Email this article Hybrid RFCNN Model for Accurate Prediction of Road Accident Severity
Abstract
The socio-economic impact of road accidents is huge in developing countries. Employing appropriate measures of defining determinants of accident severity enhances emergency response and informed policy decisions. This study proposes a hybrid framework RFCNN that integrates deep learning and machine learning conducted by combining Random Forest (RF) and Convolutional Neural Network (CNN). Through utilizing the US Road Accident dataset, crucial parameters such as temperature, visibility and other weather were retrieved. The model was implemented with all available features as well as selected features, producing superior results echoing discoveries made with RF, AdaBoost and the CNN systems. This hybrid model helps automate accident severity prediction and offers an intelligent tool to support transportation safety management and emergency response planning.
Keywords
References
World Health Organization, Global Status Report on Road Safety 2015, World Health Org., Geneva, Switzerland, 2015.
W. Gissane, ‘‘Accidents—A modern epidemic,’’ J. Inst. Health Educ., vol. 3, no. 1, pp. 16–18, 1965.
H. Manner and L. Wünsch-Ziegler, ‘‘Analyzing the severity of accidents on the German autobahn,’’ Accident Anal. Prevention, vol. 57, pp. 40–48, Aug. 2013.
J. C. Milton, V. N. Shankar, and F. L. Mannering, ‘‘Highway accident severities and the mixed logit model: An exploratory empirical analysis,’’ Accident Anal. Prevention, vol. 40, no. 1, pp. 260–266, 2008.
N. V. Malyshkina and F. L. Mannering, ‘‘Markov switching multinomial logit model: An application to accident-injury severities,’’ Accident Anal. Prevention, vol. 41, no. 4, pp. 829–838, Jul. 2009.
K. Haleem, P. Alluri, and A. Gan, ‘‘Analyzing pedestrian crash injury severity at signalized and non-signalized locations,’’ Accident Anal. Prevention, vol. 81, pp. 14–23, Aug. 2015.
M. Bedard, G. H. Guyatt, M. J. Stones, and J. P. Hirdes, ‘‘The independent contribution of driver, crash, and vehicle characteristics to driver fatalities,’’ Accid Anal. Prevention, vol. 34, no. 6, pp. 717–727, 2002.
S. S. Zajac and J. N. Ivan, ‘‘Factors influencing injury severity of motor vehicle–crossing pedestrian crashes in rural connecticut,’’ Accident Anal. Prevention, vol. 35, no. 3, pp. 369–379, May 2003.
W.-H. Chen and P. P. Jovanis, ‘‘Method for identifying factors contributing to driver-injury severity in traffic crashes,’’ Transp. Res. Rec., J. Transp. Res. Board, vol. 1717, no. 1, pp. 1–9, Jan. 2000.
S. Sarkar, S. Vinay, R. Raj, J. Maiti, and P. Mitra, ‘‘Application of optimized machine learning techniques for prediction of occupational accidents,’’ Comput. Oper. Res., vol. 106, pp. 210–224, Jun. 2019.
K. Rumar, ‘‘Transport safety visions, targets and strategies: Beyond 2000,’’ First Eur. Transp. Saf. Lecture, Brussels, Eur. Transp. Saf. Council, pp. 6–8, 1999.
T. Hummel, ‘‘Land use planning in safer transportation network planning,’’ Leidschendam, Inst. Road Saf. Res., Citeseer, 2001.
A. S. Edlin, Per-Mile Premiums for Auto Insurance. Cambridge, MA, USA: National Bureau of Economic Research, Dec. 1998. [Online]. Available: https://ssrn.com/abstract=142667, doi: 10.2139/ssrn.142667.
R. Wittink, ‘‘Promotion of mobility and safety of vulnerable road users: Final report of the European research project promising (promotion of measures for vulnerable road users),’’ Inst. Road Saf. Res., Tech. Rep., 2001.
D. Mohan and G. Tiwari, ‘‘Traffic safety in low-income countries: Issues and concerns regarding technology transfer from high-income countries,’’ in Reflections of the Transfer of Traffic Safety Knowledge to Motorising Nations, vol. 56. Melbourne, Global Traffic Safety Trust, 1998.
S. Ameratunga, M. Hijar, and R. Norton, ‘‘Road-traffic injuries: Confronting disparities to address a global-health problem,’’ Lancet, vol. 367, no. 9521, pp. 1533–1540, May 2006.
M. N. Ghani, A. Zainuddin, R. R. Umar, and H. Hussain, ‘‘Use of exposure control methods to tackle motorcycle accidents in Malaysia research report 3/98,’’ Road Saf. Res. Centre, Serdang, Malaysia, Tech. Rep., 1998.
T. Litman, ‘‘Integrating public health objectives in transportation decisionmaking,’’ Amer. J. Health Promotion, vol. 18, no. 1, pp. 103–108, Sep. 2003.
P. F. Waller, ‘‘The genesis of GDL,’’ J. Saf. Res., vol. 34, no. 1, pp. 17–23, Jan. 2003.
Y. Zou, B. Lin, X. Yang, L. Wu, M. M. Abid, and J. Tang, ‘‘Application of the Bayesian model averaging in analyzing freeway traffic incident clearance time for emergency management,’’ J. Adv. Transp., vol. 2021, pp. 1–9, Mar. 2021.
Refbacks
- There are currently no refbacks.
Copyright © 2013, All rights reserved.| ijseat.com
International Journal of Science Engineering and Advance Technology is licensed under a Creative Commons Attribution 3.0 Unported License.Based on a work at IJSEat , Permissions beyond the scope of this license may be available at http://creativecommons.org/licenses/by/3.0/deed.en_GB.
Â