ABSTRACT
This paper presents the classification of the corneal arcus (CA), as an indicator of hyperlipidemia presence. We used two data-sets, comprising of the normal and abnormal eyes (CA). The first step is, to normalize the data -set, before extracting its features.
These images extracted to get the statistical features using gray level co-occurrence matrix (GLCM). Next, used the statistical
features as input to the classifier for training and testing the data features for classification. Our proposed system, using the
Bayesian regularization (BR) classifier with a sensitivity of 94.1%, a specificity of 97.3%, and 96%, is accuracy. The results
obtained shows that the proposed method able to classify the corneal arcus successfully. This classification allows the proposed
method used to identify the presence of hypercholesterolemia in a way of a non-invasive test.
Journal of Built Environment, Technology and Engineering, Vol. 1
COMPARISON OF CLASSIFIERS FOR DETECTING THE CORNEAL ARCUS AS A
SYMPTOM OF HYPERLIPIDEMIA
Ridza Azri Ramlee
*
,
Faculty of Engineering, Communications and Network Engineering,
Universiti Putra Malaysia, 43400 UPM,
Serdang, Selangor, Malaysia.
*
Email: ridza
@utem.edu.my
, Tel: 6019
–
4739367
Abd Rahman Ramli,
Faculty of Engineering, Communications and Network Engineering,
Universiti Putra Mal
aysia, 43400 UPM,
Serdang, Selangor, Malaysia
.
Marsyita Hanafi,
Faculty of Engineering, Communications and Network Engineering,
Universiti Putra Malaysia, 43400 UPM,
Serdang, Selangor, Malaysia.
Syamsiah Mashohor
Faculty of Engineering,
Communications and Network Engineering,
Universiti Putra Malaysia, 43400 UPM,
Serdang, Selangor, Malaysia
.
Zarina Mohd Noh
Faculty of Electronic
and Computer Engineering,
Universiti Teknikal Malays

2016

Download Full Abstract: JBETE-78