Forecasting A Cycling Distance based on Personal Health Data with Hybrid GA-SVR Approach

Authors

  • Pawnwipa Meeklueb Center of Business Analytics and Synthetic Intelligence Strategy, King Mongkut’s Institute of Technology Ladkrabang, Thailand
  • Busayamas Pimpunchat Department of Mathematics, School of Science, King Mongkut's Institute of Technology Ladkrabang, Thailand
  • Benjawan Rodjanadid School of Mathematics, Institute of Science Suranaree University of Technology, Nakhon Ratchasima, Thailand

Abstract

The aim of this study is to forecast the optimal cycling distance of 30 minutes approximately for physically constrained individuals, especially those having a congenital disease or elderly person. Data illustrations are collected from having 94 people who cycled in Ladkrabang by questionnaires. The research focuses on forecasting optimal distances by exploiting Support Vector Regression based on Genetic Algorithm (GA-SVR) that will be employed to improve the accuracy of the numerical study. We offer performance comparisons of our model against Multiple Linear Regression (MLR) and Support Vector Regression (SVR) algorithms. The experimental results demonstrate that GA-SVR outperforms MLR and SVR based on the Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE). This GA-SVR model is proven to be an effective approach to predict cycling distances.

Downloads

Published

2021-12-15

How to Cite

Meeklueb, P. ., Pimpunchat, B., & Rodjanadid, B. . (2021). Forecasting A Cycling Distance based on Personal Health Data with Hybrid GA-SVR Approach. MATEMATIKA: Malaysian Journal of Industrial and Applied Mathematics, 135–146. Retrieved from https://matematika.utm.my/index.php/matematika/article/view/1349

Issue

Section

Articles