Universiti Teknologi Malaysia Institutional Repository

Primary stability recognition of the newly designed cementless femoral stem using digital signal processing

Mohd. Yusof, Baharuddin and Shaikh Salleh, Sheikh Hussain and Hamedi, Mahyar and Zulkifly, Ahmad Hafiz and Lee, Muhammad Hisyam and Mohd. Noor, Alias and A. Harris, Arief Ruhullah and Abdul Majid, Norazman (2014) Primary stability recognition of the newly designed cementless femoral stem using digital signal processing. Biomed Research International, 2014 . ISSN 2314-6133

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1155/2014/478248

Abstract

Stress shielding and micromotion are two major issues which determine the success of newly designed cementless femoral stems. The correlation of experimental validation with finite element analysis (FEA) is commonly used to evaluate the stress distribution and fixation stability of the stem within the femoral canal. This paper focused on the applications of feature extraction and pattern recognition using support vector machine (SVM) to determine the primary stability of the implant. We measured strain with triaxial rosette at the metaphyseal region and micromotion with linear variable direct transducer proximally and distally using composite femora. The root mean squares technique is used to feed the classifier which provides maximum likelihood estimation of amplitude, and radial basis function is used as the kernel parameter which mapped the datasets into separable hyperplanes. The results showed 100% pattern recognition accuracy using SVM for both strain and micromotion. This indicates that DSP could be applied in determining the femoral stem primary stability with high pattern recognition accuracy in biomechanical testing.

Item Type:Article
Uncontrolled Keywords:femoral stem, primary stability
Subjects:Q Science > QH Natural history
Divisions:Biosciences and Medical Engineering
ID Code:62330
Deposited By: Widya Wahid
Deposited On:05 Jun 2017 11:31
Last Modified:05 Jun 2017 11:31

Repository Staff Only: item control page