Article Per Year (5 Year)
p-Index From 2021 - 2026
0.882
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Teknik Elektro Komputer dan Informatika (JITEKI) Jurnal Teknologi Informasi dan Ilmu Komputer INTEGER: Journal of Information Technology Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat Jurnal Mandiri IT
Dewi, Ni Wayan Emmy Rosiana
Unknown Affiliation
Religion Humanities Computer Science & IT Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Library & Information Science Mathematics Nursing Public Health Social Sciences

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
Comparison of decision tree and naive bayes methods in glioma classification based on clinical and molecular factors Dewi, Ni Wayan Emmy Rosiana; Putra, I Made Suwija; Simanungkalit, Erwinsyah; Manoppo, Franky Gerald Cliford
Jurnal Mandiri IT Vol. 13 No. 4 (2025): April: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v13i4.389

Abstract

This study compares the performance of Decision Tree and Naive Bayes classifiers in classifying gliomas based on clinical and molecular factors. The dataset consists of 839 patient records with features including Grade, Gender, Age, Race, and gene mutation status. The evaluation showed that the Decision Tree classifier achieved 98% accuracy on the training data and 76% on the test data, while the Naive Bayes classifier obtained 74% and 71% accuracy, respectively. Both models demonstrated strong predictive ability, with feature importance analysis highlighting the IDH1 gene mutation as a significant factor in glioma classification. This study aims to identify the most effective method for supporting clinical decision-making in glioma diagnosis. It contributes to the development of medical decision support systems and provides insight into the application of machine learning models, particularly in utilizing molecular markers such as IDH1.
Klasifikasi Genre Buku Berbasis Judul dan Sinopsis Menggunakan Metode Support Vector Machine Dewi, Ni Wayan Emmy Rosiana; Putra, I Made Suwija; Githa, Dwi Putra
INTEGER: Journal of Information Technology Vol 10, No 1 (2025): April
Publisher : Fakultas Teknologi Informasi Institut Teknologi Adhi Tama Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31284/j.integer.2024.v10i1.7562

Abstract

Tantangan besar dalam manajemen perpustakaan tradisional adalah menciptakan metode untuk mengkategorikan buku sesuai dengan genrenya. Penelitian ini mengusulkan penggunaan metode Support Vector Machine (SVM) untuk mengklasifikasikan buku berdasarkan judul dan sinopsisnya. Dataset penelitian ini diambil dari CMU Book Summary Dataset, yang mencakup berbagai genre buku. Hasil penelitian menunjukkan bahwa metode SVM dengan kernel linier melakukan tugas klasifikasi genre buku dengan lebih baik dibandingkan metode K-Nearest Neighbors (K-NN), serta preprocessing teks dan ekstraksi fitur menggunakan Term Frequency-Inverse Document Frequency (TF-IDF). Akurasi tertinggi SVM adalah 47,7% dalam skenario 90 persen data pelatihan dan 10 persen data pengujian, sedangkan K-NN hanya memiliki 31,53% dalam skenario 80 persen dan 20 persen data pelatihan dan pengujian. Hasil menunjukkan bahwa SVM lebih baik daripada K-NN dalam menangani klasifikasi teks berdasarkan judul dan sinopsis. Namun, untuk validasi lebih lanjut, penelitian lebih lanjut diperlukan dengan dataset yang lebih besar dan dalam berbagai bahasa.
Optimalisasi Hidroponik dan Vertikultur Komunitas Perkotaan: Meningkatkan Pendapatan dan Ketahanan Pangan Dewi, Ni Nyoman Sri Rahayu Trisna; Bimantara, Putu Oki; Dewi, Ni Wayan Emmy Rosiana; Permana, I Made Adhi
Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat Vol. 5 No. 6 (2025): November 2025 - Jurnal Altifani Penelitian dan Pengabdian kepada Masyarakat
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/altifani.v5i6.937

Abstract

Banjar Pelagan, Desa Penatih, Kota Denpasar menghadapi penyempitan lahan akibat pembangunan, yang menurunkan produktivitas Kelompok Wanita Tani (KWT) Ratna Sari. Program ini menawarkan solusi berupa penerapan sistem hidroponik dan vertikultur untuk optimalisasi lahan sempit. Metode ini memungkinkan panen lebih cepat, ramah lingkungan, serta menghasilkan produk organik bernilai ekonomi tinggi. Pemberdayaan KWT dilakukan melalui pelatihan budidaya modern dan digital marketing, sehingga akses pasar menjadi lebih luas melalui media sosial dan e-commerce. Hasil program tidak hanya mengatasi keterbatasan lahan, tetapi juga meningkatkan pendapatan, keberlanjutan ekonomi, serta menjadi model pengembangan pertanian perkotaan.
Analisis dan Perbaikan Proses Bisnis Sistem Terintegrasi Pembayaran Uang Kuliah dengan Metode Business Process Improvement (BPI) pada Universitas X Dewi, Ni Wayan Emmy Rosiana; Nirmala, Putu Yogie Ayu; Putra, I Made Suwija; Sudana, A.A. Kompiang Oka
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 10 No 2: April 2023
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.20235770

Abstract

Selama beberapa tahun terakhir, peran teknologi semakin berkembang pesat. Penerapan Sistem Terintegrasi Pembayaran Uang Kuliah telah membantu pengelolaan kampus yang terintegrasi. Namun, pada penerapan Sistem Terintegrasi Pembayaran Uang Kuliah ditemukan beberapa proses yang tidak sesuai dengan harapan. Hal ini disebabkan karena beberapa proses bisnis belum memiliki tujuan untuk mengefektifkan, mengefisienkan, serta mudah diadaptasikan dengan proses-proses lain dalam sistem. Perlu adanya perbaikan sistem serta proses bisnis yang menghasilkan proses bisnis rekomendasi untuk menyelesaikan masalah tersebut. Sebuah metode evaluasi diperlukan dalam analisa pemodelan proses bisnis pada suatu organisasi untuk membantu proses perbaikan pada organisasi tersebut. Business Process Improvement (BPI) merupakan salah satu metode yang diterapkan untuk melaksanakan Continuous Improvement. BPI dapat diartikan sebagai kerangka sistematis yang memiliki tujuan untuk membantu mewujudkan kemajuan yang signifikan dalam berjalannya proses bisnis pada suatu organisasi. Penerapan Metode BPI dalam dalam menganalisa proses bisnis menghasilkan proses bisnis kritis, yaitu Proses Bisnis Manajemen Laporan. Penelitian ini menghasilkan rekomendasi proses bisnis dengan waktu rata-rata untuk menjalankan proses yang lebih singkat dibandingkan proses bisnis saat dan sesuai dengan kebutuhan pengguna. Penerapan rekomendasi proses bisnis tersebut diharapkan dapat menjadikan kinerja Sistem Terintegrasi Pembayaran Uang Kuliah lebih optimal dan efektif.Abstract Over the past few years, the role of technology has grown rapidly. The implementation of the Integrated Tuition Payment System has helped the integrated campus management. However, in the implementation of the Integrated Tuition Payment System, several processes were found that were not as expected. This is because some business processes do not yet have a goal to make it more effective, efficient, and easily adapted to other processes in the system. It is necessary to improve systems and business processes that produce business process recommendations to solve these problems. An evaluation method is needed in the analysis of business process modeling in an organization to assist the improvement process in the organization. Business Process Improvement (BPI) is one of the methods applied to implement Continuous Improvement. BPI can be interpreted as a systematic framework that has the aim of helping to realize significant progress in the running of business processes in an organization. The application of the BPI method in analyzing business processes produces critical business processes, namely Business Process Management Reports. This research produces business process recommendations with an average time to run processes that are shorter than current business processes and according to user needs. The application of these business process recommendations is expected to make the performance of the Integrated Tuition Payment System more optimal and effective.
Game Recommendation System Using Transformer with Remastered Feature Putra, I Made Suwija; Arturito, Made Jiyestha; Sudana, Anak Agung Kompiang Oka; Dewi, Ni Wayan Emmy Rosiana
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 11 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v11i4.31345

Abstract

The rapidly growing game industry makes it difficult for players to find games that match their preferences. Conventional recommendation methods are often unsatisfactory due to a lack of personalization. This study aims to design and build a web-based game recommendation system using the content-based filtering method by leveraging a fine-tuned Transformer embedding model, all-MPNet-base-v2, to deeply analyze the textual content of games. The research methodology included data collection from the Steam API (43,900 games), text preprocessing with TF-IDF for keyword extraction, and significantly, fine-tuning the all-MPNet-base-v2 model using the Knowledge Distillation method with jina-embedding-v3 as the teacher model. A novel game series identification feature using fuzzy string matching was also implemented. The resulting embedding vectors were indexed using LanceDB and deployed in a Flask web application. The research contributions are the successful domain-specific adaptation of MPNet via Knowledge Distillation and the implementation of the series identification feature. Quantitative evaluation demonstrated the fine-tuned model's superiority, achieving substantial improvements over the baseline in MRR@10 (0.5857), MAP@10 (0.5149), and Hit Rate@3 (0.90). User Acceptance Testing (UAT) with 15 respondents showed high acceptance (92.89%). Limitations include the Steam-only dataset, potential information loss from TF-IDF, and the small UAT sample size. This study confirms that fine-tuned Transformer embeddings within a content-based framework, enhanced by Knowledge Distillation, can produce effective, accurate, and well-received game recommendations, further improved by context-aware features like series identification.
Co-Authors Anak Agung Kompiang Oka Sudana Arturito, Made Jiyestha Bimantara, Putu Oki Dewi, Ni Nyoman Sri Rahayu Trisna Dwi Putra Githa Manoppo, Franky Gerald Cliford Nirmala, Putu Yogie Ayu Permana, I Made Adhi Putra, I Made Suwija Simanungkalit, Erwinsyah Sudana, A.A. Kompiang Oka