Nurhafizah Mahri

Nurhafizah Mahri

Auto-generated profile, based on publicly available information

Nurhafizah Mahri

International Islamic University Malaysia

Research Focus & Metrics

Academic Career Length

17Years (2010-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 August 2010
Verified
Conference Paper
Closed access
NMNurhafizah Mahri
Nurhafizah Mahri
SSShahrel Azmin Suandi
Shahrel Azmin Suandi
BRBakhtiar Affendi Rosdi
Bakhtiar Affendi Rosdi
In this paper, we propose an algorithm for finger vein recognition with less complexity in the image preprocessing phase, where finger vein pattern extraction is not included at all. In the proposed algorithm, we implement phase-only correlation (POC) function at the matching stage with a very simple preprocessing technique. Experimental evaluation of the proposed algorithm using a set of finger vein images captured from a low cost device have resulting an efficient recognition performance where the equal error rate (EER) was 0.9803% with a total processing time of 0.6362s.

26 January 2017 in Journal of Medical Engineering & Technology
Verified
Journal Article
Closed access
NMNurhafizah Mahri
Nurhafizah Mahri
Kok Beng GanKok Beng Gan
Kok Beng Gan
RMRusna Meswari
Rusna Meswari
MJMohd Hasni Jaafar
Mohd Hasni Jaafar
MAMohd. Alauddin Mohd. Ali
Mohd. Alauddin Mohd. Ali
Myocardial infarction (MI) is a common disease that causes morbidity and mortality. The current tools for diagnosing this disease are improving, but still have some limitations. This study utilised the second derivative of photoplethysmography (SDPPG) features to distinguish MI patients from healthy control subjects. The features include amplitude-derived SDPPG features (pulse height, ratio, jerk) and interval-derived SDPPG features (intervals and relative crest time (RCT)). We evaluated 32 MI patients at Pusat Perubatan Universiti Kebangsaan Malaysia and 32 control subjects (all ages 37–87 years). Statistical analysis revealed that the mean amplitude-derived SDPPG features were higher in MI patients than in control subjects. In contrast, the mean interval-derived SDPPG features were lower in MI patients than in the controls. The classifier model of binary logistic regression (Model 7), showed that the combination of SDPPG features that include the pulse height (d-wave), the intervals of “ab”, “ad”, “bc”, “bd”, and “be”, and the RCT of “ad/aa” could be used to classify MI patients with 90.6% accuracy, 93.9% sensitivity and 87.5% specificity at a cut-off value of 0.5 compared with the single features model.

24 March 2016 in Journal of Medical Engineering & Technology
Verified
Journal Article
Closed access
PDF file
NMNurhafizah Mahri
Nurhafizah Mahri
Kok Beng GanKok Beng Gan
Kok Beng Gan
MAMohd. Alauddin Mohd. Ali
Mohd. Alauddin Mohd. Ali
MJMohd. Hasni Jaafar
Mohd. Hasni Jaafar
RMRusna Meswari
Rusna Meswari
The risk of heart attack or myocardial infarction (MI) may lead to serious consequences in mortality and morbidity. Current MI management in the triage includes non-invasive heart monitoring using an electrocardiogram (ECG) and the cardic biomarker test. This study is designed to explore the potential of photoplethysmography (PPG) as a simple non-invasive device as an alternative method to screen the MI subjects. This study emphasises the usage of second derivative photoplethysmography (SDPPG) intervals as the extracted features to classify the MI subjects. The statistical analysis shows the potential of “a-c” interval and the corrected “a-cC” interval to classify the subject. The sensitivity of the predicted model using “a-c” and “a-cC” is 90.6% and 81.2% and the specificity is 87.5% and 84.4%, respectively.

1 February 2012
Verified
Conference Paper
Closed access
NMNurhafizah Mahri
Nurhafizah Mahri
Kok Beng GanKok Beng Gan
Kok Beng Gan
MAMohd. Alauddin Mohd. Ali
Mohd. Alauddin Mohd. Ali
Photoplethysmography (PPG) signals are always corrupted with motion artifacts and resulting in bad quality PPG signals. The proper designed data acquisition protocol may help in acquisition of reliable and consistence PPG signal. However, in most cases, the acquired PPG are bad quality signals. The repeated acquisition sessions sometimes can not be performed due to ethical issues and time consuming. As such an essential step is needed to deal with the corrupted PPG signal. In this report, an algorithm to select best pulse in PPG signal through comparative method of valley detection is proposed. The clinical data showed that this algorithm is a promising tool to analyze low quality PPG signals especially during data acquisition.

1 December 2014
Verified
Conference Paper
Closed access
NMNurhafizah Mahri
Nurhafizah Mahri
Kok Beng GanKok Beng Gan
Kok Beng Gan
MAMohd. Alauddin Mohd. Ali
Mohd. Alauddin Mohd. Ali
Electrocardiography (ECG) is the most reliable tool to measure the heart electrical activity. It is noted that the setting and measurement procedure of ECG are always complex and time consuming. This complexity has motivated us to extract the important ECG features using photoplethysmography (PPG). The aim of this paper is to study the feasibility of extracting feature similar to ECG QT interval using second derivatives PPG (SDPPG). A pilot study has been conducted using simultaneous data acquisition system to acquire PPG and ECG signals. Five healthy subjects have been participated in this study. A signal processing algorithm has been developed to extract the feature that is similar to ECG QT interval. In this work, the feature refers to AB index, which is the interval of the SDPPG that has been illustrated in Figure 6. The paired T-test shows that there is no significant difference between QT interval using ECG and AB index extracted from second derivatives PPG (p<;0.05).

1 March 2019
Verified
Conference Paper
Closed access
SJShaliza Jumahat
Shaliza Jumahat
Kok Beng GanKok Beng Gan
Kok Beng Gan
NMNORBAHIAH BINTI MISRAN
NORBAHIAH BINTI MISRAN
MIMohammad Tariqul Islam
Mohammad Tariqul Islam
NMNurhafizah Mahri
Nurhafizah Mahri
In automatic electrocardiogram (ECG) signal analysis, the QRS onset must be identified prior to QT interval or QRS duration measurements. These measurements are decisive ECG parameters for diagnosing cardiac abnormalities among cardiologists. Hence, the efficiency of the developed automatic algorithm to detect the QRS onset is essential to obtain an accurate result of the ECG parameters. In this report, an algorithm to detect the QRS onset based on secant line slope formula is proposed. The preprocessing and wave delineation process were implemented in MATLAB using modified Pan-Tompkins algorithm (an established adaptive threshold method). The window of the preceding Q-wave was determined before calculating the slope of secant line along the descending slope for QRS onset detection. The performance of the proposed algorithm was evaluated using 25 subjects from Pusat Perubatan Universiti Kebangsaan Malaysia (PPUKM) and volunteered participants under the approval of Research and Ethics Committee, PPUKM (Code of ethics approval: FF-2013-313). All data were acquired using biosignal amplifier (g.USBamp by g.tec, Austria) with 2 minutes duration of recording and sampled at 512 Hz. The efficiency of the proposed algorithm has obtained a sensitivity of 99.67%, positive predictivity of 99.39%, and accuracy of 99.07%. The result shows stable performance and insensitivity of the proposed algorithm towards ECG wave morphology changes.