PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY

 

e-ISSN 2231-8526
ISSN 0128-7680

Home / Regular Issue / JST Vol. 32 (3) Apr. 2024 / JST-4635-2023

 

An Accident Prediction Model Based on ARIMA in Kuala Lumpur, Malaysia, Using Time Series of Actual Accidents and Related Data

Boon Chong Choo, Musab Abdul Razak, Mohd Zahirasri Mohd Tohir, Dayang Radiah Awang Biak and Syafiie Syam

Pertanika Journal of Science & Technology, Volume 32, Issue 3, April 2024

DOI: https://doi.org/10.47836/pjst.32.3.07

Keywords: Accident models, accident prediction, digitalisation, Malaysia’s accidents, R studio

Published on: 24 April 2024

Recently, there has been an emerging trend to analyse time series data and utilise sophisticated tools for optimally fitting time series models. To date, Malaysian industrial accident data is underutilised and lacks informative records. Thus, this paper aims to investigate the Malaysian accident database and further evaluate the optimal forecasting models in accident prediction. The model’s input was based on available data from the Department of Occupational Safety and Health, Malaysia (DOSH), from 2018 until 2021, with 80% of the dataset to train the models and the remaining 20% for validation. The negative binomial and Poisson distribution prediction showed a mean absolute percentage error (MAPE) of 33% and 51%, respectively. It indicated that the negative binomial performed better than the Poisson distribution in accident frequency prediction. The available time series accident data were gathered for four years, and stationarity was checked in R Studio software for the Augmented Dickey-Fuller test. The lowest Akaike Information Criterion (AIC), Bayesian Information Criterion (BIC) and other error values were used to justify the best model, which was the ARIMA(2,0,2)(2,0,0)(12) model. The ARIMA models were considered after the data showed autocorrelation. The MAPE for both ARIMA in R and manual time series were 40% and 49%, respectively. Therefore, the accident prediction by using R Studio would outperform the manually negative binomial and Poisson distribution. Based on the findings, industrial safety practitioners should report accidents to DOSH truthfully in the era of digitalisation. It could enable future data-driven accident predictions to be carried out.

  • Abdulqader, Q. M., Hassan, M. T., & Ahmad, K. H. (2020). Building a mathematical SARIMA model for forecasting the number of monthly injured people by traffic accidents in Erbil City. Technology Reports of Kansai University, 62(3), Article 909916.

  • Abdullah, D. N. M. A., & Wern, G. C. M. (2011). An analysis of accidents statistics in Malaysian construction sector. International Conference on E-Business, Management and Economics, 3(1), 1–4.

  • Ahmed, A., Sadullah, A. F. M., Yahya, A. S., Akhtar, M. N., & Azam, Q. (2020). How accurate are locations in Malaysian accident data? Development of a rectification procedure based on nested filtered search technique. Transportation Research Procedia, 48, 1125–1141. https://doi.org/10.1016/j.trpro.2020.08.138

  • Alabdulrazzaq, H., Alenezi, M. N., Rawajfih, Y., Alghannam, B. A., Al-Hassan, A. A., & Al-Anzi, F. S. (2021). On the accuracy of ARIMA based prediction of COVID-19 spread. Results in Physics, 27, Article 104509. https://doi.org/10.1016/j.rinp.2021.104509

  • Alawad, H., Kaewunruen, S., & An, M. (2019). Learning from accidents: Machine learning for safety at railway stations. IEEE Access, 8, 633–648. https://doi.org/10.1109/ACCESS.2019.2962072

  • Al-Hasani, G., Khan, A. M., & Al Reesi, H. (2019). Diagnostic time series models for road traffic accidents data modelling, analysis and forecasting road traffic accidents view project design and verification of safety critical embedded systems view project. International Journal of Applied Statistics and Economics, 2, 19–26.

  • Ali, D., Yusof, Y., & Adam, A. (2017). Safety culture and issue in the Malaysian manufacturing sector. MATEC Web of Conferences, 135, Article 00031. https://doi.org/10.1051/matecconf/201713500031

  • Attwood, D., Khan, F., & Veitch, B. (2006). Validation of an offshore occupational accident frequency prediction model - A practical demonstration using case studies. Process Safety Progress, 25(2), 160–171. https://doi.org/10.1002/prs.10128

  • Ayob, A., Shaari, A. A., Zaki, M. F. M., & Munaaim, M. A. C. (2018). Fatal occupational injuries in the Malaysian construction sector-causes and accidental agents. IOP Conference Series: Earth and Environmental Science, 140(1), Article 012095. https://doi.org/10.1088/1755-1315/140/1/012095

  • Bora, B., Chattopadhyaya, S., & Kumar, R. (2020). Development of mathematical model for friction stir welded joint using “R” programming. Materials Today: Proceedings, 27(3), 2142–2146. https://doi.org/10.1016/j.matpr.2019.09.083

  • Chong, H. Y., & Low, T. S. (2014). Accidents in Malaysian construction industry: Statistical data and court cases. International Journal of Occupational Safety and Ergonomics, 20(3), 503–513. https://doi.org/10.1080/10803548.2014.11077064

  • Choo, B. C., Razak, M. A., Radiah, A. B. D., Tohir, M. Z. M., & Syafiie, S. (2022). A review on supervised machine learning for accident risk analysis: Challenges in Malaysia. Process Safety Progress, 41(S1), S147-S158. https://doi.org/10.1002/prs.12346

  • Denham, B. E. (2020). Poisson and negative binomial regression. In Categorical Statistics for Communication Research (1st ed.: pp. 74–94). John Wiley & Sons.

  • de Souza, J. A. F., Silva, M. M., Rodrigues, S. G., & Santos, S. M. (2022). A forecasting model based on ARIMA and artificial neural networks for end–OF–life vehicles. Journal of Environmental Management, 318, Article 115616. https://doi.org/10.1016/j.jenvman.2022.115616

  • Domingos, P. (2012). A few useful things to know about machine learning. Communications of the ACM, 55(10), 78–87. https://doi.org/10.1145/2347736.2347755

  • Esmaili, N., Buchlak, Q. D., Piccardi, M., Kruger, B., & Girosi, F. (2021). Multichannel mixture models for time-series analysis and classification of engagement with multiple health services: An application to psychology and physiotherapy utilization patterns after traffic accidents. Artificial Intelligence in Medicine, 111, Article 101997. https://doi.org/10.1016/j.artmed.2020.101997

  • Freivalds, A., & Johnson, A. B. (1990). Time-series analysis of industrial accident data. Journal of Occupational Accidents, 13(3), 179–193. https://doi.org/10.1016/0376-6349(90)90020-V

  • Hadi, N. A. A., Tamrin, S. B. M., Guan, N. Y., How, V., & Rahman, R. A. (2017). Association between non-reporting of accident and contributing factors in Malaysia’s construction industry. The Japanese Journal of Ergonomics, 53(Supplement2), S648-S651. https://doi.org/10.5100/jje.53.S648

  • Hajakbari, M. S., & Minaei-Bidgoli, B. (2014). A new scoring system for assessing the risk of occupational accidents: A case study using data mining techniques with Iran’s Ministry of labor data. Journal of Loss Prevention in the Process Industries, 32, 443–453. https://doi.org/10.1016/j.jlp.2014.10.013

  • Ismail, N., & Zamani, H. (2013). Estimation of claim count data using negative binomial, generalized Poisson, zero-inflated negative binomial and zero-inflated generalized Poisson regression models. Casualty Actuarial Society E-Forum, 41(20), 1–28.

  • Jian, T. (2021, October 22-24). Statistical analysis and countermeasures study on major accidents of highway and waterway in China. [Paper presentation]. 6th International Conference on Transportation Information and Safety (ICTIS), Wuhan, China. https://doi.org/10.1109/ICTIS54573.2021.9798527

  • Khattak, M. W., Pirdavani, A., De Winne, P., Brijs, T., & De Backer, H. (2021). Estimation of safety performance functions for urban intersections using various functional forms of the negative binomial regression model and a generalized Poisson regression model. Accident Analysis and Prevention, 151, Article 105964. https://doi.org/10.1016/j.aap.2020.105964

  • Kidam, K., Abidin, Z. Z., Sulaiman, Z., Hashim, M. H., Ripin, A., Ali, M. W., Safuan, H. M., Haron, S., Othman, N., Zakaria, Z. Y., Fandi, F. M., Masri, M. F., Hassan, S. A. H. S., Ali, N. M., Ahmad, A., & Asri, H. (2015). Current status of industrial accident learning in Malaysia. Journal of Occupational Safety and Health, 12(1), 1-4.

  • Kim, S., Lee, J., & Kang, C. (2021). Analysis of industrial accidents causing through jamming or crushing accidental deaths in the manufacturing industry in South Korea: Focus on non-routine work on machinery. Safety Science, 133, Article 104998. https://doi.org/10.1016/j.ssci.2020.104998

  • Koc, K., Ekmekcioğlu, Ö., & Gurgun, A. P. (2022). Accident prediction in construction using hybrid wavelet-machine learning. Automation in Construction, 133, Article 103987. https://doi.org/10.1016/j.autcon.2021.103987

  • Kuşkapan, E., Çodur, M. Y., & Atalay, A. (2021). Speed violation analysis of heavy vehicles on highways using spatial analysis and machine learning algorithms. Accident Analysis and Prevention, 155, Article 106098. https://doi.org/10.1016/j.aap.2021.106098

  • Li, X., Liu, Y., Fan, L., Shi, S., Zhang, T., & Qi, M. (2021). Research on the prediction of dangerous goods accidents during highway transportation based on the ARMA model. Journal of Loss Prevention in the Process Industries, 72, Article 104583. https://doi.org/10.1016/j.jlp.2021.104583

  • Manan, M. M. A., Jonsson, T., & Várhelyi, A. (2013). Development of a safety performance function for motorcycle accident fatalities on Malaysian primary roads. Safety Science, 60, 13–20. https://doi.org/10.1016/j.ssci.2013.06.005

  • Marhavilas, P. K., Koulouriotis, D. E., & Spartalis, S. H. (2013). Harmonic analysis of occupational-accident time-series as a part of the quantified risk evaluation in worksites: Application on electric power industry and construction sector. Reliability Engineering and System Safety, 112, 8–25. https://doi.org/10.1016/j.ress.2012.11.014

  • Meel, A., O’Neill, L. M., Levin, J. H., Seider, W. D., Oktem, U., & Keren, N. (2007). Operational risk assessment of chemical industries by exploiting accident databases. Journal of Loss Prevention in the Process Industries, 20(2), 113–127. https://doi.org/10.1016/j.jlp.2006.10.003

  • Meel, A., & Seider, W. D. (2006). Plant-specific dynamic failure assessment using Bayesian theory. Chemical Engineering Science, 61(21), 7036–7056. https://doi.org/10.1016/j.ces.2006.07.007

  • Melchior, C., Zanini, R. R., Guerra, R. R., & Rockenbach, D. A. (2021). Forecasting Brazilian mortality rates due to occupational accidents using autoregressive moving average approaches. International Journal of Forecasting, 37(2), 825–837. https://doi.org/10.1016/j.ijforecast.2020.09.010

  • Mohamad, E., Shern, T. Y., Jamli, M. R., Mohamad, N. A., Rahman, M. A. A., Salleh, M. R., Oktavianty, O., & Ito, T. (2019, September 25-27). Readiness of Malaysian manufacturing firms in implementing industry 4.0. [Paper presentation]. Proceedings of the 29th Design Engineering and Systems Division Lecture Meeting of the Japan Society of Mechanical Engineers, Sendai, Japan. https://doi.org/10.1299/jsmedsd.2019.29.1201

  • Muhamad, M. Q. B., Syed Mohamad, S. J. A. N., & Mat Nor, N. (2021). When digital intelligent taking over: Addressing SMEs readiness on Industry 4.0 in Malaysia. International Journal of Academic Research in Business and Social Sciences, 11(1), 543-551. https://doi.org/10.6007/ijarbss/v11-i1/8335

  • Quddus, M. A. (2008). Time series count data models: An empirical application to traffic accidents. Accident Analysis and Prevention, 40(5), 1732–1741. https://doi.org/10.1016/j.aap.2008.06.011

  • Radzuan, N. Q., Hassan, M. H. A., Majeed, A. P. P. A., Musa, R. M., Razman, M. A. M., & Kassim, K. A. A. (2020). Predicting serious injuries due to road traffic accidents in Malaysia by means of artificial neural network. In Z. Jamaludin & M. N. A. Mokhtar (Eds.), Intelligent Manufacturing and Mechatronics (pp. 75-80) Springer. https://doi.org/10.1007/978-981-13-9539-0_8

  • Rafindadi, A. D. U., Napiah, M., Othman, I., Mikić, M., Haruna, A., Alarifi, H., & Al-Ashmori, Y. Y. (2022). Analysis of the causes and preventive measures of fatal fall-related accidents in the construction industry. Ain Shams Engineering Journal, 13(4), Article 101712. https://doi.org/10.1016/j.asej.2022.101712

  • Rohani, J. M., Atan, H., Hamid, W. H. W. Johari, M. F., & Ramly, E. (2015). Occupational accident cost estimation: A case study in wood based related industries. Journal of Occupational Safety and Health, 12(1), 109–116.

  • Rohayu, S., Rahim, S. A. S. M., Marjan, J. M., & Voon, W. S. (2012). Predicting Malaysian road fatalities for year 2020. Malaysian Institute of Road Safety Research (MIROS)

  • Sari, M., Selcuk, A. S., Karpuz, C., & Duzgun, H. S. B. (2009). Stochastic modeling of accident risks associated with an underground coal mine in Turkey. Safety Science, 47(1), 78–87. https://doi.org/10.1016/j.ssci.2007.12.004

  • Thakali, L., Fu, L., & Chen, T. (2016). Model-based versus data-driven approach for road safety analysis: Do more data help? Transportation Research Record, 2601(1), 33–41. https://doi.org/10.3141/2601-05

  • Warner, P. (2015). Poisson regression. Basic Biostatistics for Medical and Biomedical Practitioners, 41(3), 591-595.

  • Weng, J., Qiao, W., Qu, X., & Yan, X. (2015). Cluster-based lognormal distribution model for accident duration. Transportmetrica A: Transport Science, 11(4), 345–363. https://doi.org/10.1080/23249935.2014.994687

  • Zein, R. M., Halim, I., Azis, N. A., Saptari, A., & Kamat, S. R. (2015). A survey on working postures among Malaysian industrial workers. Procedia Manufacturing, 2, 450–459. https://doi.org/10.1016/j.promfg.2015.07.078

  • Zermane, A., Tohir, M. Z. M., Baharudin, M. R., & Yusoff, H. M. (2022). Risk assessment of fatal accidents due to work at heights activities using fault tree analysis: Case study in Malaysia. Safety Science, 151, Article 105724. https://doi.org/10.1016/j.ssci.2022.105724

  • Zhu, J. J., Jiang, J., Yang, M., & Ren, Z. J. (2023). ChatGPT and environmental research. Environmental Science & Technology, 57(46), 17667–17670. https://doi.org/10.1021/acs.est.3c01818