Article Per Year (5 Year)
p-Index From 2021 - 2026
0.817
P-Index
This Author published in this journals
All Journal MATRIK : Jurnal Manajemen, Teknik Informatika, dan Rekayasa Komputer International Journal of Research and Applied Technology (INJURATECH) Journal of Embedded Systems, Security and Intelligent Systems
Ema Utami
Universitas Amikom Yogyakarta, Yogyakarta, Indonesia
Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering Engineering

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

Found 4 Documents
Search

 1 
Leveraging Vector Quantized Variational Autoencoder for Accurate Synthetic Data Generation in Multivariate Time Series Mohammad Diqi; Ema Utami; Kusrini Kusrini; Ferry Wahyu Wibowo
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 24 No. 3 (2025)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v24i3.4514

Abstract

This study addresses the challenge of generating high-quality synthetic financial time series data, acritical issue in financial forecasting due to limited access to complete and reliable historical datasets.The aim of this research was to compare the performance of the standard Variational Autoencoder andthe Vector Quantized Variational Autoencoder (VQ-VAE) in generating synthetic multivariate time seriesdata using the Adaro Energy Indonesia stock dataset. The VQ-VAE incorporates a discrete latentspace to improve the structure and control of the data generation process, whereas the standard VAEutilizes a continuous latent space. This research method was based on the implementation of bothmodels, followed by a quantitative evaluation using statistical metrics, including mean absolute error(MAE), mean squared error (MSE), root mean squared error (RMSE), and R² score. This researchshowed that the VQ-VAE outperformed the standard VAE in replicating the statistical characteristicsof stock prices, as shown by lower error values and higher R² scores across all tested features. The discretelatent space of the VQ-VAE led to the generation of more structured and statistically consistentsynthetic data. The implications of these findings suggest that the VQ-VAE model is highly suitablefor financial forecasting applications and indicate the potential for future enhancements throughintegration with hybrid models, such as attention mechanisms or generative adversarial networks.
Operational Weakness Mapping of Machine Learning–Based IntrusionDetection Systems under Realistic Deployment Scenarios Fathoni Mahardika; Ema Utami; Kusrini; Ferry Wahyu Wibowo
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol. 25 No. 3 (2026)
Publisher : Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v25i3.6147

Abstract

As machine learning-based intrusion detection systems increasingly support information security risk management, prior systematic literature review findings indicate that many studies still emphasize benchmark accuracy while paying limited attention to robustness, interpretability, and operational feasibility. This study aims to map the operational weaknesses of machine learning-based intrusion detection systems under realistic deployment stressors. A directed replication and scenario-based stresstesting approach was applied using four public intrusion detection datasets, namely CICIDS2017, CICIDS2018, UNSW-NB15, and RanSMAP. The data were obtained from public repositories, converted to binary labels, cleaned by removing identifiers and non-numeric attributes, imputed with median values, scaled with MinMax normalization, and split into training and testing subsets. Supervised models, including Random Forest and XGBoost, were compared with unsupervised baselines, including Isolation Forest, LOF/kNN-distance, and DBSCAN, across scenarios covering baseline benchmarking, class imbalance, telemetry degradation, drift, parameter sensitivity, and micro-batch inference. The results show that supervised models achieved near-perfect baseline performance but degraded sharply under minor Gaussian noise, with F1-score dropping to 0.16 for Random Forest and 0.41 for XGBoost. Unsupervised models showed limited detection capability and high sensitivity to parameters. Although micro-batch inference achieved high throughput, alert burden remained a practical concern. These findings demonstrate that benchmark accuracy alone is insufficient for deployment readiness and that IDS evaluation should include robustness, interpretability, and alert-management analysis.
An Analysis of Requirement Engineering and Techniques: A Literature Review Fariz Zakaria; Ema Utami
International Journal of Research and Applied Technology Vol. 4 No. 1 (2024): International Journal of Research and Applied Technology (INJURATECH)
Publisher : Universitas Komputer Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34010/injuratech.v4i1.13731

Abstract

This research explores the essentiality of software requirements engineering in cycles software development. The focus lies on three main techniques, namely Functional Requirement, Non-Functional Requirement, Viewpoint Orientation Requirement Definition (VORD), and analysis through USECASE (Use Case Diagram and Use Case Scenario). Through a review systematic literature, ten relevant articles have been comprehensively reviewed in order to understand these techniques. The research results show that functional and non-functional needs have a role central to software development. Functional requirements describe what is should be carried out by the system, while non-functional requirements include aspects such as performance and security aspects. The VORD approach is proven to be efficient in understanding various angles views involved in system requirements, through the steps of identification, structure, documentation, and system point of view mapping. Besides that, the USECASE method helps describe user interactions with the internal system real-world situations, providing deep insight into user needs. This research make significant contributions to understanding the nature of software requirements engineering, and provide an important foundation for future research and practice
Advances in Mixed-Type Data Clustering: A Systematic Review of Algorithms, Similarity Measures, and Validation Strategies Hendi Setiawan; Ema Utami; Alva Hendi Muhammad; Hanif Al Fatta
Journal of Embedded Systems, Security and Intelligent Systems Vol 7 No 3 (2026): September 2026
Publisher : Program Studi Teknik Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59562/jessi.v7i3.14574

Abstract

Purpose - This study reviews recent research on clustering mixed-type data and examines how clustering algorithms, distance or similarity measures, validation methods, and application domains are combined, with particular attention to education and special education. Design/methods/approach - A systematic literature review with descriptive evidence mapping was conducted using Scopus-indexed studies published from 2020 to 2025. The search identified 2,065 records, and the documented selection process resulted in 57 included studies. Each study was mapped by clustering algorithm, distance or similarity function, internal validation, external validation, and application domain. Findings - K-Means was the most frequently reported algorithm (18 studies), followed by HDBSCAN (10) and DBSCAN (9). Euclidean distance appeared in 49 studies, while Gower distance appeared in one. Internal validation was not reported in 35 studies and external validation was not reported in 36. When validation was reported, the Silhouette Score and Accuracy were the most common measures, while DBCV and Adjusted Rand Index (ARI) were uncommon. Research implications/limitations - The findings show a recurring gap between heterogeneous data structures and methods that are mainly designed for numerical or compact cluster structures. Future studies should test mixed-type distance measures, density-based clustering, and compatible internal and external validation. The review is limited to Scopus, English-language publications, the 2020-2025 period, accessible full text under the review protocol, and the information available in the review record. Originality/value - The review connects similarity representation, clustering structure, and validation instead of discussing each component separately. It identifies a weighted Gower-HDBSCAN-DBCV-ARI configuration as a testable research direction. This configuration is not presented as an empirically validated or superior method.
Co-Authors Alva Hendi Muhammad Fariz Zakaria Fathoni Mahardika Ferry Wahyu Wibowo Hanif Al Fatta Hendi Setiawan Kusrini Mohammad Diqi