International Journal of Advances in Data and Information System
Not a member yet
161 research outputs found
Sort by
Analysis of A Deep Learning Algorithm for Fracture Detection In X-Ray Images
Full text linkIdentifying bone fractures in X-ray images is a complex task that requires special expertise from radiologists and can be time-consuming in clinical workflows. Deep learning offers a significant automated diagnostic solution to improve accuracy and efficiency. This study aims to analyze the performance of three Convolutional Neural Network (CNN) architectures namely, ResNet50, DenseNet169, and EfficientNet-B3 and specifically compare the performance of models trained using augmented data with that of models trained without augmentation. The research method utilizes a local dataset, which is divided equally between the fractured and non-fractured classes. Preprocessing techniques such as Contrast Limited Adaptive Histogram Equalization (CLAHE) were applied, and the models were evaluated on a separate test set (hold-out test set). Model evaluation was conducted using accuracy, precision, recall, F1-score, ROC-AUC metrics, as well as analysis through confusion matrix, classification report, sensitivity, specificity, and calibration curve to assess overall performance. The experimental results show that the application of data augmentation consistently improves the accuracy and robustness of all three models. In the augmentation scenario, EfficientNet-B3 showed the best performance, achieving an accuracy of 93.33%. This study concludes that the combination of the EfficientNet-B3 architecture with the data augmentation strategy is the most optimal and recommended approach for developing a reliable automatic detection system on local X-ray image datasets
Web-Based Village Land Information System Development for Optimizing Regional Land Administration
Full text linkAccess to land information in Indonesia is restricted, especially at the village and sub-district levels, where detailed data is essential for efficient land administration. This research aims to create a web-based Village Land Information System to improve regional land administration through the provision of organized, accessible, and dependable land data. The study employed a Research and Development (R&D) methodology using a prototyping approach, gathering data through observation, surveys, and literature analysis. Data were examined using both descriptive and quantitative methods, with validation and reliability assessments conducted on questionnaires administered to 100 respondents. The assessment employed the End User Computing Satisfaction (EUCS) and Importance-Performance Analysis (IPA) methodologies. The system development encompassed multiple phases: requirements analysis, prototype design, implementation, functionality testing, and evaluation. The Unified Modeling Language (UML) was utilized for system modeling, and user interfaces were crafted with a focus on usability. Functionality tests verified that all features functioned well, and user assessments revealed significant satisfaction with the system’s content, correctness, format, usability, and promptness. The application markedly enhanced land administration by providing comprehensive land information, facilitating access, elucidating service procedures, and systematizing data storage. The results illustrate the capability of web-based technologies to enhance regional land administration and facilitate village government in improving service delivery and land information management
Factor Affecting User Satisfaction of Property Management Helpdesk Mobile Application Using End User Computing Satisfaction (EUCS) Modification Model
Full text linkThe property industry has benefited from ongoing technological advancements in apartment management. In Indonesia, apartments are among the fastest-growing real estate types. Consequently, tenants face greater competition for quality services, especially in helpdesk support. The property management helpdesk application is a modern solution developed by the property business to improve service delivery. Tenants can submit requests and complaints directly through mobile apps. This study employs a modified End User Computing Satisfaction (EUCS) model to evaluate user satisfaction with the helpdesk application. Additional variables include system quality, perceived usefulness, and attitude toward use. A simple random sampling strategy and quantitative methodology were applied. Primary data were collected through questionnaires from 336 users of the property management helpdesk application. Findings indicate that system quality, content, accuracy, format, ease of use, and timeliness positively affect users’ attitudes toward the application. The results also show that both system quality and attitude toward use have a significant positive impact on user satisfaction. These data provide valuable insights for improving the application functionalities and user experience. The findings assist property management in improving service quality via enhanced application performance, elevating user happiness and renter retention in a competitive property landscape
Customer Transaction Clustering with K-Prototype Algorithm Using Euclidean-Hamming Distance and Elbow Method
Full text linkThis study aims to cluster customer transactions in a Japanese food stall using the K-Prototype Algorithm with a combination of Euclidean-Hamming Distance and the Elbow method. Facing intense industry competition, this study seeks to understand customer purchasing behavior to increase loyalty and sales. From 9.721 initial entries, 9.705 cleaned and transformed records were analyzed. K-Prototype was chosen because of its ability to handle numeric features (Total Sales, Product Quantity) and categorical features (Payment Method, Order Type, Day Category and Time Category). The combination of Euclidean-Hamming distances was used for distance measurement. The optimal number of clusters was determined using the Elbow method, with the results recommending three clusters as the most optimal number. A Silhouette score of 0.6191 indicates a Good Structure clustering result, effectively identifying three distinct customer grouping: "Loyal Regulars" (49.5%), "Casual Shoppers" (42.3%), and "Premium Shoppers" (8.2%). Statistical validity was also tested using ANOVA and Chi-Square, the results showed significant differences between the clusters in numerical and categorical variables with a p-value <0.0001. The clusters are statistically valid in both numerical and categorical aspects. These insights provide an understanding of customer characteristics and reveal a strategically valuable cluster for targeted marketing
Machine Learning-Based Prediction of Divorce Verdicts Using Posita Data and Imbalanced Data Handling: A Case Study in Padang Sidempuan
Full text linkThis study aims to develop a predictive model for divorce verdicts ("Granted" or "Rejected") in the Religious Courts of Indonesia using machine learning techniques. The dataset consists of 2,026 finalized divorce cases from the Religious Court of Padang Sidempuan between 2018 and 2025, incorporating structured variables and posita—narrative texts describing the plaintiff’s reasons for divorce. Keyword-based feature extraction was applied to transform these texts into interpretable indicators. To handle class imbalance, Synthetic Minority Over-sampling Technique (SMOTE) was implemented on the training data. Six classical machine learning algorithms were evaluated: Decision Tree, Naïve Bayes, K-Nearest Neighbors, Random Forest, LightGBM, and XGBoost. Performance was measured using accuracy, precision, recall, F1-score, F2-score, and AUC. The results indicate that Naïve Bayes achieved the highest recall (100%) for the “Granted” class, while LightGBM and XGBoost demonstrated the most balanced performance across both classes. Feature importance analysis revealed that mediation outcomes, domestic violence, and economic hardship were among the most influential factors in determining verdicts. The study highlights the applicability of interpretable machine learning in legal decision support and discusses limitations such as the single-court scope and challenges in predicting minority class outcomes. Future work may explore multi-jurisdictional data, deep learning approaches, and domain-specific embeddings for enhanced performance
Multi-Task Learning for Traffic Sign Recognition using Multi-Scale Convolutional Neural Networks
Full text linkTraffic signs are an essential component of road infrastructure. According to the Department of Transportation, Indonesia has over 300 distinct traffic signs, categorized based on their functions and purposes. TSR systems have been widely integrated into various intelligent transportation technologies, such as Driver Assistance Systems (DAS), Advanced Driver Assistance Systems (ADAS), and Autonomous Driving Systems (ADS). The output generated by TSR serves as a critical input for DAS, ADAS, ADS, and other intelligent systems. This article presents a CNN-based classification for traffic sign recognition using multi-task learning (MTL), focusing on traffic signs in Indonesia. The dataset was collected from direct capture with the help of a cellphone camera, indirect capture by utilizing screenshots on a digital map application, and they are captured from several different angles, during the day and at night. The proposed CNN architecture incorporates multi-scale within an MTL framework. The use of a multi-scale approach will hopefully enhance the model’s ability to recognize traffic signs in varied and complex environments. And the integration of MTL will enable the model to handle multiple related tasks concurrently, sharing learned features across tasks. During the training stage, the MS-CNN outperformed a standard CNN model by demonstrating lower initial loss, higher starting accuracy, and achieving 100% accuracy by the 8th epoch with a minimal error rate of just 0.003. In the testing stage, the model achieved exceptional results, as shown by the confusion matrix, it successfully classified all traffic sign types (10 classes) and accurately categorized each sign into one of two categories—warning or prohibition. All performance metrics, including precision, recall, and F1-score, reached 100% for both output tasks, confirming the robustness and reliability of the model
Web-Based Geographic Information System to Find Viral Culinary Tourist Spots
Full text linkThe development and implementation of a Web-Based Geographic Information System (GIS) designed to help users discover viral culinary tourist spots, focusing on promoting local food culture. The system is built using the PHP programming language, leveraging its robust server-side scripting capabilities for dynamic web development. The GIS platform integrates various functionalities, including real-time mapping, geolocation services, and user-generated content, to offer an interactive experience for tourists. The platform allows users to search for culinary hotspots, view their locations on an interactive map, get directions, and read reviews from other users. Business owners can register and update information about their culinary spots, contributing to an up-to-date, community-driven database. The system employs a MySQL database to store location data, user profiles, and reviews, while Google Maps API is used for map visualization and geolocation services. The backend structure is built to handle high-traffic environments, using PHP\u27s object-oriented features for efficient and scalable code management. Administrators can moderate content, ensuring the reliability and quality of the information provided. Implementing this system in PHP highlights the language’s flexibility in creating web-based GIS platforms, demonstrating how culinary tourism can be enhanced through modern web technologies. This paper discusses the technical aspects of the system’s architecture, database management, and frontend-backend integration, offering insights into the benefits of using PHP for developing similar GIS applications
Adoption Drivers of Digital Platform for Coal Production Planning: an Extended UTAUT Model Using PLS-SEM Analysis
Full text linkIn 2022, the coal production industry encountered unprecedented challenges accompanied by a substantial global commodity price surge. The operational impact of this situation surpasses current technological capabilities of coal companies, particularly in optimizing coal blending scenarios. A pivotal aspect of digital transformation involves integration of new digital platform for production planning. This study employs the Unified Theory of Acceptance and Use of Technology in conjunction with decision theory to identify key factors influencing the platform adoption at a coal mining company. Structured questionnaires were utilized, followed by analysis using the SmartPLS 4.0.9.9 software. Findings reveal that both Performance Expectancy and Effort Expectancy positively influence users’ behavioral intention to adopt digital platform for production planning. Behavioral Intention, in turn, significantly impacts actual usage behavior. Unanticipated situational factors and others\u27 attitudes were found to have negligible mediating effects, while variables such as age and experience showed no moderating influence on the pathways from behavioral intention to usage behavior. Companies are advised to improve digital platform performance through functionalities enhancements and pilot testing to reduce perceived effort and stimulate behavioral intention. Additionally, fostering a positive organizational mindset through routine motivational communications can further stimulate usage behavior
Forensic Analysis of the WhatsApp Application Using the National Institute of Justice Framework
Full text linkThe advancement of communication media has rapidly evolved with the emergence of various communication applications on smartphones, which have now surpassed mere communication functions to become complex social media platforms. This change has transformed the way we interact, not only through messages and voice but also through the exchange of videos and images. However, along with these developments, there has been a surge in digital crimes such as defamation, fraud, and drug trafficking. This investigation aims to compare the performance of forensic tools in obtaining digital evidence by utilizing applications like Mobiledit, Belkasoft, Mobile Forensic SPF, and Magnet Axiom, and by applying the National Institute of Justice framework, which consists of five stages: identification, collection, examination, analysis, and reporting. The output of the investigation is presented through reports and evidence, resulting in text chat files, contacts, images, audio, and view-once images. Forensic tools have a 100% success rate in finding pieces of evidence. The comparison of the four tools showed different percentages: Mobiledit Forensic 40%, Magnet Axiom 80%, Belkasoft 60%, and Mobile Forensic SPF 60% in obtaining evidence. Digital evidence can be used as strong support in court proceedings
Industry 5.0 Research in the Sustainable Information Systems Sector: A Scoping Review Analysis
Full text linkIndustry 4.0, centered on cyber-physical production systems, has been criticized for prioritizing profit over social and environmental concerns. In contrast, Industry 5.0 emphasizes AI efficiency while promoting human-centric, resilient, and sustainable approaches, integrating economic, social, and environmental systems. Previous research has often focused solely on conceptual frameworks and technologies, overlooking Industry 5.0\u27s sector-specific impacts. This study addresses that gap by conducting a scoping review to map research findings, identify trends, and highlight knowledge gaps and future research opportunities. By systematically analyzing literature from the Scopus database (2016-present), the study refined a large dataset to focus on Industry 5.0\u27s relevance. The analysis revealed significant attention to sectors like Industry and Producer Services, while Agriculture and Retail, particularly natural resource-based sectors like agriculture and fisheries, are often neglected. Key findings indicate that Industry 5.0 is likely to be driven by the industrial sector, followed by product services and financial industries. The study also highlights the strong connection between IoT and AI in optimizing operations with real-time data and automation and identifies blockchain as a promising technology for enhancing transparency and security, despite existing implementation challenges. This research not only serves as a foundational record of Industry 5.0\u27s implications across various sectors but also provides valuable insights into its role in Information Systems (IS). It lays the groundwork for future exploration of Industry 5.0 in diverse sectors and industries