Article Per Year (5 Year)
p-Index From 2021 - 2026
0.444
P-Index
This Author published in this journals
All Journal Jurnal Media Informatika International Journal of Applied Mathematics and Computing.
Dharmaesa, Dio
Unknown Affiliation
Computer Science & IT Mathematics

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
INTEGRASI MOBILE APLIKASI UNTUK KLASIFIKASI HARGA LAPTOP MENGGUNAKAN METODE SUPPORT VECTOR CLASSIFICATION DAN LOGISTIC REGRESSION Arrasyid Supriyanto, Muhammad Ibadurrahman; Rasendrya Hasan, Abdullah Arkananta; Dharmaesa, Dio; Aththar, Reviansa Fakhruddin; Febrinato, Surya Abdi; Sari, Chalsi Mala
Jurnal Media Informatika Vol. 6 No. 4 (2025): Jurnal Media Informatika
Publisher : Lembaga Dongan Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55338/jumin.v6i4.6576

Abstract

Penelitian ini bertujuan mengembangkan aplikasi mobile terintegrasi untuk klasifikasi harga laptop menggunakan metode machine learning guna membantu konsumen membuat keputusan pembelian yang objektif dan akurat. Masalah utama yang diatasi adalah kesulitan konsumen dalam mengklasifikasikan laptop berdasarkan kategori harga yang sesuai dengan kebutuhan dan anggaran mereka akibat kompleksitas variasi spesifikasi teknis dan proses klasifikasi manual yang subjektif. Dataset terdiri dari 1.500 sampel laptop dengan fitur brand, prosesor, RAM, penyimpanan, VGA, dan harga yang diklasifikasikan menjadi tiga kategori: Budget (≤10 juta), Mid-range (10-25 juta), dan Premium (>25 juta). Preprocessing data meliputi penghapusan missing values, deteksi outlier menggunakan Interquartile Range (IQR), dan feature engineering untuk kategorisasi tier VGA dan prosesor. Sistem scoring dikembangkan berdasarkan weighted features dengan rentang skor 5-50 untuk setiap komponen. Dua algoritma machine learning diimplementasikan: Support Vector Classification (SVC) dengan kernel RBF dan Logistic Regression (LR) dengan regularisasi L2. Evaluasi model menggunakan 5-fold cross-validation dengan pembagian data 80% training dan 20% testing menggunakan stratified sampling. SVC dengan kernel RBF mencapai akurasi 92% dengan confusion matrix yang menunjukkan dominasi diagonal tanpa kesalahan false positive/negative yang signifikan, sedangkan LR mencapai akurasi 85% dengan kecepatan training yang superior. Aplikasi mobile yang dikembangkan menggunakan React Native berhasil menyediakan fitur real-time classification, confidence scoring, dan export hasil untuk membantu konsumen dalam pengambilan keputusan pembelian laptop yang objektif dan akurat. Sistem scoring berbasis weighted features terbukti efektif dalam memberikan klasifikasi objektif menggantikan proses manual yang subjektif dan tidak konsisten.
A Comparison of SVM and ELM Algorithms Based on SMOTE for Anemia Classification Using Hematology Data Dharmaesa, Dio; Hamdani, Hamdani; Suyatno, Addy
International Journal of Applied Mathematics and Computing Vol. 3 No. 3 (2026): July: International Journal of Applied Mathematics and Computing
Publisher : Asosiasi Riset Ilmu Matematika dan Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/ijamc.v3i3.376

Abstract

Anemia remains a significant global health concern, and its diagnosis through manual interpretation of Complete Blood Count (CBC) results is susceptible to bias and misinterpretation. Machine learning techniques offer a promising solution for identifying complex patterns in medical data. however, their performance is often affected by class imbalance issues commonly found in healthcare datasets. Therefore, this study aims to evaluate and compare the performance of Support Vector Machine (SVM) and Extreme Learning Machine (ELM) algorithms enhanced with the Synthetic Minority Over-sampling Technique (SMOTE) for anemia classification. The proposed approach employs SVM and ELM classifiers with parameter optimization using K-Fold Cross Validation, while SMOTE is applied to address the imbalance in class distribution. The study utilizes a secondary CBC dataset consisting of 364 patient records categorized into Anemia and Non-Anemia classes. Experimental results indicate that the SMOTE-based SVM model achieved an accuracy of 94.52%, precision of 97.14%, recall of 91.89%, and an F1-score of 94.44%, with a computation time of 0.013 seconds. In comparison, the SMOTE-based ELM model attained an accuracy of 91.78%, precision of 89.74%, recall of 94.59%, and an F1-score of 92.11%, while requiring only 0.002 seconds of computation time. The findings suggest that SVM delivers more stable performance and the highest precision, making it highly effective in reducing false positive predictions. On the other hand, ELM demonstrates greater sensitivity to the incorporation of synthetic samples but outperforms SVM in terms of recall and computational efficiency, making it a suitable alternative when rapid processing and higher sensitivity are prioritized.
Co-Authors Addy Suyatno, Addy Aththar, Reviansa Fakhruddin Febrinato, Surya Abdi Hamdani Hamdani Rasendrya Hasan, Abdullah Arkananta Sari, Chalsi Mala Supriyanto, Muhammad Ibadurrahman Arrasyid