Article Per Year (5 Year)
p-Index From 2021 - 2026
5.483
P-Index
This Author published in this journals
All Journal Information System for Educators and Professionals : Journal of Information System Informatics for Educators and Professional : Journal of Informatics JURNAL MANAJEMEN INFORMATIKA (JUMIKA) Angkasa: Jurnal Ilmiah Bidang Teknologi JURIKOM (Jurnal Riset Komputer) JOURNAL INFORMATICS, SCIENCE & TECHNOLOGY Jurnal ICT : Information Communication & Technology Jurnal Accounting Information System (AIMS) Narada : Jurnal Desain dan Seni Jurnal Dinamika Informatika (JDI) Hello World Journal of Artificial Intelligence and Engineering Applications (JAIEA) Jurnal Sistim Informasi dan Teknologi AMMA : Jurnal Pengabdian Masyarakat Jurnal Informatika: Jurnal Pengembangan IT Jurnal Accounting Information System (AIMS) Journal of Literature Review Bianglala Informatika Linier: Literatur Informatika dan Komputer
Arif Rinaldi Dikananda
STMIK IKMI Cirebon
Arts Humanities Automotive Engineering Chemistry Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Environmental Science Languange, Linguistic, Communication & Media Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Nursing Social Sciences Other

Published : 42 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 42 Documents
Search

 1   2   3   4   5 
Optimizing Naïve Bayes Algorithm Through Principal Component Analysis To Improve Dengue Fever Patient Classification Model Santi Nurjulaiha; Rudi Kurniawan; Arif Rinaldi Dikananda; Tati Suprapti
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.798

Abstract

Dengue fever is an infectious disease that has a significant impact on public health in tropical regions, including Indonesia. Early detection and proper classification of DHF patients is essential to reduce severity and mortality. For this reason, a method that can improve the accuracy in diagnosing this disease is needed. Principal Component Analysis (PCA) and Naïve Bayes (NB) are two commonly used techniques in medical data analysis. PCA is used to reduce the dimensionality of data to reduce complexity, while Naïve Bayes is used for classification of data based on probability. This study aims to optimize the use of PCA and Naïve Bayes in improving the accuracy of the dengue patient classification model. The method used in this study involves processing a medical dataset of dengue patients containing various clinically relevant attributes. The dataset was then processed using PCA to reduce dimensionality and identify key features that affect classification. Next, Naïve Bayes was applied to classify the data based on the selected features. This study compares the performance of classification models that use a combination of PCA and Naïve Bayes with models that only use Naïve Bayes without dimensionality reduction. The results show that the use of PCA in data processing significantly improves the accuracy of the classification model compared to the model that only uses Naïve Bayes. The combination of PCA and Naïve Bayes produces a more efficient model and has a higher accuracy rate in identifying patients with DHF risk. Thus, the application of PCA and Naïve Bayes in the classification of DHF patients can be an effective tool in assisting the medical diagnosis process, which in turn can reduce misdiagnosis and improve patient recovery rates. This research contributes to the development of artificial intelligence technology in the medical field, especially to improve the accuracy of dengue disease diagnosis, and serves as a basis for further research in the use of machine learning techniques in healthcare. This study analyzes the performance of the Naïve Bayes algorithm in classifying dengue fever patient data, by comparing models that use Principal Component Analysis (PCA) as a dimension reduction method and models that do not use it. The results show that the Naïve Bayes model without PCA has an accuracy of 49.96%, which is close to the random guess rate. This finding indicates that the model is less effective in recognizing patterns in the data. In contrast, the application of PCA successfully increased the model's accuracy to 50.03%
Sales Data Analysis using Linear Regression Algorithm on Raw Water Sales Eti Rohayati; Martanto; Arif Rinaldi Dikananda; Dede Rohman
Journal of Artificial Intelligence and Engineering Applications (JAIEA) Vol. 4 No. 2 (2025): February 2025
Publisher : Yayasan Kita Menulis

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59934/jaiea.v4i2.809

Abstract

This study aims to assess the effectiveness of linear regression algorithm in predicting raw water demand by considering customer transaction data, raw water volume, and seasonal variables. The method used is Knowledge Discovery in Databases (KDD), including data selection, preprocessing, transformation, data mining, and result evaluation. The dataset is divided 80% for training and 20% for testing. The analysis results show that the linear regression model has a coefficient of determination (R²) of 0.77, which means that the model can explain 77% of the data variability. The prediction error value is low, with Mean Absolute Error (MAE) 0.06, Mean Squared Error (MSE) 0.01, and Root Mean Squared Error (RMSE) 0.08, indicating good accuracy. In the comparison between actual and predicted values, for actual data of 7,000 liters, the model predicts 7,984.70 liters. The variable number of customer transactions has the greatest influence on raw water demand, with a coefficient of 16,940.46, while seasonal factors have less influence. Based on these findings, it can be concluded that the linear regression algorithm is effective in predicting raw water demand, however further development is required to improve accuracy at extreme values, by adding variables or using more complex algorithms.
Co-Authors Abrar Hiswara Ade Irma Purnamasari Ade Irma Purnamasari Ade Rizki Rinaldi Agie Maulana Agus Surip Agus Surip Ahmad Faqih Ahmad Faqih Ahmad Faqih Ahmad Rifa'i Ahmad Rifai Ahmad Rifa’i Ariska Sari Aruka Wijaya Aulia Nur Rochmah Azzahra Rizky Artoti Bambang Irawan Bani Nur Hakim Bani Nurhakim Candra Rahmawati Candra Cistia Ningrum Dadang Sudrajat Dede Rohman Denni Pratama Denni Pratama Dian Ade Kurnia Dias Bayu Saputra Edi Wahyudin Eti Rohayati Fania Lusiano Farid Ali Ma'ruf Fathurrohman Fathurrohman Fathurrohman Fathurrohman Faturrohman Fidya Arie Pratama Ginaselvia Ananda Hanifah Nur Aulia Harry B. Santoso Hilpad Hidayat Ica Pandia Ica Iin Irfan Ali Irfan Ali Irfan Ali Julia Eka Yanti Kanda Muhamad Ishak Laylatunna'imah Lukman Dwi Kusuma Martanto . Mochamad Arief Saputra Mochammad Fatha Mudzhaffar Muhamad Abdurohman Muhamad Aji Pratama Muhamad Firly Ramadan Muhammad Adhari Febriyan Muhammad Adithya Pratama Muhammad Hilman Mulyawan Nana Suarna Nenda Alfadil Seputra Nining Rahaningsih Nova Nur Sakbani NoviFirda Aini Nuraeni Nurilah Odi Nurdiawan Panji Adi Putra Pratama, Fidya Arie Putri Apriyani Raditya Danar Dana Raja Al-Fath Hidayat Rinovian Rais Rudi Kurniawan Ryan Hamonangan Ryan Ryan Agung Prasetyo Saeful Anwar Saeful Anwar Santi Nurjulaiha Siskawati suroso, amat Tati Suprapti Tiar Imam Muarif Tio Prasetya Umi Hayati Wiratriyana Yoga Nugraha Yudhistira Arie Wijaya