Ahmed, N., Abdulqader, Q. (2023). Enhancing the ARIMAX model by using the bivariate wavelet denoising: Application on road traffic accidents. , 20(2), 15-29. doi: 10.33899/iqjoss.2023.181146
Nawroz mikaeel Ahmed; Qais Mustafa Abdulqader. "Enhancing the ARIMAX model by using the bivariate wavelet denoising: Application on road traffic accidents". , 20, 2, 2023, 15-29. doi: 10.33899/iqjoss.2023.181146
Ahmed, N., Abdulqader, Q. (2023). 'Enhancing the ARIMAX model by using the bivariate wavelet denoising: Application on road traffic accidents', , 20(2), pp. 15-29. doi: 10.33899/iqjoss.2023.181146
Ahmed, N., Abdulqader, Q. Enhancing the ARIMAX model by using the bivariate wavelet denoising: Application on road traffic accidents. , 2023; 20(2): 15-29. doi: 10.33899/iqjoss.2023.181146

Enhancing the ARIMAX model by using the bivariate wavelet denoising: Application on road traffic accidents

IRAQI JOURNAL OF STATISTICAL SCIENCES
Volume 20, Issue 2, December 2023, Pages 15-29    PDF (564.83 K)
Document Type: Research Paper
DOI: 10.33899/iqjoss.2023.181146
Authors
Nawroz mikaeel Ahmed* 1; Qais Mustafa Abdulqader* 2
1Statistics Department-College of Administration and Economic-University of Duhok, Duhok, Iraq
2Petroleum Geology Department–Technical College of Petroleum and Mineral Science-Duhok Polytechnic University, Duhok, Iraq
Abstract
The purpose of this study is to determine whether an enhanced confound model representing bivariate wavelet-autoregressive integrated moving average with exogenous variable BWARIMAX is beneficial for predicting monthly traffic accidents. A wavelet-based multiresolution analysis MRA, conducted before the ARIMAX model fitting, shows that the performance of ARIMAX models in predicting traffic accidents can be significantly improved. The method described in this study identifies the ideal wavelet function, wavelet transform, and number of decomposition levels for the MRA and consequently considerably improves forecast accuracy. The analysis of the study demonstrated the superiority of the suggested approach and revealed that utilizing the BWARIMAX method, we can extract more information from the series, which enhances the performance of the original ARIMAX model in terms of predicting. Additionally, it has been demonstrated through extensive empirical testing using a wide range of wavelet families that Daubechies and Coiflet wavelets are excellent choices for denoising data. Furthermore, the study concluded that out of the two wavelet families, the performance of the Coiflet wavelet of order 3 was better

Highlights

In this paper, the issue of the possibility of improving the traditional ARIMAX model based on the ‎bivariate wavelet analysis method was mentioned. A proposed model was applied to the monthly data ‎that represents the number of traffic accidents. Based on the results of the statistical analysis, the ‎following can be concluded:‎

‎1- The hybrid model BWARIMAX (3,0,0) represents the optimal reliable model for predicting the number of ‎traffic accidents.

‎2- The Fixed-Form threshold level was determined better than the other thresholds used in the ‎analysis.

‎3- Among the wavelet family group used in the analysis, the Coiflet wavelet of order 3 gave the best ‎result.

‎4- The soft rule threshold was better than the hard rule to obtain the best result.‎

‎5- Depending on the selected BWARIMAX (3,0,0) model, a slight decrease will happen in the number of traffic ‎accidents in 2023 compared to 2022.‎

Keywords
Keywords:; Traffic accidents; Excessive speed; ARIMAX; Time series; Bivariate wavelet
References
  1. S. Al-Ghamdi, “Time Series Forecasts for Traffic Accidents, Injuries, and Fatalities in Saudi Arabia,” J. King Saud Univ. - Eng. Sci., vol. 7, no. 2, pp. 199–217, 1995, doi: 10.1016/S1018-3639(18)30627-5.
  2. Mustafa, “Comparing the Box - Jenkins models before . and after the wavelet filtering in terms of reducing the orders with application,” J. Concr. Appl. Math., vol. 11, pp. 190–198, 2013.
  3. Tsirigotis, E. I. Vlahogianni, and M. G. Karlaftis, “Does Information on Weather Affect the Performance of Short-Term Traffic Forecasting Models?,” Int. J. Intell. Transp. Syst. Res., vol. 10, no. 1, pp. 1–10, 2012, doi: 10.1007/s13177-011-0037-x.
  4. Zhang and T. Shi, “Spatial analysis of traffic accidents based on WaveCluster and vehicle communication system data,” Eurasip J. Wirel. Commun. Netw., vol. 2019, no. 1, 2019, doi: 10.1186/s13638-019-1450-0.
  5. Zheng, S. Ahn, D. Chen, and J. Laval, “Applications of wavelet transform for analysis of freeway traffic: Bottlenecks, transient traffic, and traffic oscillations,” Transp. Res. Part B Methodol., vol. 45, no. 2, pp. 372–384, 2011, doi: 10.1016/j.trb.2010.08.002.
  6. Agarwal, P. Kachroo, and E. Regentova, “A hybrid model using logistic regression and wavelet transformation to detect traffic incidents,” IATSS Res., vol. 40, no. 1, pp. 56–63, 2016, doi: 10.1016/j.iatssr.2016.06.001.
  7. Hossain, “A Hybrid Approach of Traffic Flow Prediction Using Wavelet Transform and Fuzzy Logic,” Electron. Theses Diss., pp. 1–62, 2017, [Online]. Available: https://scholar.uwindsor.ca/etd/5987.
  8. Zhang, X. Wang, J. Cao, M. Tang, and Y. Guo, “A multivariate short-term traffic flow forecasting method based on wavelet analysis and seasonal time series,” Appl. Intell., vol. 48, no. 10, pp. 3827–3838, 2018, doi: 10.1007/s10489-018-1181-7.
  9. C. Ihueze and U. O. Onwurah, “Road traffic accidents prediction modelling: An analysis of Anambra State, Nigeria,” Accid. Anal. Prev., vol. 112, no. November 2017, pp. 21–29, 2018, doi: 10.1016/j.aap.2017.12.016.
  10. H. Ali and M. S. Ali, “Analysis of Some Linear Dynamic Systems with Bivariate Wavelets,” Iraqi J. Stat. Sci., vol. 16, no. 3, pp. 85–108, 2019, doi: http://dx.doi.org/10.33899/iqjoss.2019.164176.
  11. A. Getahun, “Time series modeling of road traffic accidents in Amhara Region,” J. Big Data, vol. 8, no. 1, 2021, doi: 10.1186/s40537-021-00493-z.
  12. Meißner and J. Rieck, “Multivariate Forecasting of Road Accidents Based on Geographically Separated Data,” Vietnam J. Comput. Sci., vol. 8, no. 3, pp. 433–454, 2021, doi: 10.1142/S2196888821500196.
  13. Lunacek et al., “A data-driven operational model for traffic at the Dallas Fort Worth International Airport,” J. Air Transp. Manag., vol. 94, no. June 2020, p. 102061, 2021, doi: 10.1016/j.jairtraman.2021.102061.
  14. Nasser and V. Simon, “Wavelet-attention-based traffic prediction for smart cities,” IET Smart Cities, vol. 4, no. 1, pp. 3–16, 2022, doi: 10.1049/smc2.12018.
  15. Soo-Yeon, J. Bong Keun, K. Charles, L. Nandi, and H. J. Dong, “Forecasting network events to estimate attack risk: Integration of wavelet transform and vector auto regression with exogenous variables,” J. Netw. Comput. Appl., vol. 203, no. 1, 2022, doi: https://doi.org/10.1016/j.jnca.2022.103392.
  16. A. Ndume, E. C. Rutalebwa, and A. K. Runyoro, “Prediction of Road Accidents Trend in Tanzania Using ARIMA Model : The Road Safety Implication by 2021-2030,” vol. 11, no. 1, pp. 1–7, 2022, doi: 10.5923/j.ijtte.20221101.01.
  17. J. Brockwell and R. A. Davis, Introduction to Time Series and Forecasting - Second Edition. 2002.
  18. PANKRATZ, Forecasting With Univariate Box- Jenkins Models: Concept and cases. John Wiley & Sons, 1983.
  19. E. P. Box, G. M. Jenkins, R. G. C, and G. M. Ljung, Time series analysis: Forecasting and Control, Fifth edit. WILEY, 2015.
  20. R. Makridakis S, Wheelwright SC, Forecasting methods and applications, Third. Jhon Wiley and Sons,INC., 1997.
  21. K. Vishwakarma et al., “Forecasting steel prices using ARIMAX model: A case study of Turkey,” Resources Policy, vol. 35, no. 8. pp. 297–310, 2020, [Online]. Available: https://www.statista.com/download/MTUzNDM2Mjk3MSMjMzAxOTMzIyM1MDM0OSMjMSMjcGRmIyNTdHVkeQ==%0Ahttps://doi.org/10.1016/j.eneco.2017.09.010%0Ahttps://revistas.unal.edu.co/index.php/ceconomia/article/view/73067%0Ahttps://doi.org/10.1016/j.resourpol.2019.10155.
  22. J. Hyndman and G. Athanasopoulos, Forecasting: Principles and Practice, 2nd ed. Monash University, Australia, 2018.
  23. A. Yaffee and M. McGee, Introduction to Time Series Analysis and Forecasting: with Applications of SAS and SPSS, 2nd ed. ACADEMIC PRESS, INC, 1999.
  24. Amelia, D. Y. Dalimunthe, E. Kustiawan, and I. Sulistiana, “ARIMAX model for rainfall forecasting in Pangkalpinang, Indonesia,” IOP Conf. Ser. Earth Environ. Sci., vol. 926, no. 1, 2021, doi: 10.1088/1755-1315/926/1/012034.
  25. Islam and M. A. Imteaz, “The effectiveness of ARIMAX model for prediction of summer rainfall in northwest Western Australia,” IOP Conf. Ser. Mater. Sci. Eng., vol. 1067, no. 1, p. 012037, 2021, doi: 10.1088/1757-899x/1067/1/012037.
  26. H. Andrews, M. D. Dean, R. Swain, and C. Cole, “Building ARIMA and ARIMAX Models for Predicting Long-Term Disability Benefit Application Rates in the Public / Private Sectors Sponsored by Society of Actuaries Health Section Prepared by University of Southern Maine,” Soc. Actuar., no. August, 2013.
  27. B. Percival and A. T. Walden, “Wavelet Methods for Time SeriesAnalysis,” Wavelet Methods for Time SeriesAnalysis. 2000, doi: 10.1017/cbo9780511841040.
  28. S. Burrus, R. A. Gopinath, and H. Guo, Introduction to Wavelets and Wavelet Transforms: A Primer. 1998.
  29. Torrence and G. P. Compo, “A Practical Guide to Wavelet Analysis,” Bull. Am. Meteorol. Soc., vol. 79, no. 1, pp. 61–78, 1998, doi: 10.1175/1520-0477(1998)079<0061:APGTWA>2.0.CO;2.
  30. Shim, J. J. Soraghan, and W. H. Siew, “Detection of PD utilizing digital signal processing methods Part 3: open-loop noise reduction,” IEEE Electr. Insul. Mag., vol. 17, no. 1, pp. 6–13, 2001, doi: 10.1109/57.901611.
  31. Wongdhamma, “Upgrade from ARIMA to ARIMAX to Improve Forecasting Accuracy of Nonlinear Time-Series : Create Your Own Exogenous Variables Using Wavelet Analysis WAVELET TRANSFORMATION : BACKGROUND,” Sas, vol. 3, no. 34, pp. 1–16, 2016.
  32. Xu et al., “Ultra-short-term wind speed forecast based on WD-ARIMAX-GARCH model,” Proc. 2019 IEEE 2nd Int. Conf. Autom. Electron. Electr. Eng. AUTEEE 2019, pp. 219–222, 2019, doi: 10.1109/AUTEEE48671.2019.9033198.
  33. Ramazan, S. Faruk, and W. Brandon, An introduction to wavelets and other filtering methods in finance and economics, 1st ed. Academic Press, 2002.
  34. Charles K., An introduction to wavelets, 1st ed. Academic Press, 1992.
  35. Ergen, “Signal and Image Denoising Using Wavelet Transform,” Adv. Wavelet Theory Their Appl. Eng. Phys. Technol., no. May, 2012, doi: 10.5772/36434.
  36. Lo Cascio, “Wavelet Analysis and Denoising: New Tools for Economists,” no. 600, 2007.
  37. Pallavi L, and B. Raskar, V., “Image Denoising With Wavelet Thresholding Method for Different Level of Decomposition,” Int. J. Eng. Res. Gen. Sci., vol. 3, no. 3, pp. 1092–1099, 2015.
  38. Misiti, Y. Misiti, G. Oppenheim, and J. Poggi, Wavelet Toolbox For Use with M ATLAB. Wellesley Cambridge Press, 1996.
  39. G. Bruce and H. Y. E. Gao, “Understanding WaveShrink: Variance and bias estimation,” Biometrika, vol. 83, no. 4, pp. 727–745, 1996, doi: 10.1093/biomet/83.4.727.
  40. S. Chourasia and A. K. Tiwari, “Design Methodology of a New Wavelet Basis Function for Fetal Phonocardiographic Signals,” Sci. World J., vol. 2013, 2013.
  41. Kwiatkowski, P. C. B. Phillips, P. Schmidt, and Y. Shin, “Testing the null hypothesis of stationarity against the alternative of a unit root. How sure are we that economic time series have a unit root?,” J. Econom., vol. 54, no. 1–3, pp. 159–178, 1992, doi: 10.1016/0304-4076(92)90104-Y.
Statistics
Article View: 298
PDF Download: 319


Journal Management System. Powered by iJournalPro.com