Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal Jurnal Ilmiah Informatika Komputer Jurnal Ilmiah Teknologi dan Rekayasa Jurnal Sisfokom (Sistem Informasi dan Komputer) Prosiding SeNTIK STI&K
Mutiara Romana Kusuma
Universitas Megarkencana
Automotive Engineering Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Economics, Econometrics & Finance Education Electrical & Electronics Engineering Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Materials Science & Nanotechnology

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Pembuatan Visual Novel dengan Tujuan Edukasi Berbasis Android Mutiara Romana Kusuma; Suryadi; Hasanuddin Djamil; Irwan Bastian; Aqwam Rosadi Kardian
Prosiding Seminar SeNTIK Vol. 1 No. 1 (2017): Prosiding SeNTIK 2017
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Paper ini menyajikan visual novel sebagai media edukasi alternative bagi siswa SMA. Cerita pada permainan ini berdasarkan kehidupan sekolah sehari-hari seperti, berinteraksi dengan teman sebaya, ujian, dan lain-lain. Visual novel merupakan sebuah genre permainan yang dapat menggabungkan cerita dan ujian tersebut. Terdapat beberapa epilog cerita yang didapatkan berdasarkan hasil ujian. Pemain harus mendapat nilai ujian yang baik untuk mendapatkan epilog cerita baik. Visual novel ini dibuat menggunakan Ren’Py dan Ren’Py Android Packaging Tool, sehingga game ini dapat dimainkan pada perangkat Android. Metode yang digunakan adalah analisis kebutuhan, desain, implementasi, dan pengujian. Hasil pengujian menunjukkan bahwa permainan ini berhasil melewati tes yang dilakukan pada permainan.
KLASIFIKASI HAMA SERANGGA BERBASIS CNN DENGAN PENDEKATAN TRANSFER LEARNING MOBILENETV2 Alysia Naifah Aileen; Antonius Angga Kurniawan; Mutiara Romana Kusuma
Jurnal Ilmiah Informatika Komputer Vol 30, No 1 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/ik.2025.v30i1.14302

Abstract

Hama serangga merupakan salah satu ancaman utama bagi sektor pertanian, yang dapat menurunkan produktivitas dan menyebabkan kerugian ekonomi signifikan. Identifikasi manual jenis hama memerlukan keahlian khusus dan memakan waktu, sehingga dibutuhkan solusi otomatis berbasis teknologi. Penelitian ini mengembangkan sistem klasifikasi hama serangga menggunakan transfer learning dengan arsitektur MobileNetV2. Tahapan penelitian mencakup pra-pemrosesan data, pembagian dataset, augmentasi, pelatihan model, evaluasi, dan integrasi ke dalam aplikasi web. Dataset dibagi menjadi subset pelatihan, validasi, dan pengujian. Augmentasi data dilakukan melalui rescale, rotasi, pergeseran, sudut kemiringan, horizontal flip, dan zoom untuk meningkatkan variasi data. Dua model diuji: model pertama (40 epoch, augmentasi intensif) menerapkan transformasi data secara agresif—seperti rotasi besar dan zoom tinggi—sehingga menyebabkan overfitting (akurasi pelatihan 90,25%, validasi 68,29%). Sebaliknya, model kedua (50 epoch, augmentasi moderat) menggunakan transformasi yang lebih realistis dan terbatas, menghasilkan performa lebih stabil (akurasi pelatihan 94,88%, validasi 89,84%). Evaluasi menggunakan confusion matrix dan classification report menunjukkan model kedua lebih andal dalam mengklasifikasikan berbagai jenis hama. Model terbaik disimpan dalam format HDF5 dan digunakan dalam aplikasi web untuk klasifikasi otomatis berbasis gambar. Temuan ini menekankan pentingnya konfigurasi augmentasi dan jumlah epoch yang optimal dalam menghindari overfitting dan meningkatkan akurasi model klasifikasi citra.
Penerapan Teknik Ensemble Learning untuk Deteksi Dini Penyakit Jantung Menggunakan Metode Voting Classifier dan Stacking Classifier Kusuma, Mutiara Romana; Kurniawan, Antonius Angga
Jurnal Ilmiah Teknologi dan Rekayasa Vol 30, No 2 (2025)
Publisher : Universitas Gunadarma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35760/tr.2025.v30i2.14826

Abstract

Heart disease can be detected early by identifying risk factors that may contribute to its development. The Farmingham Study has conducted research on these risk factors. Machine learning models can be applied to perform early detection automatically based on data from the study. The obtained data is then processed through several pre-processing stages to prepare it for use in the modeling process. Afterward, models are built using the Random Forest, Logistic Regression, and K-Nearest Neighbor algorithms. Models built with individual algorithms show quite good performances, with the highest accuracy value of 0.91 for the Random Forest algorithm and the lowest accuracy of 0.67 for the Logistic Regression algorithm. Ensemble learning techniques such as the Voting Classifier and Stacking Classifier techniques are applied in this study to improve accuracy. The stacking technique successfully increased accuracy to 0.92. However, the voting technique does not outperform the Random Forest model. This is because the voting technique is more suitable for combining algorithms with balanced performance, whereas in this study, the Random Forest and Logistic Regression models have a significant difference in performance.
Implementation of Digital Archive Management in The Administration of International Missions Police Bureau Syah, Rama Dian; Kurniawan, Antonius Angga; Kusuma, Mutiara Romana; Ariyani, Rizki
Jurnal Sisfokom (Sistem Informasi dan Komputer) Vol. 15 No. 02 (2026): MAY
Publisher : ISB Atma Luhur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32736/sisfokom.v15i02.2622

Abstract

Advances in information technology have accelerated digital transformation in public sector administration, including archival management systems. However, limited studies have examined the implementation of digital archive systems within high-mobility and security-sensitive governmental units. This study aims to design and implement a digital archive management system for the administrative division of the International Missions Police Bureau (POLRI) to enhance correspondence supervision and operational efficiency. The research adopts the Waterfall development model, consisting of requirements analysis, system design, implementation, and testing stages. System requirements were identified through structured observation, semi-structured interviews, and literature review. The system was designed using use case modeling, database schema design, and flowchart analysis, and implemented as a web-based application using PHP and the CodeIgniter framework with a MySQL database. Functional validation was conducted using black box testing to ensure conformity between system features and specified requirements. The developed system includes modules for managing incoming letters, outgoing letters, official memoranda, archival records, and meeting room scheduling. Testing results indicate that all functional components operate according to expected specifications, demonstrating functional reliability and operational feasibility. The implementation of this system improves document traceability, administrative monitoring, and information accessibility without spatial and temporal limitations. This study contributes to the field of digital governance and information systems by providing an empirical implementation framework for digital archive management in a specialized law enforcement administrative context. The findings demonstrate the practical applicability of structured system development methods in supporting digital transformation within government institutions.
Co-Authors Alysia Naifah Aileen Antonius Angga Kurniawan Aqwam Rosadi Kardian Ariyani, Rizki Hasanuddin Djamil Irwan Bastian Kurniawan, Antonius Angga Suryadi Syah, Rama Dian