Claim Missing Document
Check
Articles

Machine Learning Klasifikasi Penyakit Jiwa Menggunakan Metode K-Nearest Neighbor Berbasis Web M. Althaf Kiram; Eva Darnila; Ilham Sahputra
Jurnal Ners Vol. 9 No. 2 (2025): APRIL 2025
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/jn.v9i2.43319

Abstract

Gangguan jiwa merupakan masalah kesehatan yang dapat berdampak signifikan terhadap kehidupan individu jika tidak terdiagnosis dan ditangani dengan baik. Untuk mendukung deteksi dini dan mempermudah proses klasifikasi penyakit jiwa, penelitian ini mengembangkan sistem berbasis K-Nearest Neighbor (KNN) yang diimplementasikan dalam aplikasi berbasis web. Dataset yang digunakan diperoleh dari Rumah Sakit Jiwa Aceh dengan total 564 data pasien, yang mencakup gejala seperti kecemasan, penyakit persepsi, serta tingkat keparahan dalam kehidupan sehari-hari. Proses klasifikasi dilakukan melalui serangkaian tahapan, termasuk pembersihan data, normalisasi, pemilihan parameter optimal, dan evaluasi model. Dengan K=10 model diuji menggunakan confusion matrix untuk mengukur performa dengan metrik akurasi, presisi, recall, dan F1-score, yang menghasilkan nilai 100% untuk semua kategori penyakit jiwa yang diklasifikasikan, yaitu Depresi Berat, Depresi Ringan, Skizofrenia Paranoid, dan Skizofrenia Hebefrenik. Hasil ini menunjukkan bahwa metode KNN dapat digunakan secara efektif dalam mendiagnosis penyakit jiwa berdasarkan gejala yang diberikan. Selain itu, implementasi berbasis web memungkinkan akses lebih luas bagi tenaga medis dan masyarakat dalam melakukan klasifikasi awal tanpa harus bergantung sepenuhnya pada diagnosis manual. Dengan hasil yang akurat dan sistem yang responsif, penelitian ini diharapkan dapat berkontribusi dalam meningkatkan pelayanan kesehatan mental serta memberikan solusi berbasis teknologi untuk mendukung upaya deteksi dini penyakit jiwa.
A Natural Language Processing-Based Chatbot as a Medium for Consultation and Education on Direct-Contact Infectious Diseases Serlina Serlina; Eva Darnila; Rini Meiyanti
Journal of Mathematics Instruction, Social Research and Opinion Vol. 5 No. 1 (2026): March
Publisher : MASI Mandiri Edukasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58421/misro.v5i1.984

Abstract

Direct-contact infectious diseases such as influenza, diphtheria, tuberculosis (TB), scabies, varicella, impetigo, herpes simplex, and HIV remain public health threats. Limited access to accurate information encourages the development of chatbots as educational media. This study aims to design and build an NLP-based chatbot named SerMediCare to provide consultation and education on infectious diseases. The Research and Development (R&D) method with an iterative approach was used, including needs analysis, data collection from journals and medical books, and interviews with healthcare workers; system design; model training; and implementation on a web platform. The dataset was prepared in JSON format, including patterns, responses, and tags, and trained with a Transformer-based model to accurately recognize user intent. Evaluation results show that SerMediCare achieves 86% accuracy, indicating its ability to provide relevant responses to user queries. Black box testing confirmed that all features function properly. This chatbot is expected to be an effective digital tool for improving health literacy and facilitating public access to reliable information about infectious diseases.
Learning Media Application for Basic Digital Courses Using Augmented Reality with the Marker Based Tracking (MBT) Method Syamsul Buchori Pane; Eva Darnila; Fajriana Fajriana
ITEJ (Information Technology Engineering Journals) Vol. 10 No. 2 (2025): December
Publisher : Pusat Teknologi Informasi dan Pangkalan Data IAIN Syekh Nurjati Cirebon

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24235/itej.v10i2.263

Abstract

The rapid development of digital technology opens up opportunities to increase the effectiveness of learning media, one of which is by utilizing Augmented Reality (AR) technology. This study aims to develop an AR-based digital basic course learning media application with the marker-based tracking method. The materials presented include number systems, logic gates, boolean algebra, Karnaugh maps, and flip-flops. The development process is carried out through a waterfall approach which includes literature studies, needs analysis, system design, implementation, and testing. The results of the study show that the developed application is able to display 3D objects interactively and in real-time through features such as rotation, zoom, and audio, so as to improve students' understanding and interest in learning. The application of AR technology has proven to be an innovative and effective medium in conveying abstract concepts in digital learning.