cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Husni Teja Sukmana
Contact Email
husni@bright-journal.org
Phone
+62895422720524
Journal Mail Official
jads@bright-journal.org
Editorial Address
Gedung FST UIN Jakarta, Jl. Lkr. Kampus UIN, Cemp. Putih, Kec. Ciputat Tim., Kota Tangerang Selatan, Banten 15412
Location
Kota adm. jakarta pusat,
Dki jakarta
INDONESIA
Journal of Applied Data Sciences
Published by Bright Publisher
ISSN : -     EISSN : 27236471     DOI : doi.org/10.47738/jads
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management
One of the current hot topics in science is data: how can datasets be used in scientific and scholarly research in a more reliable, citable and accountable way? Data is of paramount importance to scientific progress, yet most research data remains private. Enhancing the transparency of the processes applied to collect, treat and analyze data will help to render scientific research results reproducible and thus more accountable. The datasets itself should also be accessible to other researchers, so that research publications, dataset descriptions, and the actual datasets can be linked. The journal Data provides a forum to publish methodical papers on processes applied to data collection, treatment and analysis, as well as for data descriptors publishing descriptions of a linked dataset.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 543 Documents
 46   47   48   49   50 
Dynamic Model for Budget Allocation in via Multi-Criteria Optimization Gulbakyt, Sembina; Almaz, Abdualiyev; Saule, Sagnayeva; Suhrab, Yoldash
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.935

Abstract

This research introduces a dynamic multi-criteria optimization framework for fair budget distribution across four districts in Kazakhstan’s Almaty region. Its main objective is to promote transparency, equity, and efficiency in allocating a constrained regional budget of 42,656,543 thousand tenge across seven activity areas (AA): education, healthcare, transport, infrastructure, digitalization, culture, and ecology. The framework incorporates four weighted criteria: citizen satisfaction (0.2 weight), strategic development priorities (0.2), basic needs fulfillment (0.3), and urbanization level (0.3). Two optimization techniques were employed: Sequential Quadratic Programming (SQP) in MATLAB, converging in 100 iterations with an objective function value of 18,519,864.85 thousand tenge, and Genetic Algorithm (GA) in Python, achieving a slightly higher value of 18,520,000.00 thousand tenge after 500 generations. The minimal difference of 135.15 thousand tenge (0.0007% of the budget) underscores the reliability of both methods. All seven sectors received funding, with healthcare (22.05%) and transport (21.11%) allocated the largest portions, and education (7.03%) the smallest. Fairness is evidenced by a standard deviation of sectoral shares at 5.69%, a coefficient of variation of 0.398, and a Gini coefficient of 0.223. Participatory budgeting was simulated using synthetic citizen voting data derived from demographic factors. Visualizations depict the optimization process’s convergence and budget distribution across feasible solutions. A proposal for pilot testing within Kazakhstan’s e-government system (Egov) has been submitted to the Ministry of Digital Development. Future enhancements will include explainable AI, stakeholder-driven weight adjustments, and real demographic and budgetary data to foster transparency and public confidence. This framework provides a scalable, data-driven approach to participatory budgeting, harmonizing strategic objectives, socio-economic demands, and citizen preferences. SQP and GA methods achieved near-optimal solutions with objective function values of 18,519,864.85 and 18,520,000.00 thousand tenge, respectively. The 135.15 thousand tenge difference (0.0007% of the budget) is negligible, confirming their robustness.
Enhancing VIX Shock Prediction via a Probabilistic Attention Transformer Kim, Jin Su; Lee, Zoonky
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.947

Abstract

This study proposes a Probabilistic-Attention Transformer for forecasting abrupt shifts in the Volatility Index (VIX), advancing volatility modeling by directly embedding externally estimated shock probabilities into the attention mechanism. The core idea is to modify similarity-based attention scores with daily shock probabilities derived from stochastic diffusion equations, thereby enhancing the model’s sensitivity to extreme-value dynamics. The primary objective is to improve predictive accuracy during market stress, particularly under warning (20 ≤ VIX ≤ 30) and shock (VIX 30) regimes where conventional models often fail. Using 35 years of historical VIX data (1990–2024), the framework is benchmarked against GARCH (1,1) and a standard Transformer under distinct volatility regimes. Empirical findings show that the proposed model consistently outperforms alternatives: during warning regimes, prediction error is reduced by over 40% relative to both benchmarks, while in shock regimes, improvements exceed 50%, with performance gains validated by Diebold–Mariano tests at the 1% significance level. These results demonstrate both statistical and practical significance, offering risk managers and investors more reliable forecasts during periods of heightened market instability. The contribution of this research lies in providing not only empirical evidence of improved predictive performance but also a generalizable framework for integrating probabilistic indicators into deep learning architectures. The novelty is in showing that probabilistic weighting of attention can transform standard neural architectures into early-warning systems capable of capturing regime shifts in financial markets. Beyond VIX forecasting, this methodological contribution has broader applicability to equities, exchange rates, and commodities, where identifying and responding to volatility shocks is critical for risk management and investment decision-making.
Hybrid Ensemble Learning with SMOTEENN and Soft Voting for Stunting Risk Prediction: A SHAP-Based Explainable Approach Furqany, Nuwairy El; Subianto, Muhammad; Rusyana, Asep
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.829

Abstract

Stunting remains a critical public health concern in Indonesia, with long-term consequences for physical growth, cognitive development, and human capital. This study introduces a hybrid machine learning framework to predict household-level stunting risk by integrating Synthetic Minority Over-sampling Technique with Edited Nearest Neighbors (SMOTEENN), soft voting ensemble, and SHapley Additive exPlanations (SHAP). The objective is to enhance both predictive accuracy and interpretability in identifying high-risk households. A dataset of 115,579 household records from West Sumatra, comprising 20 demographic, socioeconomic, health, and housing predictors, was utilized. Preprocessing steps included handling missing values, categorical encoding, and applying SMOTEENN exclusively on the training set to mitigate class imbalance. The baseline models demonstrated limited sensitivity, with XGBoost performing best at 74.56% accuracy and 71.08% F1-score on imbalanced data. After applying SMOTEENN, performance improved substantially, with XGBoost achieving 91.82% accuracy and 91.74% F1-score. Further improvements were obtained through hybridization, where the Random Forest and XGBoost soft voting ensemble reached 91.95% accuracy and 92.46% F1-score, representing a notable gain over individual classifiers. SHAP analysis added interpretability by identifying family members, education level, diverse food consumption, occupation, and drinking water source as dominant predictors of stunting risk. The novelty of this study lies in the integration of SMOTEENN with ensemble learning and SHAP, providing not only robust performance but also transparency in feature contributions. The findings demonstrate that the proposed framework improves sensitivity to minority classes, delivers superior predictive accuracy compared to baseline models, and offers interpretable insights to guide targeted interventions. By combining methodological rigor with explainability, this research contributes a practical decision-support tool for policymakers, supporting early detection of at-risk households and accelerating stunting reduction efforts in Indonesia.
ACLM Model: A CNN-LSTM and Machine Learning Approach for Analyzing Tourist Satisfaction to Improve Priority Tourism Services Arsyah, Ulya Ilhami; Pratiwi, Mutiana; Fryonanda, Harfeby; Anam, M. Khairul; Munawir, Munawir
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.974

Abstract

Tourist satisfaction is a key proxy for destination service quality, yet automatic sentiment analysis of online reviews still faces class imbalance, overfitting, and limited deployability. This study proposes ACLM, a hybrid sentiment classification pipeline that learns semantic and temporal features with a CNN-LSTM backbone and evaluates three classifier heads (Softmax, Logistic Regression, XGBoost) on a three-class corpus (neutral, satisfied, dissatisfied). The objective is to deliver an accurate and operational model for decision support in tourism services. The idea combines Word2Vec embeddings, a compact CNN for local patterns, an LSTM for sequence dependencies, and a training workflow with text cleaning, SMOTE based balancing, and regularization to curb overfitting; outputs are exposed through a simple Streamlit interface. Results show that CNN-LSTM with a Softmax head attains accuracy 0.89, macro precision 0.89, macro recall 0.84, and macro F1 0.86, outperforming Logistic Regression (accuracy 0.87, macro precision 0.84, macro recall 0.82, macro F1 0.82) and XGBoost (accuracy 0.85, macro precision 0.80, macro recall 0.82, macro F1 0.80). The findings indicate that deep sequence features paired with a simple Softmax head provide the best tradeoff between accuracy and stability for three-way sentiment classification. The contribution is a reusable, end to end blueprint from preprocessing and balanced training to quantitative evaluation and an inference GUI, and the novelty lies in testing interchangeable classifier heads on a single CNN-LSTM feature extractor while explicitly addressing data imbalance and deployment constraints. The GUI is implemented using the highest accuracy model, namely CNN-LSTM with Softmax.
Image-Based Fish Freshness Classification Using Two-Phase Transfer Learning with Deep Learning Fusion Model Helmud, Ellya; Edi Widodo, Catur; Dwi Nurhayati, Oky
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.988

Abstract

This study introduces a novel deep learning approach for automated fish freshness classification using image analysis. The objective is to design and validate a Deep Learning Fusion Model that combines the strengths of EfficientNetB0 and InceptionV3 architectures to improve accuracy and robustness in classifying fresh and non-fresh fish. Input images were subjected to extensive augmentation, including RandomFlip, RandomRotation, RandomZoom, RandomContrast, RandomBrightness, and RandomTranslation, applied exclusively to the training dataset to enhance generalization, followed by backbone-specific pre-processing. Extracted features were fused via global average pooling and forwarded to a newly designed classification head with dropout and L2 regularization to mitigate overfitting. A two-phase transfer learning strategy was employed: initially training the classification head with frozen backbones, followed by fine-tuning the backbone layers using the Adam optimizer with a reduced learning rate. To highlight the contribution of the fusion strategy, ablation studies were conducted with single-backbone models. The EfficientNetB0 model achieved 89.17% validation accuracy, 85.83% test accuracy, and an F1-score of 85.69%, while the InceptionV3 model achieved 86.67% validation accuracy, 81.67% test accuracy, and an F1-score of 81.59%. In contrast, the proposed Fusion Model achieved 93.33% validation accuracy, 95.00% test accuracy, and an F1-score of 94.95%. Additional evaluations with confusion matrices, ROC curves, AUC, and precision-recall curves confirmed the model’s superiority. The findings demonstrate that integrating features from diverse CNN architectures enables the model to learn richer representations, resulting in significantly improved classification performance. The novelty of this work lies in the effective fusion of complementary backbones through global average pooling and fine-tuned transfer learning, establishing a human-centric computational approach that offers a reliable solution for practical fish freshness assessment in food safety and market scenarios.
Acceptance and Success Model for AI Use in Higher Education: Development, Instrument Decomposition, and Its Triangulation Testing Subiyakto, Aang; Huda, Muhammad Q; Hakiem, Nashrul; Suseno, Hendra B; Arifin, Viva; Azmi, Agus N; Sani, Asrul; Yuniarto, Dwi; Hartawan, Muhammad S; Suryatno, Agung; Muji, Muji; Kurniawan, Fachrul; Kusumawati, Ririen; Balogun, Naeem A; Ahlan, Abd. Rahman
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.619

Abstract

Prior social computing studies described that the performance of technology products is about how the product use benefits the users, including Artificial Intelligence (AI). To have an impact, ensuring how AI is used is a prerequisite after the development. Furthermore, its use is also influenced by how users accept AI. This study aimed to develop an acceptance and success model of AI use in the higher education world from the user perspective, to decompose the model into its instrument level, and to test the validity and reliability of the research instrument. The researchers developed the model by adopting and combining the Technology Acceptance Model (TAM) and the Information System Success Model (ISSM) and adapting the proposed model in the context of AI use in higher education learning. The measurement items were derived from definitions of the variables and indicators of the model. The instrument was tested sequentially using triangulation methods. The quantitative testing was online survey with about 51 respondents and the qualitative one was interview involving five experts. This study may contribute methodologically as one of the guidance for novice scholars in similar works. It may relate to the clarity of the research procedure and the implementation of the mixed testing methods. Of course, the assumptions, samples, and data used in the study cannot be generalized for the other studies. Referring to the model development, the proposed model may not cover the other factors related to the ethical, cultural, and organizational barriers for adopting AI. These barriers may also affect its acceptance and success. Thus, the adoption of the factors related the barriers may also be interesting to study further.
Classification of Batak Toba Ulos Motifs Based on Transfer Learning with MobileNetV2 Limbong, Tonni; Simanullang, Gonti; Silitonga, Parasian DP.; Silalahi, Donalson
Journal of Applied Data Sciences Vol 6, No 4: December 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i4.1036

Abstract

Indonesia possesses a rich cultural heritage, including the traditional Batak Toba Ulos textile, which is known for its diverse motifs and deep philosophical meanings. However, the preservation and visual recognition of Ulos remain challenging, particularly in terms of systematic documentation and automated classification. This study presents a visual recognition system for Batak Toba Ulos motifs using a transfer learning approach based on the MobileNetV2 architecture. The methodology involves the construction of a curated dataset of Ulos images, the application of data augmentation and preprocessing techniques, and model training utilizing ImageNet pre-trained weights. The system’s performance was evaluated using accuracy, precision, recall, and F1-score metrics. Results show that the model is capable of accurately classifying all 12 Ulos classes, achieving F1-scores ranging from 0.93 to 0.97. These findings demonstrate that transfer learning is effective in overcoming the limitations of culturally specific, small-scale datasets. This research contributes to the development of artificial intelligence tools for cultural preservation and supports the digital documentation and promotion of Batak Toba Ulos to younger generations and broader audiences in an efficient and scalable manner.
The Application of Deep Learning in Qur’anic Tafsir Retrieval Using SBERT, FAISS and BERT-QA Herliana, Asti; Najiyah, Ina; Susanti, Sari; Billah, Lutfhi Muayyad
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1000

Abstract

Accurate understanding of the Qur’an requires access to reliable tafsir, yet many classical tafsir resources remain non-digital, making search and retrieval time-consuming. This study presents a semantic-based retrieval system for Tafsir Ibn Kathir, covering 114 entries and 6,236 Verses, using SBERT embeddings and FAISS indexing. The system enables users to perform semantic queries, retrieving relevant passages in response to their questions. Evaluation was conducted using 50 representative queries spanning diverse topics, including Fiqh, Aqidah, History, and Spirituality. Relevance judgments were independently provided by three Qur’anic studies experts and reconciled through discussion, with inter-annotator agreement indicating substantial consistency. Each query included 20 non-relevant passages as negative samples to increase evaluation difficulty. Two approaches were tested: retrieval-only and retrieval combined with a zero-shot QA module for span extraction. Retrieval-only achieved slightly higher top-1 accuracy (0.72), but retrieval + QA improved ranking-oriented metrics, including Accuracy@5 (0.88), Mean Reciprocal Rank (MRR = 0.76), and normalized Discounted Cumulative Gain at 5 (nDCG@5 = 0.82), with the increase in Accuracy@5 statistically significant (p = 0.01). The zero-shot QA module enabled the system to extract more precise and contextually relevant information, enhancing overall retrieval quality and robustness. These results indicate that the proposed system effectively retrieves relevant tafsir passages and provides accurate, context-specific answers. The study demonstrates the potential and limitations of zero-shot QA for domain-specific religious texts and supports the development of web-based applications or Islamic chatbots, facilitating easier access to shahih tafsir knowledge for scholars and the broader Muslim community.
Multiclass Skin Lesion Classification Algorithm using Attention-Based Vision Transformer with Metadata Fusion Furqan, Mhd.; Katuk, Norliza; Hartama, Dedy
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1017

Abstract

Early and accurate classification of skin lesions is essential for timely diagnosis and treatment of skin cancer. This study presents a novel multiclass classification framework that integrates dermoscopic images with clinical metadata using an attention-based Vision Transformer (ViT) architecture. The proposed model incorporates a mutual-attention fusion mechanism to jointly learn from visual and tabular inputs, augmented by a class-aware metadata encoder and imbalance-sensitive loss function. Training was conducted using the HAM10000 dataset over 30 epochs with a batch size of 32, utilizing the Adam optimizer and a learning rate of 0.0001. The model demonstrated superior performance compared to a ViT Baseline, achieving 93.4% accuracy, 92.2% F1-score, 0.95 AUC, and significant reductions in MAE and RMSE. Additionally, Grad-CAM visualizations confirmed the model’s ability to focus on diagnostically relevant regions, enhancing interpretability. These findings suggest that the integration of structured clinical information with transformer-based visual analysis can significantly improve classification robustness, particularly in underrepresented lesion types. However, the model’s current performance is evaluated only on the HAM10000 dataset, and its generalizability to other clinical or non-dermoscopic image sources remains to be validated. Future studies should therefore explore multi-institutional datasets and real-world deployment scenarios to assess robustness and scalability. The proposed framework offers a practical, interpretable solution for AI-assisted skin lesion diagnosis and demonstrates strong potential for clinical deployment.
Assessing Consumer Perception in Muslim-made Cosmetics: A Relationship Quality Perspective Scorita, Kurnia Budhy; Handaru, Agung Wahyu; Wibowo, Setyo Ferry
Journal of Applied Data Sciences Vol 7, No 1: January 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i1.1016

Abstract

This study investigates the drivers of repurchase intention in the Muslim-made cosmetics market by examining the mediating roles of trust and satisfaction within a relationship quality framework. Grounded in Relationship Quality Theory and the Stereotype Content Model, the research integrates perceived product quality, brand image, and perceived AI warmth as key antecedents influencing consumer loyalty. A comparative analysis of two structural models (Model 1 and Model 2) is conducted to explore the directionality of the mutually reinforcing relationship between trust and satisfaction. Data were collected via structured online surveys from 439 Muslim consumers in Jakarta, Indonesia, and analyzed using PLS-SEM. Findings reveal that perceived AI warmth is the strongest predictor of both trust (t=7.587, p0.001) and satisfaction (t=8.874, p0.001). In Model 1, trust significantly precedes satisfaction (t=4.869, p0.001); conversely, in Model 2, satisfaction reciprocally enhances trust (t=5.280, p0.001), supporting a dynamic, co-evolutionary process. Perceived product quality significantly impacts trust (t=3.780, p0.001) but only affects satisfaction when satisfaction is modeled as an antecedent to trust (Model 2: t=1.984, p=0.048). Brand image exerts a strong effect on satisfaction (Model 1: t=4.235, p0.001; Model 2: t=4.855, p0.001) but loses its direct path to trust in Model 2. Both trust and satisfaction have significant direct effects on repurchase intention (Model 1, Trust t=4.577, p0.001, Satisfaction t=8.538, p0.001; Model 2, Trust: t=4.630, p0.001; Satisfaction t=8.130, p0.001). The study validates the dual mediating roles of trust and satisfaction in translating perceptions of product quality, brand symbolism, and AI-induced warmth into behavioral loyalty. Theoretically, it advances a reciprocal, experience-driven model of relationship quality, extending prior discussions of reciprocity beyond traditional unidirectional frameworks. Practically, it offers actionable insights for marketers seeking to leverage AI personalization and identity-based branding to cultivate long-term loyalty in culturally sensitive, value-driven markets.

Page 48 of 55 | Total Record : 543

 46   47   48   49   50 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue Vol 7, No 2: May 2026 Vol 7, No 1: January 2026 Vol 6, No 4: December 2025 Vol 6, No 3: September 2025 Vol 6, No 2: MAY 2025 Vol 6, No 1: JANUARY 2025 Vol 5, No 4: DECEMBER 2024 Vol 5, No 3: SEPTEMBER 2024 Vol 5, No 2: MAY 2024 Vol 5, No 1: JANUARY 2024 Vol 4, No 4: DECEMBER 2023 Vol 4, No 3: SEPTEMBER 2023 Vol 4, No 2: MAY 2023 Vol 4, No 1: JANUARY 2023 Vol 3, No 4: DECEMBER 2022 Vol 3, No 3: SEPTEMBER 2022 Vol 3, No 2: MAY 2022 Vol 3, No 1: JANUARY 2022 Vol 2, No 4: DECEMBER 2021 Vol 2, No 3: SEPTEMBER 2021 Vol 2, No 2: MAY 2021 Vol 2, No 1: JANUARY 2021 Vol 1, No 2: DECEMBER 2020 Vol 1, No 1: SEPTEMBER 2020 More Issue