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
1,242 Documents
<![CDATA[Predicting Mental Health Status using a Fine-Tuned CNN-LSTM Hybrid Model ]]>
<![CDATA[Agustin, Agustin]]>;
<![CDATA[Junadhi, Junadhi]]>;
<![CDATA[Erlinda, Susi]]>;
<![CDATA[Arita Fitri, Triyani]]>;
<![CDATA[Efrizoni, Lusiana]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 3 (2026): JUTIF Volume 7, Number 3, June 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.3.5882
<![CDATA[Mental health has become a critical global concern in the digital era, particularly as social media platforms increasingly serve as spaces where users express psychological conditions, emotions, and personal struggles. This study aims to predict mental health status from Twitter text using a fine-tuned hybrid CNN–LSTM deep learning model. A total of 12,214 tweets were collected, cleaned, and labeled into five categories: Normal, Stress, Anxiety, Depression, and High-Risk Condition. The dataset was split using stratified sampling into 70% training, 15% validation, and 15% testing portions. Text was transformed into numerical representations through tokenization, padding, and 100-dimensional word embeddings. The hybrid CNN–LSTM architecture combines the CNN’s ability to extract local linguistic features with the LSTM’s strength in capturing long-term contextual dependencies, supported by dropout, early stopping, and hyperparameter fine-tuning. Experimental results show that the hybrid model achieves superior performance compared to standalone CNN and LSTM architectures, obtaining an overall accuracy of 0.892, macro precision of 0.874, macro recall of 0.861, and a macro F1-score of 0.865. Class-wise evaluation indicates that the Normal category achieves the highest accuracy (0.960), followed by Anxiety (0.884) and High-Risk Condition (0.808). Meanwhile, Stress (0.751) and Depression (0.745) show lower accuracies due to semantic overlap in linguistic expressions commonly found on social media. The training process demonstrates stable convergence without significant overfitting, confirming the effectiveness of the selected architecture and training strategy. Overall, this study highlights the effectiveness of the hybrid CNN–LSTM model for early mental health detection based on text data. The findings provide a strong foundation for developing scalable and data-driven mental health monitoring systems in digital environments and contribute to advancing natural language processing approaches for mental health analysis.]]>
<![CDATA[Preference-Driven Medical Image Retrieval using a Dual-Head DenseNet-121 and Multi-Objective Skyline Query for COVID-19 Detection ]]>
<![CDATA[Handoko, Slamet Handoko]]>;
<![CDATA[Prayitno, Prayitno]]>;
<![CDATA[Tena, Silvester]]>;
<![CDATA[Putra, Karisma Trinanda]]>;
<![CDATA[Sunardi, Sunardi]]>;
<![CDATA[Prasetyo, Eko]]>;
<![CDATA[Damarjati, Cahya]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 3 (2026): JUTIF Volume 7, Number 3, June 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.3.5884
<![CDATA[This study addresses the limitation of single-objective content-based image retrieval in medical imaging, which fails to consider multiple clinical preferences such as image quality. The objective is to develop a preference-driven retrieval system for COVID-19 chest radiography images. A hybrid approach is proposed by integrating a Dual-Head DenseNet-121 model for feature extraction and quality regression with a multi-objective skyline query algorithm for retrieval optimization. The system evaluates multiple image quality dimensions, including sharpness, contrast, exposure, signal-to-noise ratio, and entropy. Experimental results demonstrate that the proposed method achieves 100% Pareto efficiency and improves diversity and hypervolume coverage compared to conventional methods. This approach provides a more flexible and effective multi-objective retrieval mechanism, contributing to the advancement of intelligent medical image retrieval systems in computer science.]]>
<![CDATA[Comparative Analysis of Temporal Fusion Transformer and Long Short-Term Memory Architecture Resilience in Predicting Solana Price Volatility Across Different Market Phases ]]>
<![CDATA[Putra, Mahdy Eka]]>;
<![CDATA[Oktavia, Tanty]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 3 (2026): JUTIF Volume 7, Number 3, June 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.3.5894
<![CDATA[Abstract must be written in English. The high volatility of cryptocurrency markets, particularly for altcoins like Solana (SOL), presents a significant challenge for predictive modeling. Traditional deep learning architectures often struggle to adapt to sudden market regime shifts. Therefore, this study aims to provide a comparative analysis of the resilience between the Temporal Fusion Transformer and Long Short-Term Memory architectures in predicting Solana price volatility across three distinct market phases: the bull market of 2024, the bear market of 2025, and the recovery phase of 2026. We utilized hourly historical price and volume data combined with technical indicators such as Relative Strength Index (RSI). The models were evaluated using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and a specific performance degradation rate formula. The results demonstrate that while LSTM performs adequately during stable trends, its accuracy degrades massively by 1575.69% during high-volatility regime changes due to memory inertia causing a severe lagging effect. Conversely, the TFT model exhibited superior resilience, limiting its performance degradation to only 218.53% during the extreme bear market phase. The inherent attention mechanism and skip connections in TFT allow it to dynamically adapt to sudden structural breaks in real-time without delay. Furthermore, the implementation of the TFT architecture proved to be 62% more computationally efficient than LSTM. This research significantly contributes to the field of computer science and informatics, specifically in adaptive time-series forecasting, by proving that attention mechanisms and skip connections can efficiently solve the memory inertia problem in recurrent networks during real-time structural breaks.]]>
<![CDATA[Diabetes Mellitus Prediction from Primary Health Care Laboratory Data Using Random Forest, Extreme Gradient Boosting, and Light Gradient Boosting Machine with Resampling and Optuna-Based Hyperparameter Optimization ]]>
<![CDATA[Zaky, Umar]]>;
<![CDATA[Agustia, Yuwanis Fazlina]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 3 (2026): JUTIF Volume 7, Number 3, June 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.3.5751
<![CDATA[This study examines the use of machine learning models to classify diabetes mellitus status based on laboratory test data. The dataset consists of 484 laboratory test results with 10 clinical parameters, which were used as the main input for model development. Three algorithms, Random Forest, Extreme Gradient Boosting, and Light Gradient Boosting Machine, were compared by applying several resampling techniques and hyperparameter tuning using Optuna to address class imbalance and improve overall model performance. The results show that each algorithm responded differently to the applied resampling methods and tuning strategies, indicating that model performance is influenced by these approaches. Among the evaluated models, Random Forest combined with Synthetic Minority Oversampling Technique and hyperparameter optimization achieved the best performance, with an accuracy of 72.60% and an area under the receiver operating characteristic curve of 76.74%. This performance indicates a moderate ability to distinguish between diabetes and non-diabetes cases based on the available laboratory parameters. Overall, the findings suggest that machine learning can be considered as a potential tool to support clinical decision making, especially when using structured laboratory data. However, given that the performance is still not optimal, further improvement, validation, and exploration of additional data are necessary before considering its implementation in real clinical settings.]]>
<![CDATA[A Web-Based Expert System Using Forward Chaining for Identifying Engine Power Loss Problems in the BMW 3 Series E36 ]]>
<![CDATA[Fawzi, Muhammad Ihsan]]>;
<![CDATA[Permadi, Ipung]]>;
<![CDATA[Chasanah, Nur]]>;
<![CDATA[Ramadhany, Emha Diambang]]>;
<![CDATA[Amirulbahar, Azis]]>;
<![CDATA[Shofro, Puteri Awaliatush]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 3 (2026): JUTIF Volume 7, Number 3, June 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.3.6307
<![CDATA[The BMW 3 Series with production code E36, built between 1991 and 1998, remains widely owned in Indonesia, yet its age of more than two decades makes power loss a frequent complaint. Although the E36 engine is partially computerized, owners living far from an authorized or specialist workshop equipped with a diagnostic scanner cannot easily determine the cause of the power loss they experience. This study builds a web-based expert system, “Si Pak-E”, that identifies power loss problems on the BMW 3 Series E36 engine and recommends solutions. Knowledge was acquired through structured interviews with a BMW specialist mechanic and represented as a knowledge base of 22 problems, 33 symptoms, 22 solutions, and 22 production rules derived from a 33 × 22 decision table. Forward chaining was selected as the inference engine because diagnosis proceeds from observed symptoms toward a conclusion, while the waterfall model guided development. The system was implemented in PHP, MySQL, and Bootstrap with three user roles. Evaluation combined functional black-box testing with knowledge-base verification against the expert. Black-box testing executed 95 scenarios across 36 test cases and three roles, and all 95 (100%) produced the expected output. Rule-coverage verification traced all 22 production rules as consultation cases, and the system returned the problem and solution expected by the expert in 22 of 22 cases (100% agreement). The findings show that forward chaining is effective for symptom-driven automotive fault identification and that the system is a practical, transparent, and accessible diagnostic aid for E36 owners. Keywords: BMW E36, expert system, fault diagnosis, forward chaining, power loss, web-based.]]>
<![CDATA[Neural Network Performance Enhancement Using the Modified Orca Predation Algorithm for Time Series Forecasting: A Comparative Review ]]>
<![CDATA[Syaharuddin Syaharuddin]]>;
<![CDATA[Mariono Mariono]]>;
<![CDATA[Alfiana Sahraini]]>;
<![CDATA[Saba Mehmood]]>;
<![CDATA[Wasim Raza]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 4 (2026): JUTIF Volume 7, Number 4, August 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.4.4951
<![CDATA[Neural Networks (NNs) are extensively used in time series forecasting due to their ability to learn nonlinear and complex temporal relationships. However, NN performance is frequently limited by training challenges, including slow convergence and suboptimal parameter optimization. This study aims to systematically examine the role of the Modified Orca Predation Algorithm (MOPA) in enhancing neural network performance for time series forecasting, particularly in comparison with other metaheuristic optimization approaches. This research employed a qualitative method using a Systematic Literature Review (SLR) approach. Relevant journal and conference articles published between 2015 and 2025 were collected from reputable scientific databases. The selected studies were analyzed thematically and bibliometrically using VOSviewer to identify research trends, application domains, and performance characteristics of MOPA-based neural network optimization. The results indicate that the integration of MOPA into neural network training consistently improves convergence speed, forecasting accuracy, and model stability across various application domains. Compared to conventional optimization methods, MOPA demonstrates superior capability in handling nonlinear and volatile time series data, particularly in energy forecasting, financial time series analysis, and climate-related prediction. The findings also reveal that MOPA-based optimization contributes to better generalization performance by reducing prediction error and output variance. This study provides a structured synthesis of recent research on MOPA-enhanced neural networks and contributes to the understanding of metaheuristic optimization strategies in time series forecasting. The results serve as a reference for researchers in selecting effective optimization methods for neural network-based forecasting models.]]>
<![CDATA[Optimization of LSTM and Linear Regression Models with Hyperparameters and Genetic Algorithm for Forest and Land Fire Risk Prediction: ]]>
<![CDATA[Mega Otafyani]]>;
<![CDATA[Putri Yuli Utami]]>;
<![CDATA[Istikoma Istikoma]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 4 (2026): JUTIF Volume 7, Number 4, August 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.4.5034
<![CDATA[Forest and land fires are a serious environmental challenge in Indonesia, especially in peatland areas such as Kubu Raya Regency, West Kalimantan. This study aims to develop and compare two forest and land fire risk prediction models, namely LSTM and Linear Regression, each optimized using hyperparameters and Genetic Algorithms. Climate data (temperature, rainfall, humidity, wind speed) and hotspots from 2019–2024 were used as input features. The pre-processing stage included normalization and handling of missing data. Forest and land fire risk was categorized into three classes based on thresholds set by Manggala Agni. The LSTM model was tested with one and two layers of neurons. The best results were obtained from the two-layer neuron architecture with an RMSE of 0.2364, MAE of 0.1955, and MAPE of 12.90%. As a comparison, the optimized linear regression model showed lower performance with an RMSE of 0.3026, MAE of 0.2602, and MAPE of 17.95%. These results indicate that LSTM is superior in recognizing temporal and non-linear patterns in time series data. Spatial analysis indicates that the districts of Sungai Raya, Sungai Kakap, and Kuala Mandor B are high-risk areas, particularly toward the end of the dry season. These findings underscore the potential of LSTM-based deep learning approaches in supporting early warning systems and mitigation strategies for forest and land fires. Integrating predictive models with spatial analysis could serve as an effective strategy for more targeted forest and land fire management.]]>
<![CDATA[Impact of Kernel Size on CNN-Based Fingerprint Gender Classification ]]>
<![CDATA[Sri Suwarno]]>;
<![CDATA[Joko Purwadi]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 4 (2026): JUTIF Volume 7, Number 4, August 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.4.5059
<![CDATA[This paper presents a straightforward CNN model designed to classify gender based on fingerprints. The model consists of three convolutional layers and a classification layer. To ensure computational efficiency, we select kernel sizes ranging from 3×3 to 8×8. For training, we utilized the NIST (National Institute of Standards and Technology) dataset, which includes 500 male fingerprints and 500 female fingerprints. The region of interest (ROI) for the fingerprints is set at 128×128 pixels, centered horizontally and positioned in the upper quarter vertically. To enhance image quality, we applied the CLAHE (Contrast Limited Adaptive Histogram Equalization) method. The experimental results indicate that the model achieves a validation accuracy of up to 74.176%, with an execution time of under 10 minutes. Our results indicate a potential direction for future research in the use of simple CNN architectures, despite the fact that the validation accuracy of our model is lower than that of advanced CNNs, such as ResNet or its modification, the Dense Dilated Convolution ResNet Autoencoder (DDC-ResNet), which achieves 96.5%.]]>
<![CDATA[Building a Trustworthy Credit Default Classification Model using Interpretable Machine Learning ]]>
<![CDATA[Haikal Djauhari]]>;
<![CDATA[Anton Yudhana]]>;
<![CDATA[Sunardi Sunardi]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 4 (2026): JUTIF Volume 7, Number 4, August 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.4.5149
<![CDATA[In peer-to-peer lending, a single misjudged borrower can result in significant investor losses and erode the platform's credibility. Although machine learning models have demonstrated superior predictive performance in identifying potential loan defaults, their opaque decision-making process creates mistrust and regulatory friction, impeding their trustworthy adoption. This study addresses the critical trade-off between accuracy and interpretability by proposing an interpretable machine learning framework for trustworthy credit default classification using Bondora peer-to-peer lending data. We deploy and benchmark three classifiers —Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Random Forest (RF) — to assess their predictive effectiveness. To overcome the black-box nature of these models, we integrate two complementary interpretability techniques: SHapley Additive exPlanations (SHAP) for global feature attribution and Local Interpretable Model-agnostic Explanations (LIME) for granular, instance-level decision insights. The high AUC, which exceeds 0.96, and F1 score (0.937-0.940) show that all models can effectively support risk management. Our results also demonstrate that pairing high-performing classifiers with interpretability tools enhances model transparency, fosters accountability, and promotes the responsible use of machine learning in credit risk assessment.]]>
<![CDATA[Improving BiLSTM News Articles Classification with Frozen DistilBERT Embedding ]]>
<![CDATA[Hans Fanolo Kristian Daeli]]>;
<![CDATA[Jasmir Jasmir]]>;
<![CDATA[Nurhadi Nurhadi]]>
<![CDATA[ Jurnal Teknik Informatika (Jutif) Vol. 7 No. 4 (2026): JUTIF Volume 7, Number 4, August 2026 ]]>
Publisher : <![CDATA[Informatika, Universitas Jenderal Soedirman ]]>
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.52436/1.jutif.2026.7.4.5175
<![CDATA[News classification is critical for organizing digital content and enhancing user engagement. Static embeddings such as GloVe, however, often fail to capture dynamic contextual relationships, limiting classifier performance. This study investigates the integration of frozen DistilBERT embeddings used strictly as feature extractors into a BiLSTM news‐classification pipeline to harness context‐aware representations while preserving computational efficiency. Experiments were conduccted on the Fancyzhx/ag_news dataset, which contains 127,700 samples, using a controlled 70/30 train–test split, comparing three BiLSTM variants: baseline (no pretrained embeddings), GloVe‐BiLSTM, and DistilBERT‐BiLSTM. Model architectures and hyperparameters are held constant to ensure a fair evaluation. Experimental results demonstrate that DistilBERT‐BiLSTM achieves 93.2 % accuracy, outperforming GloVe‐BiLSTM by 1.3% and the baseline by 2.5%. UMAP visualizations reveal more distinct semantic clusters with DistilBERT embeddings, and token‐level heatmaps confirm sharper intra‐sentence focus on domain‐specific terms. These findings contribute to informatics research by demonstrating the value of frozen transformer embeddings for lightweight yet high-performing text classification, with practical applications in information retrieval, content moderation, and real-time news analytics.]]>
