cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Edi Sutoyo
Contact Email
journalijadis@gmail.com
Phone
+62895410194922
Journal Mail Official
info@ijadis.org
Editorial Address
Indonesian Scientific Journal (Jurnal Ilmiah Indonesia) Jl. Pasar Atas No 3, Kompleks Setramas Kota Cimahi, Bandung
Location
Unknown,
Unknown
INDONESIA
International Journal of Advances in Data and Information Systems
Published by Indonesian Scientific Journal
ISSN : -     EISSN : 27213056     DOI : https://doi.org/10.25008/ijadis
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
International Journal of Advances in Data and Information Systems (IJADIS) (e-ISSN: 2721-3056) is a peer-reviewed journal in the field of data science and information system that is published twice a year; scheduled in April and October. The journal is published for those who wish to share information about their research and innovations and for those who want to know the latest results in the field of Data Science and Information System. The Journal is published by the Indonesian Scientific Journal. Accepted paper will be available online (free access), and there will be no publication fee. The author will get their own personal copy of the paperwork. IJADIS welcomes all topics that are relevant to data science, and information system. The listed topics of interest are as follows: Data clustering and classifications Statistical model in data science Artificial intelligence and machine learning in data science Data visualization Data mining Data intelligence Business intelligence and data warehousing Cloud computing for Big Data Data processing and analytics in IoT Tools and applications in data science Vision and future directions of data science Computational Linguistics Text Classification Language resources Information retrieval Information extraction Information security Machine translation Sentiment analysis Semantics Summarization Speech processing Mathematical linguistics NLP applications Information Science Cryptography and steganography Digital Forensic Social media and social network Crowdsourcing Computational intelligence Collective intelligence Graph theory and computation Network science Modeling and simulation Parallel and distributed computing High-performance computing Information architecture
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 195 Documents
 16   17   18   19   20 
Towards Robust Cross-Dataset Pothole Detection Through Multi-Dataset Pretraining Hanifatus Sa’diyah Widihasaniputri; Oddy Virgantara Putra; Murhadi Murhadi
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1551

Abstract

Pothole detection based on deep learning has achieved high detection accuracy; however, most existing studies evaluate models using the same dataset for both training and testing, providing limited evidence of robustness under unseen data distributions. This study investigated the cross-dataset generalization capability of YOLOv8n using three publicly available pothole datasets with different visual characteristics: the Multi-Weather Pothole Dataset (MWPD), the Jaygala dataset, and the Andrew dataset. The proposed framework evaluated same-dataset and cross-dataset detection performance, quantified robustness through generalization gap analysis, examined the influence of dataset characteristics, and assessed the effectiveness of multi-dataset pretraining. Experimental results showed that the Andrew dataset achieved the highest same-dataset performance (mAP@50 = 0.816) but also exhibited the largest generalization gap (0.246), indicating limited robustness across datasets. In contrast, multi-dataset pretraining reduced the generalization gap for MWPD from 0.093 to 0.048, demonstrating improved cross-dataset robustness, although the improvement was not consistent across all datasets. These findings indicate that same-dataset accuracy alone is insufficient for evaluating model robustness and that cross-dataset evaluation provides a more realistic assessment of deployment performance in heterogeneous road environments.
Integrating Holt-Winters Exponential Smoothing and SAW for Distribution Priority Optimization Muhammad Rohman Irsyadi; Mohammad Idhom; Afina Lina Nurlaili
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1561

Abstract

Effective distribution planning requires both accurate demand forecasting and objective prioritization mechanisms to ensure operational efficiency and service reliability. At CV. Citra Nalar Teknologi, distribution scheduling was previously conducted manually without incorporating predictive demand analysis, resulting in inconsistent and subjective prioritization decisions. This study proposes an integrated decision support framework that combines Holt–Winters Exponential Smoothing (HWES) for demand forecasting and Simple Additive Weighting (SAW) for multi-criteria distribution ranking. Monthly sales data from January 2024 to December 2025 (24 periods) were analyzed using the additive HWES model to capture level, trend, and seasonal components. The forecasting results achieved MAPE values ranging from 3.82% to 7.47%, supported by low RMSE, MAE, and sMAPE, indicating high predictive accuracy. Comparative evaluation further shows that HWES outperforms baseline methods, including Moving Average and Seasonal Naive. The forecasted demand was then incorporated as a primary criterion in the SAW model, alongside delivery distance, customer priority level, and stock availability. The proposed framework was evaluated using two sets of actual customer orders (January 4–5 and January 6–7, 2026). The results demonstrate that the integration produces consistent, data-driven distribution priorities and improves decision objectivity and transparency compared to manual scheduling. This study contributes by integrating time series forecasting with multi-criteria decision-making into a unified framework for practical distribution optimization.
Spatio-Temporal Forest and Land Fire Risk Modeling in Sumatra Using Atmospheric-Edaphic Integration via Bivariate Fuzzy C-Means Ade Firmansyah; Dedi Darwis
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1564

Abstract

The study focused on the persistent forest and land fires in Sumatra and the conventional early warning systems that showed limitations in capturing the dynamics of the soil-atmosphere and tended to overestimate risk zones during the peak periods of fires. Existing multivariate systems also showed limitations when there was a lack of integration between atmospheric water demand and edaphic (soil) vulnerability, resulting in lower spatial efficiency in the risk area. This paper presented a new bivariate physics-based model called the VPD-LVI Integrated Fuzzy (VLIF) Model, which integrated Vapor Pressure Deficit (VPD) and Land Vulnerability Index (LVI). For the VLIF-Model, to ensure a high level of spatial detail, the model processed 2,614,056 spatiotemporal observations, representing a grid resolution of 0.1° over a two-year period (2023–2024). The model showed acceptable structural stability at k=3 (FPC = 0.6137), with distinct risk zoning contrasts. Furthermore, validation against 61,015 VIIRS thermal anomalies indicated the model's predictive reliability with an ROC-AUC of 0.8288 and a Brier Score of 0.0169, suggesting good discrimination and calibration. In the spatial efficiency analysis, 17.80% of the area categorized as 'high' risk captured 62.28% of actual thermal anomaly grids, achieving a lift factor of 3.50 and a recall of 88.91%. The VLIF-Model provided clearer contouring of peak fire zones and enabled a more targeted spatial risk intelligence layer for specific tropical peatland mitigation efforts.
Robust Clustering Analysis of Village Potential Data in South Sumatra Using MMCD-Based Mahalanobis Distance Dwi Fitrianti; Anwar Fitrianto; Anang Kurnia
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1568

Abstract

Village potential data often contain outliers that can distort clustering results when classical distance measures are applied. This study evaluates the effectiveness of the Robust Mahalanobis Distance based on the Matrix Minimum Covariance Determinant (RMD-MMCD) for clustering village potential data in South Sumatra Province, Indonesia. The proposed approach is compared across K-means, K-medoids, DBSCAN, and DB-Kmeans algorithms, with performance assessed using the Silhouette coefficient, Dunn index, Davies–Bouldin index, Rand Index, and Adjusted Rand Index. The findings demonstrate that incorporating robust covariance estimation through MMCD improves clustering stability and enhances resistance to outliers while preserving the inherent matrix structure of multivariate data. Notable differences in cluster composition are observed primarily in the accessibility and transportation and public service dimensions. These results confirm the advantage of robust distance measures for producing more reliable and structurally consistent clustering solutions in village potential data.
Impact of DTW-Based K-Medoids and Fuzzy C-Means Clustering on the Forecasting Accuracy of ARIMA, TCN, and Hybrid Models in Anomalous Time Series Meavi Cintani; I Made Sumertajaya; Yenni Angraini
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1569

Abstract

This study investigates the impact of Dynamic Time Warping (DTW)-based clustering on forecasting accuracy in anomalous time series data. Monthly export values from 30 provinces in Indonesia are clustered using K-Medoids and Fuzzy C-Means (FCM) based on DTW distances reduced through Multidimensional Scaling (MDS). Cluster validation results indicate that FCM demonstrates better stability under anomalous conditions, with a Silhouette Score of 0.62 and a Davies–Bouldin Index of 0.57, compared to K-Medoids with a Silhouette Score of 0.61 and a Davies–Bouldin Index of 0.58. Forecasting performance is systematically evaluated through an expanding-window scheme using standalone ARIMA and Temporal Convolutional Network (TCN) models as baselines against a hybrid ARIMA–TCN approach. The results show that the hybrid ARIMA–TCN model achieves the lowest Mean Absolute Percentage Error (MAPE) in clusters with relatively stable patterns by effectively combining linear and non-linear components. However, for clusters characterized by higher volatility and irregular patterns, the standalone TCN model yields better forecasting accuracy. Furthermore, FCM clustering produces better overall forecasting accuracy, with an average MAPE of 7.11%, compared to 8.42% for K-Medoids. The relatively small difference in evaluation results between clean and empirical data suggests that the proposed DTW–MDS–clustering–forecasting framework maintains consistent performance in the presence of anomalies. The final model is then applied to generate export forecasts for the next 12 periods.
Evaluation of Resampling Methods in Multigroup Truncated Spline Semiparametric Path Analysis: A Simulation Study of Artificial Intelligence in Student Learning M. Dziqri Nur Rohiim; Adji Achmad Rinaldo Fernandes; Achmad Efendi; Mujiono Mujiono; Kamelia Hidayat
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1577

Abstract

This study aims to evaluate the performance of group-specific resampling in a truncated spline-based semiparametric multigroup path analysis model with heterogeneous relationship structures across groups. The study used a simulation approach based on empirical patterns in AI Literacy data. The multigroup concept is represented by the interaction of dummy variables within a single semiparametric model, thereby allowing for differences in the structures of linear and nonlinear relationships across data groups. The evaluation was conducted across four resampling method combinations: bootstrap-bootstrap, jackknife-jackknife, bootstrap-jackknife, and jackknife-bootstrap. Method performance was evaluated using the average bias, average standard error, standard error ratio, and coefficient of determination ( ). The results indicate that all method combinations yield relatively consistent average bias values. However, the jackknife-jackknife combination produce the smallest average standard error and standard error ratio, thereby providing better inference stability compared to the other combinations. The results also indicate that the jackknife method tends to be more adaptive for nonlinear relationships based on truncated splines. Thus, the selection of resampling methods for semiparametric multigroup models must consider the characteristics of the relationships within each data group to yield more stable and accurate inferences.
Traffic Sign Recognition using Capsule Network Mutaqin Akbar; Agus Sidiq Purnomo; Supatman Supatman; Bernadete Deta
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1599

Abstract

Traffic sign recognition (TSR) is critical for systems that rely on its output to inform downstream decisions. This study investigates TSR using Capsule Network (CapsNet), an advancement over the convolutional neural network (CNN) that captures spatial relationships between image features, conferring robustness to affine transformations. The proposed architecture comprises a convolutional layer (256 filters, 9X9 kernel, stride 1, ReLU activation), a primary capsule layer (32 channels of 6X6 capsules, each an 8-dimensional vector), and a class capsule layer (one 16-dimensional capsule per target class). The model was evaluated on both original and augmented datasets, the latter incorporating rotations ranging from -5 degrees to +5 degrees. On the original dataset, CapsNet achieved 100% training and testing accuracy with a training loss of 0,0048 at epoch 20. On the augmented dataset, the model achieved 100% training accuracy (loss: 0,0056) and 98% testing accuracy (5 misclassifications). Compared to multi-scale CNN (MS-CNN), which produced 7 misclassifications on the augmented dataset, CapsNet demonstrated superior consistency and robustness under affine transformations. These findings suggest that CapsNet is a viable and effective architecture for real-world TSR applications.
Tourist Satisfaction Analysis of East Aceh Coastal Ecotourism Using Stacking Machine Learning and GUI Integration Imam Gunanjar; Ryanda Saputra; Shary Armonitha Lusiana; Martahadi Mardhani; M. Khairul Anam
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1614

Abstract

Tourist satisfaction is a key indicator for evaluating service quality and improving destination management in coastal ecotourism. East Aceh has several coastal tourism destinations with strong ecotourism potential, but tourist opinions are not always systematically analyzed for service improvement. This study analyzes tourist satisfaction in East Aceh coastal ecotourism using a stacking machine learning approach and integrates the best-performing model into a Graphical User Interface (GUI). The dataset consists of 1,679 tourist opinions collected from several coastal tourism objects in East Aceh and labeled into three classes: Satisfied, Neutral, and Dissatisfied. To prevent data leakage, the dataset was first divided into training and testing sets using a 60:40 split; TF-IDF fitting and SMOTE resampling were then applied only to the training data, while the testing set was kept unchanged. The evaluated base models include Naive Bayes, Random Forest, Support Vector Machine, and XGBoost, with Logistic Regression used as the stacking meta-model. The results show that the stacking model with SMOTE achieved the best performance with 87.05% accuracy, 87% precision, 87% recall, and 87% F1-score, outperforming the individual models in this experimental setting. However, the improvement over stacking without SMOTE was modest and was not statistically tested. The best-performing model was implemented in a GUI-based prototype that demonstrates how tourist opinions can be uploaded and classified into satisfaction categories. The prototype provides a preliminary interface for presenting classification results and has not yet been validated as an operational decision-support system.
Evaluating GPT-4o-based Data Augmentation for Imbalanced Multiclass Sentiment Classification of GoPay Reviews Using IndoBERT-LoRA Muhammad Yusran; Farit Mochamad Afendi; Anwar Fitrianto
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1620

Abstract

This study evaluated GPT-4o-based data augmentation for imbalanced multiclass sentiment classification of GoPay user reviews using IndoBERT-LoRA. The main problem addressed in this study was the limited representation of minority sentiment classes, particularly the neutral class, which could reduce the model’s ability to recognize all sentiment categories proportionally. The dataset consisted of 16,955 Google Play Store reviews that were manually labeled into positive, neutral, and negative classes. Two augmentation strategies were compared, namely prompt-based augmentation and fine-tuning augmentation. The generated synthetic data were evaluated using novelty, diversity, duplication, and manual validation of sampled reviews before being incorporated into the training data. The IndoBERT-LoRA model was trained under four scenarios: baseline, class weighting, prompt-based augmentation, and fine-tuning augmentation. The results showed that fine-tuning produced better lexical-level quality indicators, as indicated by more stable novelty and diversity scores and a lower duplication rate. Both augmentation strategies improved macro recall and macro F1-score compared with the baseline and class weighting scenario. The largest improvement occurred in the neutral class, where recall increased from 0.5633 to 0.7801 with prompt-based augmentation and to 0.8133 with fine-tuning augmentation. These findings indicate that GPT-4o-based augmentation improved minority-class recognition, although the improvement involved a trade-off between recall, precision, and implementation cost.
Performance Evaluation of the XGBoost Method for Measuring Uncertainty in Small Area Estimation Fida Fariha Amatullah; Khairil Anwar Notodiputro; Anwar Fitrianto
International Journal of Advances in Data and Information Systems Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems
Publisher : Indonesian Scientific Journal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59395/ijadis.v7i2.1621

Abstract

This study looks at using Small Area Estimation (SAE) to assess per capita spending in subdistricts of Jambi Province. Direct estimators in small areas usually show high variance because of small sample sizes, so model-based methods are needed. The Fay–Herriot model based on EBLUP–FH was used as the primary indirect estimation method, while XGBoost served as a flexible machine learning benchmark. These approaches show fundamentally different methods. EBLUP-FH acts as a model-based estimator with a clear sampling-error framework, while XGBoost functions as a prediction model. Its uncertainty is evaluated through bootstrap resampling, so their standard errors can't be directly compared. Before modeling, data was cleaned and winsorized to lessen outlier impact. The normality assumption for the sampling error in EBLUP-FH was breached, and a logarithmic transformation was used which improved the model components' distribution. XGBoost achieved the smallest bootstrap-based standard error, indicating reduced variability in predictions across resamples rather than greater estimation accuracy. Subdistrict-level analysis revealed that XGBoost tends to produce homogeneous estimates that fail to capture contextual socioeconomic variation, confirming that a small bootstrap standard error does not necessarily indicate accurate small-area estimates.

Page 19 of 20 | Total Record : 195

 16   17   18   19   20 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol. 7 No. 2 (2026): August 2026 - International Journal of Advances in Data and Information Systems Vol. 7 No. 1 (2026): April 2026 - International Journal of Advances in Data and Information Systems Vol. 6 No. 3 (2025): December 2025 - International Journal of Advances in Data and Information Syste Vol. 6 No. 2 (2025): August 2025 - International Journal of Advances in Data and Information Systems Vol. 6 No. 1 (2025): April 2025 - International Journal of Advances in Data and Information Systems Vol. 5 No. 2 (2024): October 2024 - International Journal of Advances in Data and Information System Vol. 5 No. 1 (2024): April 2024 - International Journal of Advances in Data and Information Systems Vol. 4 No. 2 (2023): October 2023 - International Journal of Advances in Data and Information System Vol. 4 No. 1 (2023): April 2023 - International Journal of Advances in Data and Information Systems Vol. 3 No. 2 (2022): October 2022 - International Journal of Advances in Data and Information System Vol. 3 No. 1 (2022): April 2022 - International Journal of Advances in Data and Information Systems Vol. 2 No. 2 (2021): October 2021 - International Journal of Advances in Data and Information System Vol. 2 No. 1 (2021): April 2021 - International Journal of Advances in Data and Information Systems Vol. 1 No. 2 (2020): October 2020 - International Journal of Advances in Data and Information System Vol. 1 No. 1 (2020): April 2020 - International Journal of Advances in Data and Information Systems More Issue