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
Enhancing Field-Controlled DC Motors with Artificial Intelligence-Infused Fuzzy Logic Controller Essam Natsheh
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.v6i1.508

Abstract

Servomotors play a pivotal role in a wide array of everyday and industrial applications. Field-controlled DC motors particularly stand out for positioning tasks owing to their advantageous speed-torque characteristics. An optical encoder, integrated with the rotor, provides feedback to a PID controller, which in turn generates corrective signals for precise motor positioning. To enhance response speed and minimize hunting, the PID controller incorporates fuzzy logic programming. This paper introduces a novel optimization design approach utilizing a Performance-Oriented Rule-Based Controller (PDFCS) in conjunction with various PID fuzzy controller design methods to attain specific performance goals. Given the criticality of constructing membership functions in fuzzy controllers, a self-optimized membership functions algorithm is proposed. Accuracy analysis demonstrates that the proposed design method achieves a 2.9-second reduction in rise time, a 2.0-second decrease in settling time, and a 1.9% reduction in overshoot compared to conventional design methods. Furthermore, robustness analysis reveals a 4.0-second improvement in rise time, a 1.7-second enhancement in settling time, and a 0.79% decrease in overshoot. These findings underscore the superior accuracy and robustness of employing the proposed performance model alongside various PID fuzzy controller design methods, compared to relying solely on conventional design approaches.
Development and Research of an Autonomous Device for Sending a Distress Signal Based on a Low-Orbit Satellite Communication System Nurbolat Ondyrbayev; Sabyrzhan Zhumagali; Katipa Chezhimbayeva; Yelaman Zhumanov; Nursultan Nurzhauov
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.v5i3.289

Abstract

Due to the importance of providing reliable communication for sending distress signals, research on the development of an autonomous device via low-orbit satellites is becoming particularly relevant, offering innovative solutions capable of providing fast and reliable communication in extreme situations. The purpose of this study was to investigate a device capable of operating autonomously in emergency situations and providing fast transmission of a signal about the need for help. The comparative method, statistical method, and analysis were used in the framework of research. The results of the study showed the significant potential of Long-Range Wide Area Networks (LoRaWAN) technology in the field of wireless communication. It provides high stability and noise immunity of data transmission, which makes it an attractive choice for various applications. Due to its high scalability, LoRaWAN is capable of servicing tens and hundreds of thousands of devices, making it an ideal solution for large-scale projects. LoRaWAN can achieve data transmission rates between 0.3 kbps to 50 kbps, with power consumption as low as 1.2 µA in sleep mode and 28 mA in transmit mode, and communication ranges up to 15 km in rural environments. Because of its low power consumption, it is ideal for use in battery-powered devices such as smart and distress sensors. In addition, it was found that the use of EBYTE E32 modules in LoRaWAN devices ensures reliable and efficient data transfer. The study confirms the potential of LoRaWAN technology for developing efficient and reliable wireless communication systems for various Internet of Things applications, ensuring reliable data transmission under various conditions. The results obtained are of great practical importance for the creation and further improvement of autonomous devices for the rapid sending of distress signals, contributing to increased safety and responsiveness to emergency situations.
An Adaptive Random Forest for Data Stream Sentiment Classification under Concept Drift Brian Farrel Arkana; Sudianto Sudianto; Nenen Isnaeni
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.v7i2.1153

Abstract

Data labeling plays a crucial role in determining the performance of machine learning models, especially in data stream environments where concept drift frequently occurs. The primary objective of this study is to analyze the effectiveness of adaptive learning models in managing dynamic data distribution changes and to evaluate the influence of different labeling strategies on sentiment classification performance using user reviews from the OVO mobile application. The research contributes to understanding how labeling approaches interact with adaptive modeling under real-time data stream conditions. Two labeling methods were employed: score-based labeling derived from user ratings and content-based labeling generated automatically using the IndoRoBERTa language model. These labeled data streams were evaluated using two classifiers: a conventional Random Forest model and an Adaptive Random Forest model designed to handle evolving data distributions. The evaluation was conducted through streaming experiments that continuously fed new review data to simulate real-world drift scenarios. The results reveal that in the score-based labeling scenario, the conventional Random Forest model’s accuracy gradually declined, reaching a final accuracy of 31%, while the Adaptive Random Forest achieved 80%, reflecting a 49% performance gap. In the content-based labeling scenario, both models improved over time, with final accuracies of 57% for Random Forest and 76% for the adaptive model, resulting in a 19% difference. These findings indicate that Adaptive Random Forest is more robust in adapting to distributional and temporal changes in data streams regardless of the labeling strategy used. This study implies that combining adaptive learning with semantically rich labeling approaches can substantially enhance model reliability in real-time sentiment analysis tasks. Future research may further explore hybrid adaptive mechanisms to improve the resilience of data stream classification models across various domains.
Improving Evaluation Metrics for Text Summarization: A Comparative Study and Proposal of a Novel Metric Junadhi Junadhi; Agustin Agustin; Lusiana Efrizoni; Finanta Okmayura; Dedi Rahman Habibie; Muslim Muslim
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.v6i2.547

Abstract

This research evaluates and compares the effectiveness of various evaluation metrics in text summarization, focusing on the development of a new metric that holistically measures summary quality. Commonly used metrics, including ROUGE, BLEU, METEOR, and BERTScore, were tested on three datasets: CNN/DailyMail, XSum, and PubMed. The analysis revealed that while ROUGE achieved an average score of 0.65, it struggled to capture semantic nuances, particularly for abstractive summarization models. In contrast, BERTScore, which incorporates semantic representation, performed better with an average score of 0.75. To address these limitations, we developed the Proposed Metric, which combines semantic similarity, n-gram overlap, and sentence fluency. The Proposed Metric achieved an average score of 0.78 across datasets, surpassing conventional metrics by providing more accurate assessments of summary quality. This research contributes a novel approach to text summarization evaluation by integrating semantic and structural aspects into a single metric. The findings highlight the Proposed Metric's ability to capture contextual coherence and semantic alignment, making it suitable for real-world applications such as news summarization and medical research. These results emphasize the importance of developing holistic metrics for better evaluation of text summarization models.
Predictive and Analytics using Data Mining and Machine Learning for Customer Churn Prediction Chandra Lukita; Lalu Darmawan Bakti; Umi Rusilowati; Asep Sutarman; Untung Rahardja
Journal of Applied Data Sciences Vol 4, No 4: DECEMBER 2023
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v4i4.131

Abstract

This research aims to predict and analyze customer churn using Data Mining and Machine Learning methods. The background of this research is based on the importance of understanding the factors that influence customer decisions to churn, as well as improving the effectiveness of customer retention strategies in a business context. The method used in this research involves the use of a customer bank dataset that includes information about customers who left in the past month, services registered by customers, customer account information, and demographic info about customers. The factors most influential to churn were identified through heatmap analysis, including MonthlyCharges, PaperlessBilling, SeniorCitizen, PaymentMethod, MultipleLines, and PhoneService. This research compares the performance of several machine learning algorithms, including Random Forest, Logistic Regression, Adaboost, and Extreme Gradient Boosting (XGBoost), to predict customer churn. Accuracy metrics and confusion matrix results are used to evaluate the performance of these algorithms. The results showed that XGBoost proved to be the best algorithm in predicting customer churn with high accuracy. The factors that have been correctly identified do not provide missed precision, showing a significant influence on customer churn decisions. The novelty and uniqueness of this research lies in focusing on the factors that have the most influence on customer churn and comparing the performance of machine learning algorithms. This research provides more specific and relevant insights for companies in developing effective customer retention strategies. However, this research has some limitations. One of them is the use of a dataset limited to a customer bank, so the generalizability of the findings of this research may be limited to that business context. In addition, other factors that are not the focus of this research may also contribute to the prediction of customer churn.
A Hybrid LSTM–Stacking–SMOTE Model for Weather-Aware Palm Oil Price Prediction Addressing Data Imbalance and Forecast Accuracy Kusmanto Kusmanto; S Subagio; Erni Manja
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.v6i4.922

Abstract

Accurate forecasting of palm oil prices is crucial for agribusiness decision-making due to high market volatility influenced by dynamic weather conditions. This study proposes a novel hybrid deep learning model combining Long Short-Term Memory (LSTM), Stacking Ensemble, and Synthetic Minority Over-sampling Technique (SMOTE) to improve predictive accuracy and handle class imbalance in price trend classification. The model was trained using a multivariate time-series dataset sourced from Kaggle, consisting of daily records of temperature, humidity, rainfall, and palm oil prices. A binary classification scheme was applied by labeling instances as either price increase (class 1) or price stable/decrease (class 0), based on a 0% price change threshold. Four experimental configurations were evaluated: standard LSTM, LSTM + SMOTE, LSTM + Stacking, and the proposed LSTM + SMOTE + Stacking. The proposed model outperformed all baselines, achieving the highest accuracy of 83.12%, an F1-score of 0.8466, MAE of 0.1688, RMSE of 0.4109, and a perfect recall of 1.0000, indicating excellent sensitivity to minority class trends. In contrast, the standard LSTM achieved only 77.32% accuracy and an F1-score of 0.7224, showing limited ability in handling imbalanced data. Visualization of loss curves and confusion matrices confirmed the model’s learning stability and classification effectiveness. This study contributes a novel integration of ensemble learning and oversampling in time-series commodity forecasting and demonstrates the effectiveness of this approach in capturing weather-driven price patterns, offering a robust framework for predictive analytics in agriculture.
Leveraging K-Nearest Neighbors with SMOTE and Boosting Techniques for Data Imbalance and Accuracy Improvement Adyanata Lubis; Yuda Irawan; Junadhi Junadhi; Sarjon Defit
Journal of Applied Data Sciences Vol 5, No 4: DECEMBER 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i4.343

Abstract

This research addresses the issue of low accuracy in sentiment analysis on Israeli products on social media, initially achieving only 64% using the K-NN algorithm. Given the ongoing Israeli-Palestinian conflict, which has garnered widespread international attention and strong opinions, understanding public sentiment towards Israeli products is crucial. To improve accuracy, the study employs SMOTE to handle data imbalance and combines K-NN with boosting algorithms like AdaBoost and XGBoost, which were selected for their effectiveness in improving model performance on imbalanced and complex datasets. AdaBoost was chosen for its ability to enhance model accuracy by focusing on misclassified instances, while XGBoost was selected for its efficiency and robustness in handling large datasets with multiple features. The research process includes data pre-processing (cleaning, normalization, tokenization, stopwords removal, and stemming), labeling using a Lexicon-Based approach, and feature extraction with CountVectorizer and TF-IDF. SMOTE was applied to oversample the minority class to match the number of instances in the majority class, ensuring balanced representation before model training. A total of 1,145 datasets were divided into training and testing data with a ratio of 70:30. Results demonstrate that SMOTE increased K-NN accuracy to 77%. Interestingly, combining K-NN with AdaBoost after SMOTE achieved 72% accuracy, which, although lower than the 77% achieved with SMOTE alone, was higher than the 68% accuracy without SMOTE. This discrepancy can be attributed to the added complexity introduced by AdaBoost, which may not synergize as effectively with SMOTE as XGBoost does, particularly in this dataset's context. In contrast, K-NN with XGBoost after SMOTE reached the highest accuracy of 88%, demonstrating a more effective combination. Boosting without SMOTE resulted in lower accuracies: 68% for KNN+AdaBoost and 64% for KNN+XGBoost. The combination of K-NN with SMOTE and XGBoost significantly improves model accuracy and reliability for sentiment analysis on social media.
Optimizing XGBoost with Optuna for Attendance-Based Prediction of Student Academic Success Marcello Roy; Ririn Ikana Desanti; Iwan Prasetiawan; Suryasari Suryasari
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.v7i2.1116

Abstract

The growth of data analytics in higher education has increased the need for predictive models that identify students’ academic potential and support data-driven decision-making. Academic institutions are able to enhance student outcomes by implementing suitable interventions that are based on an accurate early prediction of Grade Point Average (GPA). This study aims to develop a practical and accurate GPA prediction model based on Extreme Gradient Boosting (XGBoost), enhanced through Optuna-based hyperparameter tuning, to support academic monitoring systems in higher education. This model is intended to assist academic monitoring systems in higher education. Using academic performance data, attendance records, and course load information obtained from 961 undergraduate students, a quantitative predictive modeling approach was implemented. The CRISP-DM framework was implemented during the modelling process, which included the following stages: data understanding, data preparation, modelling, evaluation, and deployment. To ensure the stability and relevance of the model, exploratory analysis and correlation assessments were implemented to determine feature selection. Optuna was employed to optimize hyperparameters, utilizing Bayesian optimization with adaptive trial pruning to efficiently examine the parameter space. Experimental results demonstrate that the Optuna-tuned XGBoost model achieved superior predictive performance compared to baseline XGBoost models and models optimized using Grid Search and Random Search. The proposed model attained a coefficient of determination (R²) of 0.8637 and a Root Mean Square Error (RMSE) of 0.1165, indicating improved accuracy and robustness in handling large prediction errors. To enhance practical applicability, the final model was deployed in a Streamlit-based web application that enables real-time GPA prediction and supports academic advisors. Overall, the findings confirm that Optuna-based hyperparameter tuning significantly enhances XGBoost performance and provides a solution for data-driven academic monitoring in higher education institutions.
Intelligent Web Search Recommender System: An Application of Ensemble of Convolution Neural Network for Deep Semantic Content Analysis of Web Documents Suruchi Chawla
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.v6i2.571

Abstract

Web Information retrieval is widely used for retrieving web documents relevant to the user search query. Search engines retrieve huge collection of web documents for a given search query and an information overload problem arises for the web user.  Web page recommender systems are widely used to deal with the information overload problem. Quality of the web page recommendations for a given search query depends heavily on the document feature representation. In this research a novel method is explained for Intelligent web search based on deep semantic content analysis of clicked web documents using an ensemble of convolution neural network. Deep learning model Convolution neural network has been used in the research for feature generation and it effectively represents the text characterization for classification. The optimized web document feature vector is generated using the ensemble of CNN is finally averaged at the output layer for clustering. The resulting clusters of optimal web documents optimized feature vector therefore groups semantic similar web documents in a given cluster for web page recommendations during web search. Experiment results confirm the improvement in average precision to 93% across all selected domains that shows the relevant web documents are increased in the recommendations based on clusters of web document optimal feature vectors generated using ensemble of CNN. Thus, the proposed system performs the Intelligent web search recommendations based on the deep semantic deep content analysis of web documents using an ensemble of CNN.
Applied Regression Modelling to Recommend Sustainable Tourism Development Policies: A Case Study of Danang City in Vietnam Nguyen Duc Tien
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.v5i2.188

Abstract

Sustainable tourism development is one of the top focuses not only in Vietnam but also around the world. Especially when Covid-19 began to break out in early 2020, causing most tourism activities to stop and causing many communities that considered tourism to be completely independent from other industries to have time to look back. Thus, the article aims to identify the main factors contributing to sustainable tourism development in Danang City, Vietnam. Accordingly, some contents need to clarify factors affecting sustainable tourism development, measuring the characteristics and the role of each factor impacting sustainable tourism development. Finally, policy implications for sustainable tourism development in the future are proposed. Based on the goal, the author surveyed 600 tourists and used the regression modeling method from data processed using SPSS 20.0. In addition, the results showed six factors affecting sustainable tourism development with a significance of 0.01. This situation requires more practical recommendations from state management agencies and tourism enterprises. The contributions of this study suggest sustainable tourism development policies to balance economic development, social stability, and environmental protection. The article evaluates sustainability, considering the cohesion and balance of sustainable development aspects, such as economic, social, and environmental, thereby going deeper and identifying groups of activities. The main drivers to achieve sustainable tourism development include economics, society, environment, tourism resources, tourism products and services, and infrastructure. The research novelty discusses proposed six recommendations, which include (1) infrastructure development, (2) developing technical facilities for the tourism industry, (3) developing human resource training, (4) level of organization and management of the tourism industry, (5) quality of tourism services, and (6) community participation for sustainable tourism development in Danang City, Vietnam.