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
,
INDONESIA
JOURNAL OF APPLIED INFORMATICS AND COMPUTING
Published by Politeknik Negeri Batam
ISSN : -     EISSN : 25486861     DOI : 10.3087
Core Subject : Science,
Computer Science & IT
Journal of Applied Informatics and Computing (JAIC) Volume 2, Nomor 1, Juli 2018. Berisi tulisan yang diangkat dari hasil penelitian di bidang Teknologi Informatika dan Komputer Terapan dengan e-ISSN: 2548-9828. Terdapat 3 artikel yang telah ditelaah secara substansial oleh tim editorial dan reviewer.
Arjuna Subject : -
Articles 1,006 Documents
 97   98   99   100   101 
A Lightweight Qdisc Triggered Controller (QTC) for Congestion Aware Software Defined Networks Mustafa Ayad Anwer; Zaid Shakir Kadhim Al-Shammari; Ahmed Sabri Ghazi Behadili
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13631

Abstract

Software Defined Networking (SDN) enables centralized and programmable traffic management. However, maintaining service quality under congestion remains a challenging task while using heavy computation or delayed network wide optimization. This paper presents a lightweight Qdisc Triggered Controller (QTC) for congestion aware path switching in SDN. The suggested controller monitors queueing discipline statistics specifically packet drops and qdisc overlimit events. The proposed mechanism is implemented using Ryu controller and evaluated in a Mininet based topology under normal, persistent, transient and sequential bottleneck scenarios. The experimental findings show that QTC maintains near baseline performance under normal network operation and provides substantial improvements under congestion. In the persistent bottleneck scenario, throughput increased from 2.102 Gbit/s with fixed path forwarding to 30.0 Gbit/s with QTC, while ICMP packet loss decreased from 5% to 0%. These results indicate that QTC provides a lightweight rule based solution for responsive congestion aware traffic engineering in SDN.
Comparative Analysis of MobileNetV2, Xception, and EfficientNet for Batik Pattern Classification Maxentia Kathleen; Christy Atika Sari
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13639

Abstract

Indonesia boasts a rich cultural heritage in the form of batik, which has gained international recognition. However, the wide variety of batik motifs makes visual identification difficult for both locals and tourists. The limitations of manual observation and a lack of understanding regarding the significance behind each design pose a significant barrier to cultural preservation in the digital age. This study aims to conduct a comparative analysis of Deep Learning models to identify the most effective architecture for automatically classifying batik motifs. The method employed involved comparing three Convolutional Neural Network architectures: MobileNetV2, Xception, and EfficientNet. This study was conducted using a dataset containing 3,700 batik images that had been processed through a careful data distribution process. The primary objective of this evaluation is to find the optimal balance between high classification accuracy and efficient use of computational resources, enabling implementation on platforms with limited specifications. The results of this study indicate that these models can recognize complex batik patterns with outstanding validation accuracy rates ranging from 98% to 100%. These findings provide a strong technical foundation for selecting the most appropriate model architecture for developing intelligent systems aimed at preserving traditional batik. This study also shows that MobileNetv2 is the most optimal model architecture because it achieves a perfect balance between 100% accuracy and the fastest total inference time of 36.74 seconds, with an average inference time per sample of 0.0525 seconds. It is hoped that this research will make the batik identification process faster, more accurate, and accessible to the general public, thereby supporting the sustainability of Indonesia’s cultural heritage.
Evaluation of Support Vector Machines and Adaptive Boosting in Classifying the Compliance Levels of Property and Building Taxpayers Using Receiver Operating Characteristic (ROC) Saumina Saumina; Munirul Ula; Asrianda Asrianda
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13643

Abstract

Taxpayer compliance is a critical factor in increasing Property Tax (PBB) revenue. A low level of compliance can reduce local government revenue, making accurate classification methods essential for identifying taxpayer compliance. This study aims to compare the performance of Support Vector Machine (SVM) and Adaptive Boosting (AdaBoost) in classifying property taxpayer compliance. The dataset consisted of 58,998 property tax records collected from Lhokseumawe City, covering the districts of Banda Sakti, Blang Mangat, Muara Dua, and Muara Satu. The research stages included data preprocessing, label encoding, Min–Max normalization, data splitting using 80:20 and 70:30 scenarios, model training, and performance evaluation using accuracy, precision, recall, F1-score, and Area Under the Curve (AUC). Under the 80:20 data split, SVM achieved an accuracy of 92.89%, precision of 93.12%, recall of 98.81%, F1-score of 95.87%, and AUC of 80.59%, while AdaBoost achieved an accuracy of 92.86%, precision of 93.11%, recall of 98.78%, F1-score of 95.86%, and AUC of 80.76%. Under the 70:30 data split, SVM achieved an accuracy of 93.02%, precision of 93.18%, recall of 98.90%, F1-score of 95.95%, and AUC of 80.32%, whereas AdaBoost achieved an accuracy of 92.99%, precision of 93.18%, recall of 98.87%, F1-score of 95.93%, and AUC of 80.97%. Overall, both methods demonstrated comparable classification performance, while AdaBoost exhibited slightly better discriminative capability based on the AUC values.
Hybrid VMD-CNN1D Framework: Evaluating Decomposition’s Contribution to PM2.5 Prediction Dwi Yuwono; Arya Adhyaksa Waskita; Tukiyat Tukiyat
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13685

Abstract

Fine particulate matter (PM2.5) pollution in Jakarta reached an annual average of 37.3 µg/m³ in 2023, 7.4 times the WHO threshold, causing over 10,000 premature deaths annually. Accurate short-term prediction is essential for early-warning systems, yet two gaps remain common in decomposition-based deep learning literature: Variational Mode Decomposition (VMD) parameters are rarely selected via systematic sensitivity analysis, and prediction bias is rarely corrected explicitly. This study addresses both gaps using 32,144 PM2.5 observations from Jakarta (2015-2025). A grid search over 20 parameter combinations identified K=6, alpha=500 as optimal (reconstruction error 1.88%). Each of six IMFs was predicted independently using CNN1D, reconstructed additively, and bias-corrected using validation-set mean bias error. Decomposition, not model complexity, drove accuracy: a non-decomposed baseline reached only R²=0.4302, versus R²=0.9151 (RMSE=4.83 µg/m³) for the proposed framework. We further validated fixed- and adaptive-parameter variants (VMD, AVMD) across 5 independent runs. VMD-CNN1D achieved R²=0.9177±0.0173, RMSE=4.7346±0.5064, while AVMD-CNN1D (K=7 selected consistently) achieved R²=0.9238±0.0089, RMSE=4.5388±0.2649. Diebold-Mariano tests showed AVMD outperforming VMD in 4 of 5 runs (p<0.0001) with lower variance, though a paired t-test across runs was not significant (p=0.684). Ablation identified the lowest-frequency IMF as most critical, consistent with Jakarta's dry-season and land-fire pollution patterns, while residual analysis revealed heteroscedasticity as a limitation. These findings show that rigorous parameter selection, bias correction, and multi-run validation, not architectural complexity alone, make decomposition-based deep learning reliable for PM2.5 prediction, offering a reproducibility-aware baseline for a future Jakarta air-quality early-warning system.
Indonesian Cyberbullying Detection Using IndoBERTweet-BiGRU Model on Class-Imbalanced X (Twitter) Data Fajria Ulumin Nafiah; Aviolla Terza Damaliana; Kartika Maulida Hindrayani
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13686

Abstract

Cyberbullying on social media platforms, particularly X (formerly Twitter), has become a serious issue that negatively affects users' mental health and well-being. Automatic cyberbullying detection in Indonesian remains challenging due to the widespread use of informal language, slang, abbreviations, and highly imbalanced class distributions. This study proposes a hybrid deep learning model that integrates IndoBERTweet with a Bidirectional Gated Recurrent Unit (BiGRU) to improve cyberbullying detection performance on Indonesian tweets. A dataset of Indonesian tweets was collected from X and annotated using a multi-stage dual large language model (LLM) labeling strategy to reduce the time and effort required for manual annotation while maintaining label consistency. To address class imbalance, this study investigates the effectiveness of Focal Loss and label distribution modification through multiple experimental scenarios. The proposed approach was evaluated using accuracy, precision, recall, and F1-score. The best performance was achieved by combining Focal Loss with a modified four-class label configuration consisting of Rude and Vulgar Words, Sexual Harassment, Body Shaming and Hate Speech, and Non-Cyberbullying. This configuration obtained an accuracy of 0.93, precision of 0.90, recall of 0.90, and F1-score of 0.90. These findings demonstrate that integrating contextual language representations with sequential modeling, supported by an efficient LLM-assisted labeling strategy and class imbalance handling, provides an effective approach for Indonesian cyberbullying detection and offers a practical solution for large-scale social media content moderation.
AQUARA: Development of an AI-Assisted Integrated Web and Mobile Digital Platform for Fisheries Information Services and Aquaculture Business Analysis Nur Budi Nugraha; Rendi Rendi; Fauzan Ishlakhuddin
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13695

Abstract

Fish farmers in Indramayu Regency face difficulties in accessing fisheries information, evaluating aquaculture business feasibility, and communicating with the local fisheries authority because existing digital services are fragmented across multiple platforms. This study aims to develop AQUARA, an integrated web and mobile based platform that combines fisheries information, government services, aquaculture business analysis, discussion forums, a fish farmer directory, and AI assisted digital consultation. The platform was developed using a Research and Development (R&D) approach consisting of requirement analysis, system design, platform development, testing, and evaluation. System functionality was verified through Black Box Testing, non functional aspects were examined through performance, security, and compatibility testing, and usability was evaluated using the System Usability Scale (SUS). The testing results confirmed that all implemented features operated according to the specified requirements, the platform demonstrated acceptable response time, role based access control, and encrypted authentication, and it achieved a SUS score of 82.7 (Grade A), indicating excellent usability and high user acceptance. The integration of automated business feasibility analysis and the Dr. Fisho AI computer vision based preliminary fish disease detection feature within a single platform provides a practical solution for supporting the digital transformation of the aquaculture sector. The proposed platform improves information accessibility, supports business decision making, and strengthens collaboration among fish farmers and fisheries stakeholders.
Comparative Performance of Apriori, FP-Growth, and ECLAT for Menu Bundling Astriana Putri Kumala Dewi; Noor Latifah; Supriyono Supriyono
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13696

Abstract

Transaction data at Selaras Coffee and Space had not been systematically utilized to evaluate menu combinations or determine which association rule mining algorithm best suited the data characteristics. This study compares Apriori, FP-Growth, and ECLAT for generating menu-bundling recommendations. Sales records from 1–31 December 2025 were preprocessed by removing 950 operational transaction-item pairs, resulting in 6,213 transactions and 76 unique menus. The algorithms were evaluated on the same binary matrix using a minimum support of 0.01, a minimum confidence of 0.20, and a lift ratio greater than 1. The evaluation included parameter sensitivity, 30 repeated measurements of execution time and peak Python memory allocation, scalability using 25–100% of the transactions, and rule quality based on support, confidence, lift, leverage, conviction, and cosine similarity. All algorithms produced identical outputs of 68 frequent itemsets and five eligible rules. On the full dataset, ECLAT recorded the lowest mean execution time at 0.037701 s, followed by Apriori at 0.040419 s and FP-Growth at 0.069637 s. FP-Growth used the lowest mean peak memory at 1.026966 MB, while ECLAT showed the lowest runtime growth as the dataset size increased. The strongest rule was Mie Laksa → Air Mineral 330 Ml, with a lift of 2.755987. These findings show that no algorithm dominated every criterion: ECLAT offered the best full-data runtime and scalability, FP-Growth was the most memory-efficient, and the extracted rules provided measurable candidates for menu-bundling strategies.
Benchmarking Random Forest, Support Vector Machine, and XGBoost for Flood Risk Classification Using a Synthetic Dataset: A Case Study of Indramayu Regency Nur Budi Nugraha; Rendi Rendi; Yaqutina Marjani Santosa
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13708

Abstract

Flood risk assessment plays a critical role in disaster mitigation planning, yet flood classification studies in Indonesia have largely relied on a single machine learning algorithm without systematically evaluating alternative classifiers under identical experimental conditions. This study benchmarks Random Forest (RF), Support Vector Machine (SVM), and XGBoost for three-class flood risk classification (Low, Medium, and High) in Indramayu Regency, Indonesia, using a literature-informed synthetic dataset of 4,500 samples generated from seven flood-related features. To ensure a fair comparison, all models were trained and evaluated under an identical preprocessing, hyperparameter optimization, and validation framework, with Logistic Regression and Decision Tree included as baseline classifiers. Experimental results show that SVM achieved the highest predictive performance with an accuracy of 88.56% and a macro F1-score of 86.83%, followed closely by XGBoost (88.44% accuracy, 86.76% macro F1), while RF obtained 85.00% accuracy and an 83.57% macro F1-score. Statistical significance testing confirmed that SVM and XGBoost significantly outperformed RF, whereas no significant difference was observed between SVM and XGBoost. Feature importance analysis consistently identified rainfall and river distance as the two most influential predictors across all models. Although SVM provided the strongest overall classification performance, RF demonstrated competitive predictive capability with better generalization characteristics than XGBoost, supporting its suitability for operational flood mitigation decision-support systems where model interpretability and robustness are important. Because the benchmark is based on a synthetic dataset, further validation using real observational flood data is recommended before operational deployment.
Benchmarking YOLO26 Against YOLOv11 for Minority Class Waste Detection on an Augmented TACO Dataset Lingga Kurnia Ramadhani; Bajeng Nurul Widyaningrum
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13712

Abstract

This study benchmarks YOLO26 against YOLOv11 for detecting minority waste categories (Hazardous/B3 and Residue), evaluating whether YOLO26's Progressive Loss Balancing (ProgLoss) and Small-Target-Aware Label Assignment (STAL) mechanisms address class imbalance and small-object detection challenges. Both models were trained under identical conditions (50 epochs, 640×640) on a combined TACO, RecyBat24, and Food Waste Detection dataset (2,326 images, 70:15:15 split), across three scenarios: YOLOv11 baseline, YOLO26 default, and YOLO26 with class weighting and copy-paste augmentation. YOLO26 (default) achieved a marginally higher mAP@0.5:0.95 (0.393 vs 0.385) and modestly faster CPU inference (≈20% faster) than YOLOv11, with near-identical mAP@0.5 across scenarios. B3 performed consistently well (mAP@0.5 ≈ 0.99), and class weighting improved its detection robustness without raising overall mAP. Residue detection remained the weakest across all scenarios (mAP@0.5 0.076–0.085) and worsened under weighting, indicating that ProgLoss and STAL alone do not resolve its structural visual heterogeneity; this weak, stable Residue performance was confirmed reproducible across three additional training runs with different seeds (mAP@0.5:0.95 = 0.046 ± 0.001). These findings partially support the research hypothesis, positioning YOLO26 (default) as a favorable accuracy-efficiency trade-off for automated waste sorting, while Residue detection requires further data enrichment and augmentation strategies beyond architectural improvements alone.
Comparative Analysis of the SMART and ARAS Methods in a Decision Support System for Motorcycle Loan Applicant Eligibility Sri Kurnia; Dahlan Abdullah; Nurdin Nurdin; Munirul Ula; Muchlish Abdul Muthalib
Journal of Applied Informatics and Computing Vol. 10 No. 4 (2026): August 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i4.13714

Abstract

Motorcycle financing is one of the most popular consumer financing products in Indonesia. However, the credit eligibility assessment process at PT Mega Central Finance (MCF) Lhokseumawe Branch is still performed manually, making it susceptible to inconsistent evaluations and increasing the risk of non-performing loans. This study aims to implement and compare two Multi-Criteria Decision-Making (MCDM) methods, namely the Simple Multi-Attribute Rating Technique (SMART) and the Additive Ratio Assessment (ARAS), for evaluating motorcycle financing eligibility based on seven criteria, including age, monthly income, occupation, marital status, number of dependents, outstanding debt balance, and down payment (DP). The study utilized primary data from 223 loan applicants collected during the 2024 to 2025 period through interviews and document reviews using a total sampling technique. Criterion weights were determined using expert judgment from credit analysts. The results show that the SMART method classified 96 applicants as eligible and 127 applicants as not eligible, whereas the ARAS method classified 181 applicants as eligible and 42 applicants as not eligible, using a minimum eligibility threshold of 0.60. The difference in the results is primarily attributed to the distinct normalization mechanisms of the two methods. SMART is more sensitive to extreme values in highly weighted criteria, resulting in a more selective evaluation process, whereas ARAS produces a more balanced distribution of preference scores by normalizing criterion values relative to the optimal solution, leading to a more flexible assessment. The findings indicate that the two methods complement each other. SMART is recommended for organizations adopting a conservative credit approval policy, while ARAS is more suitable for organizations seeking to expand the number of eligible applicants while maintaining a balanced consideration of all evaluation criteria.

Page 100 of 101 | Total Record : 1006

 97   98   99   100   101 

Filter by Year

2017 2026


Reset
Filter By Issues
All Issue Vol. 10 No. 4 (2026): August 2026 Vol. 10 No. 3 (2026): June 2026 Vol. 10 No. 2 (2026): April 2026 Vol. 10 No. 1 (2026): February 2026 Vol. 9 No. 6 (2025): December 2025 Vol. 9 No. 5 (2025): October 2025 Vol. 9 No. 4 (2025): August 2025 Vol. 9 No. 3 (2025): June 2025 Vol. 9 No. 2 (2025): April 2025 Vol. 9 No. 1 (2025): February 2025 Vol. 8 No. 2 (2024): December 2024 Vol. 8 No. 1 (2024): July 2024 Vol. 7 No. 2 (2023): December 2023 Vol. 7 No. 1 (2023): July 2023 Vol. 6 No. 2 (2022): December 2022 Vol 6 No 1 (2022): July 2022 Vol 5 No 2 (2021): December 2021 Vol. 5 No. 2 (2021): December 2021 Vol 5 No 1 (2021): July 2021 Vol. 5 No. 1 (2021): July 2021 Vol 4 No 2 (2020): Desember 2020 Vol. 4 No. 2 (2020): Desember 2020 Vol 4 No 1 (2020): Juli 2020 Vol 3 No 2 (2019): Desember 2019 Vol 3 No 1 (2019): Juli 2019 Vol 2 No 2 (2018): Desember 2018 Vol 2 No 1 (2018): Juli 2018 Vol. 2 No. 1 (2018): Juli 2018 Vol 1 No 2 (2017): Desember 2017 Vol 1 No 1 (2017): Juli 2017 More Issue