Fracture healing diagnosis by neural network

Authors:
Agnieszka Lesniewska;Wlodzimierz Choromanski
Affiliations:
Warsaw University of Technology, Warsaw, Poland;Warsaw University of Technology, Warsaw, Poland
Venue:
BioMED '08 Proceedings of the Sixth IASTED International Conference on Biomedical Engineering
Year:
2008

Citing 2
Cited 0

Data preparation for data mining

Data preparation for data mining
Data Mining: Concepts and Techniques

Data Mining: Concepts and Techniques

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper the fracture healing diagnosis is studied. The study based on experimental data carried out by 3D model of unilateral external fixator -- bone. Based on this data, a neural network was built and trained. Input of network includes an axial, variable load, different fracture size, different value of a distance between bone and external fixator's device, different fracture inclination, variable stress distribution at external fixatror's frame. Output of the network is defined by variable fracture stiffness (variable Young's modulus at the fracture side). Mechanical analysis done by commercial package CATIA P3 V5R11, neural network was carried out by commercial package Matlab 6.5.