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
The Development of Stacking Techniques in Machine Learning for Breast Cancer Detection Lucky Lhaura Van FC; M. Khairul Anam; Saiful Bukhori; Abd Kadir Mahamad; Sharifah Saon; Rebecca La Volla Nyoto
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.v6i1.416

Abstract

This study addresses the challenges of accurately detecting breast cancer using machine learning (ML) models, particularly when handling imbalanced datasets that often cause model bias toward the majority class. To tackle this, the Synthetic Minority Over-sampling Technique (SMOTE) was applied not only to balance the class distribution but also to improve the model's sensitivity in detecting malignant tumors, which are underrepresented in the dataset. SMOTE was effective in generating synthetic samples for the minority class without introducing overfitting, enhancing the model's generalization on unseen data. Additionally, AdaBoost was employed as the meta model in the stacking framework, chosen for its ability to focus on misclassified instances during training, thereby boosting the overall performance of the combined base models. The study evaluates several models and combinations, with K-Nearest Neighbors (KNN) + SMOTE achieving an accuracy of 97%, precision, recall, and F1-score of 97%. Similarly, C4.5 + Hyperparameter Tuning + SMOTE reached 95% in all metrics. The stacking model with Logistic Regression (LR) as the meta model and SMOTE achieved a strong performance with 97% accuracy, precision, recall, and F1-score all at 97%. The best result was obtained using the combination of Stacking AdaBoost + Hyperparameter Tuning + SMOTE, reaching an accuracy of 98%. These findings highlight the effectiveness of combining SMOTE with stacking techniques to develop robust predictive models for medical applications. The novelty of this study lies in the integration of SMOTE and advanced stacking methods, particularly using AdaBoost and Logistic Regression, to address the issue of class imbalance in medical datasets. Future work will explore deploying this model in clinical settings for accurate and timely breast cancer detection.
Lion-Optimized ANFIS Control for a Hybrid PV–Wind–Battery System with a Reduced-Switch 31-Level Inverter for Induction Motor Drives R K Padmashini; D Lakshmi; J N Rajesh Kumar; C N Ravi; P Jeyarani
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.v7i3.1466

Abstract

This study proposes and experimentally validates a hybrid photovoltaic–wind–battery energy conversion system for driving a three-phase induction motor under variable renewable-source conditions. The system integrates a high-gain SEPIC converter, a PWM rectifier, a bidirectional battery converter, a reduced-switch 31-level cascaded H-bridge inverter, and a Lion Optimization Algorithm–tuned adaptive neuro-fuzzy inference system controller. The proposed controller performs maximum power point tracking and regulates the common DC-link voltage by adjusting the converter and rectifier switching commands in response to changes in solar irradiance, photovoltaic temperature, and wind-side voltage. The system was evaluated using MATLAB/Simulink and an FPGA-based experimental prototype. The photovoltaic array produced approximately 134 V and 75 A under the tested operating conditions, while the SEPIC converter and PWM rectifier maintained the DC-link voltage near 400 V. The battery state of charge remained around 60%, indicating balanced charging and discharging operation. The 31-level inverter generated a stable multilevel output with an RMS voltage of approximately 499 V and real power of approximately 4990 W. The simulated total harmonic distortion was 1.39%, while the experimental prototype achieved 2.85%. The experimental results were consistent with the simulation outcomes and confirmed the effectiveness of the proposed controller in improving transient response, reducing steady-state fluctuations, and maintaining stable power delivery to the induction motor. The proposed configuration provides a feasible solution for renewable-powered motor-drive and marine propulsion applications requiring high voltage gain, adaptive control, energy-storage coordination, and low harmonic distortion.
Elevator Group Scheduling by Improved Dayan Particle Swarm Algorithm in Computer Cloud Computing Environment Jie Yu; Bo Hu
Journal of Applied Data Sciences Vol 3, No 2: MAY 2022
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v3i2.60

Abstract

The world is entering the era of cloud computing. Due to the rapid development of computer technology, as the core content of elevator transportation technology, elevator group control dispatching systems and group intelligent algorithms will have a wide range of application prospects due to their significant advantages. The purpose of this paper is to study the elevator group scheduling problem of the improved Dayan particle swarm algorithm in the computer cloud computing environment.This article first summarizes the research status of elevator group control technology and algorithms, and then analyzes and studies the basic theory of cloud computing task scheduling. Combined with the improved Dayan particle swarm algorithm, the elevator prediction model is established. This paper systematically expounds the theory and algorithm principle of the basic particle swarm algorithm, and analyzes the Dayan particle swarm algorithm on this basis. In this paper, the experimental research is carried out by comparing the two algorithms on the simulation software. Research shows that the improved Dayan particle swarm algorithm has better scheduling performance than the traditional basic particle swarm algorithm.
Improving MCDM University Rankings through Statistical Validation Using Spearman’s Correlation and THE Benchmark Septi Andryana; Teddy Mantoro; Aris Gunaryati; Alfarizky Esah Raffliansyah
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.v6i3.796

Abstract

The evaluation of higher education institutions is a critical field for informing data-driven policy and institutional benchmarking. A key problem in this area is the lack of transparency and consistency in university rankings, particularly when using Multi-Criteria Decision-Making (MCDM) methods such as MABAC and MAIRCA, with limited research on how weighting techniques affect the reliability and alignment of these rankings with international standards like the Times Higher Education (THE) Rankings. This study proposes the use of MABAC and MAIRCA methods combined with two weighting techniques—Rank Order Centroid (ROC) and Rank Sum (RS)—to assess 20 top Indonesian universities based on five performance indicators: research quality, research environment, teaching, industry, and international outlook. Spearman’s rank correlation is used to compare the MCDM-generated rankings with THE Rankings 2025. The study contributes empirical evidence on the impact of weighting schemes on the consistency and reliability of university rankings and demonstrates that the MAIRCA-ROC method achieves the highest agreement with THE Rankings, with a correlation coefficient of 0.8135 and a p-value of 0.00001. These results validate the use of MCDM methods in higher education evaluation and emphasize the importance of selecting appropriate weighting techniques to develop transparent and robust ranking frameworks that support evidence-based policy decisions.
Asynchronous Programming based on Services with Application of Neural Networks as a Method of Taking Legitimate Measures at DDoS Attacks Kairat Tokpayev; Agyn Bedelbayev
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.v5i3.276

Abstract

The relevance of this study is conditioned by the growing threat of various attacks in the modern information space. The purpose of this study was to analyze and evaluate the effectiveness of applying asynchronous programming and neural networks to combat availability attacks. A rudimentary C# programme was created to simulate a DDoS attack detection system, and a comparative table was generated to assess different DDoS attack countermeasure services. The results illustrate the pragmatic importance of utilizing neural networks and asynchronous programming in detecting DDoS attacks, emphasizing their capacity to enhance the effectiveness, precision, and flexibility of detection systems. Such methods allow for a quick and effective response to attacks and ensure the stability of information systems, reducing the risk of loss of availability and financial losses. The study also highlights the importance of evaluating the scalability and performance of these methods in actual network environments. The practical significance of this study is that it provides new ways and tools to protect information resources from attacks, contributes to the advancement of scientific knowledge and provides certain solutions to combat information threats.
Quantum-Inspired Optimization for Traffic Congestion: A QUBO-Based Approach with Simulated Annealing Toufan Diansyah Tambunan; Andriyan Bayu Suksmono; Ian Joseph Matheus Edward; Rahmat Mulyawan
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.v7i1.905

Abstract

Urban traffic congestion remains a persistent challenge, especially when road segments exceed vehicle capacity, leading to increased travel times and road density. This study introduces a new QUBO framework designed to dynamically reduce congestion by optimizing vehicle routes while considering the capacity constraints of road segments. The proposed model establishes quadratic penalties for road segments that exceed the set capacity thresholds, providing incentives to redistribute vehicles to alternative routes while maintaining overall traffic flow efficiency. The QUBO formulation also incorporates road density as a factor to distribute vehicle routing more evenly. The challenge is to ensure that the chosen route does not create potential congestion on the next road segment. We conducted the simulation on a road network consisting of 15 segments (edges) to effectively manage up to 21 vehicles in dense traffic. This QUBO model was created using a quantum annealing approach, but its execution was carried out on an annealing simulation with the Fixstars Amplify and D-Wave Neal machines. The results indicate that the proposed QUBO congestion model can maintain road segment density between 60% and 80% across almost all segment routes. The QUBO congestion model is capable of distributing vehicles evenly, with a Gini coefficient reaching 0.0496 (in an experiment with 21 vehicles), which has the potential to reduce vehicle congestion on road segments. In addition, this model is also capable of avoiding segment choices that exceed road capacity, which is expected to reduce vehicle congestion. Therefore, the resulting QUBO model can be applied to QA engines to reduce congestion on road segments.
Student Engagement in E-Learning During Crisis: An Unsupervised Machine Learning and Exploratory Data Analysis Approach Rachid Ait Daoud; Abdellah Amine; Karim Abouelmehdi; Ayoub Razouk
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.v6i1.458

Abstract

The lockdown caused by COVID-19 has forced educational institutions to rapidly adopt e-learning, which has revealed many significant challenges related to student engagement. Following the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology, the present work aims to provide teachers and university administrators with a framework based on unsupervised machine learning and exploratory data analysis to identify engagement levels and understand the potential reasons for low engagement. Various data sources, including Microsoft Teams logs, demographic, and educational data, were merged to create a comprehensive dataset with the most relevant and useful measures for the success of our approach. This study was structured around three main research questions to achieve our goal. First, we sought to identify the most effective Microsoft Teams measures for identifying students' engagement levels. Then, our analysis focused on comparing different clustering models (two-level, three-level, and four-level models) to determine which one is most accurate in identifying low-engaged students. Finally, we examined the demographic and educational factors influencing low student engagement. The results revealed that: by applying the Sequential Forward Selection (SFS) technique, ScreenShareTime, VideoTime, NbrViewedVideos, Recency, and AvgTeamsSessionDay are the most relevant Microsoft Teams engagement metrics, improving the silhouette width from 0.37 to 0.70 when using these selected measurements. The four-level clustering model (Low, Medium, High, and Super) proved most effective in identifying low-engaged students. Analysis of factors showed that low engagement is primarily related to limited living conditions, with 66% of low-engaged students having low incomes. In addition, 50% do not use online services and 62% of low-engaged students took more than three years to reach their final year, indicating pre-existing academic difficulties. These findings provide educational institutions with valuable insights to enhance student engagement in distance learning, particularly during crisis periods such as the COVID-19 pandemic.
A Fibonacci-Based Dynamic Neural Network Architecture for Imbalanced Classification of Higher Education Performance Muhammad Ardiansyah Sembiring; Syahril Efendi; Mohammad Andri Budiman; T.Henny Febriana Harumy
Journal of Applied Data Sciences Vol 7, No 4: December 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i4.1459

Abstract

This study aims to address two problems in neural network design: the lack of a principled method for choosing hidden-layer neuron counts, and the reliability loss caused by severe class imbalance. To meet this objective, the study propose the Fibonacci Dynamic Neural Network, contributing, to our knowledge, the first architecture unifying number-theoretic hidden-layer sizing with imbalanced-learning correction, an unbiased selection property proven formally, and cross-domain validation. Conceptually, candidate hidden-layer widths are generated from the Fibonacci sequence: because consecutive terms grow proportionally toward the Golden Ratio, the resulting set spans a non-redundant, well-distributed range of capacities, unlike arbitrary sets from conventional methods. One candidate is drawn per layer via a discrete uniform distribution, giving every option equal selection probability, while class imbalance is corrected through synthetic minority oversampling applied only to training data. The architecture was evaluated experimentally on three benchmark datasets spanning higher education, credit card fraud, and charitable donation prediction, with imbalance ratios from about eighteen-to-one to nearly five hundred eighty-to-one, tested across five seeds against five baselines and an ablation study via the Wilcoxon signed-rank test. It achieved macro F1-scores of approximately 0.83, 0.94, and 0.81, improvements of sixteen, five, and sixteen percent over the strongest baseline, with the smallest training-test performance gap of any model tested; oversampling and Fibonacci spacing contributed most to these gains. These findings suggest number-theoretic structures offer a practical, reproducible basis for architecture design under class imbalance, useful for future work on automated range selection and for deploying reliable classifiers in imbalanced real-world settings.
Assessing Factors and Simulating Innovation: A Study of Innovative Capacities Among Data Science Professionals in China Yongfeng Zhang; Thosporn Sangsawang; Piyanan Pannim Vipahasna
Journal of Applied Data Sciences Vol 4, No 3: SEPTEMBER 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i3.123

Abstract

This study aims to analyze the multifaceted factors influencing the innovative capabilities of data science professionals in China and assess the impact of simulations on their innovative skills. The sample comprises seventeen experts who actively participated in discussions and provided 36 perspectives on the factors affecting their innovation abilities. The research methodology utilized the Delphi method, involving four rounds of questionnaires distributed to 363 data science professionals to evaluate the factors affecting their innovation capacity. The data was rigorously analyzed using mathematical statistics and SPSS, with a strong emphasis on questionnaire validity and reliability. In the reliability analysis, Cronbach's α was found to be 0.98, indicating a high level of internal consistency. The research results yielded an average score of 4.79, SD = 0.39, IQR = 1, reflecting a strong consensus among experts in agreement with the research findings. Exploratory factor analysis was employed for validity assessment, revealing that the 12th factor accounted for a cumulative variance explanation rate of 76.54%, exceeding the threshold of 60%, signifying the robust structural validity of the questionnaire data. The study also utilized AMOS software to simulate sample data and assess the influence coefficients of individual, organizational, and family characteristics on innovation capacity, resulting in values of 0.53, 0.39, and 0.22, respectively, all greater than 0, indicating favorable influence relationships. Building upon these findings, a comprehensive model of creativity abilities among Chinese data science professionals is proposed. This research critically examines the innovation potential of data science professionals in Chinese academia, with the overarching goal of enhancing their creative skills and competitiveness within the data science field. Additionally, it lays the theoretical groundwork for fostering innovation within the university setting.
Structural Equation Modeling Factors That Influence Online Course Acceptance in University Students Yuniansyah Yuniansyah; Febria Sri Handayani; Eka Hartati; Yarza Aprizal
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.v6i4.863

Abstract

Online courses are currently growing rapidly, influenced by various factors, especially among college students. This study uses the Technology Acceptance Model, by adding the variable of facilitating conditions. This study aims to determine the effects of perceived ease of use, perceived usefulness, and facilitating conditions on the actual use of online courses, mediated by intention to use. This study is the first conducted on students in university in South Sumatra, Indonesia, who have used or are currently using online courses. The data collection was carried out from June 24, 2024, to August 9, 2024. The research instrument used was a questionnaire based on a 5-point Likert scale. The sampling technique used in this study was purposive sampling, targeting students at universities under the Higher Education Service Institution Region II in Indonesia. A total of 360 students participated as respondents. The questionnaire results were analyzed using Structural Equation Modeling – Partial Least Squares (SEM-PLS). Data analysis was conducted using the SmartPLS software, version 4.1.1.2. The results showed that perceived ease of use had a significant influence on intention to use (path coefficient = 0.281, T-statistic = 6.642, P-value = 0.000), and perceived usefulness also had a positive influence on intention to use (path coefficient = 0.155, T-statistic = 4.545, P-value = 0.000). Facilitating conditions also had a positive influence on intention to use (path coefficient = 0.476, T-statistic = 8.880, P-value = 0.000), and intention to use significantly influenced actual use (path coefficient = 0.452, T-statistic = 10.490, P-value = 0.000). These findings highlight the important role of perceived ease of use, perceived usefulness, and facilitating conditions—mediated by intention to use—in significantly influencing the actual use of online courses among students, particularly at universities under the jurisdiction of the Higher Education Service Institution Region II in Indonesia.

Page 96 of 127 | Total Record : 1270