Forecasting Trip Generation For High Density Residential Zones of Akure, Nigeria: Comparability of Artificial Neural Network And Regression Models

Author:

Etu J.E.,Oyedepo O. J.

Abstract

Evidence from literature has shown the absence of the use of Artificial Neural Network techniques in formulating trip generation forecasts in Nigeria, rather the practice has consisted more on use of regression techniques. Therefore, in this study, the accuracy of Radial Basis Function Neural Network (RBFNN) and Multiple Linear Regression model (MLR) in formulating home-based trips generation forecasts was assessed. Datasets for the study were acquired from a household travel survey in the high density zones of Akure, Nigeria and were analysed using SPSS 22 statistical software. Results of data analysis showed that the RBFNN model with higher Coefficient of Determination (R2) value of 0.913 and lower Mean Absolute Percentage Error (MAPE) of 0.421 performed better than the MLR with lower R2 value of 0.552 and higher MAPE of 0.810 in predicting the number of home-based trips generated in the study area. The study demonstrated the higher accuracy of the RBFNN in producing trip generation forecasts in the study area and is consequently recommended for researchers in executing such forecasts.

Publisher

UNIMAS Publisher

Subject

General Medicine

Reference24 articles.

1. [1] Owolabi, A. O. (2009). Paratransit Modal Choice in Akure, Nigeria-Applications of Behavioral Models. ITE Journal, 54-58.

2. [2] Ibeh, G. F., Agbo, G. A., Rabia , S., & Chikwenze, A. R. (2012a). Comparison of empirical and artificial neural network models for the correlation of monthly average global solar radiation with sunshine hours in Minna, Niger State, Nigeria. International Journal of Physical Sciences, 7(8), 1162-1165.

3. [3] Ibeh, G. F., Agbo, G. A., Oboma, D. N., Ekpe, J. E., & Odoh, S. (2012b). Comparison of Angstrom-Prescott, Multiple Regression and. Global Journal of Computer Science and Technology, 12(11), 6-12.

4. [4] Ibeh, G. F., Agbo, G. A., Agbo, P. E., & Ona. (2012c). Comparison of Artificial Neural Network (ANN) and Angstrom-Prescott models in correlation between sunshine hours and global solar radiation of Uyo city, Nigeria. Archives of Applied Science Research, 4(3), 1213-1219.

5. [5] Ojo, A. K., & Adeyemo, A. B. (2013). A Comparison Of The Predictive Capabilities Of Artificial Neural Networks And Regression Models For Knowledge Discovery. Computing, Information Systems, Development Informatics & Allied Research Journal, 4(2), 15-22.

Cited by 7 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3