cover
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
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.
Articles 1,270 Documents
Intelligent Solar Panel Monitoring Using Machine Learning and Cloud-Based Predictive Analytics J. Dhilipan; N. Vijayalakshmi; D.B. Shanmugam; Siti Sarah Maidin; Wong Ling Shing
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.720

Abstract

The increasing global energy demand necessitates reliable and sustainable solutions, with solar photovoltaic (PV) technology emerging as a key carbon-neutral option. However, optimizing solar energy systems requires advanced monitoring and predictive analytics to enhance efficiency and ensure long-term performance. This study introduces an Internet of Things (IoT)-based solar energy monitoring system, integrating machine learning algorithms and cloud computing to enhance real-time performance assessment. The proposed system employs K-Means Clustering for condition classification, Support Vector Machine (SVM) for fault detection, Long Short-Term Memory (LSTM) for energy forecasting, Prophet for time-series predictions, and Isolation Forest for anomaly detection. The system was validated using a 125-watt photovoltaic module, monitoring temperature, solar radiation, voltage, and current. A Wi-Fi-enabled microcontroller collects data, which is processed through a cloud-based platform and visualized via the Blynk application. Experimental results demonstrate 94.2% energy prediction accuracy using LSTM, 89.7% fault classification accuracy with SVM, and 88.5% anomaly detection accuracy with Isolation Forest, confirming high reliability. The system's wireless tracking mechanism minimizes resource consumption, ensuring scalability and adaptability for commercial and industrial applications. The integration of IoT, machine learning, and cloud analytics provides a cost-effective and scalable approach for solar PV optimization. Future enhancements include deep learning models and reinforcement learning algorithms to improve energy forecasting, fault detection, and adaptive optimization, ensuring greater efficiency, resilience, and sustainability in solar energy management.
Urban Heat Island Spatial Model for Climate Village Program Planning Munsyi Munsyi; Agung Nugroho; Ahmad Jauhari; Moh Reza Faisal
Journal of Applied Data Sciences Vol 5, No 2: MAY 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i2.223

Abstract

Global warming and climate change are critical issues impacting ecosystems, human habitats, and the overall environment. Urban Heat Island (UHI) is a significant phenomenon resulting from increased urban temperatures due to dense urban development, the use of heat-absorbing materials, and reduced vegetation. This study focuses on analyzing the UHI effect in Banjarmasin, Indonesia, using spatial regression and descriptive spatial analysis methods. By employing Land Surface Temperature (LST) data from Landsat 9 and Sentinel-2 satellite imagery, combined with data from wireless sensor networks (WSN), this research aims to develop a comprehensive UHI spatial model to inform climate village program planning. The results reveal substantial temperature variations within Banjarmasin, with urban areas showing significantly higher LST values compared to vegetated outskirts. The integration of satellite data with real-time WSN measurements provides a robust validation method, ensuring accurate environmental monitoring. This study underscores the importance of enhancing green spaces and implementing sustainable spatial planning to mitigate UHI effects. The proposed UHI spatial model offers a valuable tool for urban planners and policymakers in developing strategies to improve urban environmental quality and resilience to climate change.
Image-Based Detection of Reduced Security Features in Indonesian Banknotes Using U-Net Architecture Silfia Andini; Tukino Tukino
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.v7i1.1087

Abstract

The circulation of fake currency banknotes in Indonesia continues to rise alongside rapid technological advancements, while conventional verification systems remain limited and often ineffective in detecting subtle authenticity cues. The main objective of this study is to develop an image-based fake currency detection system using the U-Net deep learning architecture and its modified version, T-Net, to enhance feature extraction and classification accuracy. The key contribution of this research lies in combining convolutional architectures with a practical, web-based interface that enables real-time image analysis, thus bridging the gap between model performance and user accessibility. A quantitative experimental method was employed, involving model development in Python using TensorFlow and Keras, and implementation of a Flask-based web application for real-time classification. The research utilized a dataset of 2,141 Indonesian rupiah banknote images, consisting of 1,015 genuine and 1,126 fake currency samples synthetically generated through digital modification of security features such as watermarks and color-shifting ink. Image preprocessing included resizing, normalization, and augmentation techniques such as random flipping and brightness adjustment to enhance data quality. Three convolutional architectures U-Net, ResNet-50, and the modified T-Net were trained and compared using identical hyperparameters. The T-Net model achieved the best performance, with 97.8% training accuracy, 82.6% validation accuracy, precision of 0.83, recall of 0.80, and an F1-score of 0.81. Despite the performance gap indicating overfitting, the model effectively distinguishes genuine from fake currency notes. The Flask-based interface allows users to upload images and receive classification results from all three models within 0.3–1.8 seconds per image. The findings demonstrate the feasibility and efficiency of U-Net based architectures for image-driven fake currency detection and provide a foundation for developing advanced, reliable, and real-time financial authentication systems that can strengthen digital security infrastructures in future applications.
Searching Sahih Hadiths Based on Queries using Neural Models and FastText Sari Susanti; Ina Najiyah; Yudi Ramdhani; Asti Herliana; Masaldi Kharisma Muckti; Fani Rahma Oktaviani
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.467

Abstract

Hadith is the second source of Islamic law after the Qur’an, and the availability of accurate and easily accessible information about hadith is crucial, as it directly affects a person’s belief (aqidah). This highlights the importance of having hadith collections as essential guidance in everyday life. Today, digital versions of hadiths are available in various applications, e-books, and websites. However, users often complain that these sources are incomplete and do not contain the entire collection of the Prophet's hadiths from al-Kutub as-Sittah. Additionally, the complex presentation of these digital resources makes it difficult to find relevant hadiths efficiently. This study aims to improve access to accurate and relevant hadith information, focusing specifically on al-Kutub as-Sittah, using Information Retrieval systems that search for hadiths based on keywords. IR is employed because it has proven effective in retrieving precise documents according to the search terms. A Neural Network is used to match user queries with the document collection, while FastText word embedding is implemented for text representation. FastText is particularly useful for detecting similar meanings across different words, which is essential when interpreting Indonesian-translated hadiths that require nuanced understanding. The dataset used in this study consists of 31,275 Indonesian-translated hadiths from al-Kutub as-Sittah. In this study, it was found that many hadith translations have ancient language so that query reformulation is needed to get the right hadith because users often enter commands with currently trending words. In this study, it was also found that word2vec has less performance than FastText in weighting words in hadith translations. The results indicate that the neural network performs well in retrieving relevant hadith content according to the user’s commands or keywords. With a training data proportion of 70% and a testing data proportion of 30%, the Recall value was 0.7721 and the Precision value was 0.75112.
Circular Economy Determinants in Electronics Supply Chain: A Pythagorean Fuzzy Clustering Approach Samiksha Budakoti; Vishal Gupta
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1420

Abstract

The realignment from traditional linear models to circular economy has become indispensable in Electronics industry of developing nations such as India. This transition is crucial to combat issues related to resource scarcity and burgeoning e-waste. This research seeks to determine and classify the pivotal determinants impacting circular economy assimilation in India’s electronics supply chain. An extensive literature review coupled with feedback from industry and academic experts, identified twenty-three such determinants. These determinants were integrated with six supply chain stages in order to develop a structured questionnaire. A five-point linguistic scale was used in the questionnaire to gather expert responses on each determinant-stage combination. The experts’ responses were then converted to Pythagorean fuzzy numbers for quantitative analysis of the information. Using multi-criteria decision-making framework involving aggregation, score function and normalization, a de-fuzzified similarity matrix of determinants was obtained. Ward’s method of agglomerative hierarchical clustering in RStudio was applied to the similarity matrix in order to obtain four different clusters of determinants. Strategic and technological determinants formed cluster 1; regulatory and resource-efficiency determinants were highlighted in cluster 2; cluster 3 reflected market and network drivers; macro-institutional and contextual determinants were represented in cluster 4. These clusters together indicate varied yet interconnected determinants affecting implementation of circular economy practices in India’s electronics supply chain. The robustness of the study was also validated by performing sensitivity analysis of the results. This analysis resulted in a mean Adjusted Rand Index of 0.862 reflecting a high degree of consistency in the analytical results. By integrating two robust quantitative methodologies, this research introduces a novel empirical framework for classification of circular economy determinants. This study can aid policymakers, industry practitioners and academicians to formulate coordinated measures for circular economy adoption in India’s electronics supply chains.
Development of Computer Intelligent Control System Based on Modbus and WEB Technology Longyi Ran; Yenchun Jim Wu
Journal of Applied Data Sciences Vol 4, No 1: JANUARY 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i1.75

Abstract

With the increasing popularity of intelligent computer control systems in our country, the accuracy and efficiency of intelligent control in the current computer control systems have attracted more and more attention. Modbus and WEB technology have a simple chassis format, compact and powerful functions. On this basis, based on the current research status of intelligent computer control technology, this article analyzes the problem of optimizing intelligent computer control systems based on Modbus bus and WEB technology in the application process, and improves the intelligent computer control systems based on Modbus bus and WEB technology.
An Effective Hybrid Approach for Predicting and Optimizing Business Complexity Metrics and Data Insights Rahmad B.Y Syah; Marischa Elveny; Rana Fathinah Ananda; Mahyuddin K.M Nasution; Hartono Hartono
Journal of Applied Data Sciences Vol 6, No 3: September 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i3.830

Abstract

This study proposes a hybrid approach for optimizing complexity prediction in the domain of business intelligence by integrating three powerful techniques: the Multi-Objective Complexity Prediction Model (MPK), Principal Component Analysis (PCA), and the XGBoost regression algorithm. The MPK model serves as a state-based simulator to capture system complexity dynamics, while PCA is employed to reduce data dimensionality and eliminate redundancy among features. Subsequently, XGBoost is used as a non-linear predictive model to estimate complexity values based on the refined input features. The results show that this hybrid approach significantly improves prediction accuracy, reduces data noise, and streamlines the modelling process. Quantitative evaluation using Mean Squared Error (MSE), Mean Absolute Error (MAE), and the R-squared (R²) metric demonstrates exceptional performance, with an MAE of 0.000035, an MSE of 6.7 × 10⁻⁹, and an R² of 0.9999999. These results confirm that the integration of MPK, PCA, and XGBoost is highly effective for complexity prediction tasks and can provide accurate and insightful outcomes in business intelligence analytics.
Assessing the Performance and Competitive Strategies of Bamboo Weaving MSMEs in Bali Using Quantitative Associative Causal Design I Made Kartika; I Made Sumada; I Made Adi Suwandana; Yudistira Adnyana; I Dewa Gede Putra Sedana; I Wayan Meryawan
Journal of Applied Data Sciences Vol 5, No 3: SEPTEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i3.320

Abstract

This study explores the factors influencing the competitiveness and performance of bamboo weaving Micro, Small, and Medium Enterprises (MSMEs) in Bali, using a quantitative associative causal design. Bamboo weaving, an integral part of Balinese culture, faces significant challenges post-COVID-19. This research aims to analyze key factors such as business capabilities, product quality, infrastructure, technology, resources, government policies, and external support, and their impact on the competitiveness and performance of these MSMEs. Data were collected from 100 bamboo weaving MSMEs in Buleleng and Bangli using structured surveys. The collected data were analyzed using Partial Least Squares (PLS) structural equation modeling to validate the proposed hypotheses. The study reveals that product quality (path coefficient = 0.275, t-statistic = 3.048, p-value = 0.003), infrastructure (path coefficient = 0.187, t-statistic = 2.176, p-value = 0.032), technology (path coefficient = 0.239, t-statistic = 3.231, p-value = 0.002), resources (path coefficient = 0.179, t-statistic = 2.048, p-value = 0.043), and external support (path coefficient = 0.185, t-statistic = 2.387, p-value = 0.019) significantly influence the competitiveness of bamboo weaving MSMEs. In contrast, business capabilities (path coefficient = 0.169, t-statistic = 1.856, p-value = 0.066) and government policies (path coefficient = - 0.031, t-statistic = 0.283, p-value = 0.778) were found to be insignificant in this context. The findings indicate that improvements in product quality, better infrastructure, adoption of modern technologies, effective resource management, and robust external support systems are critical in enhancing competitiveness. However, the expected positive impact of competitiveness on MSME performance (path coefficient = 0.182, tstatistic = 1.269, p-value = 0.207) was not statistically significant. This suggests that factors beyond competitiveness, such as market conditions and internal business processes, play a more substantial role in determining performance outcomes. This study provides practical recommendations for MSMEs to enhance competitiveness, emphasizing the need for improved product quality, infrastructure, technology adoption, resource management, and leveraging external support. Additionally, the research highlights the necessity for stronger, more effective government policies tailored to the unique challenges of bamboo weaving MSMEs. These insights are valuable for MSME owners, policymakers, and stakeholders aiming to support the bamboo weaving industry in Bali, ensuring its sustainability and growth in the post-pandemic era.
Multidimensional Data-Driven Modeling of Sustainable E-Commerce Development with Direct and Interaction Effects Mai Thanh Loan; Phan Thanh Tam
Journal of Applied Data Sciences Vol 7, No 2: May 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i2.1213

Abstract

Sustainable e-commerce development has become a critical issue for emerging economies as digital markets expand rapidly, alongside growing concerns about regulatory effectiveness, trust, and resource efficiency. This study investigates the key factors influencing sustainable e-commerce development in Vietnam by explicitly integrating Institutional Theory, the Technology–Organization–Environment (TOE) framework, and the Resource-Based View (RBV) into a unified structural equation modeling (SEM) framework. Institutional Theory is operationalized through regulatory quality, capturing the role of formal rules and enforcement mechanisms in shaping market stability and legitimacy. The TOE framework is reflected in digital infrastructure, government support, and competitive pressure, which together represent technological readiness and environmental conditions. RBV is operationalized through resource availability and management capacity, emphasizing firms’ internal capabilities to sustain long-term e-commerce performance. In addition, trust is incorporated as both a direct determinant and a moderating mechanism that strengthens the effectiveness of institutional and organizational factors. A mixed-method research design was employed. The qualitative phase involved in-depth discussions with 35 policymakers, business managers, and e-commerce platform managers to refine the theoretical integration and measurement scales. Based on these insights, a structured questionnaire was administered to frequent online shoppers in Ho Chi Minh City and Dong Nai Province, yielding 653 valid responses. SEM results indicate that regulatory quality, digital infrastructure, government support, competitive pressure, resource availability, and trust all have significant positive effects on sustainable e-commerce development. Resource availability and regulatory quality exert the strongest impacts, while trust and management capacity significantly moderate the effects of regulatory quality and resource availability, respectively. By explicitly mapping institutional, technological, organizational, and relational constructs into a coherent SEM framework, this study provides a theoretically grounded and empirically validated model of sustainable e-commerce development in an emerging economy context. The findings offer valuable implications for policymakers and practitioners seeking to foster a resilient, trustworthy, and sustainable e-commerce ecosystem in Vietnam and similar developing economies.
Enhancing Digital Marketing Strategies with Machine Learning for Analyzing Key Drivers of Online Advertising Performance Berlilana Berlilana; Taqwa Hariguna; Ibrahiem M. M. El Emary
Journal of Applied Data Sciences Vol 6, No 2: MAY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i2.658

Abstract

The rapid growth of digital advertising has underscored the need for data-driven strategies to optimize campaign performance. This study applies machine learning techniques to analyze online advertising data, aiming to identify key performance drivers and provide actionable insights for optimizing marketing strategies. The dataset includes metrics such as clicks, displays, costs, and revenue, which were preprocessed, analyzed, and modeled using ensemble methods, including Random Forest and Gradient Boosting. These ensemble methods were chosen for their ability to handle high-dimensional data, mitigate overfitting, and capture complex, nonlinear relationships between variables. Random Forest, with its bagging approach, enhances generalization by reducing variance, while Gradient Boosting incrementally corrects errors by focusing on hard-to-predict instances, improving overall predictive performance. Descriptive analysis revealed significant variability in campaign outcomes, with cost and user engagement emerging as primary predictors of revenue. Machine learning models demonstrated strong predictive accuracy, with Random Forest achieving 92% accuracy and an F1-score of 89%. Visualizations such as feature importance charts, correlation heatmaps, and learning curves validated the robustness of the models and highlighted key insights, including inefficiencies in cost allocation and the limited impact of certain categorical features like placement. The study emphasizes the potential of machine learning to optimize digital marketing strategies by identifying critical factors that influence campaign success. The findings provide a scalable framework for resource allocation, audience targeting, and strategic decision-making in online advertising. Future research could further enhance predictions by incorporating additional features, such as audience demographics and temporal trends, to provide deeper insights into campaign dynamics.

Page 100 of 127 | Total Record : 1270