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[Design and Evaluation of Multilayered Guardrails for Securing Large Language Model and Retrieval Augmented Generation Based Employee Recruitment Chatbots ]]>
<![CDATA[Angga Pratama]]>;
<![CDATA[Kalamullah Ramli]]>
<![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.2026.7.5.5761
<![CDATA[Large Language Models (LLM) deployed in sensitive public services, particularly staff selection chatbot systems, are critically vulnerable to prompt injection and jailbreak attacks, yet existing guardrail solutions remain homogeneous and prone to single points of failure. This research designs, implements, and evaluates a novel multi-layered guardrail architecture based on a defence-in-depth strategy, systematically integrated across the input, retrieval, and output stages of a Retrieval-Augmented Generation (RAG) pipeline. A comparative experimental study was conducted, benchmarking the proposed architecture against state-of-the-art baselines, Llama Guard and NeMo Guardrails, across security and performance metrics. The proposed architecture achieved a Harmful Refusal Rate of 99.5% and demonstrated confirmed robustness against prompt injection, jailbreak, and data leakage vectors as validated by the Garak Vulnerability Scanner. Despite the inherent latency trade-off of layered processing, the system maintained superior efficiency with a median latency of 8.29 seconds, outperforming Llama Guard (8.80 s) and NeMo Guardrails (8.56 s). These findings establish that a defence-in-depth guardrail approach delivers an optimal balance between security and performance, and contribute a replicable architectural framework to the field of AI security for hardening LLM-RAG systems in high-stakes, public-sector deployments.]]>
<![CDATA[Spatio-Temporal Clustering of Land Fire Hotspots Using HDBSCAN with Haversine Distance and Temporal Proximity for Pattern Analysis in Sulawesi ]]>
<![CDATA[Muh Fuad Zahran Firman]]>;
<![CDATA[Andi Ahmad Taufiq]]>;
<![CDATA[Dyah Darma Andayani]]>;
<![CDATA[Dewi Fatamarani Surianto]]>;
<![CDATA[Iwan Suhardi]]>
<![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.2026.7.5.5765
<![CDATA[Land fires are an environmental issue that requires data-driven monitoring to better understand their occurrence patterns at an operational level. Although satellite hotspot data provide rich spatial and temporal information, their analysis still faces challenges such as uneven data distribution, variations in density, and the presence of noise that can affect the identification of fire episodes. This study aims to develop a spatiotemporal clustering framework to extract wildfire hotspot episodes in Sulawesi using NASA’s Fire Information for Resource Management System (FIRMS) data from 2023. Each hotspot is represented as (lat, lon, t), with spatial proximity calculated using the Haversine distance and combined with temporal proximity in a spatiotemporal distance matrix based on precomputed distances. A grid search was conducted across 912 configurations and compared against three density-based clustering methods: HDBSCAN, DBSCAN, and OPTICS. Evaluation was performed using internal metrics—namely, the Silhouette coefficient and Density-Based Clustering Validation (DBCV)—while also considering noise proportion and coverage to ensure the resulting clusters remain representative. The results show that HDBSCAN provides the best balance by producing 26 clusters, 21.78% noise, 78.22% coverage, and competitive metric values, thus making it the primary method. Visualization of the results shows that episode activity increases from mid- to late-year and is concentrated in specific zones, while Fire Radiative Power (FRP) characterization reveals variations in intensity between episodes. This study contributes to providing a more transparent and representative hotspot analysis framework to support pattern analysis, the determination of priority monitoring areas, and data-driven decision-making in the fields of environmental informatics and geospatial analytics.]]>
<![CDATA[Design of a Business Intelligence-Based Employee Performance Dashboard Using Design Science Research to Support Data-Driven Decision Making in Operational Banking Environments ]]>
<![CDATA[Septri Hazano]]>;
<![CDATA[Setiawan Assegaff]]>;
<![CDATA[Sharipuddin Sharipuddin]]>
<![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.2026.7.5.5770
<![CDATA[In the current information era, decision-making in banking operations is often hindered by fragmented data and subjective performance evaluations. At Bank XYZ, employee performance monitoring is still conducted using conventional methods, resulting in delayed information and data inconsistencies. This study aims to design and develop a Business Intelligence-based employee performance dashboard to support objective and data-driven decision-making at the operational level. The research adopts the Design Science Research approach, consisting of six stages: problem identification, objective definition, design and development, demonstration, evaluation, and communication. The system is developed as a web-based application using HTML, PHP, JavaScript, and MySQL. Evaluation is conducted using the System Usability Scale involving 18 internal users. The results show a usability score of 70.55, indicating that the system falls into the acceptable category and is sufficiently usable to support performance monitoring and decision-making processes. This study contributes by providing an empirically validated Business Intelligence dashboard that is acceptable to users and tailored for operational banking environments. The findings highlight the importance of usability-oriented BI system design in improving decision-making effectiveness and operational efficiency in banking practice.]]>
<![CDATA[Spatial Business Intelligence Using K-Means Clustering and GeoJSON Mapping for Epidemiological Insights in East Java ]]>
<![CDATA[Shynta Ayu Dwi Darmawan]]>
<![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.2026.7.5.5772
<![CDATA[The dynamics of disease patterns in densely populated areas like East Java cannot be fully addressed with traditional data reporting alone. A more advanced data analysis technique is necessary. This study aims to develop a spatial Business Intelligence (BI) dashboard by integrating the K-Means algorithm with GeoJSON mapping with the goal of accurately identifying trends in the disease burden. Official epidemiological data for 38 districts and cities in East Java covering hypertension, diabetes, dengue fever, and tuberculosis (2022–2024) were used. We processed official epidemiological data first, then validated the model using three major metrics: the Calinski-Harabasz Index, the Silhouette Score, and the Davies-Bouldin Index Index. The study findings show that a 6-cluster arrangement is the most efficient model, with a Silhouette Score of 0.61 and a Davies-Bouldin Index of 0.43. These values demonstrate extremely high group cohesiveness. On the other hand, spatial analysis identified contrasting epidemiological patterns: the disease burden is disproportionately concentrated in metropolitan and industrial districts, whereas rural areas have a low burden. In fact, the findings of this study show that combining BI and geographical analysis can increase the efficiency of health resource allocation by identifying observable epidemiological trends. The developed architecture is also scalable and stable for use in regional smart health surveillance systems.]]>
<![CDATA[Fake News Detection on Social Media Based on Indonesian Public Opinion Sentiment Analysis Using Naïve Bayes and Deep Neural Networks ]]>
<![CDATA[Nuril Lutvi Azizah]]>;
<![CDATA[Ade Eviyanti]]>;
<![CDATA[Mochamad Alfan Rosid]]>;
<![CDATA[Julia Atmaranti]]>
<![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.2026.7.5.5786
<![CDATA[The rapid growth of social media in Indonesia has intensified the spread of fake news, posing serious threats to public opinion, social stability, and democratic processes. This research proposes a fake news detection model based on sentiment analysis of Indonesian public opinion using Naïve Bayes and Deep Neural Network (DNN) classification methods. Textual data were collected from 4,990 records across Instagram (1,298), Twitter/X (2,004), and Facebook (1,690), with fact-checking verification conducted using TurnBackHoax (MAFINDO). After preprocessing — including normalization, tokenization, stopword removal, and stemming — 4,548 records were retained. Sentiment analysis was applied to capture public emotional tendencies, followed by TF-IDF feature extraction. The Naïve Bayes classifier achieved 87.25% accuracy, with macro recall of 0.5633 and macro F1-score of 0.6382. The DNN model achieved higher accuracy at 90.99%, with macro recall of 0.7204 and macro F1-score of 0.7951, demonstrating better performance across minority sentiment classes. These findings confirm that integrating sentiment analysis with machine learning and deep learning approaches significantly enhances fake news detection on Indonesian social media, with DNN models showing strong potential for deployment in automated detection systems driven by public opinion, thereby supporting more effective misinformation mitigation and national digital literacy initiatives in Indonesia.]]>
<![CDATA[Retrieval-Augmented Generation Chatbot Using Gemini AI for Public Internship Information Services ]]>
<![CDATA[Ihda Nur Maulidia Hanum]]>;
<![CDATA[Ajib Susanto]]>;
<![CDATA[Miftakhul Ashfania]]>
<![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.2026.7.5.5788
<![CDATA[Chatbot is a technology designed to assist humans by simulating text or voice based conversations to provide efficient information services powered by Artificial Intelligence. This study addresses the difficulties prospective interns face in finding internship information at the Central Java Regional Police and the lack of prompt responses from office staff, which often results in delays in information delivery due to manual processing. Many prospective applicants also feel confused about how to inquire regarding the registration process, required qualifications, and other important details. To address these issues, this research was conducted to develop a web-based internship system equipped with an advanced chatbot implementing the Retrieval Augmented Generation (RAG) method and integrated with a vector database for semantic retrieval. This platform ensures that all information provided is relevant and accurate by providing real-time responses based on the agency’s official documents. Based on functional testing, the system achieves an accuracy rate of 93.3% with and average response latency of 1.8 seconds. This research significantly improves access to information and demonstrates how the RAG framework effectively mitigates LLM hallucinations, ensuring data integrity within highly regulated public service.]]>
<![CDATA[Efficient Household Waste Material Classification Using Artificial Neural Network with RGB–HSV Color and Shape Features ]]>
<![CDATA[Mukrim Mukrim]]>;
<![CDATA[Muh Alfi Maolani]]>;
<![CDATA[Ahmad Zulfaiz Heruny]]>;
<![CDATA[Andi Baso Kaswar]]>;
<![CDATA[Muhammad Fajar Bakri]]>;
<![CDATA[Satria Gunawan Zain]]>
<![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.2026.7.5.5790
<![CDATA[The dominance of deep learning in image-based waste classification has led to high accuracy but often requires large datasets and significant computational resources, limiting its applicability in resource-constrained environments. Conversely, lightweight feature-based methods offer efficiency but typically suffer from lower robustness. This study addresses this gap by proposing a balanced approach that combines computational efficiency with competitive classification performance. An automatic image-based classification system is developed to categorize household waste into three material classes: paper, plastic, and metal. The proposed method utilizes complementary color features from RGB and HSV color spaces along with shape features, which are processed using a lightweight Artificial Neural Network (ANN). The model is evaluated using a dataset of 300 images with a 90:10 train-test split. Experimental results show that the proposed feature combination achieves a training accuracy of 94.444% and a testing accuracy of 90.000%. In addition, the model demonstrates balanced performance with precision, recall, and F1-score values of up to 0.976, 0.956, and 0.948 on training data, and consistent values of 0.900 on testing data. These results indicate that the proposed approach achieves competitive performance while maintaining low computational cost, with an average testing time of 0.007 seconds. This study contributes to the field of computer vision by demonstrating that a carefully designed feature-based ANN model can serve as an efficient alternative to deep learning for waste classification tasks. The proposed method offers a practical trade-off between accuracy and computational efficiency, making it suitable for real-world deployment in resource-limited environments.]]>
<![CDATA[End-to-End Nutritional Label Analysis of Packaged Beverages Using YOLOv8, Optical Character Recognition, and Support Vector Machine for Health Risk Assessment ]]>
<![CDATA[Firji Achmad Fahresi]]>;
<![CDATA[Muh Faqih S Musgamy]]>;
<![CDATA[Hanum Zalsabilah Idham]]>;
<![CDATA[Andi Baso Kaswar]]>;
<![CDATA[Muh Fajar Bakri]]>;
<![CDATA[Dyah Darma Andayani]]>;
<![CDATA[Muliadi Muliadi]]>
<![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.2026.7.5.5793
<![CDATA[The increasing consumption of packaged beverages high in sugar, sodium, and fat has raised concerns about their contribution to non-communicable diseases. Although nutritional information is available on product packaging, consumers often face difficulties in locating, reading, and interpreting it accurately, especially under varying lighting conditions and on complex package surfaces. This study aims to develop and evaluate an integrated nutritional label analysis system for packaged beverages by combining object detection, OCR-based text extraction, structured feature construction, health status classification, and potential disease risk mapping. The proposed system uses YOLOv8 for label detection, applies preprocessing and postprocessing to improve Tesseract v5 OCR results, constructs structured numerical features, balances training data using SMOTE, normalizes features with the z-score method, and classifies products into safe and unsafe categories using an SVM model. The dataset consisted of 2,414 augmented images derived from 1,207 selected nutritional label images. The results show that YOLOv8 achieved an mAP@0.5 of 0.969 for nutritional label detection. In the OCR stage, preprocessing and postprocessing reduced recognition errors across different image conditions, with WER and CER reaching zero in the ideal- and low-light evaluation samples. The optimized SVM-RBF model achieved a test accuracy of 0.9959 in classifying safe and unsafe products. These findings indicate that the proposed system provides an interpretable computational framework that contributes to computer vision and health informatics by transforming visual nutritional labels into structured health-related information to support nutritional literacy and healthier consumption decisions.]]>
<![CDATA[Systematic Literature Review of Machine Learning and Multi Criteria Decision Analysis for Digital Payment Investment Evaluation ]]>
<![CDATA[Rahmat Rambe]]>;
<![CDATA[Lukman Abdurrahman]]>;
<![CDATA[Hanif Fakhrurroja]]>
<![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.2026.7.5.5797
<![CDATA[The rapid growth of digital payment technologies has expanded investment opportunities in the fintech sector while increasing decision-making complexity due to multiple criteria, including financial, technological, market, and risk factors. Conventional evaluation approaches are often inadequate to address these multidimensional challenges. This study aims to provide a structured approach for intelligent investment evaluation by integrating Machine Learning (ML) and Multi-Criteria Decision Analysis (MCDA). A Systematic Literature Review based on the PRISMA 2020 framework was conducted, analyzing 30 selected studies published between 2021 and 2026. The review identifies key evaluation dimensions and examines existing integration approaches, including the use of Analytic Hierarchy Process for weighting and TOPSIS for ranking. The findings indicate that ML enhances prediction and risk assessment, while MCDA ensures structured and interpretable evaluation, leading to improved decision quality in terms of adaptability, transparency, and analytical capability. However, the integration of ML and MCDA remains limited, as most studies apply them separately. To address this gap, this study proposes a conceptual ML–MCDA framework that provides more consistent and data-driven outcomes. The proposed framework contributes to the development of intelligent, adaptive, and reliable decision support systems for digital payment investment.]]>
<![CDATA[Gender Classification On Indonesian Audio Recordings Using Mfcc Feature Extraction And Nadam-Optimized Bidirectional Long Short-Term Memory ]]>
<![CDATA[Rezal Suryadi Putra]]>;
<![CDATA[Agus Komarudin]]>;
<![CDATA[Edvin 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.2026.7.5.5800
<![CDATA[Speaker gender classification is a critical component in automatic speech processing systems, particularly for enabling personalized voice-based services. This study proposes a speaker gender classification system for Indonesian audio recordings by combining Mel-Frequency Cepstral Coefficients (MFCC) feature extraction with a Bidirectional Long Short-Term Memory (BiLSTM) deep learning architecture optimized using the Nadam optimizer. The dataset utilized is Mozilla Common Voice version 24.0 Indonesian, comprising 21,545 gender-labeled audio clips with a distribution of 13,965 male clips (64.8%) and 7,580 female clips (35.2%). Audio preprocessing includes resampling to 16,000 Hz, Z-score normalization, and conversion from stereo to mono. Feature extraction yields 120 features per time step, composed of 40 MFCC coefficients, 40 Delta, and 40 Delta-Delta components, producing an input matrix of 501×120 per audio clip. Class imbalance is addressed through the class weight technique. The dataset is partitioned using a stratified 70:15:15 split for training, validation, and testing. The proposed BiLSTM model architecture consists of two bidirectional LSTM layers (128 and 64 units), a fully connected dense layer, and a sigmoid output layer, supported by Dropout and Batch Normalization regularization techniques. Evaluation results demonstrate that the model achieves an accuracy of 98.58%, F1-Score of 98.58%, sensitivity of 98.90%, and specificity of 97.98%, surpassing all prior Indonesian-language gender classification studies and demonstrating that the integration of delta-features and bidirectional architectures significantly overcomes previous limitations in regional accent variability, thereby providing a robust foundation for future Indonesian speech-based intelligent systems.]]>
