Claim Missing Document
Check
Articles

Found 3 Documents
Search

Business Architecture TOGAF ADM Case Study: Desa Bungin Office Sister, Maya Gian; Hikmah , Maulida; Imelda
International Journal of Research in Vocational Studies (IJRVOCAS) Vol. 5 No. 1 (2025): IJRVOCAS - April
Publisher : Yayasan Ghalih Pelopor Pendidikan (Ghalih Foundation)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53893/ijrvocas.v5i1.386

Abstract

Desa Bungin, located in the Paringin Selatan District of Balangan Regency, has begun adopting information technology to enhance administrative activities. However, administrative management at the Desa Bungin Office still faces several challenges, including manual record-keeping, reliance on hard-copy archives, and dependence on a centralized system without an integrated information system. These limitations result in inefficiencies in time management, an increased risk of errors, and obstacles to providing optimal administrative services to the community. To address these issues, this study proposes an enterprise architecture framework to align business functions with information technology needs. The TOGAF ADM approach is employed as a structured methodology for developing an integrated architectural blueprint. This study focuses on three key phases of TOGAF ADM: the Preliminary Phase, Architecture Vision, and Business Architecture, with a strong emphasis on Business Architecture design. Business Architecture plays a crucial role in structuring and analyzing business processes, identifying key actors, and understanding interactions within the organization. This research examines essential elements such as workflows, resources, and inter-process relationships. The findings present a well-structured Business Architecture model that serves as the foundation for developing a comprehensive Enterprise Architecture. This framework is expected to enhance efficiency, streamline administrative processes, and support the digital transformation of Desa Bungin’s governance.
Diagnosis Dini Demam Berdarah Berdasarkan Data Hematologi Menggunakan Algoritma Machine Learning Nita, Yulia; Sister, Maya Gian; Triyono, Gandung
Jurnal Nasional Teknologi dan Sistem Informasi Vol 11 No 2 (2025): Agustus 2025
Publisher : Departemen Sistem Informasi, Fakultas Teknologi Informasi, Universitas Andalas

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25077/TEKNOSI.v11i2.2025.185-191

Abstract

Infeksi virus dengue yang dikenal sebagai DBD masih menjadi tantangan serius dalam layanan kesehatan di Indonesia karena sifatnya yang menular dan terus menimbulkan masalah hingga saat ini. Penyebaran DBD yang cepat dan peningkatan angka kejadian memerlukan strategi deteksi dini yang lebih efektif untuk mencegah komplikasi serius. Sayangnya, metode konvensional seperti pemeriksaan NS1, IgM/IgG, dan PCR masih menghadapi keterbatasan dalam ketersediaan serta biaya. Penelitian ini difokuskan pada pengembangan Sistem Pendukung Keputusan (SPK) yang berbasis algoritma Naïve Bayes dengan memanfaatkan data hematologi rutin untuk mengklasifikasikan tingkat risiko infeksi DBD. Dataset yang digunakan berasal dari platform Kaggle dengan 924 data pasien yang telah melalui tahap pembersihan dan normalisasi. Data yang digunakan terdiri dari variabel-variabel seperti usia, gender, tekanan darah, gula darah, suhu tubuh, denyut jantung, dan level risiko. Algoritma Naïve Bayes dipilih untuk membangun model Atas dasar kapasitasnya dalam mengolah data secara optimal dengan asumsi bahwa setiap atribut bersifat independen. Dataset Pembagian data dilakukan ke dalam dua subset, di mana sebagian besar (80%) ditujukan untuk training, dan sisanya (20%) untuk testing. Kinerja model dievaluasi menggunakan metrik seperti akurasi, presisi, recall, serta F1-score. Dari hasil pengujian, model mampu memperoleh tingkat akurasi sebesar 98,03%, dengan performa sangat baik di seluruh kelas risiko, terutama recall sempurna pada kelas risiko tinggi. Hal ini menunjukkan kemampuan model dalam mengidentifikasi kasus-kasus berisiko tinggi tanpa terlewat. Dengan demikian, penelitian ini membuktikan bahwa data hematologi yang sederhana dapat dimanfaatkan secara optimal untuk deteksi dini DBD. Sistem yang dikembangkan berpotensi menjadi alat bantu diagnosis yang cepat, hemat biaya, dan dapat diimplementasikan secara luas untuk mendukung pelayanan kesehatan primer.
Early Detection of Hepatitis Disease Using Machine Learning Algorithms Sister, Maya Gian; Nita, Yulia; Solichin, Achmad
Indonesian Journal of Artificial Intelligence and Data Mining Vol 8, No 3 (2025): November 2025
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v8i3.38084

Abstract

Hepatitis is an inflammation of the liver caused by viral infections, autoimmune disorders, or exposure to toxic substances. Hepatitis B and C are major public health concerns because they may progress to cirrhosis or liver cancer. In Indonesia, the transmission rate remains high, primarily through blood contact, unsterile needles, transfusions, and maternal delivery. Limited public awareness, coupled with the often asymptomatic nature of hepatitis, leads to delayed detection, which increases the risk of severe complications and mortality. Therefore, early detection is crucial to minimizing the disease burden.This study proposes a risk prediction model for hepatitis using non-laboratory clinical data and machine learning methods. Eight classification algorithms were compared, Naïve Bayes, K-Nearest Neighbor (K-NN), Random Forest, Support Vector Machine (SVM), Decision Tree, AdaBoost, XGBoost, CatBoost, and LightGBM. Model performance was evaluated through K-fold cross-validation using accuracy, precision, recall, F1-score, and AUC. The results show that the SVM with a linear kernel achieved the highest performance, with 87% accuracy and balanced F1-scores across all classes. The model successfully classified four categories, Acute Hepatitis, Chronic Hepatitis, Liver Abscess, and Parasitic/Viral Infections. These findings highlight the potential of machine learning to improve early detection of hepatitis effectively and efficiently.