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
 80   81   82   83   84 
Comparison of Naïve Bayes, Random Forest, and SVM Algorithm Performance in Analyzing Sentiment Regarding the Aceh Floods on Platform X Amalia Khoirunnisa; Novita Kurnia Ningrum
Journal of Applied Informatics and Computing Vol. 10 No. 2 (2026): April 2026
Publisher : Politeknik Negeri Batam

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30871/jaic.v10i2.12250

Abstract

Social media has become a means for the public to express their opinions on various events, including the floods in Aceh. This study aims to analyze public sentiment and compare the performance of the Naïve Bayes, Random Forest, and Support Vector Machine (SVM) algorithms in classifying sentiment on the X (Twitter) platform. In addition, this study also evaluates the effect of applying the Synthetic Minority Over-sampling Technique (SMOTE) on improving model performance.The dataset was collected using a crawling method utilizing Twitter Harvest on the X (Twitter) platform during the period from November 18, 2025, to January 5, 2026. The data collection process yielded 1,971 Indonesian-language data points, which after preprocessing stages such as text cleaning, stemming, and duplicate removal resulted in 1,874 data points. The dataset was then divided into 80% training data (1,499 data points) and 20% test data (375 data points). The analysis results show that the majority of public opinion has a positive sentiment of 77.9% (1460 data), while negative sentiment is 22.1% (414 data). The model evaluation results show that the application of SMOTE can improve the performance of the three algorithms. The algorithm with the best performance is Support Vector Machine (SVM) with an accuracy value of 83% and an F1-score of 75% after the application of SMOTE. Based on the results of the study, the SMOTE technique has been proven to help improve the model's ability to recognize minority classes, resulting in better classification performance.
Comparison of the Application of YOLOv5, YOLOv8, and YOLOv11 for Training Chinese Chess Objects Ahmad Mufid Panisti; Ryan Satria Wijaya; Eko Rudiawan Jamzuri; Anugerah Wibisana
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.v10i3.12252

Abstract

The use of YOLO (You Only Look Once)-based object detection algorithms has become one of the main approaches in visual object recognition and training. This study aims to compare the performance of three versions of YOLO, namely YOLOv5, YOLOv8, and YOLOv11, in training models to detect objects in Chinese chess images. The dataset used consists of images of Chinese chess boards and pieces in various positions and lighting variations. The training process was carried out using uniform parameters to ensure fair evaluation, including batch size, number of epochs, and image resolution. The performance of each model was evaluated based on detection accuracy, inference speed, and computational efficiency metrics. The results of the study show that each version of YOLO has specific advantages in certain aspects, such as training speed or detection precision. From the 7224 images used as the dataset, several results were obtained that were necessary in helping to compile this journal. These included Precision (YOLOv5: 0.94, YOLOv8: 0.96, YOLOv11: 0.98), Recall (YOLOv5: 0.93, YOLOv8: 0.98, YOLOv11: 0.96), and mAP (YOLOv5: 0.96, YOLOv8: 0.98, YOLOv11: 0.99). This study provides important insights into the advantages and disadvantages of each version of YOLO in the specific application of Chinese chess object recognition, as well as providing guidance for developers in choosing the model that suits their project needs. This study provides insights into the strengths and limitations of each YOLO version, offering guidance for selecting appropriate models in real-time Chinese chess object detection applications.
Design and Implementation of Marker-Based Augmented Reality to Enhance Public Awareness in Waste Sarah Faradilla; Caraka Aji Pranata
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.v10i3.12282

Abstract

Waste problem in Indonesia remains a complex issue for the community due to a low level of understanding and awareness about waste management and its impacts. On this research, we will aims to raise awareness and educate ranging from children, teenagers, to adults, about waste management using an Augmented Reality-based application that employs System Development Life Cycle method and evaluates the performance of Marker-Based Augmented Reality. Performance evaluation was conducted by testing the response time of marker recognition based on estimated distance and angle under normal and dim light intensity, as well as in outdoor lighting conditions. High-contrast visual markers with simple geometries were deliberately selected to maximize tracking stability. The test results showed that the system was able to recognize markers with an average response time of 0.31–0.93 seconds, which excellently meets the standard real-time AR response benchmark of under 1.0 second. Based on user assessment results through questionnaires distributed to 30 respondents and evaluated using the System Usability Scale method, the application received a perfect rating. Furthermore, preliminary pre-test and post-test evaluations indicated a significant improvement in users' comprehension when compared to conventional text-based educational methods, making it suitable for use as an interactive educational medium.
Detecting Financial Fraud Using Random Forest Machine Learning Peta Kahiomba Esther; Mabela Matendo Rostin; Kafunda Katalay Pierre; Mbuyi Mukendi Eugene; Mitelezi Mbila Jonathan; Albert Ntumba
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.v10i3.12539

Abstract

Financial fraud detection is a critical challenge for banking institutions facing increasingly sophisticated threats in digital transaction environments. This study investigates the application of the Random Forest algorithm for detecting fraudulent credit card transactions using the publicly available benchmark dataset from the Université Libre de Bruxelles (284,807 transactions, 0.172% fraud prevalence). Pre-processing includes QuantileTransformer normalization and SMOTE oversampling applied exclusively to the training set to address class imbalance. The model (n_estimators = 200) is validated using a stratified 70/30 split combined with 10-fold cross-validation to ensure robustness and prevent overfitting. Results yield an accuracy of 97%, ROC-AUC of 97%, precision of 95%, recall of 78%, and F1-score of 86%. Comparative evaluation against Logistic Regression, Support Vector Machine, and Gradient Boosting confirms that Random Forest provides the best balance between detection performance and computational efficiency (training: 45 s; inference: 0.3 ms per transaction). Feature importance analysis identifies transaction amount and PCA components V14 and V17 as the most discriminative variables. Confusion matrix analysis reveals 68 False Negatives and 142 False Positives out of 85,443 test samples. Despite these results, limitations include reduced feature interpretability due to PCA transformation, potential geographic data bias, and real-time production deployment challenges. This work confirms the relevance of Random Forest for financial fraud detection and opens perspectives toward hybrid deep learning and graph-based architectures.
Transformer-Based Abstractive Text Summarisation for Real-Time Web Applications: A Browser-Integrated System with REST API Architecture Zvinodashe Revesai; Belinda Ndlovu; Kudakwashe Maguraushe
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.v10i3.12559

Abstract

The exponential growth of digital textual content has intensified the need for efficient, accessible summarisation tools that support information processing across academic, professional, and research domains. While Transformer-based abstractive summarisation models have demonstrated strong performance in benchmark settings, their real-world deployment remains limited due to computational complexity and lack of user accessibility. This study presents a lightweight Transformer-based abstractive text summarisation system, operationalised as a Google Chrome extension and supported by a REST API, enabling seamless integration into everyday user workflows. The proposed system employs an encoder–decoder framework leveraging a pre-trained Transformer-based encoder and a sequence-to-sequence decoder with attention, fine-tuned on the CNN/Daily Mail dataset. Quantitative evaluation on the benchmark dataset achieved ROUGE-1, ROUGE-2, and ROUGE-L scores of 38.21, 16.54, and 35.12, respectively, demonstrating competitive performance relative to established neural baselines. To address the limitations of lexical evaluation metrics, a complementary human evaluation was conducted using a Likert-scale assessment across coherence, informativeness, and fluency, yielding mean scores above 4.0, thereby confirming the qualitative effectiveness of the generated summaries. In addition to model performance, system-level evaluation assessed functional correctness, latency, scalability, and usability within a real-world deployment context. The system demonstrated stable performance under concurrent usage, with an average response time of 4.2 seconds per request and positive user feedback, validating its practical applicability. The findings demonstrate that high-quality abstractive summarisation can be effectively operationalised within a lightweight, browser-integrated architecture, thereby bridging the gap between research-stage neural models and accessible end-user applications. This work contributes to deployment-oriented natural language processing by emphasising usability, modularity, and real-world integration as critical dimensions of system design.
Deep Learning and XGBoost for Pancreatic Cancer Survival Prediction: A Real-World Evaluation in a Resource-Constrained African Healthcare Setting Zvinodashe Revesai; Kudakwashe Maguraushe; Belinda Ndlovu
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.v10i3.12570

Abstract

Pancreatic cancer remains one of the most lethal malignancies worldwide, with persistently low survival rates and a pressing need for reliable prognostic tools to support treatment planning in resource-constrained healthcare environments. This study presents a structured comparative evaluation of Artificial Neural Network (ANN) and XGBoost classifiers for predicting 12-month survival using real-world clinical data from 569 pancreatic cancer patients treated at a public hospital in Zimbabwe between 2018 and 2023. The Cross-Industry Standard Process for Data Mining (CRISP-DM) framework guided data understanding, preprocessing, model development, and evaluation. A comprehensive preprocessing pipeline incorporating missing value imputation, outlier management, encoding, feature selection, and normalisation was applied, with all transformations derived exclusively from the training set to prevent data leakage. Models were trained using an 80/20 stratified split with cross-validated hyperparameter optimisation and evaluated on a strictly held-out test set using accuracy, precision, recall, F1-score, ROC analysis, and McNemar’s test. On the test dataset, the ANN model achieved 99% overall accuracy and 99% F1-score, outperforming XGBoost, which attained 90% accuracy and 90% F1-score. The performance difference was statistically significant (p < 0.05). Computational analysis demonstrated inference times below 3 milliseconds per sample, supporting feasibility for clinical deployment. While results indicate strong discriminative capacity within this single-centre dataset, external validation across multi-institutional cohorts is necessary to confirm generalisability. These findings suggest that supervised machine learning can provide clinically meaningful support for survival prediction in African tertiary healthcare settings. This study uniquely contributes a deployment-oriented, real-world evaluation of machine learning models within a resource-constrained African healthcare context, addressing a critical gap in the current oncology informatics literature.
From Web Extraction to Collaborative Filtering: An End-to-End Architecture for Reliable Recommendation Systems Lamanabwe Epus Hervé; Blaise Muhala Luhepa; Herman MATONDO MANANGA; Dieuleveut Nianga Kaya-Kaya; Benjamin Consolant Majegeza
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.v10i3.12592

Abstract

The growth of digital platforms has generated large volumes of Web-derived interaction data, but these data are often noisy, duplicated, incomplete, and temporally unstable. Recommendation quality therefore depends not only on the ranking model, but also on how extraction, validation, and temporal control are integrated upstream. This paper presents an end-to-end architecture in which Web extraction, schema normalization, cleaning, deduplication, anomaly quarantine, recency-aware processing, and recommendation generation are treated as a single operational pipeline. The contribution is not the use of hybrid recommendation alone, which is already common, but the explicit integration of these quality-control stages with temporally valid offline evaluation and system-level monitoring. Four recommendation strategies are studied within the same pipeline: global popularity, recency-weighted popularity, implicit matrix factorization, and a hybrid method that combines collaborative filtering with a recency-based fallback for sparse-user cold-start situations. Experiments are conducted on a realistic e-commerce dataset comprising approximately 50,000 users, 18,000 items, and 1.2 million interactions under a strict chronological 80/20 split. Evaluation includes Precision@K, Recall@K, NDCG@K, Coverage@K, sparse-user cold-start analysis, and system indicators. Results indicate that the hybrid approach achieves the best observed aggregate ranking performance under the present protocol, improves sparse-user robustness (Recall@10 = 0.158), maintains broad catalog coverage (38.9%), and remains operationally stable under the tested evaluation conditions (p95 latency = 48 ms; uptime = 99.7%). These findings support assessing recommendation quality as a property of the full data-to-recommendation pipeline rather than of the ranking algorithm alone.
Comparison of Feature Selection Methods in Classifying Poverty Levels in Indonesia Using Comparative Machine Learning Methods Nuniska Dwi Kamayanti; Ifnu Wisma Dwi Prastya; Sahri Sahri
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.v10i3.12604

Abstract

Poverty classification requires models capable of handling multidimensional data and imbalanced class distributions. This study aims to develop and compare several machine learning algorithms for classifying poverty levels in Indonesia, as well as to analyze the impact of feature selection and reduction methods on model performance. The study employs a comparative approach using a secondary dataset consisting of 514 districts/cities with socio-economic indicators and a binary target variable. The methodology includes data preprocessing, the application of Chi-Square, Pearson Correlation, and Principal Component Analysis (PCA), and the handling of imbalanced data using the Synthetic Minority Oversampling Technique (SMOTE). Modelling is conducted using Random Forest, Support Vector Machine (SVM), Logistic Regression, and Artificial Neural Network (ANN), with evaluation performed using Stratified K-Fold Cross Validation and metrics including accuracy, precision, recall, and F1-score. The results indicate that Chi-Square and Pearson Correlation outperform PCA, with Random Forest achieving the best performance, attaining an accuracy of 0.9854 and an F1-score of 0.9507, while effectively detecting the minority class. Therefore, the combination of Chi-Square and Random Forest is identified as the most effective approach in this study, as it produces a model that is accurate, stable, and capable of handling imbalanced data.
Perfomance Evaluation of Multi Layer Perceptron Algorithm in Rainfall Prediction Based on AWS Station Topography Characteristics Taswanda Taryo; Sajarwo Anggai; Hartanto Hartanto; Naufal Naufal
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.v10i3.12605

Abstract

Accurate rainfall prediction is crucial for mitigating hydrometeorological disasters in Indonesia, where weather patterns are highly volatile and heavily influenced by topography. This study evaluates the performance of MLP algorithm in predicting rainfall intensity using high-resolution AWS data. The evaluation compares model accuracy across three contrasting topographical characteristics: coastal area (Serang Maritime Station), open lowland area (Cengkareng Meteorological Station), and mountainous area (Citeko Meteorological Station). The MLP model utilized historical rainfall, temperature differences, and humidity differences as input variables, trained over a three-year dataset (2022-2024). The results indicate that the MLP model possesses high nowcasting capabilities with an average MAE of 0.29 mm. The coastal area yielded the best prediction performance with RMSE 1.10 mm and MAE 0.22 mm, due to stable wind circulation patterns. Conversely, the open lowland area showed the highest RMSE of 2.14 mm due to sudden extreme rainfall spikes, while the mountainous region proved the most challenging to model with MAE 0.34 mm, due to highly dynamic orographic effects. Furthermore, the study identifies a structural limitation where the MLP underestimates extreme peak amplitudes, caused by data sparsity and the conservative nature of the MSE loss function. Ultimately, while the MLP is highly reliable as an early warning system for light to moderate rainfall, it requires further architectural modifications to accurately estimate extreme heavy rainfall.
From Sparse Features to Transformers: A Statistical Evaluation of TF-IDF, FastText, and IndoBERT for Sentiment Classification of Indonesian Travel App Reviews Claudian Tikulimbong Tangdilomban; Syaifullah Yusuf Ramdhan; Muhammad Rizal; Cici Suhaeni; Bagus Sartono
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.v10i3.12610

Abstract

This study compares three text representation techniques, namely TF-IDF, FastText, and IndoBERT, in the sentiment classification task of Indonesian-language user reviews of travel applications. The dataset consists of 4.000 reviews from Traveloka and Tiket.com, collected through Google Play Store scraping and manually annotated with sentiment labels. Each representation technique was combined with three classification algorithms, namely Support Vector Machine, Logistic Regression, and Random Forest, resulting in nine experimental configurations. The evaluation was conducted using stratified 5-fold cross-validation with macro F1-score as the primary metric, supported by hyperparameter tuning using GridSearchCV, paired t-test statistical analysis, and Cohen’s d effect size measurement. The evaluation results indicate that IndoBERT generally achieved the best performance compared to TF-IDF and FastText. The best configuration was obtained by IndoBERT with Logistic Regression, achieving an F1-score of 0.9261 after tuning. The statistical test showed that the performance differences among text representations were statistically significant, with large effect sizes in the comparison between IndoBERT and TF-IDF (d = −1.36) and between IndoBERT and FastText (d = −1.10). Nevertheless, TF-IDF combined with Logistic Regression and SVM remained competitive, achieving an F1-score of approximately 0.892 after tuning, making it a lightweight and interpretable alternative. This study concludes that the quality of text representation has a more dominant influence on sentiment classification performance than the complexity of the classification algorithm.

Page 82 of 101 | Total Record : 1006

 80   81   82   83   84 

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