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[Development of a Chatbot Based on Natural Language Processing and Multinomial Naïve Bayes for Optimising Academic Administrative Services in Higher Education ]]>
<![CDATA[Rahmalia Syahputri]]>;
<![CDATA[Ammar Ismail Kochan]]>;
<![CDATA[Dika Tondo Widakdo]]>
<![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.2026.7.4.5443
<![CDATA[The transformation of academic administrative services in higher education requires intelligent systems to automate routine information delivery. This study presents a web-based chatbot using Natural Language Processing (NLP) and the Multinomial Naïve Bayes (MNB) algorithm to enhance administrative services. The system classifies user queries into 20 intent categories and provides real-time responses. Training and testing were conducted using labelled text data. The model achieved 93.62% training accuracy and 63.38% test accuracy, indicating potential overfitting due to the limited variety of test data. Evaluation metrics showed 63% precision, 60% recall, and a 61% F1-score, reflecting stable classification performance. User Acceptance Testing (UAT) was conducted with students and administrative staff, showing acceptance rates of 83.5% and 84%, respectively. These results indicate strong usability and relevance of the chatbot in academic contexts. The system integrates text classification, NLP, and user evaluation within a single framework to address repetitive administrative tasks. This research contributes a practical solution tailored to the needs of academic institutions by combining machine learning techniques with direct user evaluation. The chatbot provides faster and more consistent access to academic information, thereby reducing dependency on manual administrative processes. Future work may enhance classification accuracy by utilising richer datasets and alternative algorithms.]]>
<![CDATA[Enhancing Big Five Personality Prediction on Indonesian Tweets: A Comparative Study of LSTM-GRU Hybrid and IndoBERT/IndoXLNet with Augmentation Techniques ]]>
<![CDATA[Izzatul Ummah]]>;
<![CDATA[Fitriyani Fitriyani]]>;
<![CDATA[Novia Natasya]]>
<![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.2026.7.4.5444
<![CDATA[Over the past few years, researches on Big Five personality prediction model focusing on Indonesian tweets has mostly faced data scarcity and imbalance problem. This study aims to build Big Five personality prediction models for the low-resource language setting using Indonesian social media texts in platform X, and conduct a comparative performance analysis using deep learning model (hybrid BiLSTM-BiGRU) and transferred learning models (IndoBERT and IndoXLNet) with the optimization using various data augmentation and feature expansion techniques to overcome data scarcity and imbalance. We carried out data collection of 11746 tweets from hybrid sources (BFI questionnaire and keyword-based crawling), preprocessing using tokenization and stemming, extraction using Word2Vec and FastText, data augmentation (using SYN-REP, BACK-TRANS, RAND-INS, and SMOTE variants), Top-N feature expansion (with N = 1, 5, and 10), hyperparameter tuning using Optuna (for learning rate, batch size, dropout rate, and weight decay), and evaluating the model's accuracy, precision, recall, and F1-score. The result shows that IndoBERTweet+BACK-TRANS+Top-10 achieved 84% accuracy and an F1-score of 81.5%, surpassing IndoXLNet+BACKTRANS+Top-5 (82%) and LSTM+GRU+FastText+KMeansSMOTE+Top-5 (78%), with the BACK-TRANS technique improves overall F1 result by 13%. These findings bolster computational psychology informatics for low-resource NLP focusing on Indonesian language, as well as aiding mental health screening with 18% better generalization in imbalanced data, and enabling scalable trait inference in human resource and mental health applications.]]>
<![CDATA[Explainable Ensemble Transfer Learning with Adaptive Augmentation for Cassava Leaf Disease Detection ]]>
<![CDATA[Agus Heri Yunial]]>;
<![CDATA[Ahmad Fauzi]]>
<![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.2026.7.4.5480
<![CDATA[Cassava (Manihot esculenta) is a crucial commodity in tropical regions; yet, its output has markedly declined due to five primary categories of foliar diseases: Cassava Mosaic Disease (CMD), Cassava Brown Streak Disease (CBSD), Cassava Bacterial Blight (CBB), Cassava Green Mottle (CGM), and the healthy category. The constraints of deep learning models, which remain opaque, and data imbalances in the agriculture sector, pose significant hurdles to the development of precise and transparent diagnostic tools. This research seeks to establish an explainable deep learning framework utilizing ensemble transfer learning and adaptive augmentation to enhance the accuracy and interpretability of cassava leaf disease identification. The experimental investigation utilized 21,367 annotated photos from five disease categories within the Cassava Leaf Disease dataset. The dataset was first divided into training data (80%) and validation data (20%). The minority classes in the training data were augmented using Albumentations to rectify class distribution imbalances. As a result of this approach, an additional 51,280 photos were generated, resulting in a more balanced and representative class. The findings indicated that the ensemble averaging of ResNet50, DenseNet121, and EfficientNet-B0 achieved a validation accuracy of 86.75%, surpassing the performance of each individual model. Adaptive augmentation procedures enhance the model's generalization capabilities, while Gradient-weighted Class Activation Mapping (Grad-CAM) visualizes the leaf regions influencing classification judgments. The results validate that the use of adaptive augmentation, explainable AI, and ensemble transfer learning enhances the transparency and reliability of computer vision systems for detecting plant diseases. This study advances the creation of precise, interpretable, and pertinent AI models to enhance agricultural informatics.]]>
<![CDATA[Comparative Analysis of Decision Tree, Random Forest, and Gradient Boosting with ADASYN for Predicting Student Graduation Delay ]]>
<![CDATA[Tubagus Ahmad Marzuqi]]>;
<![CDATA[Marcel Marcel]]>
<![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.2026.7.4.5487
<![CDATA[The issue of graduation delay is one of the common issue in higher education institutions. This issue impacts the accreditation and reputation of study programs and the university. Delayed graduation increases the likelihood of student dropout, which remains a pressing concern many universities in Indonesia. The resulting consequences include a decline in institutional reputation and ranking, as well as reduced public trust in higher education standards. This research seeks to create a predictive model for delays in student graduation at University XYZ utilizing three machine learning techniques: Decision Tree, Random Forest, and Gradient Boosting. The academic dataset displays a class imbalance, with a notably larger number of students graduating later than those graduating on time. To counter this issue, the Adaptive Synthetic Sampling (ADASYN) method was implemented. The findings indicate that Random Forest with ADASYN achieves the best performance, with an accuracy of 75.55%, precision of 82.15%, recall of 81.64%, and AUC of 82.96%. The most influential factors are GPA (IPK) and the number of course repetitions. The resulting model can serve as a foundation for an early warning system to support universities in implementing timely academic interventions for at-risk students.]]>
<![CDATA[Efficiency and Security Analysis of Self-Hosted Cloud Storage: A Containerized ZTNA, Docker, and PostgreSQL Approach ]]>
<![CDATA[Zen Aufa Bahalwan]]>;
<![CDATA[Arry Avorizano]]>
<![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.2026.7.4.5518
<![CDATA[The enforcement of digital sovereignty mandates, specifically Indonesia's Government Regulation No. 71 of 2019, necessitates the adoption of private cloud infrastructures that facilitate strict data localization; however, traditional bare-metal deployments may exhibit less flexibility, while typical containerized solutions may not fully address the database integrity required for institutional scale1. This study proposes a secure, containerized self-hosted cloud architecture integrating Nextcloud, PostgreSQL, and Docker, secured via a Zero Trust Network Access (ZTNA) tunnel to achieve a "Closed-Default" security posture. To evaluate this architecture, the system was validated against a traditional bare-metal LAPP (Linux, Apache, PostgreSQL, PHP) stack using a novel Resource Efficiency Index (REI) designed to quantify the computational overhead of compliance alongside network throughput analysis over 50 iterations. Empirical results indicate that while the containerized architecture incurs a tangible virtualization overhead, resulting in a lower Resource Efficiency Index (69.44 vs. 83.51), it maintains statistical performance parity in network throughput (p > 0.05). Furthermore, the proposed architecture achieves superior CPU optimization (0.97% vs. 1.15%) and structurally reduces external attack surfaces. These findings provide a compliant, reproducible blueprint for Indonesian institutions, demonstrating that.]]>
<![CDATA[Multiple Attribute Hierarchical Fuzzy Logic System with Quartile-Based Consequent Calibration for Rainfall Forecasting in Palembang City ]]>
<![CDATA[Kanda Januar Miraswan]]>;
<![CDATA[Meylani Utari]]>;
<![CDATA[Yesinta Florensia]]>
<![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.2026.7.4.5524
<![CDATA[Global climate change is making weather conditions in Indonesia, particularly in Palembang City, increasingly difficult to predict. The unexpected high-intensity rainfall frequently triggers hydrometeorological disasters, leading to threats to human safety and substantial economic losses. Consequently, reliable rainfall forecasting systems are urgently needed to support early warning, disaster mitigation, and operational planning across critical sectors. This research aims to design an accurate rainfall forecasting model for Palembang City by applying the Multiple Attribute Hierarchical Fuzzy Logic System (HFLS) with quartile-based consequent calibration. The method integrates the strengths of both Sugeno and Mamdani fuzzy inference models within a hierarchical structure to manage data uncertainty more effectively and reduce rule complexity. Unlike conventional fuzzy rainfall models that rely on fixed rainfall intensity categories, this study introduces a quartile-based calibration of Sugeno consequent values derived from local rainfall data. The model is developed using daily meteorological variables such as temperature, humidity, sunshine duration, and wind characteristics, obtained from the BMKG station in Palembang. Two configurations of consequent values are tested, one using conventional rainfall intensity categories and the other using quartile-based local data distribution derived from empirical rainfall observations. The experimental results show that the quartile-based configuration significantly improves accuracy, achieving MAE of 12.26 mm and RMSE of 25.85 mm, outperforming the conventional configuration (with MAE of 18.89 mm and RMSE of 28.29 mm). These findings highlight the importance of integrating hierarchical fuzzy architecture with locally calibrated consequent values to enhance rainfall prediction performance in tropical regions characterized by highly skewed rainfall distributions.]]>
<![CDATA[Smart Drawer Using IoT Technology for Automatic Inventory Management and Item Security Based on Yolov8 Architecture ]]>
<![CDATA[Anas Rashidi]]>;
<![CDATA[Benfano Soewito]]>
<![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.2026.7.4.5557
<![CDATA[The use of storage systems for managing personal and work related items continues to increase in many environments. However, inventory management in small-scale storage, such as drawers, is still commonly performed manually. This approach often causes problems, including recording errors, inconsistent inventory data, and limited ability to detect missing or unauthorized items. For this reason, this study develops a smart drawer system that combines Internet of Things (IoT) technology with the YOLOv8 deep learning model to support automatic inventory management and basic item security. In the proposed system, a camera is installed inside the drawer to capture images of the stored objects. These images are processed directly on the device using the YOLOv8 object detection model to identify and count items. The detection results are then sent to an IoT platform so that inventory data and drawer activity can be monitored through a server. During operation, the system also records drawer access events, which allows irregular situations, such as missing items or unauthorized removal, to be observed. Experimental testing shows that the YOLOv8 based detection model is capable of recognizing stored objects with acceptable accuracy under typical drawer lighting conditions. The integration with the IoT platform enables inventory updates to be performed with low delay, making the system suitable for real-time monitoring. Compared with manual inventory methods, the proposed smart drawer helps reduce data inconsistencies and improves the visibility of stored items. This research indicates that the integration of computer vision and IoT can be applied effectively to small-scale storage systems using edge-based devices. The developed smart drawer can be implemented in offices, laboratories, and similar environments, and it may provide useful insights for future studies related to intelligent inventory and storage automation.]]>
<![CDATA[Retrieval-Augmented Generation and DeepSeek-R1 Large Language Models for Implementing Financial Report Chatbot for Companies Listed on the Indonesia Stock Exchange ]]>
<![CDATA[Ivana Lucia Kharisma]]>;
<![CDATA[Haldies Gerhardien Pasya]]>;
<![CDATA[Alun Sujjada]]>
<![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.2026.7.4.5562
<![CDATA[The Indonesia Stock Exchange (IDX) requires all listed companies to publish financial statements regularly to ensure transparency for investors and stakeholders. However, the increasing volume, complexity, and technical language of these reports create significant barriers for timely analysis, particularly for retail investors, regulators, and academic researchers. This limitation highlights the urgent need for intelligent systems capable of automating the extraction and interpretation of key financial information. This study aims to design and evaluate a Retrieval Augmented Generation (RAG) model to process financial reports, specifically the audited 2024 financial statements of Bank BCA and Bank Mandiri, in order to develop more efficient AI-based tools for managing complex financial documents. The research adopts a quantitative experimental approach using income statements from PT Bank Central Asia Tbk and PT Bank Mandiri (Persero) Tbk for the years 2023–2024. The methodology involves multimodal text extraction with Gemini Flash 2.0, preprocessing and cleaning using Regular Expressions (Regex), document chunking, and embedding generation with the multilingual-e5-small model. A Qdrant vector database is used for storage and retrieval, while DeepSeek-R1 serves as the transformer-based LLM for generating responses. Model performance was evaluated using BERTScore and ROUGE, supported by expert assessment. The system produced strong results, with BERTScore averages of 0.8074 (precision), 0.8253 (recall), and 0.8156 (F1-score). ROUGE evaluation yielded average scores of ROUGE-1: 0.5986 and ROUGE-2: 0.4531. Expert evaluation confirmed high parsing accuracy (94.6%) and the system’s ability to generate accurate, contextually relevant, and multilingual responses. Beyond its practical application, this study contributes to the advancement of scientific knowledge by providing an integrated framework for multimodal financial document processing using RAG-based LLMs. Overall, the study successfully developed a RAG-based LLM chatbot capable of effectively extracting, processing, and answering queries related to financial reports, demonstrating strong semantic alignment and supporting the development of more accessible AI-driven financial analysis tools.]]>
<![CDATA[Performance Evaluation of Machine Learning Models for Standardized Precipitation Index Prediction in Pandeglang ]]>
<![CDATA[Indri Hapsari]]>
<![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.2026.7.4.5566
<![CDATA[Drought is a significant climate change-driven extreme event that severely impacts agriculture and water resource management, particularly in regions like Pandeglang, Banten, which is vital for food security. This study aims to evaluate and compare the performance of four machine learning algorithms—Multiple Linear Regression (MLR), Artificial Neural Networks (ANN), K-Nearest Neighbors (KNN), and XGBoost (XGB)—in predicting the Standardized Precipitation Index (SPI) across short, medium, and long-term timescales (3, 6, 9, and 12 months). The methodology involves utilizing historical daily rainfall data (1991–2024) and executing a multi-scale comparative analysis using six different lag times within a Python-based framework. Performance was measured using RMSE, MAE, NSE, and R² metrics. The results demonstrate that predictive accuracy consistently improves as the SPI timescale increases, with the 12-month scale (SPI-12) offering the most stable results. The ANN model was the most reliable algorithm, with a peak R² of 0.961 at the 12-month scale. Conversely, the XGB model showed the poorest performance on shorter scales when historical data was limited. This research provides a localized, computationally efficient framework for informatics-based climate monitoring. By establishing optimal lag windows and model complexity requirements, it bridges the gap between algorithmic theory and practical application for developing data-driven early warning systems.]]>
<![CDATA[Herbal Leaf Classification Based on Shape, Color, and Texture Features Integration Using SVM and K-NN Algorithms ]]>
<![CDATA[Wargijono Utomo]]>;
<![CDATA[Nur Sucahyo]]>;
<![CDATA[Ike Kurniati]]>;
<![CDATA[Andy Dharmalau]]>
<![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.2026.7.4.5573
<![CDATA[Manual identification of herbal leaves often leads to errors due to visual similarities between species, variations in lighting, and morphological differences that are difficult to observe consistently. These conditions make the identification process subjective, inefficient, and less accurate, so a more reliable automated approach is needed. This study aims to evaluate and compare the performance of the Support Vector Machine (SVM) and K-Nearest Neighbor (K-NN) algorithms in classifying five types of herbal leaves using a combination of shape, color, and texture features. The dataset consists of 1,000 herbal leaf images obtained from various sources and processed through preprocessing, feature extraction of shape (metric, eccentricity), color (HSV), and texture (GLCM). The data were then normalized, divided by a ratio of 80:20, and optimized using hyperparameter tuning. Evaluation was carried out using accuracy, precision, recall, and F1-score metrics. The test results showed that SVM achieved the highest accuracy of 94.48%, outperforming K-NN which achieved an accuracy of 92.18%. SVM also showed more stable performance in handling complex feature combinations. This research contributes by presenting an effective shape–color–texture feature-based integrative classification framework for herbal leaf identification, as well as strengthening the application of machine learning in the development of plant identification systems in the field of informatics, both for desktop, web, and mobile applications.]]>
