Ahmad Fazli Abdul Aziz

Multiclass Support Vector Machines for Classification of ECG Data with Missing Values

The article presents an experimental study on multiclass Support Vector Machine (SVM) methods over a cardiac arrhythmia dataset that has missing attribute values for electrocardiogram (ECG) diagnostic application. The presence of an incomplete dataset and high data dimensionality can affect the performance of classifiers. Imputation of missing data and discriminant analysis are commonly used as preprocessing techniques in such large datasets. The article proposes experiments to evaluate performance of One-Against-All (OAA) and One-Against-One (OAO) approaches in kernel multiclass SVM for a heartbeat classification problem with imputation and dimension reduction techniques. The results indicate that the OAA approach has superiority over OAO in multiclass SVM for ECG data analysis with missing values.

Feature level fusion for biometric verification with two-lead ECG signals

Electrocardiogram (ECG) is a new generation of biometric modality which has unique identity properties for human recognition. There are few studies on feature level fusion over short-term ECG signals for extracting non-fiducial features from autocorrelation of ECG windows with an identical length. In this paper, we provide an experimental study on fusion at feature extraction level by using autocorrelation method in conjunction with different dimensionality reduction techniques over vector sets with different window lengths from short and long-term two-lead ECG recordings. The results indicate that the window and recording lengths have significant effects on recognition rates of the fused ECG data sets.

Computational fluid dynamics study of the aortic valve opening on hemodynamics characteristics

In this work, the 3D geometry of patient specific aorta was utilized to carry out CFD studies on the effect of different valve opening (45°,62.5° and fully opening) on the hemodynamic properties. The result shows that the lower valve opening induced jet flow and hampered the flow on the additional carotid arteries. Besides, the leaflets were subjected to extreme stress values having disastrous consequences. Consequently, stenosis which is characterized by weaker leaflets and low valve openings has serious impact on the well being of humans.

Non-fiducial based ECG biometric authentication using one-class Support Vector Machine

Identity recognition encounters with several problems especially in feature extraction and pattern classification. Electrocardiogram (ECG) is a quasi-periodic signal which has highly discriminative characteristics in a population for subject recognition. The personal identity verification in a random population using kernel-based binary and one-class Support Vector Machines (SVMs) has been considered by other biometric traits, but has been so far left aside for analysis of ECG signals. This paper investigates the effect of different parameters of data set size, labeling data, configuration of training and testing data sets, feature extraction, different recording sessions, and random partition methods on accuracy and error rates of these SVM classifiers. The experiments were carried out with defining a number of scenarios on ECG data sets designed rely on feature extractors which were modeled based on an autocorrelation in conjunction with linear and nonlinear dimension reduction methods. The experimental results show that Kernel Principal Component Analysis has lower error rate in binary and one-class SVMs on random unknown ECG data sets. Moreover, one-class SVM can be robust recognition algorithm for ECG biometric verification if the sufficient number of biometric samples is available.

Association of Cholesteryl Ester Transfer Protein and Endothelial Nitric Oxide Synthase Gene Polymorphisms With Coronary Artery Disease in the Multi-Ethnic Malaysian Population.

Genetic variants of cholesteryl ester transfer protein (CETP) and endothelial nitric oxide synthase (eNOS) influence high-density lipoprotein cholesterol (HDL-C) metabolism and nitric oxide (NO) synthesis, respectively, and might increase the risk of coronary artery disease (CAD). This study is to investigate the relationship between genetic polymorphisms and the risk of CAD and to evaluate their potential interactions. A total of 237 patients with CAD and 101 controls were genotyped. The association of the polymorphism with the risk of CAD varied among the ethnic groups. Moreover, the concomitant presence of both CETP B1 and eNOS 4a alleles significantly increased the risk of CAD in the Malay group (OR = 33.8, P < .001) and the Indian group (OR = 10.9, P = .031) but not in the Chinese group. This study has identified a novel ethnic-specific gene–gene interaction and suggested that the combination of CETP B1 allele and eNOS 4a allele significantly increases the risk of CAD in Malays and Indians.