cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Muhammad Zamroni Uska
Contact Email
zamroniuska@gamil.com
Phone
-
Journal Mail Official
zamroniuska@gamil.com
Editorial Address
-
Location
Kab. lombok timur,
Nusa tenggara barat
INDONESIA
EDUMATIC: Jurnal Pendidikan Informatika
Published by Universitas Hamzanwadi
ISSN : -     EISSN : 25497472     DOI : 10.29408
Core Subject : Science, Education,
Computer Science & IT Education
EDUMATIC: Jurnal Pendidikan Informatika (e-ISSN: 2549-7472) adalah jurnal ilmiah bidang pendidikan informatika yang diterbitkan oleh Universitas Hamzanwadi dua kali setahun yaitu pada bulan Juni dan Desember. Adapun fokus dan skup jurnal ini adalah (1) Komputer dan Informatika dalam Pendidikan; (2) Model Pembelajaran dan Model TIK; (3) Pengembangan Media Pembelajaran Berbasis Teknologi Informatika; (4) Interaksi Manusia dan Komputer; (5) Sistem Informasi dan Teknologi Informasi.
Arjuna Subject : -
Articles 472 Documents
 44   45   46   47   48 
Hybrid Human AI SDLC for Rapid SaaS Development: Evidence from a 60 Days Case Study Muhammad Hilmy Haidar Fawwazie; Nathan Daud; Muhammad Iqbal Rabani; Budi Fajar Supriyanto
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 1 (2026): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i1.34361

Abstract

There is a vacuum in the risk of architectural changes in critical systems because macro-architectural governance in AI-based software development is frequently ignored in current scholarly debate. The purpose of this study is to assess how well the Visualize, Integrate, Build, Execute (VIBE) architecture addresses the stability-speed contradiction in SaaS development. This study triangulated data from 465 automated CI/CD pipeline logs, 124 AI instruction tactic documentation records, and 42 test cases using comparative performance analysis and process tracking using an explanatory mixed-methods case study methodology on a stock market analytics platform. The study's key conclusions show a 50% boost in development efficiency, reducing a 60-day cycle to 30 days while preserving system reliability with an average latency of 1.2 seconds and a 99.9 percent availability rate. Specialist synergy was identified where humans became the primary cognitive players in architectural design at 90 percent, and AI as the executor of basic syntax at 85 percent. The research concludes that the architectural anchoring mechanism by humans is crucial for mitigating the risks of non-deterministic AI outputs. Theoretically, this study introduces the concept of human-AI cognitive alignment, while practically providing a validated roadmap for modernization of sensitive infrastructure such as Electronic Medical Records.
Forward Chaining Expert System for Optimizing Marketing Strategies in Social Commerce Platforms Andhika Rudiansyah; Novi Rukhviyanti
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 1 (2026): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i1.34382

Abstract

The complexity of digital performance indicators in social commerce environments poses significant challenges for small and medium enterprises (SMEs) in formulating coherent and actionable marketing strategies. This study develops and evaluates a forward chaining based expert system to support structured, data driven, and interpretable marketing decision-making. A design science research methodology was employed, encompassing problem identification, artifact development, and evaluation. Knowledge was elicited through literature synthesis, expert consultation, and empirical observation, and subsequently formalized into IF–THEN production rules within a structured knowledge base. The system applies a forward chaining inference mechanism to process key indicators, including followers, engagement rate, promotion frequency, and conversion rate, in order to generate prioritized strategic recommendations. Evaluation was conducted using scenario-based testing and expert validation to assess accuracy, consistency, and contextual appropriateness. The results demonstrate complete alignment between system outputs and expert judgment across all evaluation scenarios, indicating high reliability and logical consistency of the rule-based reasoning process. The system also produces context-sensitive and interpretable recommendations aligned with varying levels of business performance. This study contributes by advancing rule-based decision support systems in social commerce and providing an explainable and practically applicable tool to enhance marketing decision quality among SMEs.
Deep Learning for PM2.5 Prediction under Zero-Inflated Tropical Rainfall: RNN vs GRU Ikhsan Yuliyono; Aji Supriyanto
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 1 (2026): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i1.34418

Abstract

Air quality forecasting in maritime tropical regions is challenged by zero-inflated rainfall regimes, where prolonged dry periods are intermittently disrupted by extreme precipitation, generating highly non-linear PM₂.₅ dynamics and limiting the effectiveness of conventional predictive models. This study evaluate the predictive performance of Recurrent Neural Networks (RNN) and Gated Recurrent Units (GRU) under such distributional conditions. A quantitative experimental design with a comparative approach is employed using 1,461 daily observations from the Central Java Climatology Station, incorporating rainfall, temperature, and relative humidity as predictors; a chronological data split preserves temporal dependencies, and performance is assessed using MAE, RMSE, MAPE, and R² metrics. The results indicate that GRU achieves only a marginal 4.3% reduction in MAE relative to RNN, while both models exhibit substantial predictive failure, as evidenced by negative R² values and MAPE exceeding 300%, with predictions collapsing toward the mean and failing to capture extreme pollution events. These findings demonstrate that standard recurrent architectures with conventional loss functions are intrinsically limited in modeling zero-inflated environmental data, contributing empirical evidence on the boundary conditions of deep learning in tropical air quality forecasting and underscoring the necessity for specialized modeling approaches to support reliable early warning systems.
Demand-Based Product Classification Using K-Means with Intermittency Metrics Ariska Nur Anggraini; Amali Amali; Muhammad Syaibani Anwar
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 1 (2026): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i1.34435

Abstract

Inventory management at multi-SKU distribution companies becomes complex when most products have unstable and intermittent demand patterns. At PT JJA, procurement is still reactive without the use of historical patterns, while the previous approach generally relied on aggregate indicators such as average sales so that it has not been able to comprehensively capture temporal dynamics. This study aims to group products based on temporal demand patterns using K-Means Clustering in 11,988 transactions for the 2020–2025 period which are processed into 261 products through monthly aggregation, with features of average sales, coefficient of variation (CV), zero_month_ratio, Average Demand Interval (ADI), and trends. The results showed four optimal clusters (k = 4) with a Silhouette Score of 0.62 and an unbalanced distribution, where one cluster dominated 240 products. The values of zero_month_ratio (>0.80), ADI up to >12 months, and CV up to >3.5 show intermittent demand patterns and long-tail structures. The study confirms that the integration of temporal features (ADI, zero_month_ratio, CV, and trend) transforms the representation of demand from static aggregates to dynamic structures, while linking segmentation results with more adaptive procurement strategies to reduce the risk of overstock and understock.
Two-Stage Transfer Learning with EfficientNetB0 for Four-Class Banana Ripeness Classification Anhar Anhar; Farid Wajidi; Chairi Nur Insani
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 2 (2026): Edumatic: Jurnal Pendidikan Informatika (IN PRESS)
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i2.34588

Abstract

Manual visual inspection to assess banana ripeness is subjective and unable to meet the scale of industrial needs, while previous studies have used heavy CNN architectures and have not systematically explored the depth of fine-tuning. This study proposes a two-phase transfer learning framework using EfficientNetB0 on a pre-augmented dataset of 13.478 images across four ripeness classes: unripe, ripe, overripe, and rotten. Class imbalance is addressed through class weighting during training. In Phase 1 (Feature Extraction), all base layers are frozen, and the classification head is trained until it achieves a best validation accuracy of 98.58%. In Phase 2 (Fine-Tuning), the optimal unfrozen layer depth was determined through systematic ablation across five configurations (5, 10, 15, 20, and 25 layers), with the 25-layer configuration yielding the highest validation accuracy of 98.75%. Evaluation on 562 test images yielded an accuracy of 99.46% and a test loss of 0.0538, with an F1-score of 1.00 for the overripe and ripe classes, and 0.99 for the rotten and unripe classes. The ROC curve confirmed high discriminative capability with an AUC of 1.000 for the overripe and ripe classes, and 0.999 and 0.998 for the unripe and rotten classes. These results demonstrate that the combination of a two-phase strategy, depth ablation, and fine-tuning with class weights yields a robust classification system with potential for application in automated banana sorting using edge devices.
Enhancing Four-Dimensional Student Engagement Through Teacher-Guided AI in Vocational Informatics Education David Immanuel Nescossa; Azhar Ahmad Smaragdina
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 2 (2026): Edumatic: Jurnal Pendidikan Informatika (IN PRESS)
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i2.35138

Abstract

Although generative Artificial Intelligence (AI) is increasingly integrated into education, experimental evidence on how Teacher-guided AI influences multidimensional student engagement in vocational secondary education remains limited. This study examined whether Teacher-guided AI functions as a pedagogical scaffold that enhances student engagement in vocational Informatics education. A quasi-experimental pretest-posttest control group design was conducted with 49 Computer and Network Engineering students. Student engagement was assessed across behavioral, emotional, cognitive, and social dimensions using a validated questionnaire, supported by classroom observations and assignment documentation. The findings revealed a moderate positive effect on overall engagement (d = 0.58). Although the adjusted ANCOVA effect was marginal, the overall pattern favored the experimental group. Cognitive engagement emerged as the most responsive dimension, suggesting that Teacher-guided AI primarily supported knowledge construction and reflective inquiry, while emotional and social engagement demonstrated weaker effects. Observation data further indicated greater participation and deeper cognitive processing among students receiving Teacher-guided AI support. These findings suggest that AI is most effective when implemented as a pedagogical scaffold rather than an answer-generation tool. The study extends multidimensional engagement theory and provides empirical evidence for structured AI integration in vocational Informatics education.
Mapping Tourism-Driven Regional Inequality Through Village Clustering: Evidence from Gianyar Regency, Bali. I Made Agus Budiarta; Putu Manik Prihatini; Ni Nyoman Harini Puspita
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 2 (2026): Edumatic: Jurnal Pendidikan Informatika (IN PRESS)
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i2.34857

Abstract

Aggregate tourism growth in developing economies does not automatically translate into spatially equitable outcomes, as economic gains persistently concentrate in dominant nodes while surrounding villages remain structurally excluded. This study introduces longitudinal K-Means clustering combined with cluster transition mapping to track village economic mobility in Gianyar Regency, Bali across 2021–2023. Data covering 70 villages were analyzed using Adjusted Rand Index, transition tabulation, and multiple inequality indices to ensure cluster stability and spatial interpretability. Results reveal accelerating spatial bifurcation, with 72.9 percent of transitional villages reclassified into the peripheral tier by 2023 and tourism facility inequality surging from 20.03 to 54.62 times across tiers. Upward mobility to the hub tier was entirely absent throughout the observation period. These findings qualify convergence assumptions in both Growth Pole Theory and Hirschman's trickling-down framework through mechanistically distinct pathways: hub growth raises commercial viability thresholds that structurally foreclose peripheral entry, while backwash dominance operates as a potential steady state rather than a transitional precursor to spread. Policy responses must be tier-differentiated, with hub villages requiring investment redirection, transitional villages requiring supply chain integration, and peripheral villages requiring state-led infrastructure equalization as a prerequisite for economic participation.
Identity-Aware Lightweight MobileNetV2 with Distillation and Optuna for Face Spoofing Detection Alif Sahputra; Alva Hendi Muhammad
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 2 (2026): Edumatic: Jurnal Pendidikan Informatika (IN PRESS)
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i2.34863

Abstract

Presentation attacks, commonly known as face spoofing, remain a major security challenge in facial recognition-based authentication systems because forged media such as printed photos and replayed videos can deceive biometric verification. Lightweight CNN models such as MobileNetV2 are suitable for practical implementation, but their limited representational capacity may affect their ability to capture subtle spoofing cues and generalize to unseen identities. Previous evaluations may also produce inflated performance estimates when images from the same identity appear across training and testing sets. This study evaluates Knowledge Distillation and Optuna-based hyperparameter tuning on MobileNetV2 for lightweight face anti-spoofing under an identity-aware evaluation protocol. The novelty lies in an identity-aware comparison between representation enhancement through EfficientNet-B0-based Knowledge Distillation and optimization-based improvement through Optuna. A total of 60,000 CelebA-Spoof images were divided using an 80:10:10 subject-disjoint split, and four scenarios were compared. The baseline MobileNetV2 achieved the best overall balance, with an accuracy of 0.9943, F1-score of 0.9958, and ACER of 0.0058. Meanwhile, Knowledge Distillation obtained the lowest APCER of 0.0035, indicating fewer spoof samples were incorrectly accepted as live under the identity-aware evaluation setting.
Explainable Transfer Learning for Breast Cancer Histopathology Classification Using Grad-CAM Ade Fatahillah; Fandy Setyo Utomo; Taqwa Hariguna
Jurnal Pendidikan Informatika (EDUMATIC) Vol 10 No 2 (2026): Edumatic: Jurnal Pendidikan Informatika (IN PRESS)
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v10i2.34993

Abstract

Breast cancer remains one of the leading causes of cancer-related mortality among women worldwide, highlighting the need for diagnostic systems that are both accurate and interpretable. Although transfer learning has shown promising results in histopathological image classification, studies simultaneously examining predictive performance, statistical reliability, and interpretability remain limited. This study proposes an explainable transfer learning framework for breast cancer histopathology classification and investigates the relationship between classification performance and visual interpretability. Experiments were conducted using 2,013 histopathological images from the BreakHis dataset at 200× magnification. Three pretrained architectures, ResNet50, DenseNet121, and EfficientNetB0, were trained and evaluated under identical preprocessing, augmentation, and training settings. Performance was assessed using accuracy, precision, recall, F1-score, AUC, confidence intervals, McNemar testing, confusion matrix analysis, and Grad-CAM visualization. Results showed that DenseNet121 achieved the most balanced classification performance and the highest discriminative capability among the evaluated models. Statistical analysis confirmed significant performance differences, while Grad-CAM visualizations demonstrated more focused and diagnostically relevant activation regions. These findings suggest that models learning more discriminative histopathological representations tend to generate more meaningful visual explanations. The study emphasizes integrating predictive performance, statistical validation, and explainability to support reliable and transparent artificial intelligence systems for breast cancer diagnosis.
Penerapan LSTM pada Prediksi Harga Saham BBCA: Akurasi dan Interpretabilitas Model Rara Fazira; Sriani Sriani
Jurnal Pendidikan Informatika (EDUMATIC) Vol 9 No 3 (2025): Edumatic: Jurnal Pendidikan Informatika
Publisher : Universitas Hamzanwadi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29408/edumatic.v9i3.32424

Abstract

Financial market instability driven by volatility and stock–bond correlation increases the need for accurate stock price prediction for investment and risk management. Previous deep learning approaches act as black box models with low interpretability, hindering audit and model understanding. The purpose of this study is to analyze the application of the LSTM algorithm to predict the daily closing price of BBCA.JK shares and explain its internal gate mechanism in generating these predictions. The quantitative experimental method uses 1,390 samples (09/19/2019–06/26/2025) from investing.com with 30-, 60-, and 90-day windows. Results show that the 60-day window achieves the lowest RMSE 191.94 and MAE 151.99, while the 30-day window is overly sensitive to short-term fluctuations and the 90-day window retains irrelevant information. The novelty lies in gate-level interpretability analysis, which maps how the forget, input, and output gates manage memory and filter information, addressing black box limitations in prior models. Gate activation analysis shows a positive correlation between the input and output gates and price features, and a negative correlation with volume, representing adaptive information filtering under high market activity. This research expands explainable deep learning in finance and strengthens transparency and model trustworthiness for data-driven investment and risk management.

Page 47 of 48 | Total Record : 472

 44   45   46   47   48 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol 10 No 2 (2026): Edumatic: Jurnal Pendidikan Informatika (IN PRESS) Vol 10 No 1 (2026): Edumatic: Jurnal Pendidikan Informatika Vol 9 No 3 (2025): Edumatic: Jurnal Pendidikan Informatika Vol 9 No 2 (2025): Edumatic: Jurnal Pendidikan Informatika Vol 9 No 1 (2025): Edumatic: Jurnal Pendidikan Informatika Vol 8 No 2 (2024): Edumatic: Jurnal Pendidikan Informatika Vol 8 No 1 (2024): Edumatic: Jurnal Pendidikan Informatika Vol 7 No 2 (2023): Edumatic: Jurnal Pendidikan Informatika Vol 7 No 1 (2023): Edumatic: Jurnal Pendidikan Informatika Vol 6, No 2 (2022): Edumatic: Jurnal Pendidikan Informatika Vol 6 No 2 (2022): Edumatic: Jurnal Pendidikan Informatika Vol 6, No 1 (2022): Edumatic: Jurnal Pendidikan Informatika Vol 5, No 2 (2021): Edumatic: Jurnal Pendidikan Informatika Vol 5, No 1 (2021): Edumatic: Jurnal Pendidikan Informatika Vol 4, No 2 (2020): Edumatic: Jurnal Pendidikan Informatika Vol 4, No 2 (2020): Edumatic : Jurnal Pendidikan Informatika Vol 4, No 1 (2020): Edumatic : Jurnal Pendidikan Informatika Vol 4, No 1 (2020): Edumatic: Jurnal Pendidikan Informatika Vol 3, No 2 (2019): Edumatic: Jurnal Pendidikan Informatika Vol 3, No 2 (2019): Edumatic : Jurnal Pendidikan Informatika Vol 3 No 1 (2019): Edumatic: Jurnal Pendidikan Informatika Vol 3, No 1 (2019): Edumatic : Jurnal Pendidikan Informatika Vol 3, No 1 (2019): Edumatic: Jurnal Pendidikan Informatika Vol 2, No 2 (2018): Edumatic : Jurnal Pendidikan Informatika Vol 2, No 2 (2018): Edumatic: Jurnal Pendidikan Informatika Vol 2, No 1 (2018): Edumatic : Jurnal Pendidikan Informatika Vol 1, No 2 (2017): Edumatic : Jurnal Pendidikan Informatika Vol 1, No 1 (2017): Edumatic : Jurnal Pendidikan Informatika More Issue