The Partial Modelling of Non-Linear Analog Distance Sensor using Piecewise Newton Polynomials Algorithm to Minimize the Occurrence of Runge's Phenomenon

Abstract

The Sharp GP2Y0A02YK0F is an infrared-based nonlinear distance measuring sensor unit. This sensor categorized as low-cost sensor. Since this sensor has nonlinear characteristic in output voltage made this sensor is not easy to compute the measured distance. The modelling process is one of the solutions to complete this challenge. The Newton polynomial is a robust polynomial method that used in computational purpose. However, the polynomial-based modelling methods are suffered with Runge's phenomenon especially for nonlinear model. The partial modelling method with piecewise Newton polynomials algorithm has been used to minimize the occurrence of Runge's phenomenon. The piecewise Newton polynomials method has been succeeded to generate a nonlinear model and minimize the occurrence of Runge's phenomenon. The low MSE (Mean Squared Error) level by 0.001 and error percentage by 2.38% has been achieved for the generated model. The accuracy level of the final model is 97.62%.