Searching an optimum parameter value for radial basis function by bootstrap error analysis for 2D craniofacial reconstruction

In data fitting, researchers use various methods to determine the quality of a fitting. Visualization of images is crucial in observing the behaviour of data obtained. The problem in judging the accuracy of a result obtained through visual observation are commonly faced by researchers when handling...

Full description

Saved in:
Bibliographic Details
Main Authors: Ali, Nur Soffiah Sahubar, Ramli, Ahmad, Rahman, Nuzlinda Abdul
Format: Conference Proceeding
Language:English
Subjects:
Error analysis
Image quality
Image reconstruction
Missing data
Outliers (statistics)
Parameters
Radial basis function
Skull
Statistical methods
Thin plates
Two dimensional analysis
Visual observation
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In data fitting, researchers use various methods to determine the quality of a fitting. Visualization of images is crucial in observing the behaviour of data obtained. The problem in judging the accuracy of a result obtained through visual observation are commonly faced by researchers when handling contaminated data such as noisy data, missing data or outliers. In this research, study has been conducted to deal with missing data using Radial Basis Function (RBF). Error evaluation using RBF with thin plate spline (TPS) of different parameter value, c is obtained. The approach is applied to a real life data of a head injured patient on the skull using bootstrap method in RBF. This study has performed well on craniofacial reconstruction to estimate the best fit curve for the missing part of fractured region of a skull. This provides a significant contribution that could be an alternative approach in medical application especially on craniofacial reconstruction.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0018115