Utilizing LSTM networks for the prediction of driver behavior

• Autorzy: Darsono Abd Majid , Mat Yazi Nurul Husna , Ja’afar Abd Shukur , Othman Mohd Azlishah , Ahmad Muhammad Imran

Identyfikatory

DOI

10.15199/48.2024.04.34

Warianty tytułu

PL

Wykorzystanie sieci LSTM do przewidywania zachowań kierowców

• Języki publikacji: EN

Abstrakty

EN

The driving behaviour prediction system was extensively utilised for minimising traffic accidents especially in detection of abnormal driving behaviours such as rapid acceleration, emergency braking, and sudden lane changes. This paper proposes deep learning model based on LSTM to classify driving behavior using OBD-II data. Results suggest that the proposed model exhibits a natural capability to retain and utilize temporal information in the input data, surpassing conventional machine learning methods.

PL

System przewidywania zachowania kierowcy był szeroko wykorzystywany do minimalizowania liczby wypadków drogowych, zwłaszcza do wykrywania nietypowych zachowań podczas jazdy, takich jak gwałtowne przyspieszanie, hamowanie awaryjne i nagła zmiana pasa ruchu. W artykule zaproponowano model głębokiego uczenia oparty na LSTM do klasyfikacji zachowań kierowców przy użyciu danych OBD-II. Wyniki sugerują, że proponowany model wykazuje naturalną zdolność do zatrzymywania i wykorzystywania informacji czasowych w danych wejściowych, przewyższając konwencjonalne metody uczenia maszynowego.

Słowa kluczowe

EN

driving behaviour prediction; long short-term memory; LSTM; vehicle sensors; acceleration

PL

przewidywanie zachowania podczas jazdy; pamięć długotrwała; LSTM; czujnik pojazdu; przyspieszenie

• Wydawca: Wydawnictwo SIGMA-NOT
• Czasopismo: Przegląd Elektrotechniczny
• Rocznik: 2024
• Tom: R. 100, nr 4
• Strony: 182--185
• Opis fizyczny: Bibliogr. 16 poz., rys., tab.

Twórcy

autor

Darsono Abd Majid

• Universiti Teknikal Malaysia Melaka (UTeM), Machine Learning and Signal Processing Research Group

autor

Mat Yazi Nurul Husna

• Universiti Teknikal Malaysia Melaka (UTeM), Machine Learning and Signal Processing Research Group

autor

Ja’afar Abd Shukur

• Universiti Teknikal Malaysia Melaka (UTeM), Machine Learning and Signal Processing Research Group

autor

Othman Mohd Azlishah

• Universiti Teknikal Malaysia Melaka (UTeM), Machine Learning and Signal Processing Research Group

autor

Ahmad Muhammad Imran

• Universiti Malaysia Perlis (UniMAP)

Bibliografia

• [1] World health statistics 2020: monitoring health for the SDGs, sustainable development goals. https://apps.who.int/iris/handle/10665/332070
• [2] Bolovinou, A., Amditis, A., Bellotti, F., & Tarkiainen, M. Driving style recognition for co-operative driving: a survey. In ADAPTIVE 2014: The Sixth International Conference on Adaptive and Self-Adaptive Systems and Applications (2014), pp. 73-78. International Academy, Research, and Industry Association IARIA.
• [3] N. P. Chandrasiri, K. Nawa, and A. Ishii. Driving skill classification in curve driving scenes using machine learning. Journal of Modern Transportation, 24 (2016), no. 3, pp. 196– 206. doi: 10.1007/s40534-016-0098-2.
• [4] W. Wang, J. Xi, and H. Chen. Modeling and Recognizing Driver Behavior Based on Driving Data: A Survey. Math Probl Eng, (2014) pp. 1–20. doi: 10.1155/2014/245641.
• [5] J. Chmielińska and J. Jakubowski. Application of convolutional neural network to the problem of detecting selected symptoms of driver fatigue. Przegląd Elektrotechniczny, vol. 93, no. 10, pp. 6-10, 2017
• [6] F. Lindow, C. Kaiser, A. Kashevnik, and A. Stocker. AI-Based Driving Data Analysis for Behavior Recognition in Vehicle Cabin. in 2020 27th Conference of Open Innovations Association (FRUCT), IEEE, (2020) pp. 116–125.
• [7] Waisi, Najwan & Abdullah, Nawal & Ghazal, Mohammed. The Automatic Detection of Underage Troopers from Live- Videos Based on Deep Learning. Przegląd Elektrotechniczny. (2021). 85-88.
• [8] A. Girma, X. Yan, and A. Homaifar. Driver Identification Based on Vehicle Telematics Data using LSTM-Recurrent Neural Network. IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI).(2019) pp. 894–902.
• [9] C. Zhang, R. Li, W. Kim, D. Yoon and P. Patras, "Driver Behavior Recognition via Interwoven Deep Convolutional Neural Nets With Multi-Stream Inputs," in IEEE Access, (2020) vol. 8, pp. 191138-191151.
• [10] S. Bouhsissin, N. Sael and F. Benabbou, "Driver Behavior Classification: A Systematic Literature Review," in IEEE Access, (2023) vol. 11, pp. 14128-14153. doi: 10.1109/ACCESS.2023.3243865.
• [11] W. Huang, X. Liu, M. Luo, P. Zhang, W. Wang and J. Wang, "Video-Based Abnormal Driving Behavior Detection via Deep Learning Fusions," in IEEE Access, (2019) vol. 7, pp. 64571- 64582. doi: 10.1109/ACCESS.2019.2917213.
• [12] E. Khosravi, A. M. A. Hemmatyar, M. J. Siavoshani and B. Moshiri, "Safe Deep Driving Behavior Detection (S3D)," in IEEE Access, (2022) vol. 10, pp. 113827-113838. doi: 10.1109/ACCESS.2022.3217644.
• [13] J. Xu, S. Pan, P. Z. H. Sun, S. Hyeong Park and K. Guo, "Human-Factors-in-Driving-Loop: Driver Identification and Verification via a Deep Learning Approach using Psychological Behavioral Data," in IEEE Transactions on Intelligent Transportation Systems, (2023) vol. 24, no. 3, pp. 3383-3394, March 2023, doi: 10.1109/TITS.2022.3225782.
• [14] M. H. Alkinani, W. Z. Khan and Q. Arshad, "Detecting Human Driver Inattentive and Aggressive Driving Behavior Using Deep Learning: Recent Advances, Requirements and Open Challenges," in IEEE Access,(2020) vol. 8, pp. 105008-105030, 2020, doi: 10.1109/ACCESS.2020.2999829.
• [15] N. Peppes, T. Alexakis, E. Adamopoulou, and K. Demestichas, “Driving Behaviour Analysis Using Machine and Deep Learning Methods for Continuous Streams of Vehicular Data,” Sensors,(2021) vol. 21, no. 14, p. 4704, Jul. 2021, doi: 10.3390/s21144704.
• [16] M. Z. Alom et al., “A state-of-the-art survey on deep learning theory and architectures,” Electronics (Switzerland), (2019) vol. 8, no. 3. MDPI AG. doi: 10.3390/electronics8030292.

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki i promocja sportu (2025).