 [41] Martinez CM, Heucke M, Wang F-Y, Gao B, Ca o D. Driving style recognition for intelligent vehicle control and ad-vanced driver assistance: A survey. IEEE Transactions on Intel-ligent Transportation Systems. 2018; 19(3): 666-676. doi: 10.1109/TITS.2017.2706978
40. [42] Szumska EM, Jurecki R. The Effect of aggressive driv-ing on vehicle parameters. Energies. 2020; 13(24): 6675. doi: 10.3390/en13246675
41. [43] Junior JF, Carvalho E, Ferreira BV, de Souza C, Suhara Y, Pentland A, Pessin G. Driver behavior profiling: An investi-gation with different smartphone sensors and machine learning. PLoS ONE. 2017; 12(4): 1-16. doi: 10.1371/journal.pone.0174959
42. [44] Temurtaş H. Estimation of vehicle signals for autono-mous driving applications. MSc Thesis. Middle East Technical University; 2022.
43. [45] Liu X, Mei H, Lu H, Kuang H, Ma X. A vehicle steering recognition system based on low-cost smartphone sensors. Sen-sors. 2017; 17(3): 1-29. Doi: 10.3390/s17030633
44. [46] Rahmani AM, Azhir E, Ali S, Mohammadi M, Ahmed OH, Ghafour MY, Ahmed SH, Hosseinzadeh M. Artificial in-telligence approaches and mechanisms for big data analytics: A systematic study. PeerJ Comput Science. 2021; 14(7): 1-28. doi: 10.7717/peerj-cs.488
45. [47] Linardatos P, Papastefanopoulos V, Kotsiantis S. Ex-plainable AI: A review of machine learning interpretability methods. Entropy. 2021; 23(1), 18. doi: 10.3390/e23010018
46. [48] Alloghani M, Al-Jumeily D, Mustafina J, Hussain A, Aljaaf AJ. A systematic review on supervised and unsupervised machine learning algorithms for data science. In: Berry M, Mo-hamed A, Yap B. (Eds) Supervised and Unsupervised Learning for Data Science. Unsupervised and Semi-Supervised Learning. Springer, Cham; 2020. 3-22. doi: 10.1007/978-3-030-22475-2_1
47. [49] Ghandour R, Potams AJ, Boulkaibet I, Neji B, Al Barakeh Z. Driver behavior classification system analysis using machine learning methods. Applied Sciences. 2021; 11(22), 10562. doi: 10.3390/app112210562
48. [50] Akpan UI, Starkey A. Review of classification algo-rithms with changing inter-class distances. Machine Learning with Applications. 2021; 4, 100031. doi: 10.1016/j.mlwa.2021.100031
49. [51] Suyal M, Goyal P. A review on analysis of K-nearest neighbor classification machine learning algorithms based on supervised learning. International Journal of Engineering Trends and Technology. 2022; 70(7): 43-48. doi: 10.14445/22315381/IJETT-V70I7P205
50. [52] Haque MM, Sarker S, Dewan MAA. Driving maneuver classification from time series data: a rule-based machine learn-ing approach. Applied Intelligence. 2022; 52: 16900–16915. doi: 10.1007/s10489-022-03328-3
51. [53] Brahim SB, Ghazzai H, Besbes H, Massoud Y. A ma-chine learning smartphone-based sensing for driver behavior classification. Proceedings of the IEEE International Symposi-um on Circuits and Systems (ISCAS), Austin, Texas, USA. 2022; 610-614. doi: 10.1109/ISCAS48785.2022.9937801
52. [54] Ping P, Qin W, Xu Y, Miyajima C, Takeda K. Impact of driver behavior on fuel consumption: Classification, evaluation and prediction using machine learning, IEEE Access. 2019; 7: 78515-78532. doi: 10.1109/ACCESS.2019.2920489
53. [55] Taunk K, De S, Verma S, Swetapadma A. A brief review of nearest neighbor algorithm for learning and classification. Proceedings of the International Conference on Intelligent Computing and Control Systems (ICCS), Madurai, India. 2019; 1255-1260. doi: 10.1109/ICCS45141.2019.9065747
54. [56] Hu L-Y, Huang M-W, Ke S-W, Tsai C-F. The distance function effect on k-nearest neighbor classification for medical datasets. Springer Plus. 2016; 5: 1-9. doi: 10.1186/s40064-016-2941-7
55. [57] Sakoe H, Chiba S. Dynamic programming algorithm optimization for spoken word recognition. IEEE Transactions on Acoustics, Speech, and Signal Processing. 1978; 26(1): 43–49. Doi: 10.1109/TASSP.1978.1163055
56. [58] Aggarwal CC. Data classification algorithms and applica-tions. USA: CRC Press; 2015.
57. [59] Eren H, Makinist S, Akin E, Yilmaz A. Estimating driv-ing behavior by a smartphone. Intelligent Vehicles Symposium, Alcalá de Henares. 2012; 234-239. doi: 10.1109/IVS.2012.6232298