cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Jumanto
Contact Email
jumanto@mail.unnes.ac.id
Phone
+628164243462
Journal Mail Official
sji@mail.unnes.ac.id
Editorial Address
Ruang 114 Gedung D2 Lamtai 1, Jurusan Ilmu Komputer Universitas Negeri Semarang, Indonesia
Location
Kota semarang,
Jawa tengah
INDONESIA
Scientific Journal of Informatics
Published by Universitas Negeri Semarang
ISSN : 24077658     EISSN : 24600040     DOI : https://doi.org/10.15294/sji.vxxix.xxxx
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering
Scientific Journal of Informatics (p-ISSN 2407-7658 | e-ISSN 2460-0040) published by the Department of Computer Science, Universitas Negeri Semarang, a scientific journal of Information Systems and Information Technology which includes scholarly writings on pure research and applied research in the field of information systems and information technology as well as a review-general review of the development of the theory, methods, and related applied sciences. The SJI publishes 4 issues in a calendar year (February, May, August, November).
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 161 Documents
 13   14   15   16   17 
Ultra-Low-Cost Hybrid OCR–LLM Architecture for Production Grade E-KTP Extraction Saputro, Anjar Tiyo; Herlambang, Bambang Agus; Novita, Mega
Scientific Journal of Informatics Vol. 12 No. 4: November 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i4.38200

Abstract

Purpose: The purpose of this study is to be able to avoid limitations of inexpensive ID card data extraction services and preserve privacy, which can simultaneously achieve reliable operation even under an environment with minimum infrastructure, in particular if no dependency on GPU-based servers are required. Method: The proposed approach is a microservice pipeline with three stages: (1) local lightweight pre-processing on devices, (2) Tesseract CPU-based OCR. js, (3) fast text tokenization through a small premature external LLM. The system is developed as TypeScript backend utilizing the Hono framework with all image processing taking place locally in order to keeping user data private. Result: The result of the experimental evaluations with real ID card samples is that the system can run stably in low-performance VPS (1 vCPU, 1 GB RAM) with operation cost approximately IDR 2.5047 per extraction process and its accuracy level is acceptable for use in a production environment. Moreover, the results indicate that system latency is dominated by LLM inference at the cloud. Novelty: The main contribution and novelty of this study is that we demonstrate, for the first time, a cost-effective (privacy-preserving) OCR-LLM hybrid pipeline without demanding expensive GPU models at large scale which makes our system suitable under limited storage and resource constraints on-premises or edge environments in small organizations including micro-SaaS services.
Optimized LSTM Model Using Simulated Annealing for Autoignition Temperature (AIT) Prediction as a Hazard Indicator Zahra, Nurul Izzah Abdussalam; Afinda, Angel Metanosa; Kurniawan, Isman
Scientific Journal of Informatics Vol. 12 No. 4: November 2025
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v12i4.38278

Abstract

Purpose: Autoignition Temperature (AIT) is the lowest temperature at which a substance will spontaneously ignite in normal air without any external ignition source. AIT is an important safety parameter in industries that handles flammable materials. Measuring AIT with conventional method is unfortunately slow, costly, and dangerous. As an alternative, an AIT prediction model can be developed using in silico approaches, specifically based on machine learning. Methods: One of the methods that can be used is Long Short-Term Memory (LSTM) since it is good at modeling the complex relationships that is involved, but unfortunately it is difficult to tune manually due to their numerous hyperparameters. Therefore, an automated strategy can be used to find the best hyperparameters for the architecture. This study aims to develop an AIT prediction model as a hazard indicator using an LSTM model optimized with Simulated Annealing (SA). Result: The experiment showed that the SA-LSTM model which uses a cooling schedule of Delta T = 0.7 outperformed the unoptimized baseline model. Novelty: The optimization raised the R2 on test data from 0.5682 to 0.5939 while also lowering the RMSE from 74.35 K to 72.10 K and the MAPE from 9.29% to 8.87%. These results confirmed that optimizing LSTM with SA gave a more robust tool for hazard indicator.
Contact, Fulfillment, and Privacy as Key Drivers of Mobile Commerce Success: A SOR-Extended M-S-QUAL Analysis Nurdin, Alya Aulia; Nugraheni, Dinar Mutiara Kusumo; Waspada, Indra
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.34382

Abstract

Purpose: M-commerce has become crucial for facilitating grocery shopping through delivery services, yet challenges like delayed orders and systems failures continue to hinder user satisfaction and loyalty. There are still lack of research that have investigated in depth both mobile apps service quality and paid attention to the perspective of user behavior in a structured way. This study addresses a gap by uniquely integrating the Mobile Service Quality (M-S-QUAL) and Stimulus Organism Response (SOR) to find out the key drivers for enhancing m-commerce grocery shopping services quality, and analyzing the influence of the m-commerce services quality factors as Stimulus in m-commerce apps to satisfaction felt by users as Organism, and their relationship with loyalty and E-WOM as user Response. Methods: Using a quantitative approach, 362 Indonesian m-commerce user responses from online survey were analyzed through Partial Least Squares Structural Equation Modeling (PLS-SEM). Outer model and inner model was carried out to test the significance between the construct and the strength of the model. Result: Results show that Contact ( =0.229), Fulfillment ( =0.192), and Privacy ( =0.166) are the most influential factors driving perceived m-commerce service quality that has strong predictive power (R2=0.804). These findings, which repositions these specific dimensions as primary stimulus within the SOR framework significantly impacts user satisfaction as organism and positively drive both loyalty and E-WOM as response. Novelty: This study provides valuable insights and a structured perspective to explain post-adoption user behavior in m-commerce delivery. The study offers novel academic insights and practical strategies for enhancing customer service, delivery reliability, and data protection through user-centered design with more attention to factors such as Contact, Fulfillment, and Privacy (Stimulus) to drive user satisfaction (Organism), loyalty and E-WOM (Response).
Mapping the Contribution of Kasepuhan Ciptagelar Tourism to Regional Income and Community Economy using the K-Means Clustering Method Gustian, Dudih; Sembiring, Falentino; Rahma, Fanny; Suwanto, Aat; Ramli, Azizul Azhar; Supangat
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.35520

Abstract

Purpose: This study aims to map the contribution of Kasepuhan Ciptagelar tourism to regional income and the community economy as part of the UNESCO Global Geopark Ciletuh–Pelabuhanratu, Sukabumi. The research addresses the problem of limited infrastructure, poor accessibility, and low optimization of local tourism potential that hinders its contribution to regional income. The objective is to provide a data-driven understanding of tourism’s economic and socio-cultural impact. This study aims to map the contribution of Kasepuhan Ciptagelar tourism to regional income and the community economy as part of the UNESCO Global Geopark Ciletuh–Pelabuhanratu, Sukabumi. The research addresses the problem of limited infrastructure, poor accessibility, and low optimization of local tourism potential that hinders its contribution to regional income. The objective is to provide a data-driven understanding of tourism’s economic and socio-cultural impact. Methods: A mixed-method approach was used, integrating quantitative and qualitative analyses. Data were collected through questionnaires and interviews from three main respondent groups: local community (58%), tourists (31%), and government/MSMEs (11%). The K-Means Clustering algorithm was applied to classify perceptions into three contribution levels-high, medium, and low-while an ANOVA test was used to examine statistical differences among clusters. Results: The clustering results revealed three contribution categories: C1 (low) with 186 data points, C2 (medium) with 195 data points, and C3 (high) with 216 data points. The high cluster demonstrated a strong positive contribution to regional income, local economy, and infrastructure development, although challenges remain in socio-cultural sustainability. The ANOVA test confirmed significant differences in economic and infrastructure variables, while destination attractiveness was relatively uniform across clusters. Novelty: This study provides a multidimensional mapping model that integrates socio-economic and participatory data with K-Means clustering to analyze cultural tourism contribution. It introduces a data visualization information system prototype for policymakers to evaluate tourism performance interactively. The research offers new insights into evidence-based strategies for sustainable and community-centered cultural tourism development.
Unveiling IT Governance Effectiveness in e-Puskesmas Using COBIT 2019 Sumardiono, Sumardiono; Supardi, Supardi; Fitriani, Suci Lailla; Priyadi, Wiwit; Ismail, Norhafizah; Suryani, Riska
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.35868

Abstract

Purpose: This study aims to evaluate the effectiveness of IT governance implementation in the e-Puskesmas system at Pengasinan Community Health Center, Bekasi City, using the COBIT 2019 framework. The research focuses on identifying the capability level and governance gaps to ensure risk management and IT service delivery align with institutional objectives. Methods: The study employs a mixed-method approach combining qualitative interviews and quantitative questionnaires. Two COBIT 2019 domains—APO12 (Managed Risk) and DSS02 (Managed Service Requests and Incidents)—were analyzed using capability level measurements and GAP analysis to determine performance alignment with governance standards. Result: The findings reveal that e-Puskesmas achieved a high capability level, with 96.88% for APO12 and 90.47% for DSS02. Despite this success, several weaknesses were identified, including delays in patient registration, data confidentiality issues, and service disruptions. The study provides strategic recommendations to enhance user training, strengthen data security, and implement continuous risk management. Novelty: This research presents one of the first applications of COBIT 2019 in evaluating IT governance for public healthcare systems in Indonesia. It demonstrates how COBIT can serve as a practical tool for assessing digital health governance maturity, ensuring data integrity, and supporting the sustainable transformation of healthcare services.
Optimizing Fair and Efficient Group Formation in Community Service Program Using Particle Swarm Optimization Windarto, Windarto
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.36007

Abstract

Purpose: The rapid expansion and administrative complexity of community service programs (Kuliah Kerja Nyata/KKN) have made manual group formation increasingly inefficient, inconsistent, and prone to imbalance. This creates an urgent need for an automated, fair, and reliable optimization method capable of handling large-scale grouping constraints. This study aims to evaluate the performance of the Particle Swarm Optimization (PSO) algorithm in generating optimal KKN group formations, focusing on computational efficiency, convergence behavior, and solution quality. Methods: PSO was implemented to form 27 KKN groups using 10 independent runs. Performance metrics included execution time, optimal iteration counts, initial fitness scores, and best final scores. Each run was analyzed to observe convergence patterns and stagnation behaviors. Result: The results indicate that PSO is highly efficient, with very fast execution times and rapid convergence, often reaching optimal solutions in the first iteration. However, performance varied: some groups achieved low optimal scores (95–97), while many stagnated at extremely high scores (100000.0) with no improvement. This shows that PSO’s effectiveness depends heavily on problem characteristics and initialization. Novelty: This study identifies and explains stagnation patterns in PSO when applied to discrete, constraint-heavy academic group formation problems, an area rarely examined in prior research. The analysis provides insight into PSO’s strengths and limitations and highlights the need for improved parameter tuning and initialization strategies. The findings serve as a foundation for developing more robust optimization approaches for fair and efficient KKN group formation.
Optimizing Early Breast Cancer Classification Using Hybrid SVM-ANN with Ridge Embedded Feature Selection Priyanta, Sigit; Selvyana, Dita Ria; Salsabila, Aulia
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.36676

Abstract

Purpose: This study aims to enhance early breast cancer detection by systematically evaluating multiple machine learning (ML) algorithms and feature selection strategies. The goal is to identify the most effective combination of classifiers and feature selection methods for accurately distinguishing malignant from benign breast tumors, thereby improving diagnostic reliability and clinical decision support. Method: The Wisconsin Breast Cancer Dataset containing 699 samples described by nine diagnostic features was used. Tumor classes were encoded as 0 (malignant) and 1 (benign). The analysis was conducted in two stages. First, five ML algorithms—K-Nearest Neighbors (KNN), Logistic Regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), and a hybrid SVM–ANN—were evaluated to establish baseline performance. Second, two feature selection approaches (wrapper and embedded) were applied to four ML models and the optimized hybrid classifier. The embedded approach employed Ridge-based feature selection to identify the most discriminative attributes and improve model generalization. Results: The hybrid SVM–ANN combined with Ridge Embedded feature selection achieved the best performance, with an accuracy of 97.86%, precision of 96.5%, recall of 96.5%, and an F1-score of 96%. This configuration outperformed all other algorithms and feature selection techniques, affirming the effectiveness of hybrid integration and embedded feature optimization. Novelty: The novelty lies in the integration of an SVM–ANN hybrid model with Ridge-based embedded feature selection for breast cancer classification. Unlike prior works that rely primarily on conventional filter or wrapper techniques, this approach demonstrates superior accuracy and robustness. The proposed framework provides a promising pathway for developing more reliable ML-based diagnostic tools in oncology.
Robust Human Gait Recognition with Convolutional Neural Network based on Gait Energy Image Pratama, Fandy Indra; Akhmad Pandhu Wijaya; Gilar Pandu Annanto; Avira Budianita; Hairudin Farid Sunanda
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.37383

Abstract

Purpose: Human gait recognition is one of the developments in artificial intelligence technology. Gait recognition is a biometric recognition technique that uses no direct interaction with an object, allowing for identification of individuals based on their gait. However, this recognition faces challenges, including varying camera angles (00 - 1800), so this requires a more in-depth introduction. Methods: Therefore, based on the references, this study proposes using the Gait Energy Image (GEI) and Convolutional Neural Network (CNN) features for in-depth extraction and recognition of each image in the Casia B Dataset, which is then compared with the results of previous studies. Result: The results of this study, with the division of the Casia B Dataset 80% as training data and 20% as testing data and 11 camera angles between 00 - 1800 produced an accuracy rate of 99.48%. Novelty: So the accuracy achieved with this deep learning technique exceeds that of previous research using conventional methods and this gait pattern recognition technique can be used to be implemented in a biometric recognition system based on human gait patterns.
Gene Expression-Based Lung Cancer Prediction in Smokers Using SVM and Moth-Flame Optimization Algorithm Ramandha, Salma Safira; Afinda, Angel Metanosa; Kurniawan, Isman
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.38268

Abstract

Purpose: Lung cancer remains one of the leading causes of death worldwide, especially among active smokers, yet early detection is still difficult because traditional imaging methods have limited sensitivity for identifying early-stage abnormalities. This study was conducted to address the need for a more accurate computational approach capable of detecting lung cancer at a molecular level using gene expression data. The goal is to build a model that can reliably distinguish cancerous from non-cancerous samples based on genomic features. Methods: This study uses the GSE4115 gene-expression dataset consisting of 187 bronchial epithelial samples and 22,215 gene features. The Moth-Flame Optimization (MFO) algorithm was implemented to select the most informative subset of genes from this high-dimensional dataset. A Support Vector Machine (SVM) classifier was then trained using multiple kernels, with hyperparameter tuning performed to identify the optimal configuration for each kernel. Results: Experimental results show that the Polynomial kernel achieved the highest performance using 286 MFO-selected features, reaching an accuracy of 0.84 and an F1-score of 0.85. These results confirm that combining MFO with SVM improves classification performance compared to using raw gene data without feature selection. Novelty: This study provides the first application of MFO-based feature selection for lung cancer prediction in smokers using the GSE4115 dataset. The findings demonstrate the value of nature-inspired optimization for handling high-dimensional genomic data and offer a promising direction for developing early computational detection methods.
Optimization of Mineral Fuel Export Forecasting Using Attention-based Long Short-Term Memory Prasetya, Ananda; Suseno, Jatmiko Endro; Sutikno
Scientific Journal of Informatics Vol. 13 No. 1: February 2026
Publisher : Universitas Negeri Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15294/sji.v13i1.38381

Abstract

Purpose: This study aims to optimize the forecasting of the Net Value of Indonesia's mineral fuel exports using the Attention-based Long Short-Term Memory (LSTM) model, supported by Dropout and Recurrent Dropout techniques that are combined to produce an optimal model. Methods: Modeling uses an LSTM architecture equipped with an Attention mechanism, as well as Dropout and Recurrent Dropout. The research procedure uses the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology. The research material used is the Indonesian mineral fuel export dataset with HS code 27 from 2014 to 2025. Model was built using the Random Search method to optimize hyperparameters such as the number of neurons (units), activation functions (Tanh, ReLu), and optimizers (Adam, Nadam, RMSprop). Result: The Attention-based LSTM model with Dropout and Recurrent Dropout techniques achieved a MAPE of 7.76%, which was better than the other models tested. Attention analysis shows that lag 12 has the greatest dominance, while lags 11 to 10 also contribute significantly, indicating an annual seasonal pattern. Projections for the next 12 months show a moderate decline in Net Value, in line with seasonal trends and historical data. Novelty: The main contribution of this research is the optimization of an Attention-based LSTM model using a combination of Dropout and Recurrent Dropout techniques, which is effective in forecasting Indonesia's mineral fuel export values because it is able to capture annual seasonal patterns, thereby improving the accuracy and stability of the forecast results.

Page 15 of 17 | Total Record : 161

 13   14   15   16   17 

Filter by Year

2024 2026


Reset
Filter By Issues
All Issue Vol. 13 No. 1: February 2026 Vol. 12 No. 4: November 2025 Vol. 12 No. 3: August 2025 Vol. 12 No. 2: May 2025 Vol. 12 No. 1: February 2025 Vol. 11 No. 4: November 2024 Vol. 11 No. 3: August 2024 Vol. 11 No. 2: May 2024