Garuda - Garba Rujukan Digital

Article Per Year (5 Year)

All

Jurnal Ilmu Komputer dan Informasi

JIKI
Website

Published by Universitas Indonesia

ISSN : 20887051 EISSN : 25029274 DOI : 10.21609

Core Subject : Science,

Computer Science & IT Library & Information Science

Jurnal Ilmu Komputer dan Informasi is a scientific journal in computer science and information containing the scientific literature on studies of pure and applied research in computer science and information and public review of the development of theory, method and applied sciences related to the subject. Jurnal Ilmu Komputer dan Informasi is published by Faculty of Computer Science Universitas Indonesia. Editors invite researchers, practitioners, and students to write scientific developments in fields related to computer science and information. Jurnal Ilmu Komputer dan Informasi is issued 2 (two) times a year in February and June. This journal contains research articles and scientific studies. It can be obtained directly through the Library of the Faculty of Computer Science Universitas Indonesia.

Arjuna Subject : -

Articles 267 Documents

23 24 25 26 27

Performance Evaluation of TabPFN for Student Depression Prediction Across Varying Sample Sizes Florentina Yuni Arini; Muhammad Kahvi Khakam Syah; Fernando Dinar Setiawan; Rafif Musyaffa Indarto; Muhammad Danil Aminuddin; Fairuz Trideas Hilmy; Ahmad Imam Mutaqin
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i2.1716

Early prediction of depression in students is a critical challenge, often hindered by the scarcity of large, labelled datasets. While supervised tabular classifiers such as Random Forest, XGBoost, and CatBoost are powerful, they typically require sufficient data and careful hyperparameter optimisation (HPO) to generalise effectively. This paper evaluates the Tabular Prior-data Fitted Network (TabPFN), a foundation model for supervised tabular learning, as a zero-shot classifier for student depression prediction. We conduct a comparative study against five robustly configured baseline classifiers (Random Forest, XGBoost, CatBoost, SVM, and Naive Bayes) across three publicly available student mental health datasets of varying sizes sourced from Kaggle: a micro-sample dataset with 101 instances, a small-sample dataset with 7,022 instances, and a moderate-sample dataset with 27,901 instances. Dataset categorization by size is defined relative to TabPFN v2.5's operational capacity of 50,000 samples rather than general machine learning conventions. Using F1-Score as the primary evaluation metric, our empirical results demonstrate a performance crossover linked to data size. On the microsample, imbalanced dataset, TabPFN achieved the highest F1-Score of 0.727, outperforming the best baseline (CatBoost and Random Forest, F1 = 0.667). In the ablation study, both raw and preprocessed inputs yielded identical results for TabPFN on this dataset, highlighting its capacity to handle unprocessed data without performance loss. On the small and moderate datasets, the tuned baselines were competitive or superior, with CatBoost leading on the moderate-sample dataset (F1 = 0.869). We conclude that TabPFN is an effective and efficient baseline for depression prediction tasks in datascarce environments, providing competitive results without HPO, while traditional ensembles remain preferred for larger datasets.

Efficient and Robust Crosswalk Segmentation under Adverse Weather Using ConvNeXt-Enhanced DeepLabv3 Muhammad Faqih; Ridho Aulia Rahman; Khadijah Fahmi Hayati Holle
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i2.1757

Reliable crosswalk perception is crucial for first-person vision (FPV) navigation in assistive guidance and intelligent transportation, but segmentation accuracy often decreases under glare, rain reflections, nighttime illumination, and worn low-contrast markings. This study proposes ConvNeXt-Enhanced DeepLabv3 (CEDL), a pixel-level segmentation architecture that integrates DeepLabv3 atrous multiscale encoding with the modern convolutional design of ConvNeXt-Tiny. Experiments were conducted on the FPVCrosswalk2025 dataset, containing synthetic and real FPV images captured under sunny, cloudy, rainy, and night conditions. The proposed model was compared with DeepLabv3 using ResNet50 and MobileNetV3-L backbones under the same training and evaluation protocol. CEDL achieved the best overall performance, with 0.946 mean IoU and 0.972 Dice, while maintaining strong percondition robustness and improved boundary preservation for thin crosswalk structures. It also achieved practical inference speed at 20.6 ms per frame, nearly five times faster than ResNet-50, despite having more parameters than MobileNetV3-L. Qualitative results show more continuous crosswalk stripes and fewer missed segments under adverse conditions. These findings indicate that CEDL provides a robust and computationally practical solution for FPV crosswalk segmentation on a mixed synthetic-real benchmark.

Forecasting BPHTB, PBB, and Non-Property Tax Local Tax Revenues Using ARIMA, Feed-Forward Neural Networks, and LSTM: A Case Study of Banjarmasin City Government Fajar; Denny
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i2.1779

Local tax targets in Banjarmasin City, Indonesia are often set through negotiation rather than accountable calculation, which can contribute to recurring gaps between targets and revenue achievement and, consequently, to disruptions in government programs financed by local taxes. This study evaluates forecasting approaches for three major local tax streams, among them: PBB (property tax), BPHTB (land and building acquisition tax), and Non-Property Tax (non-property local taxes, including PBJT). This study using monthly payment records from January 2020 to December 2024 extracted from the city’s core tax administration system. The analysis compares ARIMA-family baselines with neural models (Feed-Forward Neural Network/FFNN and Long Short-Term Memory/LSTM) under a consistent train–test protocol, while additionally testing a multivariate setting for Non-Property Tax using sectoral components (restaurant, hotel, and entertainment tax aggregates) as explanatory inputs and ARIMAX as a statistical benchmark for the multivariate case. Model selection is based on quarterly and annual RMSE, compliance with user-acceptable error thresholds, and paired statistical testing against the closest competing model (runner-up). The results indicate that a multivariate FFNN provides the strongest performance for Non-Property Tax, an LSTM configuration is most suitable for PBB, and an FFNN configuration is preferred for BPHTB. The findings support tax-type-specific model selection as a practical and defensible basis for improving revenue target-setting and short-term fiscal planning.

Addressing Data Scarcity in Dermatology: A Systematic Literature Review of Few-Shot Learning from Metric Learning to Generative Models Dedy Van Hauten; Muhammad Hannan Hunafa; Wisnu Jatmiko
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i2.1783

Background: Dermoscopy, a non-invasive imaging technique magnifying subsurface skin structures, has become the gold standard for early skin cancer detection, reducing diagnostic errors by up to 49% compared to naked-eye examination. While Deep Learning (DL) models now achieve dermatologist-level accuracy on common malignancies like melanoma when trained on large-scale datasets (e.g., ISIC archive with tens of thousands of images), clinical dermatology encompasses over 2,000 distinct conditions following a “long-tail” distribution. This creates a critical AI divide: rare, neglected, and emerging tropical diseases lack sufficient labeled data for standard supervised learning, rendering conventional DL approaches fundamentally ill-suited and leaving thousands of rare variants diagnostically underserved. Problem: The scarcity of annotated dermoscopic images for rare skin diseases poses a severe barrier to robust Medical AI deployment, as traditional deep learning models require thousands of examples per class and catastrophically overfit or exhibit severe bias in low-data regimes. This discrepancy creates incomplete clinical safety and limited specialist utility, particularly in resource-constrained settings where diagnostic expertise is scarce. Objective: This Systematic Literature Review (SLR) investigates how Few-Shot Learning (FSL) and Meta-Learning methods have been designed, validated, and applied to bridge the data scarcity gap in dermatological diagnosis between 2020–2025, analyzing their robustness, generalization capabilities, and clinical readiness for equitable healthcare delivery across the full disease spectrum. Method: Following PRISMA 2020 guidelines, we systematically searched IEEE Xplore, Scopus, ScienceDirect, and PubMed, analyzing 16 primary studies using strict PICOC eligibility criteria and a custom 10-item quality assessment framework adapted from QUADAS-2. Results: We identify a clear technological evolution from early Metric-based methods (2020–2021) to advanced Generative Foundation Models (2024–2025), with key findings highlighting the effectiveness of Generative Adversarial Networks (GANs) for feature-level hallucination and Vision Transformer backbones for Domain Generalization. However, significant barriers persist: only 19% of studies provide publicly available code, exposing a reproducibility crisis, and frequent data leakage from improper patient-level splitting undermines reported performance. Future Direction: While generative approaches and parameter-efficient fine-tuning offer promising pathways for rare disease diagnosis, achieving clinical deployment requires prioritizing external validation across diverse populations, rigorous patient-level data splits, standardized evaluation protocols, and open science practices to ensure reproducibility, fairness, and real-world clinical utility.

Proximal Policy Optimization in Autonomous Driving: A Systematic Review of Methods, Imitation Learning, and Evaluation Practices Anas Bayu Kusuma; Yogiek Indra Kurniawan; Vektor Dewanto; Wisnu Jatmiko
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i2.1784

The development of robust decision-making policies for road-based autonomous vehicles (AV) remains a critical research challenge. While Reinforcement Learning (RL) and Imitation Learning (IL) show promise, the research landscape remains fragmented, particularly regarding Proximal Policy Optimization (PPO). This paper presents a systematic literature review synthesizing PPO applications in autonomous driving. Following the Kitchenham methodology and SEGRESS guidelines, we searched major digital libraries for studies published between 2021 and 2025. From 108 initial records, a rigorous selection process yielded 26 primary studies. Our analysis reveals that standard PPO dominates (73.1%), with modified variants accounting for 23.1%. CARLA serves as the primary evaluation platform (50.0%), with urban driving (42.3%) and lane changing (30.8%) being the most common tasks. IL integration employed diverse approaches including Behavioral Cloning, GAIL, and AIRL. A significant finding is evaluation fragmentation, with 14 unique metrics identified, though collision rate (57.7%) and success rate (30.8%) were most prevalent. Quality assessment showed 46.2% of studies achieved high methodological quality, while transparency emerged as the weakest criterion. Our findings underscore the need for standardized benchmarks, sim-to-real transfer methods, and improved reporting transparency.

Bridging Vision and Graph Attention Learning Using Swin Transformer for Brain Tumor Classification Radius Tanone; Yos Richard Beeh; Pratyaksa Ocsa Nugraha Saian; Agus Cahyo Nugroho
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v19i2.1839

Accurate brain tumor classification from MRI images is crucial for supporting clinical diagnosis. This study proposes a hybrid framework that integrates a Swin Transformer and Graph-based learning to enhance feature representation and relational modeling. The Swin Transformer, known for its linear computational complexity and multi-scale attention mechanism, serves as a hierarchical feature extractor. The Graph module, on the other hand, captures structural dependencies among the extracted features. The model is evaluated on a four-class brain MRI dataset using 5-Fold cross-validation. Experimental results consistently demonstrate high performance, with the best accuracy of 0.9907. The model achieves sensitivity and specificity of 0.9903 and 0.9970, respectively. Notably, all folds maintain accuracy above 0.9500, indicating strong robustness and generalization capability. The proposed approach effectively reduces misclassification across tumor categories and outperforms baseline methods, underscoring its potential for reliable brain tumor classification.

Optimizing Online Gambling Site Detection via XLM-RoBERTa and ResNet34-Based Early Fusion Rahmat Nugroho; Denni Kurniawan
Jurnal Ilmu Komputer dan Informasi Vol. 19 No. 2 (2026): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

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

The illegal online gambling ecosystem in Indonesia has evolved into a persistent cyber threat, driven by the adaptability of threat actors in manipulating content and network infrastructure. Conventional detection methods relying on domain reputation-based blocking (blacklists) and keyword matching now face systemic failure due to sophisticated evasion techniques such as domain hopping, SEO manipulation, and content cloaking. This study proposes an automated detection framework based on Multimodal Deep Learning that simultaneously integrates semantic, visual, and infrastructure metadata analysis. We employ an Early Fusion strategy by constructing a 1,284-dimensional combined feature vector, consisting of 768 dimensions of text embeddings from the XLM-RoBERTa model, 512 dimensions of global visual features from the ResNet34 architecture, and 4 hybrid technical metadata features. To ensure high-quality ground truth and address previous transparency concerns, this approach is evaluated using a balanced dataset of 3,546 sites constructed via active crawling using the Playwright framework. The data was rigorously verified by a panel of five security experts using a majority voting scheme, achieving a Fleiss’ Kappa agreement score of 0.87, which indicates almost perfect consensus. Experimental results demonstrate that the Early Fusion model with Random Forest classification achieved an F1-Score of 95.52%, significantly outperforming the Late Fusion strategy (91.62%) and other unimodal approaches. Furthermore, this study empirically confirms the phenomenon of adversarial adaptation, revealing that traditional metadata features contribute only 0.62% to the classification decision. These findings underscore the urgency of a paradigm shift towards Deep Content Inspection to modernize national cybersecurity filtering infrastructure.

Page 27 of 27 | Total Record : 267

23 24 25 26 27

Filter by Year

2009 2026

Filter By Issues

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
Nurul Fazriah

Contact Email
jiki@cs.ui.ac.id

Phone
+62217863419

Journal Mail Official
jiki@cs.ui.ac.id

Editorial Address
"Faculty of Computer Science Universitas Indonesia Kampus Baru UI Depok - 16424"

Location
Kota depok,

Jawa barat

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name Nurul Fazriah

Contact Email jiki@cs.ui.ac.id

Phone +62217863419

Journal Mail Official jiki@cs.ui.ac.id

Editorial Address "Faculty of Computer Science Universitas Indonesia Kampus Baru UI Depok - 16424"

Location Kota depok, Jawa barat INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
Nurul Fazriah

Contact Email
jiki@cs.ui.ac.id

Phone
+62217863419

Journal Mail Official
jiki@cs.ui.ac.id

Editorial Address
"Faculty of Computer Science Universitas Indonesia Kampus Baru UI Depok - 16424"

Location
Kota depok,

Jawa barat

INDONESIA