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[Hand Image-Based BISINDO Alphabet Classification Utilizing Convolutional Neural Network on Android Application ]]>
<![CDATA[Saniyyah Intan Salsabiila]]>;
<![CDATA[Nataniel Dengen]]>;
<![CDATA[Joan Angelina Widians]]>
<![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.2026.7.4.6294
<![CDATA[Communication barriers between people with hearing impairments and the general public remain a significant challenge in everyday interactions. BISINDO is a widely used sign language in Indonesia’s deaf community; however, public understanding of sign language remains limited. This study aims to develop a hand image-based BISINDO alphabet classification system using a Convolutional Neural Network model and implement the trained model in an Android application. The public dataset used consists of 10,686 BISINDO alphabet letter images representing 26 classes from A to Z, obtained from Kaggle. All images were preprocessed, including resizing, normalization, and data augmentation to increase the diversity of the training data. The model was trained and evaluated using accuracy, precision, recall, and F1-score metrics. The evaluation results showed that the model achieved a validation accuracy of 94.21%, precision of 94.38%, recall of 94.20%, and F1-score of 94.21%. The trained model was then integrated into an Android application named IsyaratKu using the Flutter framework and the Dart programming language. The implementation results showed that the application successfully recognized the letters of the BISINDO alphabet through camera and gallery input and performed effectively on Android devices. These results indicate that the CNN can classify the 26 BISINDO alphabet classes with validation accuracy above 94% and can be deployed in an Android application for offline alphabet classification.]]>
<![CDATA[Clustering Evaluation of Upper Air Thermodynamic Patterns Using K-Means Centroid Optimization with GA, PSO, and GWO Algorithms ]]>
<![CDATA[Ricky Aurelius Nurtanto Diaz]]>;
<![CDATA[Ni Luh Gede Pivin Suwirmayanti]]>;
<![CDATA[Emy Setyaningsih]]>;
<![CDATA[Agus Yarcana]]>
<![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.2026.7.4.6375
<![CDATA[Operationally used early warning systems for significant weather generally rely on conventional weighting-scoring schemes, namely, fixed thresholds set based on empirical experience or expert meteorological consensus. The fundamental limitation of conventional threshold-based methods and supervised classification models lies in their reliance on labeled data, while extreme weather events are naturally rare and imbalanced in historical station observation records. Such approaches are prone to generating false alarms. Therefore, a multilayered unsupervised learning approach is needed to objectively classify upper-air thermodynamic patterns without relying on subjective extreme-event labels. Although widely used, the K-Means algorithm has a fundamental weakness, namely its high sensitivity to the initial centroid determination. This study applies hybrid metaheuristic techniques with K-Means, namely GA-KMeans, PSO-KMeans, and GWO-KMeans, within a consistent evaluation framework, using the same cluster validity index, and applied to the operational meteorological domain. The test results show that the best fitness values are produced by the PSO-KMeans model with a WCSS value of 250.6012, followed by GWO-KMeans with a WCSS value of 304.7890, and finally the GA-KMeans model with a WCSS value of 330.0701. The third model used also consistently produces higher Silhouette Score values compared to the classical K-Means baseline and shows that metaheuristic hybridization is proven to be effective in improving the quality of cluster structures. Specifically within the field of computer science, the results demonstrate that employing appropriate cluster center optimization techniques can improve both clustering quality and resource efficiency when grouping various types of data.]]>
<![CDATA[Clustering Character Similarities of Vocational School Students Base On Wartegg Test Using CNN-DBSCAN ]]>
<![CDATA[Rony Arifiandy]]>;
<![CDATA[Wiranto Herry Utomo]]>
<![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.2026.7.5.4611
<![CDATA[This study explores the clustering of personality similarities among vocational school students based on their Wartegg Test results, utilizing Convolutional Neural Networks (CNN) for feature extraction and the DBSCAN algorithm for clustering. The Wartegg Test, an image-based projective test long used in psychology, presents challenges in terms of cost and time, especially for lower middle-class schools and large-scale student applications. Pre-trained CNN models, VGG16 and ResNet50, were used to extract high-dimensional feature vectors from digitized test images, which were then reduced using Principal Component Analysis (PCA) to optimize clustering. DBSCAN effectively identified clusters of students with similar personality traits without predefined cluster numbers, achieving meaningful results as validated by the DBCV metric. ResNet50 outperformed VGG16 with a higher DBCV score of 0.6997, highlighting its superior capability to capture complex image patterns. The clustering results revealed two dominant groups and a minimal presence of noise, representing unique personality traits. This work contributes to computational psychological profiling in education using AI-based techniques, offering a scalable and objective approach to personality analysis. This study lies in the integration of image-based projective psychological tests with deep learning-based feature extraction and density-based clustering, bridging psychology and computer science.]]>
<![CDATA[Machine Learning and GIS for Dengue Risk Mapping in Purwokerto ]]>
<![CDATA[Rosa Ratri Kusuma Hariningsih]]>;
<![CDATA[Diwahana Mutiara Candrasari]]>;
<![CDATA[Endang Setyawati]]>
<![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.2026.7.5.4982
<![CDATA[Dengue Hemorrhagic Fever (DHF) is one of the major health problems in Indonesia, especially in densely populated urban areas such as Purwokerto. This study aims to develop a Machine Learning (ML)-based DHF risk prediction model integrated with a Geographic Information System (GIS) to support public health preparedness. The data used came from DBD cases reported by the Banyumas District Health Office and climate parameters (air temperature, humidity, rainfall) from the BMKG for the period 2022–2024. Three Machine Learning (ML) algorithms were applied, namely Naive Bayes, Logistic Regression, and Support Vector Machine (SVM). The analysis process included data pre-processing, training and testing data division using stratified sampling techniques, and hyperparameter optimization using Grid Search Cross-Validation. Performance evaluation was conducted using accuracy, precision, recall, and F1-score calculated through a confusion matrix. The results showed that SVM provided the best performance with an accuracy of 0.82, precision of 0.80, recall of 0.84, and F1-score of 0.82, surpassing Logistic Regression with an accuracy of 0.76 and Naive Bayes with an accuracy of 0.71. The integration of classification results with GIS produced a spatial map of DHF risk zones that facilitated the identification of priority areas for intervention. This study contributed by presenting a multi-algorithm ML and GIS-based predictive model using local epidemiological data, which has the potential to improve the effectiveness of DHF mitigation and early detection in Indonesian cities.]]>
<![CDATA[Fundus Eye Disease Classification Using Vision Transformer With Fine-Tuning And Attention Map ]]>
<![CDATA[Asri Mulyani]]>;
<![CDATA[Arfah Ramadani]]>;
<![CDATA[Dede Kurniadi]]>
<![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.2026.7.5.5152
<![CDATA[Visual impairment affects over 2.2 billion people globally, with 1 billion cases preventable through early detection. This research aims to address early detection challenges by explicitly developing a classification model for eye diseases using fundus images. We employed the Vision Transformer (ViT-B/16) with fine-tuning transfer learning, trained on a balanced dataset enhanced by light data augmentation techniques such as random rotation, horizontal flipping, and brightness/contrast adjustment. Attention maps were integrated to provide visual explanations of the regions influencing model decisions, thereby supporting interpretability in clinical contexts. The fine-tuned ViT-B/16 model achieved 95% accuracy, 94% precision, 95% recall, and 94% F1-score, with AUC values of 1.00 for cataract and diabetic retinopathy, 0.99 for glaucoma, and 0.98 for normal conditions. The attention map analysis consistently highlighted clinically relevant retinal areas aligned with disease characteristics. This research contributes to the field of informatics by delivering an interpretable, high-performance AI tool for early eye disease detection and supporting scalable medical applications.]]>
<![CDATA[Optimizing Classification Algorithms With Smote And Metaheuristic Optimization For Imbalanced Breast Cancer Data ]]>
<![CDATA[Yusup Maolani]]>;
<![CDATA[Samidi Samidi]]>
<![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.2026.7.5.5307
<![CDATA[Class imbalance remains a critical challenge in medical classification, particularly in breast cancer diagnosis, where misclassification of the minority class can have severe clinical consequences. This study investigates the impact of combining the Synthetic Minority Over-sampling Technique (SMOTE) and metaheuristic optimization on the performance of three traditional classifiers: Support Vector Machine (SVM), Naïve Bayes, and Random Forest, using the Wisconsin Diagnostic Breast Cancer (WDBC) dataset. Four experimental scenarios were evaluated, including baseline models, models with SMOTE, models with metaheuristic optimization, and a hybrid approach integrating both techniques. Performance was assessed using accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). The results indicate that the effectiveness of the hybrid approach is highly model-dependent. SVM demonstrated the most consistent improvement, particularly when combined with SMOTE and Simulated Annealing, achieving a balanced performance across evaluation metrics with an AUC of 0.9960. In contrast, Random Forest exhibited stable performance across all scenarios with limited sensitivity to additional optimization, while Naïve Bayes showed performance degradation when combined with SMOTE, indicating potential disruption of the feature independence assumption due to synthetic data generation. These findings highlight that SMOTE and metaheuristic optimization are not universally beneficial but can enhance classification performance under specific conditions. This study provides empirical evidence to support the selective application of hybrid optimization strategies for imbalanced medical data and contributes to the advancement of intelligent classification methods in the field of artificial intelligence.]]>
<![CDATA[Indonesian Speech Emotion Recognition Using CNN with Hybrid Audio Features ]]>
<![CDATA[Alun Sujjada]]>;
<![CDATA[M. Ilham Nurdiansyah Alfajar]]>;
<![CDATA[Ivana Lucia Kharisma]]>
<![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.2026.7.5.5401
<![CDATA[This study develops a speech emotion recognition system for the Indonesian language using deep learning combined with hybrid audio features. A total of 300 speech samples from the IndoWaveSentiment dataset, labeled into five emotion classes neutral, happy, surprised, disgusted, and disappointed were used. The extracted features include Mel-Frequency Cepstral Coefficients (MFCC), Hilbert Multispectrum, and Cochleagram, capturing frequency, amplitude, and auditory perception characteristics of the speech signals. Three deep learning models were implemented: Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and a hybrid CNN-LSTM model. All models were trained and evaluated using accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). The CNN model achieved the highest validation accuracy of 98.3%, followed by LSTM (91.6%) and the hybrid CNN-LSTM (85%). All models demonstrated strong reliability with AUC values above 0.9. A local web-based interface using Flask was developed to enable real-time audio recording or upload for emotion prediction. This research contributes to speech emotion recognition and applied informatics in the Indonesian language, demonstrating that hybrid audio features combined with CNN provide accurate and practical solutions for emotion classification.]]>
<![CDATA[Integrating Climatic and Phenological Parameters in a Random Forest Model for Rice Harvest Prediction in Jember Regency ]]>
<![CDATA[Khoirunnisa' Afandi]]>;
<![CDATA[M. Habibullah Arief]]>;
<![CDATA[Bayu Taruna Widjaja]]>
<![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.2026.7.5.5427
<![CDATA[Food security vulnerability in Jember Regency, driven by rice production fluctuations due to extreme climate change and productive land depletion, necessitates accurate crop yield forecasting. Current prediction inaccuracies lead to significant inefficiencies in distributing essential agricultural resources, such as fertilizers and seeds, which threatens regional stability. This study aims to develop and optimize a robust machine learning-based prediction model by integrating dynamic climatic variables (temperature, humidity, wind speed) from API services with phenological data (planting area) to enhance forecasting precision. This study employs a Random Forest algorithm optimized through hyperparameter tuning and feature selection to identify critical predictors for harvest outcomes. The results demonstrate exceptional model performance with a quantitative R² score of 0.99, indicating a near-perfect correlation between predicted and actual yields. The analysis reveals a clear hierarchy where phenological features like “tanam bulan lalu” dominate, supported by substantial contributions from climatic factors. Furthermore, the model successfully identified two annual harvest peaks and highlighted a critical misalignment in current urea fertilizer distribution schedules. This research recommends a strategic shift toward predictive-based resource allocation to synchronize fertilizer timing with optimal planting cycles. This integrated approach provides a significant contribution to informatics-based precision agriculture by offering a data-driven tool for strategic decision-making and resource optimization.]]>
<![CDATA[MobiDerm-Fisher: Transfer Learning-Based MobileNetV3 Model with Cost-Sensitive Learning for Skin Disease Classification in Coastal Fishermen ]]>
<![CDATA[Deosa Putra Caniago]]>;
<![CDATA[Mhd Adi Setiawan Aritonang]]>;
<![CDATA[Muhammad Marshall Al Karim]]>;
<![CDATA[Viriya Marhan Cunis]]>;
<![CDATA[Surgiwe Surgiwe]]>;
<![CDATA[Yopy Mardiansyah]]>
<![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.2026.7.5.5442
<![CDATA[Skin disease monitoring among fishermen in remote coastal areas remains challenging due to limited access to medical facilities and delayed clinical assessment. This study proposes MobiDerm-Fisher, a transfer learning-based skin disease classification framework utilizing the MobileNetV3Large architecture combined with cost-sensitive learning to address class imbalance. The model was trained on 4,564 dermoscopic images from the DermNet dataset covering five classes: Psoriasis, Eczema, Atopic Dermatitis, Poison Ivy, and Urticaria, using a stratified 80:20 train–test split. Class weighting was integrated into the categorical cross-entropy loss function to ensure balanced learning across minority and majority classes. Performance evaluation was conducted using accuracy, precision, recall, F1-score, and confusion matrix analysis. The proposed model achieved a validation accuracy of 97.1% and a macro-average F1-score of 0.961, demonstrating consistent classification performance across all categories, including minority classes. The trained model was deployed into a Flask-based web application for real-time inference in low-resource environments. This study contributes to Informatics by presenting a lightweight and imbalance-aware deep learning framework optimized for mobile health deployment in resource-constrained maritime communities.]]>
<![CDATA[Optimasi K-Means Menggunakan Elbow Method dan Silhouette Coefficient untuk Clustering Perilaku Pengguna Aplikasi Mobile ]]>
<![CDATA[Hendri Purnomo]]>;
<![CDATA[Sylvia Sylvia]]>;
<![CDATA[Seli Puri Andani]]>;
<![CDATA[M.Galih Rama Putra]]>
<![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.2026.7.5.5460
<![CDATA[Meningkatnya ketergantungan terhadap aplikasi mobile menuntut adanya segmentasi perilaku pengguna yang akurat guna mendukung strategi retensi, personalisasi, dan pengambilan keputusan berbasis data. Namun, penentuan jumlah cluster yang optimal masih menjadi tantangan mendasar dalam penerapan algoritma K-Means karena sensitivitasnya terhadap pemilihan parameter. Penelitian ini mengusulkan kerangka clustering teroptimasi melalui integrasi Elbow Method dan Silhouette Coefficient untuk meningkatkan objektivitas dalam menentukan jumlah cluster yang optimal. Dataset sintetis yang terdiri dari 400 pengguna aplikasi mobile dengan 12 fitur perilaku multidimensi digunakan untuk mensimulasikan pola penggunaan yang realistis. Hasil eksperimen menunjukkan bahwa konfigurasi optimal diperoleh pada k = 3 dengan nilai Silhouette sebesar 0,67, yang mengindikasikan struktur cluster yang terpisah dengan baik dan stabil. Segmentasi yang dihasilkan mengidentifikasi tiga kelompok pengguna utama, yaitu Low Activity Users, Moderate Activity Users, dan High Activity Users. Secara metodologis, penelitian ini berkontribusi pada bidang Informatika dan Ilmu Komputer dengan memperkuat strategi validasi internal dalam unsupervised learning melalui penggunaan metrik evaluasi komplementer, sehingga meningkatkan reliabilitas dan validitas struktur clustering. Temuan ini memberikan kontribusi teoretis dalam optimasi K-Means serta implikasi praktis bagi pengembangan mobile analytics dan strategi retensi pengguna berbasis data.]]>
