Jurnal Teknik Informatika (JUTIF)
Jurnal Teknik Informatika (JUTIF) is an Indonesian national journal, publishes high-quality research papers in the broad field of Informatics, Information Systems and Computer Science, which encompasses software engineering, information system development, computer systems, computer network, algorithms and computation, and social impact of information and telecommunication technology. Jurnal Teknik Informatika (JUTIF) is published by Informatics Department, Universitas Jenderal Soedirman twice a year, in June and December. All submissions are double-blind reviewed by peer reviewers. All papers must be submitted in BAHASA INDONESIA. JUTIF has P-ISSN : 2723-3863 and E-ISSN : 2723-3871. The journal accepts scientific research articles, review articles, and final project reports from the following fields : Computer systems organization : Computer architecture, embedded system, real-time computing 1. Networks : Network architecture, network protocol, network components, network performance evaluation, network service 2. Security : Cryptography, security services, intrusion detection system, hardware security, network security, information security, application security 3. Software organization : Interpreter, Middleware, Virtual machine, Operating system, Software quality 4. Software notations and tools : Programming paradigm, Programming language, Domain-specific language, Modeling language, Software framework, Integrated development environment 5. Software development : Software development process, Requirements analysis, Software design, Software construction, Software deployment, Software maintenance, Programming team, Open-source model 6. Theory of computation : Model of computation, Computational complexity 7. Algorithms : Algorithm design, Analysis of algorithms 8. Mathematics of computing : Discrete mathematics, Mathematical software, Information theory 9. Information systems : Database management system, Information storage systems, Enterprise information system, Social information systems, Geographic information system, Decision support system, Process control system, Multimedia information system, Data mining, Digital library, Computing platform, Digital marketing, World Wide Web, Information retrieval Human-computer interaction, Interaction design, Social computing, Ubiquitous computing, Visualization, Accessibility 10. Concurrency : Concurrent computing, Parallel computing, Distributed computing 11. Artificial intelligence : Natural language processing, Knowledge representation and reasoning, Computer vision, Automated planning and scheduling, Search methodology, Control method, Philosophy of artificial intelligence, Distributed artificial intelligence 12. Machine learning : Supervised learning, Unsupervised learning, Reinforcement learning, Multi-task learning 13. Graphics : Animation, Rendering, Image manipulation, Graphics processing unit, Mixed reality, Virtual reality, Image compression, Solid modeling 14. Applied computing : E-commerce, Enterprise software, Electronic publishing, Cyberwarfare, Electronic voting, Video game, Word processing, Operations research, Educational technology, Document management.
Articles
1,314 Documents
<![CDATA[Classification and Association Pattern Discovery in Public Responses to Muhammad Qasim's Dreams Using CHAID and FP-Growth ]]>
<![CDATA[Tutik Khotimah]]>;
<![CDATA[Dandy Wibowo]]>;
<![CDATA[Darsin Darsin]]>;
<![CDATA[Hana Netti Purasani]]>;
<![CDATA[Jaya Mualimin]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5736
<![CDATA[Dreams are considered important spiritual experiences in Islam. Muhammad Qasim’s dreams, associated with the end times, have generated various public responses. This study aims to explore patterns of public response to these dreams using a data mining approach. Data were collected through an online questionnaire covering six main variables: dream experiences, knowledge of dreams in Islam, belief in the Apocalypse, knowledge of end-time science, and knowledge about Muhammad Qasim’s dreams, with responses from 708 participants used as class labels (positive, neutral, negative). The methods employed include CHAID for classification, and FP-Growth for association rule mining. The results show that CHAID produces a compact and interpretable model, generating 9 rules with an accuracy of 57.63%. The precision values for the negative, neutral, and positive classes are 30.77%, 38.46%, and 62.28%, while the recall values are 7.55%, 21.05%, and 87.38%. The F1-scores are 12.14%, 27.20%, and 72.72%, with a macro F1-score of 37.35% and a weighted F1-score of 64.04%. The hybrid CHAID–FP-Growth approach produces a higher proportion of high-quality rules based on support, confidence, and lift compared to conventional FP-Growth. In addition, an exact matching rule is identified across both methods: Knowledge about Muhammad Qasim’s dreams = Yes → Response = Positive, with a support of 26.5%, confidence of 83.2%, and lift of 1.436. This study contributes by proposing a segment-based hybrid approach that enhances the quality of association rules and identifies cross-validated patterns across methods. Overall, the model demonstrates fairly good performance, but still has limitations in handling minority classes.]]>
<![CDATA[A Comparative Study of RT-DETR and YOLO v11 for Real-Time Vehicle License Plate Detection ]]>
<![CDATA[Beny Beny]]>;
<![CDATA[Herti Yani]]>;
<![CDATA[Xaverius Sika]]>;
<![CDATA[Muhammad Ismail]]>;
<![CDATA[Daniel Sintong Pardamean Simanjuntak]]>;
<![CDATA[Gangga Ramadhan]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5737
<![CDATA[Vehicle license plate detection is a key component of intelligent transportation systems, with applications in automated toll collection, traffic surveillance and security systems. This task is challenging due to variations in illumination, motion blur, occlusion, diverse license plate formats, and camera viewpoints, requiring object detection models to balance accuracy and computational efficiency, especially for real-time deployment. Recent developments in deep learning have introduced different detection paradigms, particularly convolutional neural network–based and transformer-based architectures. This paper presents a systematic comparison between a transformer-based detector, RT-DETR, and a convolutional neural network–based detector, YOLO v11, for vehicle license plate detection, focusing on accuracy–efficiency trade-offs. Experimental results show that both models achieve very high detection accuracy, with an mAP@50 of 0.995. RT-DETR achieves slightly higher performance in terms of mAP@50–95 (0.912 vs. 0.907), Precision (1.000 vs. 0.999), Recall (0.992 vs. 0.984), and F1-score (0.996 vs. 0.991). However, this accuracy advantage is accompanied by higher computational cost. RT-DETR requires an average inference time of 37.99 ms per image, corresponding to an estimated throughput of approximately 25 FPS, whereas YOLO v11 achieves a significantly lower inference time of 7.7 ms, corresponding to an estimated throughput of 129.87 FPS under the same input resolution. In addition, RT-DETR requires a longer training time (1 h 52 min) compared to YOLO v11 (1 h 22 min). Overall, this study shows that RT-DETR provides slightly higher detection accuracy, while YOLO v11 is more appropriate for real-time license plate detection due to its lower computational cost.]]>
<![CDATA[Development of a Telegram-Based Automated Penetration Testing System Based on PTES and OWASP WSTG Version 4.2 ]]>
<![CDATA[Ahmad Izza Abdillah]]>;
<![CDATA[Ira Rosianal Hikmah]]>;
<![CDATA[Rahmat Purwoko]]>;
<![CDATA[Arizal Arizal]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5738
<![CDATA[The security of Electronic-Based Government Systems (SPBE) is imperative for protecting public service websites and safeguarding sensitive data. Persistent security threats, such as web defacement incidents, necessitate the adoption of more efficient and accessible security assessment methodologies. This research addresses this challenge by proposing an automated penetration testing tool integrated into a Telegram bot interface, developed using the Software Development Life Cycle (SDLC) methodology. This study contributes a fully integrated, Telegram-driven penetration testing framework aligned with standardized security testing protocols, specifically the Penetration Testing Execution Standard (PTES) and OWASP WSTG v4.2. A key technical advancement is the integration of proxychains technology to prevent IP address blocking during automated scans. Evaluation through User Acceptance Testing (UAT) yielded an overall score of 95.75%, confirming its excellent reliability (96%), usability (96%), and efficiency (95.2%). Performance testing validated the tool's capability to detect four out of five predefined vulnerability types. This research concludes that the tool is a viable solution for enhancing the security posture of government websites through standardized and regular security audits.]]>
<![CDATA[Public Sentiment Analysis of Online Gambling Using Naïve Bayes and SVM on TikTok Social Media Data ]]>
<![CDATA[Raditya Agung]]>;
<![CDATA[Jasmir Jasmir]]>;
<![CDATA[Effiyaldi Effiyaldi]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5739
<![CDATA[This study investigates public sentiment toward online gambling on TikTok social media and evaluates the performance of two machine learning algorithms, Multinomial Naïve Bayes and Support Vector Machine (SVM), for sentiment classification. The increasing spread of online gambling content on social media platforms has raised concerns regarding its social impact and the need to understand public responses toward this phenomenon. Therefore, this research aims to analyze the sentiment expressed in TikTok comments and to compare the effectiveness of Naïve Bayes and SVM in classifying sentiments into positive, negative, and neutral categories.The dataset consists of 99,065 TikTok comments obtained from Kaggle. The research process includes data collection, text preprocessing, feature extraction using TF–IDF, model training, and evaluation using a confusion matrix along with accuracy, precision, recall, and F1-score metrics. The experimental results show that the dataset is highly imbalanced, with neutral sentiment dominating the distribution.The evaluation results indicate that the Support Vector Machine model performs better than Multinomial Naïve Bayes. SVM achieved an accuracy of 98.74%, outperforming Naïve Bayes which obtained 94.72%. In addition, SVM also demonstrates higher macro-averaged precision, recall, and F1-score. These findings indicate that SVM provides more robust performance for sentiment classification in large-scale social media data and can support data-driven monitoring of public opinion regarding online gambling on social media platforms.]]>
<![CDATA[Regime-Sensitive VaR Forecasting for Indonesian Gold with Quantile LSTM: Walk-Forward Backtesting and Stress Diagnostics ]]>
<![CDATA[Antika Zahrotul Kamalia]]>;
<![CDATA[Arief Wibowo]]>;
<![CDATA[Rusdah Rusdah]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5740
<![CDATA[This study investigates regime-sensitive Value-at-Risk (VaR) forecasting for ANTAM Indonesian gold using a Quantile LSTM under a rigorous walk-forward evaluation protocol. Daily prices are transformed into log-returns, and volatility- and momentum-based features are constructed in a time-respecting manner to prevent information leakage. The model is trained with multi-quantile pinball loss to estimate one-day-ahead VaR at and . Out-of-sample performance is evaluated using a walk-forward expanding-window scheme with periodic retraining, and stress-regime diagnostics are conducted via rolling-volatility-based regime labeling to assess stability during turbulent episodes. Quantile LSTM is benchmarked against standard VaR baselines (Historical Simulation, parametric normal, EWMA, and GARCH(1,1) with normal and Student-t innovations) using violation rates, Kupiec and Christoffersen backtests, pinball loss, and loss-based model comparison. Results indicate good aggregate calibration for Quantile LSTM, with violation rates of 0.554% (6/1083) for VaR 1% and 5.079% (55/1083) for VaR 5%, passing unconditional coverage. However, at there are indications of clustered exceedances, highlighting the value of rolling and regime-based diagnostics. At the 1% tail, GARCH-t achieves lower and significantly different pinball losses, reinforcing heavy-tail models as strong benchmarks for extreme risk. Beyond accuracy metrics, the regime-sensitive diagnostics provide actionable signals for deploying Quantile LSTM within automated risk-monitoring pipelines, where rolling exceedance alarms and adaptive retraining can improve operational reliability under volatility regime shifts.]]>
<![CDATA[Benchmarking IndoBERT and Optimized Long Short-Term Memory for Sentiment Analysis on the Access by KAI Mobile Application ]]>
<![CDATA[I Gusti Ayu Agung Mas Aristamy]]>;
<![CDATA[I Gusti Ayu Putu Widhya Iswari]]>;
<![CDATA[Ni Putu Suci Meinarni]]>;
<![CDATA[Ni Wayan Wardani]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5743
<![CDATA[PT Kereta Api Indonesia (Persero), or PT KAI, is a key public transportation provider in Indonesia whose service quality significantly influences public perception. The proliferation of digital platforms allows users to voice their opinions on PT KAI’s services, rendering sentiment analysis a vital tool for evaluating public satisfaction. This study analyzes public sentiment toward PT KAI by benchmarking the performance of Long Short-Term Memory (LSTM) and IndoBERT models. We collected 82,044 user reviews from various digital platforms including X (formerly Twitter), Instagram, TikTok, YouTube, Facebook, and Google Play Store specifically focusing on the “Access by KAI” application. Data labeling utilized the InSet Lexicon, and the dataset was partitioned into training and testing sets at an 80:20 ratio. During the initial training phase, the LSTM model exhibited overfitting, evidenced by a significant disparity between training and validation performance. To mitigate this, several optimization strategies were implemented, including architecture simplification, dropout, L2 regularization, and early stopping. Post optimization, the LSTM model achieved 95.98% accuracy, while IndoBERT reached 96.15%. Although the 0.17% performance gap is marginal, IndoBERT demonstrated superior stability in processing informal social media registers without extensive normalization. Practically, this suggests that IndoBERT is more robust for real-time monitoring systems where data variety is high, whereas LSTM remains a viable, lightweight alternative for resource-constrained environments. This research contributes to computational linguistics by providing a robust performance comparison of transformer-based vs. recurrent architectures in processing the informal registers of the Indonesian language.]]>
<![CDATA[Stacking Hybrid Framework Using Random Forest, Gradient Boosting, and Ridge Regression for Bitcoin Price Forecasting ]]>
<![CDATA[Akhlis Munazilin]]>;
<![CDATA[Mochamad Agung Wibowo]]>;
<![CDATA[Rizky Parlika]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5745
<![CDATA[This research addresses a significant technical gap in Bitcoin price forecasting, specifically the extrapolation failure encountered by Deep Learning and tree-based models when prices reach unprecedented record highs (All-Time Highs). Conventional models often struggle to predict values outside their historical training range, leading to significant inaccuracies during price discovery phases. To solve this issue, a Stacking Hybrid framework is proposed, integrating non-linear components (Random Forest and Gradient Boosting) to capture volatility with a linear component (Ridge Regression) to maintain growth trends. The study utilizes 5,406 daily Bitcoin price observations from 2010 to 2025 and extracts seven key technical features, including the Relative Strength Index (RSI) and Simple Moving Averages (SMA), using the Patterned Dataset technique. Experimental results demonstrate that while single tree-based models fail during the aggressive market phases of 2025 due to their rigid data partitioning, the proposed Stacking Hybrid model achieves superior performance with a Mean Absolute Error (MAE) of $936 and a correlation coefficient ( ) of 0.99. The integration of Ridge Regression as a meta-learner successfully enables price extrapolation beyond historical limits. This framework contributes a robust methodology to the field of Computer Science for handling highly volatile time-series data in digital asset markets.]]>
<![CDATA[Hybrid Semantic Retrieval-Augmented Generation Using Dual Large Language Models for Domain-Specific Question Answering ]]>
<![CDATA[Synthia Indira Prastica]]>;
<![CDATA[Reza Mahendra Saputra]]>;
<![CDATA[Wildan Suharso]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5755
<![CDATA[The deployment of large language models (LLMs) in enterprise environments faces two fundamental challenges: single-search strategies are unable to effectively handle the structural heterogeneity of operational queries, and LLM generation without external grounding is prone to producing hallucinations on structured domain data. This research aims to design and evaluate a Hybrid Semantic Retrieval-Augmented Generation (Hybrid RAG) system that integrates a dual-LLM routing mechanism to address both issues simultaneously. The proposed system combines FAISS-based dense vector retrieval and sparse BM25 retrieval fused via Reciprocal Rank Fusion (RRF), accompanied by a routing module that directs domain-specific queries to a context-aware LLM (Grok) and general queries to a broadly knowledgeable parametric LLM (Gemini). Evaluation was conducted on 200 labeled queries using the RAGAS framework with an ablation study of six system configurations. The proposed system achieves a Faithfulness of 0.91, Answer Relevance of 0.87, Context Precision of 0.81, Context Recall of 0.86, Mean Reciprocal Rank of 0.84, and a routing accuracy of 93.5% meeting all seven set target thresholds. Ablation studies demonstrate that RRF fusion improves Context Recall by up to 30.3% compared to the dense-only baseline, while dual-LLM routing yields a 68.5% increase in Faithfulness relative to the baseline without RAG. These findings indicate that the combination of retrieval and dual-LLM routing produces a synergistic effect that cannot be achieved by either component alone, thereby providing a practical and scalable solution for structured operational data-based question-answering systems in enterprise environments.]]>
<![CDATA[Comparative Evaluation of LoRA-Based Parameter-Efficient Fine-Tuning for Indonesian Informal Text Normalization: A Study on Qwen3-14B and Mistral-14B ]]>
<![CDATA[Fatma Cahyani]]>;
<![CDATA[Febriliyan Samopa]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5758
<![CDATA[Informal Indonesian text poses challenges for NLP systems due to abbreviations, slang, and incomplete structures that deviate from standard language forms. This study evaluates the effectiveness of parameter-efficient fine-tuning (PEFT) using Low-Rank Adaptation (LoRA) to adapt large language models for informal-to-formal text normalization in a domain-specific context. Two open-weight multilingual models, Qwen3-14B and Mistral3-14B, were fine-tuned on a dataset of 1,233 formal sentences and 6.165 informal variations derived from academic information at Institut Teknologi Sepuluh Nopember (ITS). Evaluation on a held-out test set of 200 informal queries using lexical (BLEU, ROUGE) and semantic (cosine similarity and sentence-transformer-based similarity) metrics. The results show significant improvements after fine-tuning. Qwen3-14B achieved a BLEU score of 0.660, ROUGE-2 of 0.720, cosine similarity of 0.774, and semantic similarity of 0.907, while Mistral3-14B achieved 0.540, 0.624, 0.699, and 0.884, respectively. Additional experiments indicate that varying LoRA rank has minimal impact on performance, suggesting that LoRA configurations are sufficient for this task. These findings demonstrate that LoRA-based parameter-efficient fine-tuning enables effective and computationally efficient adaptation of large language models for Indonesian informal text normalization. This study provides a scalable solution for domain-specific NLP applications in low-resource settings, particularly for languages with high informal variation.]]>
<![CDATA[Comparative Evaluation and Hyperparameter Optimization of Random Forest and Extreme Gradient Boosting for Phishing Web Address Detection Using Lexical and Host-Based Features ]]>
<![CDATA[Mhd Adi Setiawan Aritonang]]>;
<![CDATA[Nugroho Syahputra]]>;
<![CDATA[Noorhamizah Mohamed Nasir]]>;
<![CDATA[Ardianto Pranata]]>;
<![CDATA[Toras Pangidoan Batubara]]>;
<![CDATA[Vadly Syafril]]>;
<![CDATA[Rudi Purwana]]>;
<![CDATA[Muhammad Nazwan]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 5 (2026): JUTIF Volume 7, Number 5, October 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.5.5760
<![CDATA[This study addresses the growing threat of phishing attacks, particularly those exploiting malicious URLs that mimic legitimate websites and bypass traditional rule-based or blacklist detection systems. The purpose of this research is to conduct a comparative analysis and optimization of ensemble learning models for phishing URL detection using a combination of lexical and host-based features. The proposed approach involves feature extraction from URL structures and domain-related attributes, followed by classification using Random Forest and XGBoost. Hyperparameter optimization is performed using Grid Search to obtain the best model configuration. Model performance is evaluated using Stratified 5-Fold Cross-Validation, with metrics including accuracy and Area Under the ROC Curve (AUC), along with statistical significance testing. The experimental results show that the optimized Random Forest model achieves the best performance with an accuracy of approximately 0.97, slightly outperforming XGBoost with an accuracy of 0.96. Statistical analysis using a paired t-test indicates that this difference is significant (p = 0.000615). The results also demonstrate that combining lexical and host-based features significantly improves classification performance.This study provides empirical evidence that optimized ensemble learning models with hybrid feature representation can effectively detect phishing URLs with high accuracy and stability. The findings contribute to the development of more reliable and robust phishing detection systems in real-world cybersecurity environments.]]>
