Farzana Kabir Ahmad

Farzana Kabir Ahmad

Auto-generated profile, based on publicly available information

Farzana Kabir Ahmad

Universiti Utara Malaysia

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

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

Representative Publications

View All Publications
1 April 2012 in Journal of Biomedical Informatics
Verified
Journal Article
Closed access
FAF.K. Ahmad
F.K. Ahmad
SDS. Deris
S. Deris
NON.H. Othman
N.H. Othman

1 December 2013
Verified
Conference Paper
Closed access
FAFarzana Kabir Ahmad
Farzana Kabir Ahmad
NYNooraini Yusoff
Nooraini Yusoff
Breast cancer is a complex and heterogeneous disease due to its diverse morphological features, as well as different clinical outcome. As a result, breast cancer patients may response to different therapeutic options. Currently, difficulties in recognizing the breast cancer types lead to inefficient treatments. Generally, there are two types of breast cancer, known as malignant and benign. Therefore it is necessary to devise a clinically meaningful classification of the disease that can accurately classify breast cancer tissues into relevant classes. This study aims to classify breast cancer lesions which have been obtained from fine needle aspiration (FNA) procedure using random forest. Random forest is a classifier built based on the combination of decision trees and has been identified to perform well in comparison to other machine learning techniques. This method has been tested on approximately 700 data, which consists of 458 instances from benign cases and 241 instances belong to malignant cases. The performance of proposed method is measured based on sensitivity, specificity and accuracy. The experimental results show that, random forest achieved sensitivity of 75%, specificity of 70% and accuracy about 72%. Thus, it can be concluded that random forest can accurately classify breast cancer types given a small number of features and it works as a promising tool to differentiate malignant from benign tumor at early stage.

8 February 2021 in Journal of Dispersion Science and Technology
Verified
Journal Article
Closed access
FAFarzana Ahmad
Farzana Ahmad
AJA-Ri Jeon
A-Ri Jeon
YJYoung Jae Jeon
Young Jae Jeon
MJMuhammad Jamil
Muhammad Jamil
In order to investigate the electro-optical characteristics of the current polymer dispersed liquid crystal (PDLC) film, zinc acrylate nanoparticles (NPs) were doped into the PDLC prepared samples. Generally for the fabrication of NPs–based PDLC film, two conventional methods such as the sandwich method and capillary methods are considered. In the conventional fabrication method of Np-doped PDLCs, the homogenous distribution of nanoparticles remained an unresolved issue. Particularly, upon the fabrication of Np-doped PDLC films, it is important to emphasis that nanoparticles are uniformly distributed inside the indium tin oxide (ITO) coated glass. For the purpose, here in this work, a new PDLC manufacturing method has been proposed to improve such shortcoming. Unlike the conventional method, the NPs acrylate layer was first coated on the ITO glass, which maintained evenly distributed NPs and then was placed onto the polymer/LC crystal mixture. By adopting the current PDLC fabricated method (with 1.0 wt% ZnA layer coating into PDLC film) the transmittance remained 93.9% and a good contrast ratio (CR) ∼ 7.0 was observed at a low driving voltage (∼ 20 V). Moreover the morphology study of current PDLCs showed a uniform size distribution of droplet morphology as well as a homogeneous distribution of NPs. Thus our investigations indicated that PDLC films prepared by this new technique achieved the goal of uniform distribution of NPs particles, homogeneous distribution of droplet morphology with the improved electro-optical characteristics. Graphical Abstract

10 August 2012 in Liquid Crystals
Verified
Journal Article
Closed access
YJYoung Jae Jeon
Young Jae Jeon
GLGae Hwang Lee
Gae Hwang Lee
KHKyu Young Hwang
Kyu Young Hwang
FAFarzana Ahmad
Farzana Ahmad
MJMuhammad Jamil
Muhammad Jamil
JJJae Eun Jung
Jae Eun Jung
In this paper, multidirectional light-control reflective (LCR) films are developed in order to create an active reflective structure that will enhance the image brightness and contrast ratio of reflective dye-doped polymer-dispersed liquid crystal (D-PDLC) displays at lower viewing angles. Advantages of LCR films are that their production is low cost and they require a simple photolithographic fabrication method. The optimum design prism-type light-control reflective film succeeded in minimising the surface scattering effect; thus, the contrast ratio is much enhanced. The symmetric and asymmetric LCR films produced multidirectional scattering that enhances the reflectance at lower viewing angles, which has importance in future display applications. In particular, the prism LCR film has been found to be more influential on the reflectance of D-PDLC films due to multidirectional scattering of light by non-symmetric arrays. The improvement in contrast ratio has been confirmed by the enhancement of optical properties for reflective D-PDLC displays at lower viewing angles below 30°.

6 May 2020 in International Journal of Interactive Mobile Technologies (iJIM)
Verified
Journal Article
Open access
PDF file
SQShahzad Qaiser
Shahzad Qaiser
NYNooraini Yusoff
Nooraini Yusoff
FAFarzana Kabir Ahmad
Farzana Kabir Ahmad
RARamsha Ali
Ramsha Ali
Sentiment Analysis of Impact of Technology on Employment from Text on Twitter

1 January 2008
Verified
Conference Paper
Closed access
FAFarzana Kabir Ahmad
Farzana Kabir Ahmad
NNNorita Md. Norwawi
Norita Md. Norwawi
SDSafaai Deris
Safaai Deris
NONor Hayati Othman
Nor Hayati Othman
The invention of DNA microarray technology has modernized the approach of biology research in such a way that scientists can now measure the expression levels of thousands of genes simultaneously in a single experiment. Although this technology has shifted a new era in molecular classification, interpreting microarray data still remain a challenging issue due to their innate nature of “high dimensional low sample size”. Therefore, robust and accurate feature selection methods are required to identify differentially expressed genes across varied samples for example between cancerous and normal cells. Successful of feature selection techniques will assist to correctly classify different cancer types and consequently led to a better understanding of genetic signatures in cancers and would improve treatment strategies. This paper presents a review of feature selection techniques that have been employed in microarray data analysis. Moreover, other problems associated with microarray data analysis also addressed. In addition, several trends were noted including highly reliance on filter techniques compared to wrapper and embedded, a growing direction towards ensemble feature selection techniques and future extension to apply feature selection in combination of heterogeneous data sources.