Deep Learning Model for Detection and Severity Analysis of Car Accidents

• Autorzy: Chatterjee Tanusree , Roy Priya , Karmakar Kamalesh , Munshi Shiladitya , Roy Sanjib

Identyfikatory

DOI

10.2478/fcds-2024-0012

• Języki publikacji: EN

Abstrakty

EN

On-road car accidents are immensely unfortunate but quite common occurrences worldwide. Instant data-centric and informed decisions of crisis management are rarely experienced due to the absence of real-time car accident detection and severity analysis mechanisms. On this background, the current paper presents a deep learning model for car accident detection and analysis of its severity so that the crisis management activities might follow without any delay saving invaluable human lives. The existing works lack in using time-series data, the proper learning model for accurate prediction, and minimizing the time taken in post-accident scenarios for the victims to receive immediate medical help. This paper introduces the Long Short Term Memory (LSTM) model in conjunction with the Gradient Boosted Regression Trees (GBRT) technique for the determination of car accidents with different levels of severity. The proposed model works with the accelerometer and gyroscopic data collected through an application installed in the smartphones of the users inside the car. The LSTM-GBRT hybrid model is proposed to achieve higher accuracy than LSTM which deals with time-variant data. The satisfactory performance of the proposed technique has been reported and the results are extensively investigated in comparison with another hybrid technique such as LSTM with Random Forest (RF) as well. The statistics confirm the superiority of the proposed model over other parallel models in terms of several performance metrics, like Accuracy, Precision, etc.

Słowa kluczowe

EN

deep learning; long short time memory; gradient boosted regression tree; car accident analytics

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Foundations of Computing and Decision Sciences
• Rocznik: 2024
• Tom: Vol. 49, No. 3
• Strony: 201--231
• Opis fizyczny: Bibliogr. 28 poz., rys., tab.

Twórcy

autor

Chatterjee Tanusree

• Future Institute of Technology Kolkata, India

autor

Roy Priya

• Future Institute of Engg. & Management Kolkata, India

autor

Karmakar Kamalesh

• Techno International New Town Kolkata, India

autor

Munshi Shiladitya

• Techno India University Tripura Agartala, India

autor

Roy Sanjib

• Future Institute of Technology Kolkata, India

Bibliografia

• [1] Road Traffic Injuries, World Health Organization, https://www.who.int/news-room/fact-sheets/detail/road-traffic-injuries, accessed on Jan 02, 2024.
• [2] List of countries by traffic-related death rate, Wikipedia, $https://en.wikipedia.org/wiki/List_of_countries_by_traffic-related_death_rate$, accessed on May 02, 2023.
• [3] Road Accidents in India 2021 Report, Ministry of Road Transport and Highways, Transport Research Wing, Govt. of India; $https://morth.nic.in/sites/default/files/RA\_2021\_Compressed.pdf$. accessed on May 30, 2023.
• [4] India Records 1,55,622 Road Accident Deaths in 2022 Report; $https://www.carandbike.com/news/india-records-1-55-622-road-accident-deaths-in-2022-3204563$. accessed on May 30, 2023.
• [5] Traffic Accidents Report Chapter 1A; https://ncrb.gov.in/sites/default/files/adsi2020\_Chapter-1A-Traffic-Accidents.pdf. accessed May 30, 2023.
• [6] Delay causes most deaths: Neurosurgeons, Times of India Report, $https://timesofindia.indiatimes.com/city/ranchi/delay-causes-most-deaths-neurosurgeons/articleshow/12818312.cms$. accessed May 30, 2023.
• [7] Aloul, F. et. al. (2015). iBump: Smartphone application to detect car accidents. Computers & Electrical Engineering Journal, vol.43, pp. 66-75. doi: 10.1016/j.compeleceng.2015.03.003.
• [8] Andersson, E., Berggren, Z. (2017). A Comparison Between MongoDB and MySQL Document Store Considering Performance. $https://www.diva-portal.org/smash/get/diva2:1161166/FULLTEXT01.pdf$ accessed on Feb 05, 2023.
• [9] Antony, J., Jayaseelan, V., Olickal, J. J., Alexis, J., & Sakthivel, M. (2021). Time to reach health-care facility and hospital exit outcome among road traffic accident victims attending a tertiary care hospital, Puducherry. Journal of education and health promotion, 10(429), pp. 1-6. doi: 10.4103/jehp.jehp\_109\_21.
• [10] Balfaqih, M. et. al. (2022). An Accident Detection and Classification System Using Internet of Things and deep Learning towards Smart City. Sustainability, 14(210). doi: 10.3390/su14010210.
• [11] Chang, W. J., Chen, L. B., Su, K. Y. (2019). Deepaccident: A Deep Learning-Based Internet of Vehicles System for Head-On and Single-Vehicle Accident Detection With Emergency Notification. IEEE Access, vol.7, pp. 148163-148175, doi: 10.1109/ACCESS.2019.2946468.
• [12] Hochreiter S., Schmidhuber J., Long Short-Term Memory, in Neural Computation, vol. 9, no. 8, pp. 1735-1780, 15 Nov. 1997, doi:10.1162/neco.1997.9.8. 1735.
• [13] Hozhabr Pour, H. et. al. (2022). A deep Learning Framework for Automated Accident Detection Based on Multimodal Sensors in Cars. Sensors, 22(10): 3634. doi: 10.3390/s22103634.
• [14] Li, P., Abdel-Aty, M., Yuan, J. (2020). Real-time crash risk prediction on arterials based on LSTM-CNN, Accident Analysis, and Prevention Journal, vol. 135, pp.1-9. doi:10.1016/j.aap.2019.105371.
• [15] Ma Z., Mei G., Cuomo S. (2021). An analytic framework using deep learning for prediction of traffic accident injury severity based on contributing factors. Accident Analysis & Prevention Journal, vol. 160, pp. 106322. doi: 10.1016/j.aap.2021.106322.
• [16] Mannering, F. L., Shankar, V. and Bhat, C. R. (2016). Unobserved heterogeneity and the statistical analysis of highway accident data, Analytic Methods in Accident Research, vol. 11, pp. 1-16. doi: 10.1016/j.amar.2016.04.001.
• [17] Mannering, F. L., Bhat, C. R. (2014). Analytic methods in accident research: Methodological frontier and future directions. Analytic Methods in Accident Research, vol. 1, pp.1-22. doi: 10.1016/j.amar.2013.09.001.
• [18] Mishra S., Rajendran P. K., Vecchietti L. F., Har D., “Sensing Accident-Prone Features in Urban Scenes for Proactive Driving and Accident Prevention,” in IEEE Transactions on Intelligent Transportation Systems, vol. 24, no. 9, pp. 9401-9414, Sept. 2023, doi: 10.1109/TITS.2023.3271395.
• [19] Prettenhofer, P., Louppe, G. (23 February 2014). Gradient Boosted Regression Trees in Scikit-Learn [Paper presentation]. PyData 2014, London, United Kingdom. https://hdl.handle.net/2268/163521.
• [20] Roy, S., Kumari, A., Roy, P., Banerjee, R. (2020, September). An arduino based automatic accident detection and location communication system. In 2020 IEEE 1st International Conference for Convergence in Engineering (ICCE) (pp. 38-43). IEEE. doi: 10.1109/ICCE50343.2020.9290701.
• [21] S-H Jo et. al. (2021). A Study on the Application of LSTM to Judge Bike Accidents for Inflating Wearable Airbags, Sensors, 2021, 21(19):6541. doi: 10.3390/s21196541.
• [22] Sarker, I. H.: Deep Cybersecurity: A Comprehensive Overview from Neural Network and Deep Learning Perspective. SN COMPUT. SCI. 2, 154 (2021). doi: 10.1007/s42979-021-00535-6.
• [23] Singh S., Yadav V. (2021). An Improved Particle Swarm Optimization for Prediction of Accident Severity. IJEER, vol. 9(3), pp. 42-7. doi: 10.37391/IJEER. 090304.
• [24] Uguz, S. Buyukgokoglan, E. (2022).A Hybrid CNN-LSTM Model for Traffic Accident Frequency Forecasting During the Tourist Season, Tehnicki Vjesnik, vol.9(6), pp. 2083-2089, doi: 10.17559/TV-20220225141756.
• [25] Yu, Y., Si, X., Hu, C., Zhang, J. (2019). A review of recurrent neural networks: LSTM cells and network architectures. Neural computation, 31(7), 1235-1270. doi: 10.1162/neco\_a\_01199.
• [26] Zhang, C. (2021). Spatio-Temporal ConvLSTM for Crash Prediction: A unique deep learning approach for accident prediction, https://towardsdatascience.com/spatial-temporal-convlstm-for-crash-prediction-411909ed2cfa accessed on April 23, 2023.
• [27] Zhang, Z., Yang, W., Wushour, S.(2020). Traffic Accident Prediction Based on LSTM-GBRT Model, Journal of Control Science and Engineering, vol.2020, Article ID. 4206919. doi: 10.1155/2020/4206919.
• [28] https://datatracker.ietf.org/doc/html/rfc7946.

Uwagi

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