Article Per Year (5 Year)
p-Index From 2021 - 2026
2.488
P-Index
This Author published in this journals
All Journal JURNAL SISTEM INFORMASI BISNIS Jurnal Ilmiah FIFO JURNAL REKAYASA TEKNOLOGI INFORMASI Go Infotech: Jurnal Ilmiah STMIK AUB JITU : Journal Informatic Technology And Communication Madani : Indonesian Journal of Civil Society GANESHA: Jurnal Pengabdian Masyarakat Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat Malcom: Indonesian Journal of Machine Learning and Computer Science SUBSERVE: Community Service and Empowerment Journal
Erni Widarti
Universitas Tunas Pembangunan Surakarta
Religion Agriculture, Biological Sciences & Forestry Humanities Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Engineering Languange, Linguistic, Communication & Media Library & Information Science Nursing Public Health Social Sciences Other

Published : 19 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Jurnal Ilmiah FIFO

 1 
Enhancing Liver Disease Classification Using Support Vector Machine with IQR-Based Outlier Handling Soares, Teotino Gomes; Tonggiroh, Mursalim; Erkamim, Moh.; Widarti, Erni
Jurnal Ilmiah FIFO Vol 17, No 1 (2025)
Publisher : Fakultas Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/fifo.2025.v17i1.010

Abstract

Liver disease is a significant health issue that requires early and accurate diagnosis to prevent serious complications. In this study, we propose an outlier filtering approach using the Interquartile Range (IQR) to enhance the performance of the Support Vector Machine (SVM) algorithm in liver disease classification. A publicly available liver dataset consisting of 1,700 patient records with various clinical attributes was used, and the IQR method was applied to detect and remove extreme values before model training. The SVM model employed the Radial Basis Function (RBF) kernel to capture nonlinear relationships in the data. The classifier was evaluated under two conditions: without and with IQR-based outlier removal. Performance metrics including accuracy, precision, recall, F1-score, and ROC-AUC were used to assess the model. The experimental results showed that the IQR-based preprocessing improved model performance, with the accuracy increasing from 84.41% to 84.74% and the ROC-AUC score rising from 92.08% to 93.28%. Notably, the recall for the negative class improved from 84.31% to 89.76%, indicating enhanced detection of healthy patients. These findings demonstrate that outlier handling using IQR can contribute to more stable and accurate classification outcomes, especially for models that are sensitive to data irregularities such as SVM.
Evaluasi Kinerja Kernel Linear, RBF, dan Polynomial pada Model Support Vector Machine untuk Prediksi Risiko Hipertensi Saifuddin, Saifuddin; Azhari, Lukman; Widarti, Erni; Wartono, Wartono
Jurnal Ilmiah FIFO Vol 17, No 2 (2025)
Publisher : Universitas Mercu Buana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22441/fifo.2025.v17i2.008

Abstract

Hipertensi adalah penyakit tidak menular dengan angka kematian tinggi dan sering disebut “silent killer” karena gejalanya kerap tidak terlihat pada awalnya. Deteksi dini diperlukan untuk mencegah komplikasi seperti penyakit jantung dan stroke. Penelitian ini bertujuan mengevaluasi kinerja tiga kernel pada algoritma Support Vector Machine (SVM): Linear, Radial Basis Function (RBF), dan Polynomial. Ketiga kernel tersebut dipilih untuk mewakili karakteristik pemetaan data yang berbeda: kernel linear berguna untuk memisahkan data secara linier, kernel RBF dapat menangani pola nonlinier yang kompleks, dan kernel polynomial untuk memodelkan interaksi antar fitur dengan tingkat kedalaman tertentu. Dataset berasal dari Kaggle dan mencakup 4.240 entri dengan 12 fitur prediktor yang merepresentasikan kondisi klinis dan perilaku pasien. Hasil eksperimen menunjukkan bahwa SVM-Linear mencapai accuracy 87,26% dengan ROC-AUC 0,9518; SVM-RBF memperoleh accuracy 87,38% dengan ROC-AUC 0,9450; dan SVM-Polynomial menghasilkan accuracy 86,56% dengan ROC-AUC 0,9422. SVM-Linear merupakan model paling optimal berdasarkan kombinasi F1-score dan ROC-AUC karena memberikan keseimbangan terbaik antara ketepatan dan sensitivitas. Sementara itu, meskipun SVM-RBF mencatat accuracy tertinggi, peningkatannya tidak konsisten pada metrik lain, dan SVM-Polynomial menunjukkan performa sedikit lebih rendah karena kompleksitas model yang kurang sesuai dengan karakteristik data. Penelitian ini berkontribusi dengan memberikan analisis komparatif terkait performa berbagai kernel SVM dalam klasifikasi risiko hipertensi.
Co-Authors Adi Nur Khofid Aditya Primahardika Agung Koes Indarto Agung Nugroho Agus Widyanto Allesandro Umbu Balla Rundi Argia Putri Ramadhani Azhari, Lukman Bayu Adi Catur Cahyo Nugroho, Ernes Danarti Karsono Hartati Dyah Wahyuningsih -STMIK AUB Surakarta Hartati Dyah Wahyuningsih -STMIK AUB Surakarta Khofid, Adi Nur Moh. Erkamim Muhamaad Naufal Ma’arif Muhammad Rakha Satriawan Muhammad Rizal Fernandita Pamungkas Muhammad Zidni Subarkah Neira Anjar Pujisusilo Nugraha, Tegar Wijanarko Surya Pamungkas, Muh. Rizal F. Pamungkas, Muhammad Rizal Fernandita Ramadhani, Argia Putri Ratna Herawati Rizal Fernandita Pamungkas, Muhammad Rundi, Allesandro U.B. Rundi, Allesandro Umbu Balla Saifuddin Saifuddin Saifuddin Saifuddin Saiful Bahri Setyawati, Nisrina Yulia Soares, Teotino Gomes Suswadi Syahputra, Ridwan Angga Tonggiroh, Mursalim Tri Wulandari, Fera Vera Wati Wartono Wartono Wartono Wartono Wati, Vera