Norhayati Baharun

Norhayati Baharun

Auto-generated profile, based on publicly available information

Norhayati Baharun

Universiti Teknologi MARA

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
1 September 2022 in IAES International Journal of Artificial Intelligence (IJ-AI)
Verified
Journal Article
Open access
PDF file
SMSuraya masrom
Suraya masrom
RRRahayu Abdul Rahman
Rahayu Abdul Rahman
MMMasurah Mohamad
Masurah Mohamad
ARAbdullah Sani Abd Rahman
Abdullah Sani Abd Rahman
NBNorhayati Baharun
Norhayati Baharun
This paper addresses the performances of machine learning classification models for the detection of tax avoidance problems. The machine learning models employed automated features selection with hybrid two metaheuristics algorithms namely particle swarm optimization (PSO) and genetic algorithm (GA). Dealing with a real dataset on the tax avoidance cases among companies in Malaysia, has created a stumbling block for the conventional machine learning models to achieve higher accuracy in the detection process as the associations among all of the features in the datasets are extremely low. This paper presents a hybrid meta-heuristic between PSO and adaptive GA operators for the optimization of features selection in the machine learning models. The hybrid PSO-GA has been designed to employ three adaptive GA operators hence three groups of features selection will be generated. The three groups of features selection were used in random forest (RF), k-nearest neighbor (k-NN), and support vector machine (SVM). The results showed that most models that used PSO-GA hybrids have achieved better accuracy than the conventional approach (using all features from the dataset). The most accurate machine learning model was SVM, which used a PSO-GA hybrid with adaptive GA mutation.

1 June 2023 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
SMSuraya masrom
Suraya masrom
RRRahayu Abdul Rahman
Rahayu Abdul Rahman
NBNorhayati Baharun
Norhayati Baharun
SRSyed Redzwan Sayed Rohani
Syed Redzwan Sayed Rohani
ARAbdullah Sani Abd Rahman
Abdullah Sani Abd Rahman
Nowadays, various innovative educational and instructional tools have been created to deliver learning material including video content. One of the important issues with video-based learning is to devise effective teaching strategies to ensure higher level of learning can be achieved by the students. Getting insight and predicting the students’ video-based learning adoption will help the educators. Thus, this study aims to examine the potential of using machine learning prediction models on video-based learning adoption in higher education institutions. Five machine learning algorithms were used to be empirically compared namely generalized linear model (GLM), random forest (RF), decision tree (DT), gradient boosted tree (GBT), and support vector machine (SVM). The performance of each machine learning algorithm in predicting the students’ learning adoption with video-based learning has been observed based on the attributes of task-technology fit theory. The findings indicated that the task-technology fit is useful in helping the machine learning algorithm to achieve high accuracy in the prediction of video-based learning adoption. The GBT is the best outperforming algorithm, followed with RF and SVM. This paper presents a fundamental research framework useful for helping educators and researchers to enhance student interest and retention on video-based learning.

1 October 2024 in Bulletin of Electrical Engineering and Informatics
Verified
Journal Article
Open access
PDF file
SMSuraya masrom
Suraya masrom
NBNorhayati Baharun
Norhayati Baharun
NRNor Faezah Mohamad Razi
Nor Faezah Mohamad Razi
ARAbdullah Sani Abd Rahman
Abdullah Sani Abd Rahman
NMNor Hazlina Mohammad
Nor Hazlina Mohammad
NSNor Aslily Sarkam
Nor Aslily Sarkam
One of the big challenges in machine learning is difficulty of achieving high accuracy in a short completion time. A more difficulties appeared when the algorithm needs to be used for solving real dataset from the survey-based data collection. Imbalance dataset, insufficient strength of correlations, and outliers are common problems in real dataset. To accelerate the modelling processes, automated machine learning based on meta-heuristics optimization such as genetic programming (GP) has started to emerge and is gaining popularity. However, identifying the best hyper-parameters of the meta-heuristics’ algorithm is the critical issue. This paper demonstrates the evaluation of GP hyper-parameters in modeling machine learning on house affordability dataset. The important hyper-parameters of GP are population size (PS), that has been observed with different setting in this research. The machine learning with GP was used to predict house affordability among employers with transport expenditure and job mobility as some of the attributes. The results from testing that run on hold-out samples show that GP machine learning can reach to 70% accuracy with split ratio 0.2 and GP PS 30. This research contributes to the advancement of automated machine learning techniques, offering potential for faster and more accurate real survey-based datasets.

1 August 2024 in International Journal of Evaluation and Research in Education (IJERE)
Verified
Journal Article
Open access
PDF file
NRNor Faezah Mohamad Razi
Nor Faezah Mohamad Razi
NBNorhayati Baharun
Norhayati Baharun
SMSuraya masrom
Suraya masrom
Education 5.0@UiTM is transforming Universiti Teknologi MARA (UiTM). This new approach emphasizes flexible learning paths that teach life and cross-disciplinary skills. To make higher education future-ready, universities must adapt fast to the significant global and technical changes caused by the 4th Industrial Revolution and transition from content-based to individualized learning. To ensure students meet Education 5.0@UiTM standards and corporate needs, the evaluation process must be reviewed. Competency-based academic achievement evaluation outperforms grades. This assessment is rarely systematically analyzed. This study was conducted to thoroughly explore the selection of input and output factors in determining student achievement efficiency using the data envelopment analysis (DEA) approach. The study reviewed publications from Scopus, Google Scholar, and Science Direct and found six themes for input variables: human resources, facilities condition and equipment, finance, curriculum, students characteristics, and community resources. output variables included student achievement, satisfaction, graduation rate, employment, research, and community resources. In DEA analysis, input and output selection affects scope, aim, production frontier, efficiency scores, accuracy and completeness. So, characterizing student achievement requires choosing relevant input and output variables. This study can enhance student evaluation processes to prepare college graduates for the next industrial revolution.

14 November 2026 in MethodsX
Verified
Journal Article
Open access
AAAnik Anekawati
Anik Anekawati
BOBambang Widjanarko Otok
Bambang Widjanarko Otok
PUPurhadi
Purhadi
DDDeshinta Arrova Dewi
Deshinta Arrova Dewi
NBNorhayati Baharun
Norhayati Baharun

1 February 2018 in Journal of Fundamental and Applied Sciences
Verified
Journal Article
Open access
PDF file
NBN. Baharun
N. Baharun
NRN. F. M. Razi
N. F. M. Razi
RAR. Z. Abidin
R. Z. Abidin
NMN. A. C. Musa
N. A. C. Musa
ZMZ. Mahmud
Z. Mahmud
Probability is a study of the rules that offers the foundational theory for the development of statistics. This sets out the investigation where students’ understanding of counting rules and its probability were explored using the Rasch measurement approach. A test instrument with 20 items was developed and administered to 74 students taking the STA150 Probability and Statistics course. Data were captured through an interactive e-learning platform that is dmodo.com and analyzed using Winsteps 3.81.0. The results from the Wright map showed that 83.8% of the students have the ability that matched well with the difficulty of the while 16.2% of the students need to be given more attention on the topic. The study was also able to show that the items can be replicated in other samples of similar characteristics. Keywords: students’ understanding; counting rules; probability Raschmeasurement model; Wright map.