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
Utilizing the Delphi Technique to Develop a Self-Regulated Learning Model Yongmei Li; Thosporn Sangsawang; Kitipoom 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.v4i3.124

Abstract

This study combines learning process theories within the context of data science education in Sichuan Province, China, and develops a customized instructional model for the self-regulated International Higher Education (IHE) Model. In collaboration with 17 experts, selected through purposive sampling, and involving 100 instructors within Sichuan, China, this research explores an instructional model designed to foster self-regulated learning in the field of data science. The Delphi data collection method is employed to investigate the relevance of various learning theories within international higher education in Sichuan Province, China, with a specific emphasis on the data science discipline. The Self-Regulated Learning in International Higher Education (SLR-IHE) model, informed by survey questionnaires, addresses pertinent challenges encountered in data science education, including issues related to English language proficiency, faculty training, curriculum development, faculty mobility, cross-border regulations, and funding constraints. The findings of this study lead to the development of an International Higher Education (IHE) Model for Sichuan Province, China, using the Delphi Technique, which consists of four distinct instructional modules. Through a linear regression analysis of the SLR-IHE model, it becomes evident that the self-regulated learning process in data science education comprises four essential stages, each contributing to the acquisition of distinct goals. These stages include: (1) activating prior knowledge; (2) fostering idea exchange and iterative improvement; (3) building organizational knowledge through understanding, memorization, analysis, and transfer; and (4) generating innovative ideas through reflexive thinking and initiating creative thought processes. These stages collectively support the achievement of specific goals associated with Self-Managed Learning (SML), Self-Regulated Learning (SRL), Self-Paced Learning (SPL), and Self-Directed Learning (SDL) in the context of data science education. This comprehensive instructional model for data science education within the framework of international higher education development in Sichuan Province, China, emphasizes globalization, collaborative efforts, and economic growth as key drivers for enhancing the quality of education in the field of data science.
Optimization of Machine Learning Models for Risk Prediction of DHF Spread to Support Management Strategies in Urban Areas Yesica Devis; Muhamadiah Muhamadiah; Yulanda Yulanda; Yuda Irawan; Refni Wahyuni
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.v6i4.898

Abstract

Dengue fever is an endemic disease that poses a serious threat to public health in tropical regions such as Indonesia. Efforts to control this disease require a data-based approach that is able to accurately predict the level of risk so that interventions can be targeted. This study aims to develop a predictive model of DHF risk using ensemble stacking method optimized with Optuna algorithm and integrated into an interactive dashboard based on Streamlit. The dataset used includes environmental, climate, and socio-demographic indicators from 2015 to 2024 with a total of 1,440 data entries. The preprocessing process includes normalization with Standard Scaler, feature selection using LASSO, and label data balancing with the SMOTE method. Model validation was performed using 10-Fold Cross Validation to ensure model generalization to new data. The stacking model is built with three basic algorithms, namely SVM, KNN, and Random Forest, which are combined using Logistic Regression as a meta-learner. The evaluation results show that the model is able to achieve an average accuracy of 97.57%, with high precision, recall, and f1-score values in all three prediction classes (low, medium, high). The ROC-AUC for each class also showed near-perfect performance. The implementation of the model in the Streamlit dashboard allows non-technical users such as health center or health office staff to perform regional risk prediction and obtain data-driven intervention recommendations automatically. This research not only contributes to the development of predictive technology, but also strengthens evidence-based health promotion practices in urban areas. Further research is recommended to integrate IoT-based real-time data and expand the scope of application areas.
Modeling Ramadan Hilal Classification with Image Processing Technology Using YOLO Algorithm Nenny Anggraini; Zulkifli Zulkifli; Nashrul Hakiem
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.v5i3.311

Abstract

This research aims to create a model for classifying hilal using the YOLO algorithm. The determination of the beginning of the month of Ramadan is an important aspect of the Islamic calendar that has an impact on the implementation of fasting. With technological advances, especially in image processing, there is potential to overcome the limitations of conventional methods currently used in hilal detection for determining the beginning of Ramadan. This research uses the prototyping method in its implementation. The dataset in this research comes from videos on the BMKG Youtube channel and images from various sources such as NASA Planetary Data System and Google Images. YOLOv5 and YOLOv8 algorithms are used to develop the object detection model. The novelty of this research is the use of the YOLO algorithm with video datasets to detect hilal to determine the beginning of the month of Ramadan and Shawwal. The best-performing model, YOLOv5m with 100 epochs and a batch size of 30, achieved a precision of 0.838 and a mAP of 0.5-0.95 of 0.735. The results indicate that YOLOv5m is more effective in hilal detection, providing a novel approach to determine the beginning of Ramadan and Shawwal with greater accuracy and consistency. This integration of advanced object detection technology with religious practice offers a significant improvement over traditional method.
Iris Identification Using Resnet Iris Feature Extraction Architecture For Better Biometric Security Hendi Sama; Tukino Tukino; Mangapul Siahaan; Erica Titoni
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.v7i2.1166

Abstract

Iris recognition is widely acknowledged as one of the most reliable biometric modalities due to its high uniqueness, rich textural patterns, and long-term stability. Unlike other biometric traits, iris characteristics resist forgery, aging effects, and environmental variations, making it suitable for high-security applications. Recently, convolutional neural networks (CNNs) have been extensively applied in iris recognition to improve feature representation and classification accuracy. However, many CNN-based approaches still depend on conventional segmentation and handcrafted features, which reduce robustness under noisy data, illumination variations, occlusions, or unconstrained environments. To address these limitations, this study proposes an enhanced iris identification framework combining a modified T-Net for precise segmentation with deep residual feature extraction for improved discrimination. Unlike conventional systems focus mainly on classification, the proposed approach emphasizes segmentation-driven feature consistency, ensuring extracted features originate from accurately localized iris regions. This design enhances stability and reliability, particularly under challenging imaging conditions. The framework leverages transfer learning and efficient representation learning strategies, enabling high accuracy even with a limited labelled data. Evaluations on three benchmark datasets CASIA-IrisV4, IITD Iris Database, and UBIRIS.v2 covering both controlled and less-constrained acquisition scenarios. Results show that it achieves classification accuracy of up to 98.35%, while maintaining computational efficiency suitable for deployment. The proposed architecture offers a robust, data-efficient, and scalable solution for secure biometric authentication, with strong potential for real-world applications such as access control, identity verification, and high-security authentication systems.
The CNN Model with YOLO Architecture for Ultrasonography Images in Early Breast Cancer Detection Astika Ayuningtyas; Hero Wintolo; Arwin Datumaya Wahyudi Sumari; Emy Setyaningsih; Asih Pujiastuti; Anton Setiawan Honggowibowo; Edi Triono Nuryatno; Anggraini Kusumaningrum
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.v6i2.587

Abstract

The rapid development of object detection technology has opened new opportunities in the healthcare sector, especially in early cancer detection. This paper presents a deep learning-based breast cancer detection system using ultrasound images. The primary goal of this study is to create a model that can effectively differentiate between malignant and benign breast tumors, assisting in early diagnosis. The proposed system employs the Convolutional Neural Network (CNN) algorithm with You Only Look Once version 5 (YOLOv5) architecture, which is renowned for its high speed and accuracy in object detection tasks. A dataset comprising 10,954 ultrasound images was used to train the model, with 70% allocated for training, 20% for validation, and 10% for testing. The study reveals that the model achieves a high accuracy rate of 92.8% for malignant tumor detection and 99.1% for benign tumors, with precision rates of 99.6% for malignant tumors and 97.5% for benign tumors. These results demonstrate the feasibility of the proposed model as a reliable tool for early breast cancer detection. The findings highlight the potential of deep learning in medical image processing, suggesting that this technology could be further developed into an accessible, efficient early detection system for breast cancer in clinical settings. Future research could explore the integration of additional imaging modalities and the application of this model in real-world healthcare environments
Exploring the Impact of Discount Strategies on Consumer Ratings: An Analytical Study of Amazon Product Reviews Berlilana Berlilana; Arif Mu’amar Wahid; Dewi Fortuna; Alfin Nur Aziz Saputra; Galih Bagaskoro
Journal of Applied Data Sciences Vol 5, No 1: JANUARY 2024
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v5i1.163

Abstract

This research delves into the influence of discount strategies on consumer ratings within the e-commerce landscape, particularly on Amazon. A logistic regression model assessed how discount percentages and product categories affect consumer ratings. The study followed a rigorous methodology, beginning with comprehensive data collection across diverse product categories on Amazon. This was succeeded by a detailed exploratory data analysis (EDA), data preprocessing, and subsequent model building. The model was then subjected to an extensive evaluation process, encompassing accuracy, precision, recall, F1-score, and ROC-AUC metrics. The evaluation revealed that the model achieved an accuracy of 74.94%, a precision of 72.69%, and a recall of 74.94%. The F1 score was calculated at 69.26%, and the ROC-AUC score was notably 78.24%. These metrics underscore the model’s capability to accurately predict consumer ratings influenced by discount strategies. Key findings highlighted the significant predictive power of discount percentages and specific product categories, particularly 'Home Kitchen', suggesting a complex relationship between discounts, product types, and consumer responses. Theoretically, the study enriches the understanding of consumer behavior in e-commerce, highlighting the nuanced impact of discount strategies on consumer satisfaction, especially in online retail contexts. For e-commerce businesses and marketers, the findings underscore the importance of strategically employing discount strategies and tailoring marketing approaches to specific product categories. This study emphasizes managing customer expectations and maintaining product quality alongside discounts. This research provides valuable insights for optimizing e-commerce strategies and paves the way for future investigations. It opens up avenues for further exploration into factors like product quality, brand reputation, shipping times, and the potential of consumer segmentation and sentiment analysis in enhancing marketing effectiveness. The study marks a significant contribution to the field by linking discount strategies with consumer ratings, using advanced data analytics to inform e-commerce practices in the digital age.
A Hybrid GRG-Neighborhood Search Model for Dynamic Multi-Depot Vehicle Routing in Disaster Logistics Dedy Hartama; Poningsih Poningsih; Lili Tanti
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.v6i4.973

Abstract

In disaster relief logistics, timely and adaptive routing is critical to meet fluctuating demands and disrupted infrastructure. This paper proposes a Hybrid GRG–Neighbourhood Search (NS) model for solving the Multi-Depot Vehicle Routing Problem with Capacity and Time Dependency (MDVRP-CTD). The model integrates the Generalized Reduced Gradient (GRG) method for handling nonlinear capacity constraints and NS for local route refinement. The objective is to minimize total travel distance, delay penalties, and maximize vehicle utilization under dynamic disaster scenarios. Tested using the SVRPBench dataset, the hybrid model achieved up to 96.5% demand fulfillment, an 11% improvement in vehicle utilization, and a reduction in total distance by 7%, outperforming Tabu Search and ALNS in three simulation scenarios. The model demonstrates enhanced adaptability and responsiveness to time-sensitive, capacity-constrained environments. Its novelty lies in the integration of nonlinear optimization with adaptive local improvement tailored for disaster contexts, providing a robust decision-support tool for real-time humanitarian logistics.
Realtime and Spatial Data Analysis-based Monitoring System for Proboscis Monkey Habitat Health to Enhance Conservation Area Management Effectiveness Anni Nurliani; Krisdianto Krisdianto; Amalia Rezeki; Munsyi Munsyi
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.v5i4.334

Abstract

The conservation of proboscis monkeys (Nasalis larvatus), an endemic primate species of Borneo, faces significant threats due to habitat degradation and declining populations. This study aims to develop a real-time and spatial data analysis-based monitoring system to improve the management of conservation areas for the species’ natural habitats. Conducted in the wetland ecosystems of Curiak Island, South Kalimantan, the research integrates remote sensing, Geographic Information Systems (GIS), and Internet of Things (IoT) technologies to monitor key environmental parameters such as vegetation health, land surface temperature (LST), and others. Indices like the Normalized Difference Vegetation Index (NDVI), Vegetation Health Index (VHI), Vegetation Condition Index (VCI), Temperature Condition Index (TCI), and Environmental Critical Index (ECI) are utilized to assess habitat conditions. Initial results showed poor vegetation health, with an NDVI of 0.6085, high LST of 20.41°C, and considerable environmental stress, reflected by an ECI of 74. Restoration efforts, however, improved conditions, with the NDVI rising to 0.7288, LST decreasing to 20.75°C, and the ECI lowering to 53 in the restoration area, signaling recovery. Though the ECI still suggests moderate environmental stress, the trend is positive. IoT sensors provided continuous real-time data, including CO levels at 0.2 PPM, CO2 at 34,045 PPM, O2 at 20.4% Vol, temperatures ranging from 33.155°C to 33.185°C, humidity between 67.45% and 67.65%, and pH at 6.8. Data on dissolved oxygen, total dissolved solids (TDS), and turbidity were also collected, providing dynamic insights into environmental conditions. The integration of community-based approaches ensures sustainable conservation efforts through local participation. This comprehensive monitoring system supports both proboscis monkey conservation and broader ecological objectives like biodiversity preservation, climate change mitigation, and ecosystem service provision, emphasizing adaptive management in conservation strategies.
Interpretive Modelling of the Dynamics of Psycho-Emotional States Based on the Analysis of Video Streams and Systems of Differential Equations Indira Bukenova; Lyazat Naizabayeva; Gani Bukenov; Bayan Kazangapova
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.v7i3.1338

Abstract

The aim of this study is to develop an interpretable mathematical model that describes the dynamics of a person’s psycho-emotional state based on video surveillance data. The main contribution of the research is a paradigm shift from static recording of emotions to continuous dynamic modeling. The proposed approach allows for the internal inertia of the psyche, delay effects, and relaxation processes, which are not accessible in traditional frame-by-frame analysis. The method is based on representing psycho-emotional states as a complex system, where latent variables reflect levels of calmness C(t), stress S(t), mood M(t), and exhaustion E(t). To control activity levels-visual arousal A(t), emotional valence V(t), and physical fatigue F(t)-objective markers extracted from the video stream using artificial intelligence methods are employed. The mathematical core of the model is a system of ordinary differential equations, which ensures the transparency and interpretability of the state control process. Numerical simulation was performed over a time interval of 300.0 s with a discretization step of 0.1 s. using the Runge-Kutta integration method. The maximum excitation was Amax = 0.944 at t = 145.6 s, and the stress reached a maximum of Smax = 1.0 at t = 133.5 s. To assess the model’s adequacy, we employed phase analysis methods and calculated Spearman’s rank correlation between the input features and the system’s latent states. The main results demonstrate that the proposed model effectively reproduces complex psychological effects, such as hysteresis and emotional memory. The findings are critical for the development of proactive monitoring systems in the fields of public safety and digital healthcare. The model has been validated with real-world data and allows not only for the detection of current stress but also for the prediction of recovery dynamics, thereby facilitating the timely prevention of dangerous situations from escalating.
Exploratory Data Analysis & Booking Cancelation Prediction on Hotel Booking Demands Datasets Pujo Hari Saputro; Herlino Nanang
Journal of Applied Data Sciences Vol 2, No 1: JANUARY 2021
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v2i1.20

Abstract

Online ordering is the latest breakthrough in the hospitality industry, but when it comes to booking cancellations, it has a negative impact on it. To reduce and anticipate an increase in the number of booking cancellations, we developed a booking cancellations prediction model using machine learning interpretable algorithms for hotels. Both models used Random Forest and the Extra Tree Classifier share the highest precision ratios, Random Forest on the other hand has the highest recall ratio, this model predicted 79% of actual positive observations. These results prove that it is possible to predict booking cancellations with high accuracy. These results can also help hotel owners or hotel managers to predict better predictions, improve cancellation regulations, and create new tactics in business.