Transportation Forecasting and Effects on Thailand-Laos Border Crossing Points after Opening of The ASEAN Economic Community
Main Article Content
Abstract
Traveling between countries these days has significantly increased in volume than before. Land transport by cars is regarded as one of the most convenient and suitable for countries with contiguous borders. When traveling through borders becomes in demand, an increase in the need for infrastructure development such as surface area and traffic lanes will therefore have to be optimized. As such, development planning is required to forecast future car volume by using currently available resources. In addition, the opening of the ASEAN Economic Community (AEC) is another major factor that will cause extensive travels between countries. This study examined the volume of vehicles travelling between Thailand - Laos borders, the impact that may arise after the launch of the AEC and the ability to handle the volume of cross-border vehicles.
Nonlinear auto regressive with exogenous input (NARX) was utilized for forecasting the traffic volume on the Mukdahan checkpoint and the Chiang Khong checkpoint. The results illustrate that the correlation coefficient is positive and the mean square error (MSE) is relatively low which implies that NARX is an accurate and a precise method. Hence, the forecast information from NARX can be used as a guide to improve cross-border services in order to prepare for the future, the opening of the AEC and applied to any Thailand’s borders with other countries.
Article Details
บทความ ข้อมูล เนื้อหา รูปภาพ ฯลฯ ที่ได้รับการตีพิมพ์ในวารสารฯ ถือเป็นลิขสิทธิ์ของวารสารฯ หากบุคคลหรือหน่วยงานใดต้องการนำทั้งหมดหรือส่วนหนึ่งส่วนใดไปเผยแพร่ต่อหรือเพื่อกระทำการใดๆ จะได้รับอนุญาต แต่ห้ามนำไปใช้เพื่่อประโยชน์ทางธุรกิจ และห้ามดัดแปลง
References
[2] Mukdahan Customs House. Number of vehicles accessing cross-borders at Mukdahan [Internet]. Mukdahan. 2013 [cited 2015 Feb 15]. Available from:https://www.danmuk.org/index.php?lay=
show&ac=article&Id=539339042
[3] Chiang Khong Customs. Number of vehicles accessing cross-borders at Chiang Khong [Internet]. Chiang Rai. 2010 [cited 2015 Feb 15]. Available from: https://www.chiangkhongcustoms.com/index.
php?lay=show&ac=article&Id=53938275&Ntype=6
[4] ASEAN Economic Community. The important goal of AEC [Internet]. Bangkok. 2012 [cited 2015 Feb 20]. Available from:https://www.thai-aec.com
[5] Irigoyen E, Minano G. A NARX neural network model for enhancing cardiovascular rehabilitation therapies. In: Corchado ES, Snasel V, Sedano J, Hassanien AE, Calvo JL, Slezak D, editors. Soft Computing Models in Industrial and Environmental Applications, 6th International Conference SOCO 2011; 2011 Apr 6-8; Salamanca, Spain. Madrid: Springer; 2011. p. 9-15.
[6] Pisoni E, Farina M, Carnevale C, Piroddi L. Forecasting peak air pollution levels using NARX models. Engineering Applications of Artificial Intelligence 2009;22:593-602.
[7] Chen D. Chinese automobile demand prediction based on ARIMA model. In: Ding Y, Peng Y, Shi R, Hao K, Wang L, editor. Biomedical Engineering and Informatics (BMEI); 2011 Oct 15-17; Shanghai. New
Jersey: IEEE; 2011. p. 2197-201.
[8] Jiang C, Song F. Sunspot Forecasting by Using Chaotic Time-series Analysis and NARX Network. J Comput 2011;6:1424-29.
[9] ASEAN-JAPAN Transport Partnership. Total number of registered road motor vehicles [Internet]. Tokyo. 2010 [cited 2015 Feb 20]. Available from:https://www.ajtpweb.org/statistics/compareasean/road_transport
[10] The World Bank. GDP per capita of Thailand and Laos [Internet]. Washington. 2015 [cited 2015 Mar 8]. Available from:https://www.worldbank.org/en/country
[11] Maddala GS, Kim IM. Unit Roots, Cointegration, and Structural Change. Cambridge: Cambridge University Press;1999.
[12] Xie Y, Lord D, Zhang Y. Predicting motor vehicle collisions using Bayesian neural network models: An empirical analysis. Accident Analysis & Prevention 2007;39:9