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 518 Documents
 48   49   50   51   52 
Process Design of Software Library Development for Deep Learning Module in Java Programming with Four-Phase Methodology: Preparation, Identification, Design, and Development Barakbah, Ali Ridho; Rachmawati, Oktavia Citra Resmi; Karlita, Tita
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.v7i1.989

Abstract

Recent advances in deep learning have driven remarkable achievements across various domains, including computer vision, natural language processing, and medical diagnostics. However, prevailing DL libraries often expose monolithic and tightly coupled codebases, making it difficult for researchers to inject custom mathematical formulations into core training routines. To address this limitation, we introduce a modular software library that empowers users in both academia and industry to extend and modify training functions with minimal friction. This paper focuses on the preparatory stages of library development in Java Programming, presenting a four-phase methodology comprising Preparation (ideation, research questions, literature review), Identification (term extraction, goal definition, environment setup), Design (architecture modeling, class and attribute specification, task scheduling), and Development (component exploration, functionality construction). Through these sequential activities, we have produced eleven detailed design documents, including vision statements, quality-attribute scenarios, architectural decision records, and API specifications, that collectively capture the rationale and technical blueprint of our library. By sharing our step-by-step process, we aim to provide a replicable framework for future researchers undertaking the architectural design of specialized Deep Learning libraries.
SiMoI New Method to Solve the Sparsity Problem in Collaborative Filtering Kurniawan, Hendra; Lestari, Sri; Saleh, Sushanty; Satrio, Rafli Banu
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.v7i1.1015

Abstract

Sparsity data is a major challenge in collaborative recommendation systems, characterized by the predominance of missing values within the user-item matrix. When a substantial portion of data is unavailable, the estimation process becomes hindered, and prediction accuracy declines due to limited usable information. To address this issue, this study introduces a novel method called SiMoI (Similarity, Mode, and Minimum Imputation), which is adaptively designed to handle high levels of sparsity. The SiMoI method combines user similarity with imputation strategies based on mode and minimum values. By leveraging subsets of the most informative users and items, the method efficiently fills missing entries while maintaining prediction stability. Evaluation was conducted using both real and synthetic datasets with varying sizes and degrees of sparsity, including an extreme scenario with 93.7% missing data. Experimental results show that SiMoI consistently produces more accurate predictions than baseline methods. Under high-sparsity conditions, SiMoI achieved an RMSE as low as 0.823, outperforming KNNI (0.947) and MEAN (1.021). Moreover, SiMoI demonstrated resilience across different data scales and sparsity distributions, indicating its flexibility and scalability in diverse contexts. These findings suggest that SiMoI is an effective and stable approach for addressing sparsity and holds strong potential for implementation in user-based recommendation systems, particularly in real-world scenarios where data availability is frequently limited.
GAN-Enhanced Radial Basis Function Networks for Improved Landslide Susceptibility Mapping Widiawati, Chyntia Raras Ajeng; Maulita, Ika; Purwati, Yuli; Wahid, Arif Mu'amar
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.v7i1.1035

Abstract

Landslide susceptibility modeling is a critical task for disaster mitigation, yet it is frequently undermined by a severe class imbalance inherent in landslide datasets, where non-landslide instances vastly outnumber actual landslide events. This imbalance leads to biased machine learning models with poor predictive power for the minority (landslide) class, resulting in unreliable hazard maps. This study, focusing on the high-risk area of Malang Regency, Indonesia, addresses this challenge by proposing an innovative framework that integrates a Generative Adversarial Network (GAN) for synthetic data augmentation with a Radial Basis Function Network (RBFN) for classification. A highly imbalanced dataset with a 1:10 ratio of landslide to non-landslide points was constructed to establish a realistic baseline. On this data, the RBFN model, while theoretically powerful for capturing non-linear relationships, failed completely, achieving a Recall of 0.00 for the landslide class. The novelty of this research lies in the specific application of a GAN, trained for 15,000 epochs, to generate high-fidelity synthetic landslide data, thereby creating a perfectly balanced training set. After retraining on this augmented data and undergoing a systematic hyperparameter tuning process, the RBFN’s performance was dramatically transformed. The optimized model achieved an F1-Score of 0.9333 and a Recall of 0.8750, elevating its performance from total failure to a level competitive with the robust Random Forest benchmark. This work validates that the integrated GAN-RBFN approach is a highly effective methodology for overcoming the data imbalance problem in geospatial hazard modeling. By turning a previously unreliable classifier into a powerful predictive tool, this method has significant practical implications for developing more accurate landslide susceptibility maps, which are crucial for informed spatial planning and enhancing early warning systems.
TF-EffBiGRU-AttNet: A Novel Deep Learning Framework for Spatio-Temporal Energy Demand Forecasting in Electric Vehicle Charging Networks Prakash, S; Aruna Mary, S; Sudhagar, G; Batumalay, M
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.v7i1.805

Abstract

Electric Vehicle Charging Stations (EVCS) are key enablers of sustainable transportation, yet accurate forecasting of their energy demand remains challenging due to complex spatial-temporal variability. This study introduces a novel hybrid deep learning framework, Two-Fold EfficientNetV2 BiGRU with Attention (TF-EffBiGRU-AttNet), optimized using the Self-Adaptive Hippopotamus Optimization Algorithm (SA-HOA), to enhance prediction accuracy and computational efficiency in EVCS energy demand forecasting. The main objective is to integrate multi-scale spatial learning, bidirectional temporal modeling, and adaptive feature prioritization within a single architecture capable of robust and interpretable forecasting. The model’s novelty lies in its dual-fold spatial feature extraction using EfficientNetV2 and dynamic optimization through SA-HOA, which adaptively balances exploration and exploitation during training. Experimental validation on two real-world datasets from Palo Alto and Perth demonstrates that the proposed model consistently outperforms state-of-the-art baselines. For the 7-1 forecasting task, TF-EffBiGRU-AttNet achieved the lowest MAE of 0.012 and RMSE of 0.051 for Palo Alto, and MAE of 0.029 with RMSE of 0.12 for Perth. For the 30-7 task, it achieved MAE of 0.0332, RMSE of 0.1654, and MAPE of 0.20% on Palo Alto, and MAE of 0.0235, RMSE of 0.0824, and MAPE of 0.37% on Perth, outperforming Bi-LSTM and EfficientNet by over 60% in RMSE reduction. Moreover, SA-HOA improved optimization efficiency with a best fitness value of 0.0003 and reduced convergence time to 1.2 seconds, surpassing PSO, GWO, and HOA. These results highlight the framework’s ability to capture spatial-seasonal and nonlinear dependencies while maintaining low computational overhead. The findings confirm the model’s potential as a robust, adaptive, and scalable solution for intelligent EV energy demand forecasting, supporting smart grid planning and sustainable energy management.
Type Deep Learning Model for Multi-Label Waste Classification in Canal Environments: A Comparative Study with CNN Architectures Umar, Najirah; Asrul, Billy Eden William; Yuyun, Yuyun
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.v7i1.1066

Abstract

The escalating environmental degradation caused by waste underscores the necessity of developing intelligent and sustainable management systems. This study introduces a deep learning–based framework with proposed a modified ConvNeXt architecture enhanced by a two-layer non-linear MLP classification, specifically designed for multi-object waste classification in canal environments. Specifically, ConvNeXt-CNN is introduced as the primary backbone for extracting visual features from waste images. Then, a modified Multi-Layer Perceptron (MLP) is employed to transform these features into multi-label predictions. To optimize the model’s generalization capability in recognizing the complexity of waste images, a hybrid data augmentation technique combining SMOTE and MixUp was applied during training. The proposed approach was then compared with ten fine-tuned Convolutional Neural Network (CNN) architectures, ResNet18, ResNet50, VGG16, VGG19, DenseNet121, MobileNet_v2, and EfficientNet (B0, B1, B2, and B3), and evaluated using accuracy, precision, recall, and F1-score metrics. The experimental dataset comprises 855 waste images containing a total of 2,662 annotated objects across 18 categories, including Bamboo, Beverage Carton, Cardboard, Fabric, Glass Bottle, Inorganic Waste, Kite, Leaf, Metal, Organic Waste, Paper, Plastic, Plastic Bottle, Plastic Cup, Residual Waste, Rubber, Small E-waste, Styrofoam, and Wood. The results show that the fine-tuned ConvNeXt achieved the best performance with an F1-score of 0.99, surpassing DenseNet121 (0.95), ResNet18 (0.91), and VGG16 (0.94). The ConvNeXt model demonstrated its robust capability by achieving consistently high identification scores across majority 18 waste categories. When it came to training efficiency, the fine-tuned MobileNetV2 model proved to be the top performer, outclassing ten other pretrained models, with a training time of 13.35s per epoch.  Results exhibit that finetuned ConvNext outperforms in terms of accuracy, recall, precision, and F1-score. In conclusion, Integrating ConvNeXt and MLP for multi-object waste classification effectively supports intelligent waste management, enabling practical real-world deployment in smart bins, Material Recovery Facilities, and IoT-integrated urban waste systems.
Applied Data Science for Sustainability Marketing: Evidence from Structural Equation Modeling of Organic Product Consumers Wibowo, Setyo Ferry; Monoarfa, Terrylina Arvinta; Sholikhah, Sholikhah; Sumarwan, Ujang; Febrilia, Ika
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.v7i1.1047

Abstract

The global demand for organic products reflects increasing awareness of sustainability in consumer behavior, especially in emerging markets such as Indonesia. Despite this growing trend, limited studies have applied data science approaches to model behavioral relationships within sustainability marketing. This study aims to examine how Sustainable Marketing (SM) influences Prosumption Motivation (PM) and Consciousness for Sustainable Consumption (CSC) among Indonesian organic product consumers. Using a quantitative design, data were collected through purposive sampling, yielding 400 valid responses from participants across Java, Sumatra, Kalimantan, Sulawesi, and Bali. Structural Equation Modeling (SEM) with AMOS was employed as a data science tool to estimate latent constructs and test predictive relationships. The results show that SM has a significant positive effect on PM (β = 0.923, CR = 19.347, p 0.001) and CSC (β = 0.991, CR = 21.764, p 0.001), while PM also significantly influences CSC (β = 0.742, CR = 19.306, p 0.001) and SM indirectly enhances CSC through PM (β = 0.652, CR = 19.306, p 0.001). These findings confirm all hypotheses and reveal a reciprocal relationship between motivation and consciousness, emphasizing a behavioral feedback loop that strengthens sustainable consumption. The study contributes to sustainability marketing by integrating SM, PM, and CSC into a unified predictive framework. Methodologically, it demonstrates how SEM serves as an applied data science technique capable of transforming behavioral data into actionable insights. The novelty lies in bridging behavioral science and data science to provide decision-support evidence for marketers and policymakers promoting prosumption and responsible consumption in emerging economies.
The Effect of Globalization on Income Inequality in Developing Countries: A Bayesian Approach Vy, Phan Dien; Lan, Dang Thi Ngoc; Oanh, Dao Le Kieu
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.v7i1.948

Abstract

The rapid advancement of economic globalization over the last several decades has sparked fierce disagreements about its impact on income inequality on a global and domestic scale. Whether globalization improves (neoclassical theory) or worsens (dependence theory) income inequality is a matter of debate at the theoretical level. The results of empirical studies have been contradictory as well. This study examines the effects of three lenses of globalization (financial openness, trade openness, and social globalization) on income inequality in developing countries. Using Bayesian estimation with Markov Chain Monte Carlo, we analyze a balanced panel of 36 developing countries from 2010 to 2022. The Bayesian method is particularly well-suited for social science research because of its capacity to effectively manage complex relationships and integrate prior information, resulting in more contextually relevant and robust results. The findings reveal significant nonlinear relationships between different dimensions of globalization and income inequality. Specifically, the impact of trade openness on income inequality is U-shaped, with a threshold of 83.35% of GDP, whereas the impact of direct foreign investment and migration is in an inverted-U shape, with respective thresholds of 13.4% of GDP and 1.276% of the total population. Importantly, all sampled countries remain below the identified thresholds for direct foreign investment and migration, indicating that these channels currently exacerbate inequality. Consequently, policy measures designed for “post-threshold” conditions should be viewed as forward-looking. This study contributes by clarifying how globalization can alternately worsen or reduce inequality depending on a country’s stage of integration. From a policy perspective, developing countries should strengthen absorptive capacity and institutional readiness so that higher direct foreign investment inflows and migration eventually yield more equitable outcomes once thresholds are surpassed. Meanwhile, countries already beyond the trade openness threshold should proceed cautiously, prioritizing export diversification, vocational training, and inclusive trade policies to mitigate inequality risks.
Enhancing the Robustness of Adaptive Class Activation Mapping (AD-CAM) Against Noisy Facial Expression Data Using Preprocessing and Adaptive Normalization Sugianto, Dwi; Hariguna, Taqwa; Utomo, Fandy Setyo
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.v7i1.1005

Abstract

In real-world computer vision applications, visual data is often corrupted by noise, reducing both the accuracy and interpretability of deep learning models. This study proposes an enhanced AD-CAM framework that integrates noise-aware preprocessing and adaptive normalization to improve robustness in both prediction and visual explanation. Experiments were conducted on the FER2013 facial expression dataset augmented with Gaussian, salt-and-pepper, and speckle noise. Using ResNet-50 as the backbone, the proposed method demonstrated significant gains across multiple evaluation metrics, including Robust Accuracy (RA), Drop Coherence (DC), Area Under Robustness Curve (AURC), and Signal-to-Noise Ratio (SNR). Compared to the baseline, the model achieved over 10% accuracy improvement and up to 0.16 DC reduction under noise. Qualitative visualizations showed that the improved model consistently highlighted semantically relevant facial regions, maintaining interpretability even under severe input degradation. These results support the adoption of noise-aware interpretability frameworks for more reliable and trustworthy deployment in real-world vision systems.

Page 52 of 52 | Total Record : 518

 48   49   50   51   52 

Filter by Year

2020 2026


Reset
Filter By Issues
All Issue 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