cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
-
Contact Email
-
Phone
-
Journal Mail Official
-
Editorial Address
-
Location
Kota denpasar,
Bali
INDONESIA
Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI)
Published by Universitas Pendidikan Ganesha
ISSN : 20898673     EISSN : 25484265     DOI : -
Core Subject : Science, Education, Engineering,
Computer Science & IT Education Engineering
Jurnal Nasional Pendidikan Teknik Informatika (JANAPATI) is a collection of scientific articles in the field of Informatics / ICT Education widely and the field of Information Technology, published and managed by Jurusan Pendidikan Teknik Informatika, Fakultas Teknik dan Kejuruan, Universitas Pendidikan Ganesha. JANAPATI first published in 2012 and will be published three times a year in March, July, and December. This journal is expected to bridge the gap between understanding the latest research Informatika. In addition, this journal can be a place to communicate and enhance cooperation among researchers and practitioners.
Arjuna Subject : -
Articles 696 Documents
 66   67   68   69   70 
Swin Transformer Enhanced with OOD Detection for Robust and Reliable Diagnosis of Ischemic Stroke from CT Image Nurmisba Nurmisba; Desi Anggreani; Muhyiddin A M Hayat; Aedah Abd Rahman
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 14 No. 3 (2025)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v14i3.102864

Abstract

Diagnosing ischemic stroke from CT scan images presents significant challenges in achieving the speed and accuracy essential for clinical decision-making, where conventional CNN-based methods show limitations. This study addresses these gaps by developing an automated diagnostic system using a Swin Transformer model integrated with an Out-of-Distribution (OOD) detection mechanism to enhance diagnostic reliability. The model was trained and validated on a dataset of 583 brain CT images from 341 patients at a regional hospital in Makassar. This dataset, labeled by two expert radiologists (κ=0.94), was categorized into ischemic stroke (206), normal (228), and non-brain CT scans (149) as the OOD class. The Swin Transformer achieved an exceptional validation accuracy of 99.15% after 10 epochs, with a highly efficient total training time of approximately 24 minutes. The model’s superiority was further confirmed by high weighted averages for precision (0.99), recall (0.99), and F1-score (0.99). Critically, the OOD detection module demonstrated perfect performance, achieving 100% accuracy in identifying irrelevant images with a 0% false positive rate, thereby preventing erroneous diagnoses from non-brain scans. Robustness testing under varied lighting conditions also showed a 100% success rate. Real-time viability was confirmed through external validation using a live camera, yielding a rapid inference time of 0.3 seconds per image. This study concludes that the developed system offers a highly accurate, robust, and safe solution, proving its readiness for clinical implementation to support ischemic stroke diagnosis in Indonesia.
Basic Pose Classification of Pendet Bali Dance Images Using Multilayer Perceptron (MLP) Based on GLCM Feature Extraction and Otsu Thresholding M Hendriawan Hadi; Pulung Nurtantio Andono; Arief Soeleman
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 14 No. 3 (2025)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v14i3.103051

Abstract

Traditional dance classification presents a significant challenge due to the complexity of body basic poses and visual similarities across gestures. This study aims to develop an intelligent system for classifying Pendet Balinese dance basic poses using artificial intelligence and image processing techniques. The research applies a quantitative experimental approach combining Otsu Thresholding for segmentation, Gray Level Co-occurrence Matrix (GLCM) for feature extraction, and Multilayer Perceptron (MLP) for classification. A total of 690 labeled images from 15 distinct Pendet basic poses were collected from professional dancers and preprocessed into binary form using Otsu’s method to isolate the dancer from the background. Subsequently, GLCM features, energy, contrast, correlation, and homogeneity, were extracted across four directions. These features served as input for the MLP classifier, trained using a 10-fold cross-validation technique. The model achieved an overall classification accuracy of 82.75%, with high precision and recall for several basic pose types such as Ngelog, Ngeseh, and Nyeregseg. However, some basic poses with overlapping poses presented classification difficulties. The confusion matrix analysis indicated the model's capacity to differentiate most basic pose types effectively. This research demonstrates the feasibility of using MLP combined with texture-based feature extraction for cultural motion classification. The findings contribute to the digital preservation of traditional Indonesian dance and offer a foundation for developing educational and archival tools. Future improvements may involve the use of deep learning techniques and temporal video data for enhanced performance.
Comparing Machine Learning and Optimized Ensemble Models for Student Retention Ketut Jaya Atmaja; Ni Wayan Sumartini Saraswati; Eddy Hartono; Ni Kadek Bumi Krismentari
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 15 No. 1 (2026)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v15i1.103164

Abstract

Student retention is a crucial issue in higher education, as low retention rates directly increase the risk of dropout and affect institutional reputation and sustainability. This study aims to compare the performance of single machine learning (ML) models, namely Naïve Bayes (NB), Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Logistic Regression (LR), Random Forest (RF), and Artificial Neural Network (ANN), with an optimized ensemble learning approach using Voting Classification. The optimization was carried out through weighted soft voting, the selection of complementary model combinations, and handling class imbalance with the SMOTE method. The student dataset was processed through preprocessing techniques and validated using 10-fold cross-validation, with model performance evaluated by accuracy, precision, recall, and F1-score metrics. The results indicate that Soft Voting Classification consistently outperforms individual models, with the KNN_ANN_SVM combination achieving the highest accuracy of 87.55%. However, the experiments also show that the application of SMOTE did not improve performance. The best-performing model has the potential to serve as the basis for developing an Early Warning System to support data-driven interventions in reducing student dropout risk.
An Intelligent System for Detecting Online Gambling Promotion on Social Media Based on BERT and Adaptive Browser Extension Gilbert Fernando Situmorang; Juliana Damayanti Manurung; Rivaldi Lubis; Nadya Sikana; Kenneth Lionggo
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 14 No. 3 (2025)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v14i3.103511

Abstract

The proliferation of online gambling promotions on social media has created serious social and legal problems in Indonesia, yet existing detection approaches are largely post-hoc, rely on general purpose language models, and struggle to identify implicit and domain specific promotional language that is deliberately used to evade moderation. Moreover, most prior studies focus solely on offline model evaluation and are rarely integrated into real time, deployable systems that can directly protect users. To address these limitations, this study proposes an intelligent detection system utilizing IndoBERT enhanced with Domain Adaptive Pre-Training on a corpus of Indonesian online gambling related text, followed by fine-tuning for text classification. The adapted model demonstrates superior performance, achieving an F1-Score of 98.58% and outperforming baseline approaches including TF-IDF+SVM, BiLSTM, multilingual BERT, and IndoBERT without domain adaptation. To bridge the gap between model development and real-world application, the proposed model is further integrated into an adaptive browser extension capable of scanning, classifying, and filtering social media content in real-time. Functional testing on YouTube and X shows that the system effectively detects and masks online gambling promotional content without disrupting neutral or anti-gambling discourse. This research contributes both methodologically, by demonstrating the effectiveness of domain adaptive pre-training for detecting implicit promotional language, and practically, by delivering a deployable system that provides proactive protection for social media users.
Improving YOLO-Based Traffic-Sign Detection on GTSDB via F1-Guided Thresholding and Confusion-Aware Analysis Taufiqurrahman Taufiqurrahman; Nahdah Salsabil Damanik; Ihsan Rafli
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 14 No. 3 (2025)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v14i3.103588

Abstract

This paper presents a practical procedure to improve YOLOv10-based traffic-sign detection on the GTSDB benchmark by coupling F1-guided operating-point selection with a confusion-aware error audit. A standard YOLOv10 detector is trained with the reference recipe and evaluated under COCO metrics. Rather than reporting only full precision-recall curves, we derive a deployable confidence threshold from the validation F1-confidence profile and apply it consistently for test evaluation and qualitative analysis. The selected operating point, defined by a tuned confidence threshold of 0.38, attains an F1 score of 0.68. At the set level, the model reaches mAP at IoU 0.50 of 0.92 (best at epoch 105) and mAP averaged over IoU 0.50 to 0.95 of 0.70 (best at epoch 126), with final-epoch values remaining close, indicating stable convergence. Normalized and count-based confusion matrices at this operating point show residual errors dominated by near-neighbor substitutions among adjacent speed-limit denominations and visually similar prohibitions, consistent with the prevalence of tiny objects. The proposed workflow translates benchmark curves into a concrete deployment rule while connecting aggregate scores to actionable diagnostics. Implications include prioritizing resolution-aware inference or cropping for tiny numerals and targeting data curation and augmentation toward the most confusable families. The approach is simple to reproduce and can be adopted alongside existing YOLO pipelines for safety-critical perception.
Hybrid Balancing and Super-Ensemble Learning With BiomedBERT for Imbalanced Medical Abstract Classification Ghulam Asrofi Buntoro; Oddy Virgantara Putra; Mauridhi Hery Purnomo
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 14 No. 3 (2025)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v14i3.103811

Abstract

The exponential growth of biomedical textual data presents new challenges for efficient classification, particularly under severe class imbalance where minority disease categories are underrepresented. This study proposes a novel framework that integrates Biomedical Bidirectional Encoder Representations from Transformers (BioMedBERT), a domain-specific transformer pretrained on biomedical corpora, with hybrid balancing strategies and a super-ensemble learning approach for medical abstract classification. The preprocessing pipeline includes label normalization, BioMedBERT-based tokenization, and fixed-length sequence alignment. To mitigate imbalance, oversampling, undersampling, and hybrid balancing are applied, and their outputs are combined in a probabilistic super-ensemble. Evaluation was conducted on a medical abstract dataset comprising 14.438 abstracts across five disease categories, using stratified 3-fold cross-validation. Experimental results demonstrate that the super-ensemble consistently outperforms individual balancing strategies, achieving an accuracy of 64.25% and a macro-F1 score of 64.12%. These results indicate improved robustness and sensitivity to minority classes compared to baseline transformer-based methods. The findings highlight that integrating domain-specific pretrained models with advanced resampling and ensemble techniques provides a promising solution for biomedical Natural Language Processing (NLP) applications, offering enhanced reliability for literature retrieval, clinical decision support, and biomedical research.
Artificial Intelligence in Essay Scoring: A Comparative Study of Transformer-Based Models Unggul Utan Sufandi; Dwi Astuti Aprijani; Bachriah Fatwa Dhini; Agung Wicaksono
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 15 No. 1 (2026)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v15i1.103823

Abstract

We compare transformer-based approaches for automated essay scoring (AES) on 3,077 student essays using two reference answers (RA1, RA2) and two models (all-MiniLM-L6-v2, all-mpnet-base-v2). Accuracy is defined as within ±10 points of human scores. all-MiniLM-L6-v2 yields the best accuracy—57.16% (RA1) and 61.13% (RA2) with stop-words kept—while all-mpnet-base-v2 attains 55.37% (RA1) and 59.59% (RA2). Removing stop-words generally reduces accuracy by ~1–2.5 points (e.g., MiniLM RA2: 61.13% → 58.70%). On efficiency, mpnet is ≈2.5× faster (avg 0.041–0.036 s/essay) than MiniLM (0.102–0.094 s/essay) across settings, indicating a clear accuracy–throughput trade-off. Complementary error metrics show MAE as low as 9.75, RMSE 12.95–14.26, and correlation up to 0.556, corroborating moderate but usable agreement. Practically, MiniLM is preferable for high-stakes precision, whereas mpnet favors large-scale, time-critical deployments. Findings also suggest retaining common words helps preserve syntactic/contextual cues, slightly boosting similarity-based scoring. We conclude with deployment guidance: report within-±10 accuracy alongside MAE/RMSE and correlation, choose the model per operational goal (precision vs. speed), and consider hybrid enhancements (rubric features + embeddings) to raise reliability for inclusive, at-scale AES in higher education.
T4EDR: Hybrid Threat Detection Framework for EDR Based on Semantic Rule Embedding and Contextual Network Flow Analysis Muh Dzikri Alfauzan Nuzul; Desi Anggreani; Muhammad Faisal; Abd Rahman Wahid; Titik Khawa Abd Rahman
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 15 No. 1 (2026)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v15i1.104059

Abstract

In response to the increasing complexity of cyber threats and attacks, this study proposes an innovative endpoint detection and response (EDR) framework named T4EDR (Transformer for Endpoint Detection and Response). Specifically, it addresses the inefficiencies of traditional systems that rely on static and less adaptive rules. T4EDR integrates semantic analysis methods to interpret security rules and a transformer-based deep learning model to contextually analyze network traffic flows. In the initial phase, thousands of security rules from Wazuh were extracted, embedded, and semantically validated against the MITRE ATT&CK framework, achieving a semantic coherence of 86.43% with a silhouette score of 0.702. Subsequently, the FlowBERT model was designed to classify network traffic flows using the CIC-IDS2018 dataset, achieving 91.1% accuracy, a macro-F1 of 0.79, and a mean Average Precision (mAP) of 0.90, surpassing the quantitative target of 85%. The integration of rule embeddings with FlowBERT hidden states through a linear projector enables adaptive mapping of endpoint activities to relevant security rules, supporting context-based automated responses. The main contribution of this study is an adaptive framework that bridges the gap between traditional rule analysis and deep learning-based detection, thereby enhancing the capability to detect multi-stage threats on modern endpoints.
Automated Identification of Learning Styles Using SARSA Reinforcement Learning Based on the Felder–Silverman Model Nesi Syafitri; Suzani Mohamad Samuri; Yudhi Arta
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 15 No. 1 (2026)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v15i1.104783

Abstract

Identifying students’ learning styles is essential for developing adaptive educational systems that enable personalized learning experiences. Traditional methods, however, often rely on static questionnaires and lack adaptive mechanisms that can learn from data. This study proposes a reinforcement learning framework for automated learning style identification using the SARSA algorithm, grounded in the Felder–Silverman Learning Style Model (FSLSM). The SARSA agent learns behavioral patterns from students’ responses to the Index of Learning Styles (ILS) questionnaire. Data were collected from 799 university students across four FSLSM dimensions: active–reflective, sensing–intuitive, visual–verbal, and sequential–global. To address class imbalance, class weighting was applied during training to ensure balanced representation across categories. The model achieved strong performance across all dimensions, with accuracy ranging from 0.92 to 0.98, and precision, recall, and F1-scores consistently above 0.90 across cross-validation folds (k = 3, 5, 10). These results confirm the model’s reliability and generalization capability. Validation on a separate dataset of 45 students yielded a Cohen’s Kappa coefficient of 1.0, indicating perfect agreement with the FSLSM-based ground truth. Overall, the findings highlight the effectiveness of the SARSA algorithm in accurately identifying learning-style patterns and demonstrate its potential for integration into adaptive and personalized learning systems.
Internet of Things (IoT)-Based Brake Fluid Condition Detection and Vapor Lock Prevention Device Dzaki Putra Prakosa; Setya Wijayanta
Jurnal Nasional Pendidikan Teknik Informatika: JANAPATI Vol. 15 No. 1 (2026)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v15i1.105070

Abstract

This research presents the development of an Internet of Things (IoT)–based system for monitoring brake fluid condition and preventing vapour lock by integrating a Type-K thermocouple with the MAX6675 amplifier, ESP32 microcontroller, relay-controlled Peltier cooling module, and Blynk cloud. The system aims to provide early detection of temperature rise beyond the dry boiling point of DOT 3 brake fluid, which significantly decreases when moisture is absorbed during vehicle operation. A series of laboratory tests was conducted to evaluate sensor accuracy, response time, system stability, and real-time notification performance. Calibration results showed that the thermocouple demonstrated stable readings with only minor deviations relative to a reference thermometer. Functional testing indicated that the cooling module and warning indicators operated reliably at predefined thresholds. The system successfully sent temperature notifications and risk warnings through Blynk with minimal latency. These results indicate that the proposed IoT-enabled device can serve as a preventive safety solution by offering continuous monitoring and early detection of vapour lock risk.

Page 69 of 70 | Total Record : 696

 66   67   68   69   70 

Filter by Year

2012 2026


Reset
Filter By Issues
All Issue Vol. 15 No. 2 (2026) Vol. 15 No. 1 (2026) Vol. 14 No. 3 (2025) Vol. 14 No. 2 (2025) Vol. 14 No. 1 (2025) Vol. 13 No. 3 (2024) Vol. 13 No. 2 (2024) Vol. 13 No. 1 (2024) Vol. 12 No. 3 (2023) Vol. 12 No. 2 (2023) Vol. 12 No. 1 (2023) Vol. 11 No. 3 (2022) Vol. 11 No. 2 (2022) Vol. 11 No. 1 (2022) Vol 11, No 1 (2022) Vol. 10 No. 3 (2021) Vol. 10 No. 2 (2021) Vol 10, No 2 (2021) Vol 10, No 1 (2021) Vol. 10 No. 1 (2021) Vol 9, No 3 (2020) Vol. 9 No. 3 (2020) Vol 9, No 2 (2020) Vol. 9 No. 2 (2020) Vol. 9 No. 1 (2020) Vol 9, No 1 (2020) Vol. 8 No. 3 (2019) Vol 8, No 3 (2019) Vol 8, No 2 (2019) Vol. 8 No. 2 (2019) Vol. 8 No. 1 (2019) Vol 8, No 1 (2019) Vol 8, No 1 (2019) Vol 7, No 3 (2018) Vol. 7 No. 3 (2018) Vol 7, No 3 (2018) Vol. 7 No. 2 (2018) Vol 7, No 2 (2018) Vol. 7 No. 1 (2018) Vol 7, No 1 (2018) Vol 7, No 1 (2018) Vol 6, No 3 (2017) Vol 6, No 3 (2017) Vol. 6 No. 3 (2017) Vol 6, No 2 (2017) Vol. 6 No. 2 (2017) Vol 6, No 2 (2017) Vol. 6 No. 1 (2017) Vol 6, No 1 (2017) Vol 6, No 1 (2017) Vol 5, No 3 (2016) Vol. 5 No. 3 (2016) Vol 5, No 3 (2016) Vol. 5 No. 2 (2016) Vol 5, No 2 (2016) Vol 5, No 2 (2016) Vol 5, No 1 (2016) Vol 5, No 1 (2016) Vol. 5 No. 1 (2016) Vol 4, No 3 (2015) Vol. 4 No. 3 (2015) Vol 4, No 3 (2015) Vol 4, No 2 (2015) Vol 4, No 2 (2015) Vol. 4 No. 2 (2015) Vol 4, No 1 (2015) Vol. 4 No. 1 (2015) Vol 4, No 1 (2015) Vol 3, No 3 (2014) Vol. 3 No. 3 (2014) Vol 3, No 3 (2014) Vol. 3 No. 2 (2014) Vol 3, No 2 (2014) Vol 3, No 2 (2014) Vol 3, No 1 (2014) Vol. 3 No. 1 (2014) Vol 3, No 1 (2014) Vol 2, No 3 (2013) Vol. 2 No. 3 (2013) Vol 2, No 3 (2013) Vol. 2 No. 2 (2013) Vol 2, No 2 (2013) Vol 2, No 2 (2013) Vol 2, No 1 (2013) Vol 2, No 1 (2013) Vol. 2 No. 1 (2013) Vol 1, No 3 (2012) Vol 1, No 3 (2012) Vol. 1 No. 3 (2012) Vol. 1 No. 2 (2012) Vol 1, No 2 (2012) Vol 1, No 2 (2012) Vol 1, No 1 (2012) Vol 1, No 1 (2012) Vol. 1 No. 1 (2012) More Issue