Abstract
Pedestrians have a higher risk of casualties on the road. To improve the situation, it is essentially needed to understand the factors contributing to fatal accidents and their contributions to frame better regulations. Yet there is a dearth of substantial superior indexes that classifies the severity of the pedestrian injury. Machine learning (ML) has been successfully implemented in many domains but it is not widely utilized in the development of pedestrian road safety rules and regulations. In this paper, an ML approach is presented to generate a set of rules for predicting the severity of an accident based on several factors, including the number of vehicles, speed of vehicles, and environment. Out of thirty-four variables, 20 variables are selected using the Chi-square technique. Three popular ML algorithms, namely Support Vector Machine (SVM), Random Forest (RF), and Decision Tree (DT) are used for the prediction of injury severity. From experiments, RF and DT are found to have similar accuracy scores, and hence, DT has been selected since it is simple to interpret and to generate a set of ‘if-then’ rules. A total of 20 safety decision rules are retrieved from the dataset, which explains the factors behind the severity of the pedestrian injury.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
References
Breiman L (2001) Random forests. Mach Learn 45(1):5–32
Breiman L, Friedman J, Stone CJ, Olshen RA (1984) Classification and regression trees. CRC Press, Boca Raton
Chen C, Zhang G, Qian Z, Tarefder RA, Tian Z (2016) Investigating driver injury severity patterns in rollover crashes using support vector machine models. Accid Anal & Prev 90:128–139
Cunto FJ, Ferreira S (2017) An analysis of the injury severity of motorcycle crashes in brazil using mixed ordered response models. J Trans Safety & Secur 9(sup1):33–46
Gårder PE (2004) The impact of speed and other variables on pedestrian safety in maine. Accid Anal & Prev 36(4):533–542
LaScala EA, Gerber D, Gruenewald PJ (2000) Demographic and environmental correlates of pedestrian injury collisions: a spatial analysis. Accid Anal & Prev 32(5):651–658
Liu J, Hainen A, Li X, Nie Q, Nambisan S (2019) Pedestrian injury severity in motor vehicle crashes: an integrated spatio-temporal modeling approach. Accid Anal & Prev 132:105272
Loo BP, Tsui K (2007) Factors affecting the likelihood of reporting road crashes resulting in medical treatment to the police. Inj Prev 13(3):186–189
Milton JC, Shankar VN, Mannering FL (2008) Highway accident severities and the mixed logit model: an exploratory empirical analysis. Accid Anal & Prev 40(1):260–266
Poh CQ, Ubeynarayana CU, Goh YM (2018) Safety leading indicators for construction sites: a machine learning approach. Autom Constr 93:375–386
Pramanik A, Harshvardhan, Djeddi C, Sarkar S, Maiti J (2020) Region proposal and object detection using hog-based cnn feature map. In: 2020 international conference on data analytics for business and industry: way towards a sustainable economy (ICDABI). IEEE, pp 1–5
Pramanik A, Sarkar S, Maiti J (2019) Oil spill detection using image processing technique: an occupational safety perspective of a steel plant. In: Emerging technologies in data mining and information security, vol 814. Springer, Singapore, pp 247–257
Pramanik A, Sarkar S, Maiti J (2021) A real-time video surveillance system for traffic pre-events detection. Accid Anal & Prev 154:106019
Pramanik A, Sarkar S, Maiti J, Mitra P (2021) Rt-gsom: rough tolerance growing self-organizing map. Inf Sci 566:19–37
Sarkar S, Baidya S, Maiti J (2017) Application of rough set theory in accident analysis at work: a case study. In: ICRCICN 2017, pp 245–250
Sarkar S, Chain M, Nayak S, Maiti J (2019) Decision support system for prediction of occupational accident: a case study from a steel plant. In: Emerging technologies in data mining and information security, vol 813. Springer, Singapore, pp 787–796
Sarkar S, Ejaz N, Maiti J (2018) Application of hybrid clustering technique for pattern extraction of accident at work: a case study of a steel industry. In: 2018 4th international conference on recent advances in information technology (RAIT), IIT Dhanbad. IEEE, pp 1–6
Sarkar S, Maiti J (2020) Machine learning in occupational accident analysis: a review using science mapping approach with citation network analysis. Saf Sci 131:104900
Sarkar S, Pateshwari V, Maiti J (2017) Predictive model for incident occurrences in steel plant in India. In: ICCCNT 2017, pp 1–5
Sarkar S, Pramanik A, Khatedi N, Maiti J (2020) An investigation of the effects of missing data handling using ‘r’-packages. In: Data engineering and communication technology. Springer, Singapore, pp 275–284
Sarkar S, Pramanik A, Maiti J, Reniers G (2020) Predicting and analyzing injury severity: a machine learning-based approach using class-imbalanced proactive and reactive data. Saf Sci 125:104616
Sarkar S, Raj R, Vinay S, Maiti J, Pratihar DK (2019) An optimization-based decision tree approach for predicting slip-trip-fall accidents at work. Saf Sci 118:57–69
Sarkar S, Vinay S, Djeddi C, Maiti J (2021) Text mining-based association rule mining for incident analysis: a case study of a steel plant in india. Pattern Recog Artif Intell 1322:257
Sarkar S, Vinay S, Raj R, Maiti J, Mitra P (2019) Application of optimized machine learning techniques for prediction of occupational accidents. Comput & Oper Res 106:210–224
Schneider RJ, Ryznar RM, Khattak AJ (2004) An accident waiting to happen: a spatial approach to proactive pedestrian planning. Accid Anal & Prev 36(2):193–211
Singh K, Raj N, Sahu S, Behera R, Sarkar S, Maiti J (2015) Modelling safety of gantry crane operations using petri nets. Int J Injury Control Safety Prom 1–12
Tang F, Ishwaran H (2017) Random forest missing data algorithms. Stati Anal Data Min: ASA Data Sci J 10(6):363–377
Vapnik V (1995) The nature of statistical learning theory, vol 8. Search PubMed, p 188
Verma A, Chatterjee S, Sarkar S, Maiti J (2018) Data-driven mapping between proactive and reactive measures of occupational safety performance. In: Industrial safety management- 21st century perspective of Asia. Springer, Singapore, pp 53–63
Wong S, Sze NN, Li YC (2007) Contributory factors to traffic crashes at signalized intersections in hong kong. Accid Anal & Prev 39(6):1107–1113
Ye F, Lord D (2014) Comparing three commonly used crash severity models on sample size requirements: multinomial logit, ordered probit and mixed logit models. Anal Methods Accid Res 1:72–85
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Rao, A., Sarkar, S., Pramanik, A., Maiti, J. (2022). Predicting and Analysing Pedestrian Injury Severity: A Machine Learning-Based Approach. In: Giri, D., Raymond Choo, KK., Ponnusamy, S., Meng, W., Akleylek, S., Prasad Maity, S. (eds) Proceedings of the Seventh International Conference on Mathematics and Computing . Advances in Intelligent Systems and Computing, vol 1412. Springer, Singapore. https://doi.org/10.1007/978-981-16-6890-6_36
Download citation
DOI: https://doi.org/10.1007/978-981-16-6890-6_36
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-6889-0
Online ISBN: 978-981-16-6890-6
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)