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
 85   86   87   88   89 
Neural Machine Translation of Balinese-Indonesian Using T5 Architecture with QLoRA Optimization Leonard Kumaro; I Gusti Ngurah Lanang Wijayakusuma; IPW Gautama
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12771

Abstract

This study proposes a Neural Machine Translation (NMT) system for Balinese–Indonesian translation by integrating the T5 architecture with Quantized Low-Rank Adaptation (QLoRA) to address low-resource constraints. The model is trained using the NusaTranslation dataset, consisting of 140,972 parallel sentence pairs, and optimized through parameter-efficient fine-tuning with 4-bit quantization and low-rank adaptation. Unlike conventional full fine-tuning, the proposed approach updates only a small fraction of parameters, significantly improving computational efficiency. Experimental results show that the proposed model achieves a BLEU score of 27.93%, ROUGE-1 of 18.94%, ROUGE-2 of 11.96%, ROUGE-L of 18.54%, and BERTScore F1 of 70.49%, indicating competitive performance in lexical, structural, and semantic evaluation aspects. These results demonstrate that QLoRA can maintain translation quality while reducing computational costs. Furthermore, qualitative analysis reveals that the model is capable of generating fluent and contextually appropriate translations, although challenges remain in handling complex sentence structures and linguistic variations. This study highlights the effectiveness of parameter-efficient fine-tuning for low-resource language translation and provides practical implications for developing scalable translation systems for regional languages.  
An End-to-End NLP Pipeline Combining Web Scraping, CamemBERT Fine-Tuning and Zero-Shot Biomedical Named-Entity Recognition for Early Epidemic Signal Detection from French-Language Online News Franklin Mwamba; Fiston Oshasha; Saint Jean Djungu; John Poma
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12773

Abstract

Epidemiological surveillance in the Democratic Republic of the Congo (DRC) suffers from reporting delays and limited digital infrastructure, while online French-language news provides a complementary real-time signal that current systems exploit poorly. We design, deploy, and rigorously evaluate an end-to-end natural-language processing (NLP) pipeline that integrates targeted web scraping of Congolese online media, sentence-level binary classification of epidemic content with a fine-tuned CamemBERT transformer, zero-shot biomedical named-entity recognition (CamemBERT-bio-GLiNER) restricted to disease, location and date, and an alerting dashboard built on a Django/Celery stack. The classifier was fine-tuned on a hybrid corpus of 11,433 sentences combining 1,433 manually annotated real news sentences and 10,000 template-generated synthetic sentences, and is benchmarked against two classical baselines (TF-IDF combined with Logistic Regression and Linear SVM) on an independent, manually annotated test set of 997 sentences (341 epidemic, 656 non-epidemic) constructed from a second scraping campaign performed three months later. We report precision, recall, F1, PR-AUC and ROC-AUC with 1,000-iteration bootstrap 95% confidence intervals. CamemBERT reaches F1 = 0.754 [0.717-0.787] and PR-AUC = 0.699 [0.644-0.756] for the epidemic class, while the Linear SVM baseline reaches F1 = 0.858 ± 0.037 and PR-AUC = 0.926 ± 0.024 in 5-fold stratified cross-validation, outperforming the transformer, a result we attribute to the dominance of synthetic data in the training corpus. A single-batch operational run of the full pipeline on MediaCongo processed 30 articles and 501 sentences in 37.5 s on a single GPU, producing 43 alerts that correctly captured the May 2026 Ebola Bundibugyo outbreak in Ituri. The system, the external benchmark, and all evaluation scripts are released as open source.
Kerangka Kerja Prediktif-Preskriptif Terintegrasi untuk Alokasi Ekspor Indonesia Menggunakan Klasifikasi Komoditas Hierarkis dan Optimasi Gurobi Zekko Jotty Nugroho; Farrikh Alzami; Amiq Fahmi; Agus Winarno; Siti Hadiati Nugraini; Muhammad Naufal; Ifan Rizqa
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12786

Abstract

Exports play a critical role in economic growth; however, existing studies often rely on aggregate data and lack integration between predictive analysis and prescriptive decision-making. This study aims to develop an integrated predictive–prescriptive framework for optimizing Indonesian export allocation using hierarchical commodity classification, multi-model forecasting, and linear programming optimization. Using United Nations Commodity Trade Statistics Database (2019-2024), commodities were classified into raw, semi-finished, and finished categories through a Large Language Model-based approach. Forecasting performance was evaluated using SARIMA, Holt-Winters, Random Forest, Gradient Boosting, and XGBoost based on Mean Absolute Percentage Error (MAPE). The results show that model performance varies across commodity stages, where Random Forest achieved 18.11% MAPE for volatile raw shrimp, while SARIMA obtained 8.07% MAPE for stable finished cassava leaves. The forecasting results were integrated into a Gurobi optimization model to generate export allocation strategies. The model increased export destination coverage for eucalyptus leaves from 79 to 130 countries and improved revenue for raw cassava leaves from USD 1,443,290 to USD 1,560,651 despite reduced export volume. This study contributes by explicitly integrating hierarchical commodity classification, multi-model forecasting, and prescriptive optimization into a unified decision-support framework, addressing the limitations of prior studies that primarily focus on forecasting without actionable optimization. However, the model remains sensitive to volatile trade data and does not yet incorporate external factors such as trade policies and regulatory dynamics, which may influence real-world applicability.
ConvNeXt with Transfer learning for Microscopic Canine Skin Disease Classification Made Ardika Mertha Putra Vaikuntha; I Gusti Ngurah Lanang Wijayakusuma
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12792

Abstract

Canine skin diseases represent a significant health concern in veterinary practice, with accurate diagnosis often requiring specialized expertise and microscopic examination. This study presents an implementation and evaluation of the ConvNeXt architecture for classifying microscopic images of four canine skin diseases: Demodex, Kokus, Malassezia, and Scabies. The dataset consists of microscopic images obtained from skin scraping preparations photographed under 400× digital microscopy and annotated by a certified veterinary. Two dataset scenarios were evaluated: a small dataset (356 images; Demodex: 104, Kokus: 47, Malassezia: 102, Scabies: 103) and a large dataset (2,963 images with near-balanced class distribution). Using transfer learning with pre-trained weights from ImageNet, the ConvNeXt model was evaluated across three input sizes (224×224, 180×180, 150×150). Augmentation balancing, including rotation, flipping, zoom, translation, shear, and color jitter, was applied to address class imbalance while preserving biological validity of morphological features Augmentation balancing was applied to address class imbalance, ensuring equal representation across all classes. Experimental results demonstrate that ConvNeXt with 224×224 input size trained on the large dataset achieved the best overall performance with 97.22% test accuracy, 0.9524 F1-score, 0.9624 Matthews Correlation Coefficient (MCC), and a perfect Area Under Curve (AUC) of 1.0000. Analysis of input size effects revealed that 224×224 is optimal for detecting small pathogens like Malassezia (3-8 μm) and Kokus (0.5-1 μm), while 150×150 better preserves spatial context for large pathogens such as Demodex (300 μm) and Scabies (200-400 μm). Visualization of feature maps provided insights into how the architecture extracts diagnostic features, producing dense, hierarchical feature representations that benefit from abundant data. This research demonstrates that transfer learning with the ConvNeXt architecture, combined with appropriate augmentation balancing, can achieve high classification accuracy for automated diagnosis support of canine skin diseases. However, clinical deployment requires further validation by veterinary and prospective clinical studies before these results can be considered clinically applicable.
Analysis of ResNet50 Model Response to Skin Tone Variations in Medical Image-Based Skin Disease Classification Made Ireina Dwiandra Divayanti; I Gusti Ngurah Lanang Wijayakusuma
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12794

Abstract

Skin disease classification with deep learning has shown promising performance, however many models are primarily trained on datasets featuring light skin tones, which raises question about their effectiveness across a variety of akin types. This study analyses the response of a ResNet50 model based on transfer learning when faced with different skin tones in order to classifying skin disease using medical images. The model was trained on the HAM100000 which categorized into three classes: benign, malignant, and non-neoplastic. A bias analysis was then performed using the Fitzpatrick 17k dataset. The model demonstrated an overall accuracy of 70.85%, a precision rate of 74.03%, and a recall rate of 65.51%. Further analysis showed that the model had a consistent pattern of predicting malignant cases, which increased with darker skin tones, rising from 54% to 68.3%. To mitigate this issue, a threshold tuning approach was applied. After mitigation, the model achieved an accuracy of 74%, a weighted F1-score of 76%, dan a macro F1-score of 55%. Fairness evaluation after mitigation showed tha the proportion of malignant predictions increased from 56,3% in FST I to 69,9% in FST VI. These findings suggest that threshold tuning can improve classification performance and partially reduce bias intensity.
Robotic Bin-Picking Object Detection Using YOLOv11-OBB with SAM2 Auto-Annotation Very Very; Eko Rudiawan Jamzuri
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12806

Abstract

Robotic bin-picking requires accurate detection of randomly oriented objects under cluttered conditions. Conventional axis-aligned bounding boxes struggle to distinguish adjacent objects, motivating the use of oriented bounding boxes (OBB). This paper proposes a complete pipeline for bin-picking object detection that combines the Segment Anything Model 2 (SAM2) with YOLOv11-OBB. A three-stage auto-annotation pipeline first applies a YOLOv11s horizontal bounding-box detector to localize each object and assign its class label. SAM2 then performs automatic instance segmentation within each detected bounding-box region without requiring manual point prompts. Last, the resulting masks are converted to OBB annotations via minimum-area rectangle fitting, reducing annotation time by approximately 877× compared with manual labeling. YOLOv11-OBB featuring C2PSA attention, C3k2 convolution blocks, and an anchor-free rotated detection head is trained for 300 epochs on a purpose-built dataset of three cylindrical object classes (white, black, and red) captured in a UR3 collaborative-robot workspace. Experiments demonstrate an overall mAP@0.5 of 0.995 and mAP@0.5:0.95 of 0.949, with an inference time of 138 ms per frame on a consumer CPU. The results indicate that the proposed pipeline is well-suited for oriented object detection in industrial bin-picking applications.
Flood Status Prediction Based on Water Level Data Using Machine Learning Models Aisyah Putri Widyastuti; Sindhu Rakasiwi
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12809

Abstract

Flooding is one of the hydrometeorological disasters that frequently occurs in Indonesia and causes various social and economic losses. This study aims to compare the performance of five machine learning algorithms, namely Random Forest, Extreme Gradient Boosting (XGBoost), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), and Logistic Regression, as well as one Long Short-Term Memory (LSTM) deep learning model in predicting flood status based on water level data from seven observation posts in the DKI Jakarta area and its surroundings. The research stages include data preprocessing, handling unbalanced data using ADASYN, hyperparameter tuning, and evaluation using accuracy, precision, recall, and F1-score. To avoid data leakage, the data division process is carried out before preprocessing and oversampling. The results show that XGBoost produces the best performance with 96.0% accuracy, 95.5% precision, 96.9% recall, and 96.2% F1-score after hyperparameter tuning. The LSTM model also demonstrated competitive performance with an accuracy of 94.5% and an F1-score of 94.5%. Learning curve analysis showed that all models exhibited normal learning patterns with no indication of data leakage. The results indicate that XGBoost and LSTM have good potential for application in flood early warning systems based on water level data.
Comparative Analysis of ConvNeXt and EfficientNet-B0 for Early Leukemia Detection through Blood Cell Classification with Grad-CAM Interpretability Made Andini Maharani; I Gusti Ngurah Lanang Wijayakusuma
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12816

Abstract

Leukemia is a hematological malignancy requiring early and accurate diagnosis for optimal patient outcomes, yet conventional microscopic examination remains subjective, time-consuming, and prone to inter-observer variability. This study presents a comprehensive comparative analysis of two state-of-the-art deep learning architectures EfficientNet-B0 and ConvNeXt-Tiny for multi-class blood cell classification aimed at early leukemia detection. Using a balanced dataset of 5,000 microscopic images encompassing five clinically significant classes (basophil, erythroblast, monocyte, myeloblast, and segmented neutrophil), both models were trained and evaluated under identical configurations with extensive data augmentation. Performance assessment encompassed classification metrics, inference speed, and interpretability through Gradient-weighted Class Activation Mapping (Grad-CAM) validated by randomization and occlusion tests. Results demonstrated that both architectures achieved exceptional performance with F1-scores exceeding 98% (EfficientNet-B0: 0.9893, ConvNeXt: 0.9920). ConvNeXt exhibited superior accuracy in distinguishing morphologically similar cells, attributed to its larger receptive fields and advanced architectural design, while EfficientNet-B0 demonstrated dramatic computational advantages with 134 FPS throughput and a compact model size of 18.3 MB six times smaller than ConvNeXt. Grad-CAM visualizations confirmed that both models focus on clinically relevant features including nuclear morphology and cytoplasmic characteristics, validated by low correlation with randomized models (average correlation <0.28) and significantly larger confidence drops during important region occlusion (6-18× greater than random occlusion). The findings establish evidence-based guidelines for model selection, ConvNeXt for high-precision diagnostic applications and EfficientNet-B0 for large-scale screening and edge deployment. This research contributes foundational evidence toward the development of transparent, reliable, and efficient computer-aided diagnosis systems, though prospective clinical validation on multi-institutional datasets remains an important direction for future work.
Performance Analysis of BERT and CLIP Models in Multimodal Sentiment Classification of Short Video Content Very Setiawan; Endang Anggiratih; Najwa Eka Putriningsih; Jonathan Eldo Kusuma
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12822

Abstract

The rapid growth of short video platforms such as YouTube Shorts has increased the need for effective sentiment analysis methods capable of capturing public opinion in multimodal content. This study analyzes and compares the effectiveness of unimodal and multimodal approaches for sentiment classification of Indonesian short videos, focusing on IndoBERT for text-based modeling and CLIP for multimodal integration. The main objective is to investigate whether incorporating visual information alongside textual data can improve sentiment classification performance compared to a text-only approach. The dataset consists of 1,128 Indonesian short videos collected from YouTube Shorts. Audio data are transcribed into text using Automatic Speech Recognition (ASR), while visual information is represented using video thumbnails. Sentiment labels are automatically categorized into three classes (positive, neutral, and negative) using a pre-trained IndoBERT model. In the training phase, the unimodal approach relies solely on textual features extracted by IndoBERT, whereas the multimodal approach integrates textual and visual features using CLIP through feature-level fusion. Model performance is evaluated using accuracy, precision, recall, F1-score, and computational time analysis. The experimental results show that the unimodal text-based model outperforms the multimodal model, achieving higher accuracy (86% vs 82%) and better overall evaluation metrics. IndoBERT also demonstrates better convergence behavior compared to English BERT, with training accuracy increasing from 0.76 to 0.86 and validation accuracy from 0.77 to 0.88, along with lower loss values. In contrast, English BERT achieves lower performance, with training accuracy rising from 0.72 to 0.79 and validation accuracy from 0.73 to 0.80. Furthermore, the unimodal approach requires significantly less computation time (18 minutes compared to 35 minutes). These findings indicate that textual information plays a dominant role in sentiment expression in Indonesian short video content, while visual features increase computational complexity without significant performance gains.
Arduino Mega-Based Transporter Robot for Box Handling in a Maze Arena Abdul Jalil; Suwatri Jura; A.Edeth Fuari Anatasya; Mursalim Sawawi; Pujianti Wahyuningsih
Journal of Applied Informatics and Computing Vol. 10 No. 3 (2026): June 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i3.12825

Abstract

The objective of this study was to develop a transporter robot designed to move boxes from one location to another within an Arduino Mega-based maze arena. The problems addressed by this transporter robot include autonomous navigation in the maze area, detection of boxes based on their colors, transferring boxes from one location to another, and climbing inclined surfaces. The method used to control the transporter robot was based on input from the TCS3200 color sensor and ultrasonic sensors, which were employed to detect box objects and navigate the robot. The Arduino Mega was used to process sensor data and control the robot according to the sensor inputs. A servo motor was utilized to actuate the robot arm and gripper, while DC motors were used to drive the wheels of the transporter robot. The results of this study indicate that the transporter robot was able to complete the mission of navigating the maze and transferring box objects to their designated locations, achieving a success rate of up to 70%, with an average mission completion time of 6.8 minutes, while unsuccessful mission attempts required up to 9.6 minutes.

Page 87 of 101 | Total Record : 1006

 85   86   87   88   89 

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