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[Intelligent System for Personal Style Recommendations Using Artificial Intelligence ]]>
<![CDATA[Meizaluna Frakasa]]>;
<![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
<![CDATA[Fashion plays a crucial role in personal identity expression, particularly among Generation Z who are highly influenced by rapid trends and social media. This condition often leads to identity confusion and difficulty in finding an authentic personal style. This study aims to analyze and propose an intelligent personal style recommendation system based on artificial intelligence that integrates outfit selection, hairstyle recommendation, and makeup suggestions. A Systematic Literature Review (SLR) was conducted following the PRISMA 2020 guidelines by analyzing peer-reviewed studies published between 2020 and 2025 from Scopus, IEEE Xplore, and ScienceDirect. A total of 30 relevant studies were selected and thematically synthesized into several domains, including fashion recommendation systems, outfit compatibility modeling, virtual try-on technologies, skin tone analysis, makeup recommendation, and hairstyle classification. The results indicate that deep learning approaches such as Convolutional Neural Networks, Graph Neural Networks, hybrid filtering, and generative models significantly improve personalization accuracy and user satisfaction compared to conventional methods. The findings also reveal a research gap in the integration of multi-domain style recommendations within a single unified system. This study contributes by proposing a comprehensive AI-based personal stylist framework that supports holistic and inclusive personalization, helping users develop an authentic style aligned with their identity while navigating contemporary fashion trends.The abstract provides a general description of the contents of the paper and line spacing 1. The maximum length of the abstract is 250 words. If there are foreign terms that have not been standardized, they are written in italics. Citations are not permitted in the abstract section. Keywords : Artificial Intelligence, Fashion Recommendation System, Personal Style, Systematic Literature Review, Generation Z, Personalization.]]>
<![CDATA[Potato Quality Classification Using Artificial Neural Networks Based on RGB Color and GLCM Texture Features ]]>
<![CDATA[Muh. Aidil Amri]]>;
<![CDATA[Muh. Fajrin Bakri]]>;
<![CDATA[Mujahidin Anwar]]>;
<![CDATA[Muhammad Fajar B]]>;
<![CDATA[Andi Baso Kaswar]]>;
<![CDATA[Dyah Darma Andayani]]>;
<![CDATA[Jumadi Mabe Parenreng]]>
<![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.2026.7.5.5593
<![CDATA[Potatoes are an important agricultural commodity whose quality directly affects market value and industrial processing efficiency. However, potato quality assessment is still dominated by manual methods, which lead to subjective assessments, inconsistent results, and limited processing capacity on a large production scale. This study aims to develop an automatic potato quality classification system based on digital image processing and Artificial Neural Networks (ANN) to provide an objective and efficient assessment method. The proposed system consists of six stages: image acquisition, pre-processing, segmentation using Otsu's threshold, morphological operations, feature extraction, and classification. A total of 272 potato images were used, consisting of 136 good-quality samples and 136 poor-quality samples, which were taken under controlled lighting conditions. Color features in the RGB color space and texture features extracted using the Gray-Level Co-occurrence Matrix (GLCM) were used as input features. The classification process used a Feedforward Backpropagation Neural Network with two hidden layers. The experimental results showed that the combination of RGB color features and GLCM texture features achieved the best performance, with an accuracy of 98.33% on the test dataset and an average testing time of 0.299 seconds per image. These results indicate that the proposed system can significantly reduce subjectivity and processing time in potato quality assessment, thereby supporting the implementation of a reliable and scalable automatic assessment system for agricultural and industrial applications.]]>
<![CDATA[A Stacking-Based Ensemble Learning Framework for Disease Severity Classification Using Electronic Medical Records ]]>
<![CDATA[Edi Ismanto]]>;
<![CDATA[Abdul Fadlil]]>;
<![CDATA[Anton Yudhana]]>
<![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.2026.7.5.5594
<![CDATA[The increasing availability of Electronic Medical Records (EMR) presents significant opportunities for improving clinical decision-making through data-driven approaches. Nevertheless, the intricacy, heterogeneity, and high degree of dimensionality of EMR data pose challenges for conventional statistical techniques and single machine learning (ML) models in accurately predicting patient conditions, particularly disease severity. This study aims to develop and evaluate a stacking-based framework for ensemble learning for disease severity classification using EMR data. The proposed approach integrates multiple ML models, including LR, SVM, K-NN, RF, and NB, using a meta-learner to enhance predictive performance. The dataset comprises 4,412 patient records with clinical and laboratory features, and the assessment is carried out using accuracy, precision, recall, and F1-score metrics. The findings of the experiment demonstrate that the stacking-based ensemble model outperforms all individual models, achieving an accuracy of 0.790, a recall of 0.660, a precision of 0.770, and an F1-score of 0.710. The model also demonstrates improved capability in identifying severe cases while maintaining a balanced performance across evaluation metrics. These results verify that ensemble learning, particularly stacking, provides a more robust and generalized solution for handling complex EMR data. This research helps the development of ML in healthcare by demonstrating the efficiency of stacking-based ensemble frameworks in improving disease severity classification, thereby supporting more reliable and accurate clinical decision-making systems.]]>
<![CDATA[Implementation of IndoBERT and XGBoost Hybrid Architecture for Sentiment Analysis on Government Budget Issues ]]>
<![CDATA[Shahnaz Tasha Kurnia]]>;
<![CDATA[Muh Fajrin Bakri]]>;
<![CDATA[Dewi Fatmarani Surianto]]>;
<![CDATA[Nur Azizah Eka Budiarti]]>;
<![CDATA[Syahrul Syahrul]]>
<![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.2026.7.5.5604
<![CDATA[Lexical similarity between sentiment classes, ambiguity of meaning, and the high number of overlapping words between labels are the main challenges in sentiment classification regarding government budget efficiency on social media. This issue is widely discussed because it relates to transparency and accountability in state financial management, so public perceptions of it need to be analyzed in context to support data-based policy evaluation. This study aims to develop an optimal sentiment classification model by integrating IndoBERT-based word representation and XGBoost classification algorithm. A total of 1,650 public comments were manually collected from platform X (Twitter), YouTube, TikTok, and Instagram, and annotated into three sentiment categories: positive, negative, and neutral, with inter-annotator reliability evaluated using Cohen's Kappa reaching 92.2%. The model was tested through three different scenarios. Experimental results show that the proposed method, a hybrid of IndoBERT fine-tuning and XGBoost, produced the best performance with an accuracy of 93% and an F1-score of 92%. Compared with the IndoBERT pre-trained model and the XGBoost baseline, the proposed model improved accuracy by 26 percentage points (from 67% to 93%). Contextual representation through fine-tuning proved effective in addressing meaning ambiguity, handling lexical similarity across classes, and improving model accuracy and stability. This study demonstrates the efficacy of hybrid transformer–ensemble models for handling high-ambiguity texts in the public-sector domain, thereby contributing to the literature on Indonesian sentiment classification.]]>
<![CDATA[Comparative Evolution of SVM Using PSO and GA for Early Childhood Nutrition Classification ]]>
<![CDATA[Olivia Diwani Saragih]]>;
<![CDATA[Solikhun Solikhun]]>;
<![CDATA[Agus Perdana Windarto]]>
<![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.2026.7.5.5623
<![CDATA[Early detection of toddler nutritional status is an important step in preventing the long-term effects of stunting. However, manual assessments are often inefficient and inconsistent, requiring a more accurate computational approach. This study aims to improve the performance of the Support Vector Machine (SVM) model in classifying the nutritional status of toddlers through hyperparameter optimization using Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). A dataset of 120,999 entries was obtained from the Kaggle platform and processed through data cleaning, normalization, and categorical encoding stages. A baseline SVM model was built as an initial benchmark before optimization. The results of the experiment showed that the PSO method produced the best performance with accuracy, precision, recall, and f1-score of 0.995, surpassing SVM without optimization (0.950) and SVM optimized by GA (0.990). These findings indicate that PSO is capable of exploring the solution space more effectively based on experimental results showing more stable and gradual convergence on the learning curve, with a smaller gap between training and validation values, and a more structured solution search process compared to GA, thereby improving model stability and accuracy. This research contributes to the development of a more accurate classification model for toddler nutritional status that can be integrated into decision support systems in the health sector, which can also be applied to improve efficiency and accuracy in data-based decision making, particularly in the context of assessing toddler nutritional status. This contribution has a significant impact on advancing the application of metaheuristic methods in various informatics applications.]]>
<![CDATA[Handling Class Imbalance in Indonesian Mobile Service App Reviews Using IndoBERT and Hierarchical Data Augmentation ]]>
<![CDATA[Sang Ayu Putu Diah Setyawati]]>;
<![CDATA[Roy Rudolf Huizen]]>;
<![CDATA[Dadang Hermawan]]>
<![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.2026.7.5.5637
<![CDATA[This study investigates sentiment classification on imbalanced Indonesian user-review data from the MyIM3 mobile application, focusing on the effectiveness of hierarchical data augmentation for improving minority-class detection. A total of 10,000 reviews were collected, of which 6,968 were retained after preprocessing and automatically labeled using the InSet Indonesian sentiment lexicon. The labeled dataset was divided into training and testing sets (70:30) and used to fine-tune an IndoBERT-based sentiment classifier. Baseline results show that IndoBERT achieves strong overall performance (accuracy = 0.93, macro-F1 = 0.89, ROC–AUC = 0.969), however, detection of the minority positive class remains limited due to class imbalance. To address this issue, three augmentation strategies were evaluated: synonym replacement, random deletion, and hierarchical augmentation. Among these, hierarchical augmentation provides the most consistent improvement, increasing the positive-class F1-score from 0.81 to 0.83 (+0.02 absolute) while maintaining stable performance on the majority class. The findings indicate that hierarchical augmentation improves contextual sentiment learning by preserving clause-level structure while introducing controlled lexical variation, which is important for Indonesian evaluative expressions. This study contributes evidence to low-resource and imbalanced text classification research by demonstrating that structurally guided augmentation enhances minority sentiment recognition without degrading majority-class accuracy in Indonesian review datasets.]]>
<![CDATA[Improving Liver Disease Classification Performance Using Random Forest Algorithm with Grid Search Hyperparameter Optimization ]]>
<![CDATA[Tiarni Catherine Pesahlita LG]]>;
<![CDATA[Solikhun Solikhun]]>;
<![CDATA[Anjar Wanto]]>
<![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.2026.7.5.5640
<![CDATA[Liver disease is one of the serious health problems that often develops without obvious early symptoms, making it difficult to detect early and increasing the risk of more severe complications. The main problem in the classification of liver disease is how to obtain a prediction model that has high accuracy and stability when faced with multivariate and complex medical data. Therefore, this study aims to improve the performance of liver disease classification by optimizing the Random Forest algorithm using the Grid Search hyperparameter optimization technique. The dataset used consisted of 1,700 patient data with eleven attributes that included demographic characteristics, lifestyle, medical risk factors, and liver function test results. The pre-processing stage includes data checking, feature normalization, and data sharing using a ratio of 80% trained data and 20% stratified test data. The Random Forest model is built as a base model and further optimized using Grid Search with a cross-validation scheme to obtain the best combination of hyperparameters. Model performance evaluation was carried out using accuracy, precision, recall, and F1-score metrics. The results showed that the baseline Random Forest model produced an accuracy of 89.71%, while after optimization using Grid Search, the accuracy increased to 91.18% accompanied by an increase in precision, recall, and F1-score values. These improvements show that the hyperparameter optimization process plays an important role in improving the generalization capabilities and stability of the model. The findings of this study confirm that the integration of Random Forest and Grid Search can be an effective approach to the classification of liver diseases and make a significant contribution to the development of medical decision support systems and the application of Machine Learning techniques in the field of health informatics.]]>
<![CDATA[A Hybrid Conversational Tourism Recommender Integrating Collaborative and Content-Based Filtering: Design and Evaluation on a Sparse Google Maps Review Dataset ]]>
<![CDATA[Robert Ananda Aritonang]]>;
<![CDATA[Aditiya Hermawan]]>;
<![CDATA[Junaedi Junaedi]]>;
<![CDATA[Riki Riki]]>;
<![CDATA[Satria Abadi]]>
<![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.2026.7.5.5644
<![CDATA[Tourism recommendation systems frequently encounter extreme data sparsity, cold-start problems, and limited personalization when relying solely on either collaborative or content-based approaches, particularly in real-world review platforms where user–item interactions are unevenly distributed. Such conditions reduce prediction reliability and weaken the practical usefulness of recommendation outputs. This study aims to design and empirically evaluate a hybrid conversational tourism recommender that improves recommendation accuracy and ranking relevance under sparse data conditions. The proposed framework integrates collaborative filtering and content-based filtering within a hybrid architecture, combining interaction-driven preference learning with textual content modeling derived from user reviews. The recommendation engine is operationalized through a conversational chatbot interface to support interactive preference elicitation and real-time recommendation delivery. The system is evaluated using a Google Maps review dataset characterized by high sparsity. Model performance is assessed using rating prediction metrics and top-K ranking metrics to ensure comprehensive evaluation. Experimental results indicate that the hybrid model achieves a Root Mean Squared Error of 0.6985 and a Mean Absolute Error of 0.5448, outperforming standalone collaborative and content-based models. In top-10 recommendation evaluation, the model attains Precision@10 of 0.52, Recall@10 of 0.91, and F1-score@10 of 0.66, demonstrating improved relevance and coverage. These findings highlight the effectiveness of hybrid conversational integration in mitigating sparsity-related limitations and provide practical implications for scalable, data-driven personalization in digital tourism platforms.]]>
<![CDATA[Bibliometric Analysis and Philosophical Reflective Analysis of Positivist and Post-Positivist Paradigms in Developing Lightweight Deep Learning Models for Rehabilitation Assessment ]]>
<![CDATA[Sirli Fahriah]]>;
<![CDATA[Catur Edi Widodo]]>;
<![CDATA[Prayitno Prayitno]]>
<![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.2026.7.5.5650
<![CDATA[Smartphone cameras and lightweight deep learning (DL) enable scalable movement analysis for post–lower-limb-injury rehabilitation; however, the scientific paradigms that guide model design and evaluation remain under-discussed. This study compares Positivist and Post-Positivist paradigms and formulates a techno-humanistic methodological framework for developing lightweight DL rehabilitation assessment systems. The core methodology integrates (i) bibliometric analysis of 35 publications (2020–2025) on lightweight DL, computer vision, explainable AI, and clinical rehabilitation, and (ii) philosophical reflective comparative analysis across ontology, epistemology, and axiology. Using VOSviewer network, overlay, and density visualizations, we map keyword co-occurrence structures and interpret their methodological orientation through the two paradigms. The results show a dominant Positivist-oriented technical cluster emphasizing measurable performance and reproducible optimization (e.g., classification, accuracy, real-time and edge deployment). In parallel, emerging Post-Positivist themes highlight external validity, interpretability (XAI), fairness, demographic representativeness, and quality-of-life outcomes, indicating a shift toward context-aware and ethically grounded evaluation. By combining bibliometric mapping with philosophical synthesis, this framework provides a reproducible methodological lens for informatics/computer science researchers to design lightweight AI that is not only efficient, but also explainable, clinically relevant, and ethically accountable. ]]>
<![CDATA[Medical Information Release Application Design Using Design Thinking And Heuristic Evaluation At Private Hospital In Bumi Serpong Damai ]]>
<![CDATA[Nerissa Adha Andrania]]>;
<![CDATA[Anastasia Cyntia Dewi Kurniawati]]>;
<![CDATA[Hosizah Hosizah]]>;
<![CDATA[Siswati Siswati]]>
<![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.2026.7.5.5653
<![CDATA[Medical information release processes in Indonesian hospitals often suffer from data inconsistency, process delays, and weak coordination, while simultaneously operating under strict regulatory and privacy requirements. This study designs a user interface (UI) for a medical information release application using a Design Thinking methodology encompassing empathize, define, ideate, prototype, and test phases. The resulting high‑fidelity prototype adopts a dual‑pathway architecture that separates navigation flows for patients/third parties and Health Information Management (HIM) personnel, and integrates 13 core features aligned with Indonesian Ministry of Health Regulation No. 24/2022, IFHIMA recommendations, and HIPAA security principles such as minimum necessary disclosure, role‑based access control, audit trail, and informed consent. Gestalt design principles are applied to optimize perception, reduce cognitive load, and support safe handling of sensitive medical data. Usability was evaluated through heuristic assessment with 22 criteria and a 0–4 severity rating scale by three expert evaluators, yielding an average Severity Rating of 1.26, categorized as cosmetic problems without impact on core functionality or user satisfaction. The prototype therefore offers both operational effectiveness and regulation-aligned security, providing a reference framework for health informatics in designing medical information release systems for highly regulated healthcare environments.]]>
