Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jurnal ULTIMATICS International Journal of Innovation Research in Education, Technology and Management (IJIRETM) Women, Education, and Social Welfare
Aprilia Nurfazila
universitas muhammadiyah jambi
Humanities Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Electrical & Electronics Engineering Engineering Environmental Science Law, Crime, Criminology & Criminal Justice Library & Information Science Social Sciences Other

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
Application of the ANFIS Model in Predicting Diabetes Mellitus Disease Aprilia Nurfazila; Hetty Rohayani
ULTIMATICS Vol 17 No 2 (2025): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v17i2.4479

Abstract

This study presents the application of the Adaptive Neuro-Fuzzy Inference System (ANFIS) model for predicting Diabetes Mellitus using two primary input features, namely glucose level and body mass index (BMI). The research employs a quantitative experimental approach using the public diabetes dataset obtained from Kaggle. The data underwent preprocessing steps, including cleaning, normalization, and splitting into training and testing subsets. The ANFIS model was designed with fuzzification, rule-based inference, and a hybrid learning algorithm to optimize membership function parameters. Model evaluation was conducted using accuracy, precision, recall, and F1-score. The results show that the ANFIS model achieved an accuracy of 69.70% on the test dataset, demonstrating strong sensitivity in detecting diabetic cases but generating a notable number of false positives. These findings indicate that ANFIS has potential as an early-screening decision support tool, although further optimization and additional features are required to enhance predictive performance.
Literature Review: Implementation of the Naive Bayes Algorithm for Classification in Various Fields of Data Mining Aprilia Nurfazila; hetty rohayani
International Journal of Innovation Research in Education, Technology and Management Vol. 3 No. 1 (2026): February 2026
Publisher : PT. BERBAGI TEKNOLOGI SEMESTA

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61098/ijiretm.v3i1.269

Abstract

The significant increase in data volume across various sectors demands efficient, accurate, and adaptive classification methods. The Naive Bayes algorithm is one of the probabilistic classification techniques widely used in data mining due to its model simplicity and its capability to handle high-dimensional data. This study aims to systematically review the application of the Naive Bayes algorithm for data classification in various sectors in Indonesia through a Systematic Literature Review (SLR) approach. Data were obtained from scientific journals published in the last five years (2019–2024) relevant to the topic and analyzed using qualitative descriptive methods. The review results show that Naive Bayes is widely applied in the fields of health, education, social sciences, economics, and technology. Most studies report high accuracy rates, particularly in text classification and imbalanced dataset cases. However, the limitation of this algorithm lies in the assumption of attribute independence, which is often not met in real-world cases. Therefore, several studies combine Naive Bayes with other methods to improve performance. This study provides a comprehensive overview of the strengths and weaknesses of Naive Bayes and serves as a reference for selecting appropriate classification methods in future data mining applications.
Application of the Certainty Factor Method in Diagnosing the Risk Level of Coronary Heart Disease Based on Patient Clinical Parameters Aprilia Nurfazila; Hetty Rohayani
Women, Education, and Social Welfare Vol. 3 No. 3 (2026): July - September 2026 | Women, Education, and Social Welfare
Publisher : WISE Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70211/wesw.v3i3.653

Abstract

Coronary Heart Disease (CHD) remains a global health challenge, yet health literacy gaps often make it difficult for the general public to understand clinical parameters and diagnostic uncertainty. In an effort to support social welfare and digital health accessibility, this study developed an expert system prototype that translates complex clinical data into easily understandable CHD risk levels (Low, Moderate, High). Utilizing the Certainty Factor (CF) method, the system is designed not as an independent clinical screening tool, but as a transparent, self-educational platform for non-specialist users. Evaluated on the extended UCI Heart Disease dataset (920 patient records), the CF approach successfully provided clear, explainable reasoning for its risk classifications. Although the initial algorithmic evaluation highlighted the limitations of static rules in handling the non-linear variability of medical data (achieving 46.30% accuracy), these findings emphasize that the primary value of digital health technology for the general public lies beyond mere computational accuracy. Instead, its significance is rooted in communication transparency, improving health information accessibility, and raising health awareness.
Co-Authors Hetty Rohayani