Article Per Year (5 Year)
p-Index From 2020 - 2025
0.408
P-Index
This Author published in this journals
All Journal PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat JISKa (Jurnal Informatika Sunan Kalijaga) Respati
Meliala, Dyan Avando
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Computer Science & IT Economics, Econometrics & Finance Electrical & Electronics Engineering Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Public Health Social Sciences

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search

 1 
SISTEM PAKAR HUBUNGAN KEKERABATAN (ERTUTUR) DALAM ADAT ISTIADAT MASYARAKAT SUKU BATAK KARO Meliala, Dyan Avando
Jurnal Teknologi Informasi RESPATI Vol 12, No 2 (2017)
Publisher : Universitas Respati Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (354.075 KB) | DOI: 10.35842/jtir.v12i2.221

Abstract

INTISARIErtutur  merupakan salah satu ciri masyarakat Karo yang pada saat ini kurang dipahami oleh generasi muda Karo. Jika hal ini dibiarkan terus, dikhawatirkan budaya ini akan hilang. Dalam penelitian ini diusulkan sebuah sistem pakar untuk ertutur pada masyarakat Karo sebagai salah satu upaya melestarikan budaya dan mendokumentasikan budaya Ertutur. Erturur dalam penelitian ini dibatasi pada penentuan hubungan kekerabatan dalam Tutur Siwaluh. Adapun untuk mengukur tingkat kepastian dipergunakan metode certainty factor.Aturan dalam penentuan hubungan kekerabatan dan tingkat kepastian dalam penelitian ini diperoleh dari Lembaga Adat Masyarakat Karo. Aturan tersebut  dibentuk berdasarkan kombinasi garis keturunan pihak yang melakukan Ertutur. Penentuan hubungan kekerabatan diperoleh berdasarkan kecocokan Merga/ Beru para pihak yang melakukan Ertutur pada setiap garis keturunan dan nilai kepastiannya dipengaruhi oleh masukan dari pakar serta masukan dari pengguna.Pada proses pengujian, sistem yang dihasilkan diuji menggunakan data aktual, yaitu data sebenarnya dari pihak yang melakukan ertutur dan diketahui hubungan kekerabatannya. Hasil pengujian dengan beberapa contoh aktual menunjukkan bahwa didapatkan beberapa kemungkinan hubungan kekerabatan dengan tingkat kepastian yang berbeda. Hubungan kekerabatan ditentukan dengan tingkat kepastian tertinggi.Kata kunci —   Ertutur, Karo, Certainty Factor, Forward Chaining, Sistem Pakar  ABSTRACTErtutur which is one of the characteristic of Karo people is poorly understood by the young generation of Karo people today. If this condition happen continually, this culture will disappear. Therefore, an expert system about Ertutur in Karo Society for preserving and documenting this culture was proposed. In this study, ertutur was limited to the determination of kinship in Tutur Siwaluh. The used method for measuring certainty was certainty factor.Rules in determining kinship and certainty in this study were obtained from the institution of Karo society. The rules were established based on the combination on the lineage combination of people doing Ertutur. Determination of kinship was obtained by matching Merga or Beru for each lineage and certainty value which was influenced by input from experts and user feedback.In the testing process, the produced system was tested using actual data from people doing ertutur and knowing their kinship. The result of the test with some actual examples showed that several possible kinship with different levels of certainty was obtained. Kinship was determined by the highest degree of certainty.Kata kunci —  Ertutur, Karo, Certainty Factor, Forward Chaining, Expert Systems
Pelatihan Penggunaan LMS untuk Peningkatan Kualitas Layanan Perkuliahan di Fakultas Sains dan Teknologi, Universitas Respati Yogyakarta: Training on Using LMS to Improve the Quality of Lecture Services at the Faculty of Science and Technology, Universitas Respati Yogyakarta Ordiyasa, I Wayan; Sugiarto, Raden Bagus Nurhadi Wijaya; Winardi, Sugeng; Meliala, Dyan Avando; Utari, Evrita Lusiana; Sahal, Ahmad
PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat Vol. 10 No. 2 (2025): PengabdianMu: Jurnal Ilmiah Pengabdian kepada Masyarakat
Publisher : Institute for Research and Community Services Universitas Muhammadiyah Palangkaraya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33084/pengabdianmu.v10i2.8500

Abstract

Training on the Use of Learning Management Systems (LMS) is essential for enhancing the quality of academic services in an era of increasingly adopting technology. The integration of LMS with conventional methods, known as blended learning, which combines distance learning, regular classes, and LMS, results in a more effective and efficient learning process. With the shift towards digital learning, LMS use becomes crucial for improving the efficiency, accessibility, and quality of academic services. Through e-learning, students not only listen to lectures but also actively observe, perform, demonstrate, and more. Teaching materials can be virtualized in various formats to create more engaging and dynamic content, motivating students to delve deeper into the learning process. This training aims to equip educators and administrative staff with knowledge of LMS features and potential, enabling them to maximize its use for content delivery, facilitating teacher-student interaction, and enhancing course management and evaluation. The training methods include presentations on basic LMS concepts, demonstrations of key features, and hands-on practice sessions that allow participants to actively engage in the learning process. Additionally, interaction between participants and facilitators is enhanced through discussions and Q&A sessions, ensuring deep understanding and practical skills in LMS usage to improve academic service quality. Consequently, this training is expected to provide a solid foundation for educational institutions to meet challenges and leverage the opportunities offered by the digital era in providing quality academic services.
Enhancing Diabetes Classification Using a Relaxed Online Maximum Margin Algorithm Meliala, Dyan Avando; Sulistyawati, Arum Kurnia; Diqi, Mohammad; Hiswati, Marselina Endah; Kristian, Tadem Vergi
JISKA (Jurnal Informatika Sunan Kalijaga) Vol. 10 No. 3 (2025): September 2025
Publisher : UIN Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/jiska.2025.10.3.267-278

Abstract

Diabetes mellitus is a growing global health concern that requires accurate and reliable classification models for early diagnosis and effective management. Traditional machine learning models often struggle with class imbalance, generalization limitations, and high false-positive rates, leading to misdiagnoses and delayed interventions. This study enhances the Relaxed Online Maximum Margin Algorithm (ROMMA) to improve the accuracy of diabetes classification. Using a publicly available dataset from Kaggle, which contains 768 medical records with nine health attributes, the model’s performance was evaluated through a confusion matrix and classification metrics. The Enhanced ROMMA achieved an accuracy of 92%, significantly improving upon the Standard ROMMA’s 85% accuracy. The recall for diabetes detection increased from 0.83 to 0.94, reducing false negatives and ensuring more accurate patient identification. While slight misclassification still exists, this improvement enhances the model’s reliability for clinical applications. Future research should incorporate larger datasets and advanced techniques to enhance robustness and generalizability. This study contributes to the development of more accurate machine learning models for diabetes prediction, ultimately supporting better healthcare decision-making.
Co-Authors Arum Kurnia Sulistyawati Evrita Lusiana Utari, Evrita Lusiana Kristian, Tadem Vergi Marselina Endah Hiswati Mohammad Diqi Ordiyasa, I Wayan Sahal, Ahmad Sugeng Winardi Sugiarto, Raden Bagus Nurhadi Wijaya