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[Data-Driven NARX Series-Parallel Levenberg-Marquardt (L-M) Model for National Zakat Forecasting and BAZNAS Poverty Alleviation Planning (2022-2024) ]]>
<![CDATA[Zulfatri Aini]]>;
<![CDATA[Tengku Reza Suka Alaqsa]]>
<![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.2026.7.5.5495
<![CDATA[The budgeting process for zakat distribution at BAZNAS is still conducted manually, creating risks of overbudgeting or underbudgeting due to fluctuations in assistance requests and variability in mustahik needs over time. This study aims to develop a data-driven forecasting model using a NARX Series-Parallel network optimized with the Levenberg-Marquardt (L-M) algorithm to support evidence-based zakat distribution and poverty alleviation planning at BAZNAS. The dataset consists of national zakat data for the 2022-2024 period, including Zakat Maal and Zakat Fitrah from 35 provinces interpolated into monthly timesteps (36 samples), and national ZIS-DSKL data for 2019-2024 interpolated into 72 monthly timesteps; all variables were normalized prior to modeling. The NARX Series-Parallel model was implemented for multi-step forecasting with performance evaluated using Mean Squared Error (MSE). The results show that the proposed model achieved low MSE values for Zakat Maal, Zakat Fitrah, and ZIS-DSKL forecasting, indicating high predictive accuracy under normalized data conditions, while model validation was conducted to mitigate overfitting and data leakage risks. This study contributes methodologically to the application of neural network-based time series forecasting in socio-economic data and highlights the limitation of interpolation-based datasets, while providing a practical quantitative basis for zakat policy planning and poverty alleviation strategies at BAZNAS in accordance with Law No. 23/2011.]]>
<![CDATA[Detecting Implicit Sexual Harassment on Instagram and X: IndoBERT vs. Random Forest Efficiency and Manual Gold Standard ]]>
<![CDATA[Wili Sandi Febriantana]]>;
<![CDATA[Philip Faster Eka Adipraja]]>
<![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.2026.7.5.5500
<![CDATA[Implicit sexual harassment on Indonesian social media frequently evades conventional keyword-based moderation due to linguistic complexity, such as slang and sarcasm. This study evaluates the trade-off between the effectiveness and efficiency of Random Forest and IndoBERT for detecting such content. Using a purposive sampling strategy to select high-risk Instagram and X (Twitter) accounts, we developed a manually labeled "Gold Standard" dataset, validated through inter-annotator agreement, to ensure high-quality ground truth. Experiments were conducted on an NVIDIA RTX 5050 environment to simulate real-world constraints, measuring F1-Score, Recall, and inference latency. The results demonstrate that IndoBERT significantly outperforms Random Forest, particularly on the imbalanced Instagram dataset, achieving an F1-Score of 0.7667 compared to Random Forest’s 0.5924. Statistical verification using the Wilcoxon Signed-Rank Test confirms this superiority. While Random Forest is computationally lighter, requiring only 0.346 ± 0.016 seconds per training fold, it failed to detect subtle harassment, evidenced by a critically low Recall of 51.67% on the imbalanced Instagram dataset. Conversely, although IndoBERT requires a 345x higher training cost (119.28 ± 1.60 seconds), it achieved a rapid inference latency of 0.0239 ± 0.0008 seconds on GPU, proving its viability for real-time systems. Ultimately, this study's primary contribution lies in proving that IndoBERT significantly outperforms traditional Random Forest algorithms, thereby offering a major methodological step forward for Natural Language Processing in Indonesian. This ensures the reliable generalization of context-aware automated content moderation, delivering significant practical impacts for the field of Informatics and real-world social media safety.]]>
<![CDATA[Experimental Simulation of SYN Flood DDoS Attacks in a Virtual Network Environment Using Metasploit ]]>
<![CDATA[Petrus Sokibi Sukanto]]>;
<![CDATA[Bambang Sugiarto]]>;
<![CDATA[Helmi Roichatul Jannah]]>
<![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.2026.7.5.5503
<![CDATA[Distributed Denial-of-Service (DDoS) attacks remain a critical threat to network service availability, with SYN Flood being one of the most commonly exploited techniques targeting the TCP three-way handshake mechanism. This study aims to experimentally simulate SYN Flood DDoS attacks in a controlled virtual network environment and to analyze their impact on server performance. The experiment was conducted using the Metasploit Framework on Kali Linux as the attack platform and Ubuntu Server as the target system, deployed within a virtualized laboratory setup. System performance was monitored using top for CPU and memory utilization, while network traffic behavior was analyzed using Wireshark. Experimental results indicate a significant increase in CPU usage (from approximately 2% under normal conditions to over 11% during the attack), a noticeable reduction in available memory, and the accumulation of half-open TCP connections caused by repetitive SYN packets without corresponding ACK responses. These effects resulted in temporary service unavailability on the targeted ports. The proposed experimental framework provides practical insights into the operational behavior of SYN Flood attacks and serves as a reproducible laboratory reference for cybersecurity education and preliminary mitigation studies. It should be noted that the experiments were conducted in a virtual environment with predefined parameters, and the results may not fully represent real-world production networks.]]>
<![CDATA[A Hybrid Linear Regression Model with Mean Reversion and Alligator Indicators for Short-Term Forex Price Trend Prediction ]]>
<![CDATA[Irvan Lewenusa]]>;
<![CDATA[Teny Handhayani]]>
<![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.2026.7.5.5514
<![CDATA[The foreign exchange (forex) market is characterized by high liquidity and rapid price fluctuations, which pose significant challenges for short-term price trend prediction using conventional statistical models. This study aims to develop a more reliable forecasting approach by addressing the limitations of standalone linear regression under volatile market conditions. To achieve this objective, a hybrid modelling framework is proposed that integrates Linear Regression with Mean Reversion principles and the Alligator technical indicator. Historical data OHLC data for three major currency pairs (AUDUSD, EURUSD, GBPUSD) were acquired from the Metatrader 5 platform, covering period from January to May 2025 with a 5-minute timeframe. The model performance was evaluated using monthly and weekly forecasting scenarios, supported by standard regression error metrics and back testing validation. The results show that compared to a baseline model using linear regression only, the proposed hybrid approach provides substantially improved predictive reliability in weekly forecasting scenarios, achieving average R2 values above 0.85 across all evaluated currency pairs. In addition, the hybrid framework facilitates clearer and more reliable buy and sell decision making by combining quantitative trend estimation with deviation base correction signals and trend structure confirmation. From a Computer Science perspective, this study contributes to predictive time series modelling and algorithmic trading research by demonstrating that hybrid integration of machine learning and technical indicators enhances model stability, interpretability, and decision support capability for short-term forex forecasting.]]>
<![CDATA[Semantic Segmentation of Corn Images Using DeepLabV3+: ResNet Backbone Comparison and mIoU Analysis ]]>
<![CDATA[Muhammad Saiful Huda]]>;
<![CDATA[Meidya Koeshardianto]]>
<![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.2026.7.5.5521
<![CDATA[Analyzing corn cobs in precision agriculture presents unique challenges due to diverse shapes, textures, and dynamic lighting, which often degrade the boundary precision of conventional algorithms. To address this, this study evaluates the semantic segmentation performance of the DeepLabV3+ architecture by comparing three residual network backbones: ResNet50, ResNet50V2, and ResNet101. The experiments utilized a public dataset comprising 1,350 corn cob images, strictly partitioned into 800 training, 450 validation, and 100 testing images with normalized pixel values to ensure rigorous testing conditions. The results reveal a distinct operational trade-off. ResNet101 achieved the highest segmentation accuracy with a peak mean Intersection over Union (mIoU) of 96.45%, making it ideal for high-fidelity offline analysis. Conversely, ResNet50V2 delivered the best computational efficiency at 9.49 frames per second, perfectly suited for resource-constrained edge devices. However, the study acknowledges a primary limitation regarding a severe class imbalance that slightly degrades the segmentation of minor objects, highlighting the continuous trade-off between absolute accuracy and computational latency. Ultimately, this research provides a vital and urgent contribution to computer vision by delivering an optimized framework that explicitly bridges the gap between complex deep learning models and practical, edge-based production pipelines for automated precision farming.]]>
<![CDATA[Real-Time Detection And Mitigation Of Address Resolution Protocol Spoofing In Software-Defined Networks Using A POX Controller Module ]]>
<![CDATA[Rayhan Zahwan Saleh]]>;
<![CDATA[Muharman Lubis]]>
<![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.2026.7.5.5522
<![CDATA[Software-Defined Networking (SDN) simplifies network control by centralizing decisions in a controller, yet many deployments still depend on legacy Layer-2 behavior that was not designed for adversarial settings. Address Resolution Protocol (ARP) spoofing illustrates this weakness, because forged IP to MAC mappings can quietly redirect traffic and enable man-in-the-middle interception. This study develops and evaluates a POX-controller module that detects and mitigates ARP spoofing in real time without modifying the data plane. The module maintains an adaptive IP to MAC binding table and validates ARP packets, with particular attention to ARP replies that attempt to update bindings. Conflicting updates are blocked and recorded as structured events to support traceability. Experiments on a Mininet test-bed indicate that the module preserves ARP-cache correctness under sustained attacks while keeping packet loss low and controller overhead modest in the tested scenarios. These findings suggest a practical security control for campus and edge SDN environments where rapid containment and auditable operation are required.]]>
<![CDATA[Uncovering Public Emotions Toward Indonesian Police via Lexicon-Based Social Media Analysis ]]>
<![CDATA[Liza Wikarsa]]>;
<![CDATA[Debby Paseru]]>;
<![CDATA[Audrey Kussoy]]>
<![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.2026.7.5.5532
<![CDATA[This study analyzes public emotions toward the performance of the Indonesian National Police as expressed on platform X. The research aims to develop an emotion detection system capable of capturing nuanced emotional patterns beyond simple polarity and for institutional performance evaluation. A lexicon-based framework integrating dictionary-based matching with corpus-based contextual rules is applied to Indonesian-language posts. Data were collected through web crawling, producing a balanced dataset of 2,100 posts across seven emotion categories. The analytical pipeline includes preprocessing, lexicon expansion, lexical matching, and contextual refinement using linguistic markers such as negations, conjunctions, and intensifiers. Results show that combining word-level and context-level processing improves detection accuracy, achieving 80.9%. Anger, fear, and sadness appear most frequently, indicating strong public concern over policing issues, while joy and trust also emerge in posts reflecting positive experiences. These patterns illustrate that public sentiment is multidimensional and shaped by both explicit lexical cues and contextual structures. The integrated method produces more precise and interpretable classifications, contributing to research on Indonesian social media emotion analysis. This work advances NLP by introducing a context-aware lexicon framework for Indonesian emotion analysis. The study concludes that the combined lexicon-based approach offers a robust, interpretable, and context-sensitive framework for examining public emotions and provides valuable insights into perceptions of institutional performance. The findings support applications in policy monitoring, public communication strategies, and evidence-based institutional decision-making. However, the model has limitations in capturing slang, implicit meanings, and evolving colloquial expressions in social media text; therefore, future work may explore hybrid lexicon–ML models, multimodal integration, and longitudinal analysis to capture deeper semantic dynamics.]]>
<![CDATA[Modification of Message Security Through Combination of Multi-layer Classical Cryptography and LSB Steganography ]]>
<![CDATA[Dhea Emma Karniasari]]>;
<![CDATA[Dian Eka Wijayanti]]>
<![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.2026.7.5.5533
<![CDATA[In today’s era of technological advancement, safeguarding personal information is very important to prevent misuse by unauthorized parties. Therefore, this study contributes to the field of information security by presenting a cryptographic-steganography modification scheme that can improve message security while maintaining image quality by combining multi-stratified encryption such as Caesar, Vigenère, and Atbash in ASCII 256 representations and inserted using the 1-bit Least Significant Bit (LSB) method. This research aims to improve the security of messages by increasing the randomness of the generated ciphertext while maintaining the overall visual integrityof the image. The methods used includmulti-layer encryption, embedding with the smallest bit modifications, as well as quality testing through histogram analysis, mean RGB, MSE, PSNR, and entropy values. The experimental findings indicated that any variation separating the original image from the stego version was nearly undetectable, both through visual inspection and statistical evaluation. With a very small MSE value, the PSNR reaches 98 dB, and a histogram that shows similarity in each color channel. Overall, the study showed that the combination of classical encryption and 1-bit LSB insertion was highly effective in maintaining the confidentiality, image quality, and concealability of messages. In practical terms, this method has the potential to be applied to digital communication security systems and image-based transmission of confidential data. However, the study still has limitations on specific test scenarios and has not evaluated its resistance to various advanced steganalysis attacks.]]>
<![CDATA[FP16 and INT8 Quantization-Based Optimization of YOLOv8 Using TensorFlow Lite for Edge-Based Tempe Quality Recognition ]]>
<![CDATA[Isa Mahfudi]]>;
<![CDATA[Mila Kusumawardani]]>;
<![CDATA[Moechammad Sarosa]]>;
<![CDATA[Chandrasena Setiadi]]>
<![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.2026.7.5.5536
<![CDATA[Tempe is a traditional Indonesian fermented soybean product whose quality is highly influenced by environmental conditions. Manual quality assessment remains subjective and inconsistent, creating the need for an automated and objective real-time detection system. This study proposes a quantization-based optimization of the YOLOv8m model using TensorFlow Lite (TFLite) for edge-based tempe quality recognition deployed on a Raspberry Pi 4 device. A dataset of 1,000 images categorized into good and defective tempe was used for model training and evaluation. The methodological novelty of this work lies in the explicit benchmarking of FP16 and INT8 post-training quantization strategies under identical hardware conditions, analyzing their impact on inference time, model size, memory usage, and detection accuracy. Experimental results show that compared to the baseline YOLOv8 FP32 model, the INT8-quantized model reduced inference time from 420 ms/frame to 120 ms/frame (71.4% faster), decreased model size from 85.6 MB to 24.9 MB (70.9% smaller), and reduced RAM usage from 780 MB to 410 MB (47.4% lower), while maintaining high detection performance with mAP@0.5 of 0.935 (1.89% accuracy drop). The FP16 model achieved intermediate efficiency gains with minimal accuracy degradation. The optimized models were integrated into a Flask-based web monitoring system, achieving stable real-time visualization with consistent frame updates under edge deployment constraints. These findings demonstrate that INT8 quantization provides the best efficiency–accuracy trade-off for embedded vision systems. This study contributes to Informatics and Computer Science by providing a systematic edge AI deployment framework for efficient model optimization and benchmarking in resource-constrained environments.]]>
<![CDATA[Brain Tumor Classification on Hash-Curated MRI Dataset Using ECA-ResNet50 and Grad-CAM ]]>
<![CDATA[Ni Luh Risma Putri Wirdianthi]]>;
<![CDATA[Yadhurani Dewi Amritha]]>
<![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.2026.7.5.5581
<![CDATA[Clinical evaluation of brain magnetic resonance imaging is challenged by subtle intensity variations and heterogeneous tumor boundaries. Many existing classification studies rely on shared repositories without explicitly addressing data redundancy, which may lead to biased performance estimation. This study introduces a brain tumor classification framework built upon an ECA-ResNet50 architecture to improve predictive consistency while maintaining computational efficiency. The ResNet50 backbone is augmented with an Efficient Channel Attention mechanism to enhance channel dependency modeling without substantially increasing model complexity. To preserve data integrity and reduce potential leakage, duplicate images were identified and removed using an MD5-based hashing procedure prior to model development. The predefined training and testing partitions supplied with the dataset were retained for evaluation to ensure non-overlapping samples. Experimental results demonstrate an overall accuracy of 90.79% and a recall of 77% for meningioma classification. Grad-CAM visualization indicates that model predictions are primarily associated with clinically relevant tumor regions, supporting interpretability and alignment with diagnostic structures. These findings suggest that combining lightweight attention mechanisms with systematic data curation enhances reliability and transparency in MRI-based brain tumor classification.]]>
