Publication Search

Advances in information technology have brought significant changes to how Micro, Small, and Medium Enterprises (MSMEs) conduct their business operations, particularly in the areas of marketing and sales. However, Stretto Pizza MSME still relies on manual processes for ordering and transaction recording, which results in limited marketing reach, suboptimal data management, and an increased risk of errors in recording. This study aims to develop a web-based e-commerce information system that can integrate sales processes and data management more effectively. System development was conducted using the Waterfall method, which includes the stages of requirements analysis, design, implementation, testing, and maintenance. The system was built using the PHP programming language with MySQL database support. System testing was performed using the Black-Box Testing method to ensure that every feature functions according to user needs. The research results show that the designed system is capable of supporting product ordering processes, customer data management, sales transactions, and report generation more efficiently. With this system, it is hoped that the Stretto Piza SME can improve its operations while expanding its marketing reach through the use of digital technology.

Explainable artificial intelligence (XAI) has become a critical requirement in cybersecurity due to the high-stakes nature of security decision-making and the limitations of black-box learning models. This study investigates the construction of an explainable cybersecurity knowledge representation by leveraging standardized terminology from the NIST cybersecurity glossary. The primary problem addressed is the lack of transparent and semantically grounded reasoning mechanisms in existing AI-driven cybersecurity systems, which limits trust, accountability, and analyst adoption. To address this challenge, we propose a NIST-based semantic knowledge graph that embeds explainability directly into its ontology structure and reasoning process. The proposed framework systematically extracts definitional entities and relations from NIST glossary entries to construct a domain ontology and a multi-relational knowledge graph. A rule-based semantic relation extraction method is employed to ensure faithful, interpretable, and reproducible reasoning paths. The resulting knowledge graph contains over 3,000 cybersecurity concepts and approximately 27,000 semantic relations, covering hierarchical, associative, dependency, and mitigation semantics. Experimental evaluation demonstrates that the proposed approach achieves a high level of explainability, with 92.4% of reasoning outcomes being fully traceable and only 1.4% classified as non-traceable. Most explainable reasoning paths are limited to two or three hops, indicating an effective balance between inferential depth and human interpretability. Structural analysis further confirms the presence of meaningful hub concepts that support multi-hop semantic inference. These results confirm that ontology-driven, standard-based knowledge graphs provide a robust foundation for explainable cybersecurity intelligence. The study concludes that explainability-by-design, grounded in authoritative standards, offers a viable and trustworthy alternative to opaque AI models for cybersecurity applications.

Heart disease is the leading cause of death in Indonesia and globally, necessitating an early screening system that is both accurate and clinically trustworthy. Although XGBoost demonstrates high predictive performance, its black-box nature undermines clinical trust, while low recall risks missed diagnosis an unacceptable consequence in population screening, especially in middle-income countries with limited healthcare resources. This study aims to develop a sensitive, transparent, and implementation-ready heart disease screening framework through the integration of SHAP-based Explainable AI. The CDC's Indicators of Heart Disease dataset (319,795 samples) was processed according to WHO/CDC standards, followed by class imbalance handling, hyperparameter optimization using RandomizedSearchCV, evaluation based on metrics sensitive to minority classes (AUC, recall, F1-score, AUC-PR), and threshold tuning to maximize recall. The baseline model showed a very low recall of 12.18%. After optimization and threshold tuning at 0.10, the model achieved recall >96% (96.79%) with a G-mean of 0.7477, supported by SHAP interpretation stability and the ability to capture non-linear interactions between advanced age (AgeCategory_WHO) and poor general health (GenHealth). SHAP analysis confirmed the alignment of dominant features with medical evidence, and its visualizations provide transparent explanations for healthcare professionals indicating its potential implementation as an interpretable clinical decision support system.

The SIAP Application is an innovation developed as a solution to support the archiving business process in the Planning Bureau. Currently, most employees still use computers and a web-based cloud system developed by Pusdatin using the PHP programming language as a storage medium for files that are no longer actively used and are categorized as dynamic archives. However, the cloud system does not have a well-structured archive management system, which often causes difficulties when employees need to retrieve archived files. As a result, employees must search for files manually by checking archived documents one by one in the cloud. This process is time-consuming and may lead to problems such as difficulties in finding files and the risk of data loss. Based on these conditions, the SIAP Application was developed to improve the effectiveness and efficiency of archive management in the Planning Bureau.The SIAP Application has an advantage in the archiving process, where employees can easily search for archives using the letter number or subject that has been entered into the system. The system will automatically display the required archive, making the retrieval process faster, more accurate, and more organized compared to the previous cloud system.The development of the SIAP Application uses PHP and HTML as the programming languages, with Bootstrap and Tailwind CSS as the user interface frameworks, and MySQL as the database. The system development method used is the Waterfall model, problem analysis is carried out using the PIECES method, and system testing is conducted through black-box testing and the System Usability Scale (SUS) to measure system usability.

Autonomous decision-making systems increasingly rely on complex artificial intelligence models to operate in dynamic and safety-critical environments. While these models provide strong predictive capabilities, their black-box nature limits transparency, trust, and accountability. This study proposes a structured research methodology for integrating Explainable Artificial Intelligence (XAI) into autonomous decision-making systems. The research adopts a conceptual–analytical approach to develop an explainability-oriented framework that embeds transparency across perception, decision-making, and action execution stages. The methodology includes literature-driven problem identification, conceptual framework construction, classification and mapping of XAI methods, and formulation of explainability evaluation criteria. The results demonstrate that effective explainability in autonomous systems requires a hybrid integration strategy, combining in-model transparency with post-hoc explanation mechanisms. A structured mapping of XAI techniques to autonomous system components and a conceptual decision-flow diagram are presented to illustrate explainability integration. The findings highlight that layered and context-aware explainability enhances system interpretability, supports human oversight, and improves safety relevance without compromising autonomous operation. This study contributes a reusable methodological foundation for the design and evaluation of explainable autonomous systems, offering practical guidance for future empirical validation and real-world deployment in safety-critical applications.

Explainable Artificial Intelligence (XAI) has become a critical area of research within artificial intelligence, focusing on improving the transparency and interpretability of machine learning (ML) models, often referred to as "black-box" models. The need for XAI techniques arises from the inherent complexity of ML models, which can make their decision-making processes difficult for users to understand. This study investigates various XAI techniques, including LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations), to assess their impact on model interpretability without significantly compromising predictive performance. A comparative experimental design was used, applying these XAI methods to different ML models, including deep neural networks and ensemble methods, within large-scale enterprise data analytics systems. The results indicate that XAI methods significantly enhance model transparency and decision traceability, allowing users to understand the influence of individual features on predictions. While a slight reduction in predictive accuracy was observed, especially with simpler models, the trade-off between interpretability and performance was deemed acceptable, particularly in fields requiring transparency, such as healthcare, finance, and autonomous systems. The use of XAI in enterprise data systems has practical implications for fostering trust and enabling informed decision-making among stakeholders. Furthermore, the study discusses the challenges and limitations of applying XAI techniques, such as complexity, scalability, and model-specific limitations. Future research is suggested to focus on developing more scalable and efficient XAI methods, enhancing their applicability across various model types, and addressing the challenges of real-time applications. This will be crucial in ensuring the widespread adoption of XAI in critical domains, promoting the ethical use of AI while maintaining predictive accuracy.

Pengujian perangkat lunak merupakan tahap penting dalam memastikan kualitas dan keandalan sistem sebelum digunakan secara luas. Salah satu metode yang umum digunakan adalah black box testing, yaitu pengujian yang berfokus pada fungsionalitas perangkat lunak tanpa memperhatikan struktur internal kode. Dalam penelitian ini, metode black box testing diterapkan dengan menggunakan teknik state transition untuk menguji sistem appointment klinik berbasis web “Citra Medica”. Pengujian dilakukan dengan memetakan alur status pengguna melalui diagram transisi, kemudian membuat skenario uji untuk setiap perubahan keadaan. Hasil pengujian menunjukkan bahwa seluruh fungsi sistem berjalan sesuai dengan spesifikasi, dengan tingkat keberhasilan pengujian mencapai 100% pada setiap skenario transisi. Metode ini terbukti efektif untuk mendeteksi kesalahan logika dan memastikan kestabilan sistem selama perpindahan status pengguna.

Penelitian ini bertujuan merancang dan mengembangkan Sistem Informasi Penjualan berbasis web untuk Gerai Oleh-Oleh Bali yang selama ini masih menggunakan pencatatan manual dengan buku besar dan perhitungan menggunakan kalkulator. Sistem manual tersebut menyebabkan risiko kesalahan pencatatan, lambatnya proses pencarian data, serta kesulitan dalam pengarsipan data penjualan, pembelian, pemesanan, dan pengelolaan stok barang. Penelitian menggunakan metode pengembangan perangkat lunak Waterfall dengan pendekatan pemodelan Unified Modeling Language (UML). Tahapan yang dilakukan meliputi analisis kebutuhan melalui wawancara dengan pemilik gerai, perancangan sistem (Use Case Diagram dan Class Diagram), implementasi, pengujian unit, pengujian sistem menggunakan metode black-box testing, serta tahap pemeliharaan (maintenance). Sistem yang dibangun mencakup fitur login, dashboard, pengelolaan data master (supplier dan barang), transaksi penjualan dengan dukungan scan barcode, transaksi pembelian, laporan penjualan dan pembelian, serta pengelolaan user. Hasil pengujian black-box menunjukkan seluruh test case berstatus Valid dan sistem berfungsi sesuai harapan. Pada tahap maintenance dilakukan contoh corrective maintenance dengan perbaikan bug pada query laporan penjualan harian.Sistem informasi penjualan berbasis web yang dihasilkan mampu mempercepat proses transaksi, mengurangi kesalahan manusia, meningkatkan akurasi data, serta memudahkan pengelolaan stok dan pembuatan laporan secara real-time. Implementasi sistem ini memberikan solusi efektif bagi Gerai Oleh-Oleh Bali dalam meningkatkan efisiensi operasional dan interaksi dengan pelanggan.

The student admission process in many educational institutions is still conducted manually, leading to issues such as data duplication, input errors, and delays in reporting. This study designs and implements a desktop-based student registration information system using VB.NET and MySQL, equipped with an admission-status checking feature and an automated quota-management module. The system was developed using the waterfall model, consisting of requirement analysis, system design using UML, implementation, and black-box testing. Two user roles are supported: admin and student. Admin users can manage applicant data, configure program quotas, open or close the registration period, and generate reports, while student users can create accounts, complete registration forms, and independently check their admission results. The implementation results show that all core functions operate validly based on testing involving two respondents. The quota-management feature successfully restricts the number of applicants according to predetermined capacities, and the admission-status module automatically displays pass or fail results. The system improves administrative efficiency, enhances data accuracy, and reduces reliance on manual record-keeping. Therefore, this desktop application serves as an effective solution for schools requiring a reliable and efficient admission management system without depending on stable internet connectivity.

Digital transformation in higher education requires an information system that is able to manage academic processes effectively, including the management of students' final projects. At Stella Maris University Sumba, the process of registering titles, guidance, and archiving of final projects is still carried out manually, causing various obstacles, such as administrative delays, difficulties in monitoring the progress of guidance, and the risk of data loss. This research aims to design and implement a web-based information system that supports the process of submitting titles, guidance management, uploading documents, and storing final project archives in the form of a digital data bank. The development method used is a software engineering approach with the stages of needs analysis, designing using UML, implementation, and system testing. The system is built with a three-layer architecture that features document management and role-based access control to ensure data security and integrity. The results of the black-box test showed that all system functions were running as needed, while the usability evaluation using the System Usability Scale (SUS) questionnaire resulted in a score that indicated the system was feasible to use. The implementation of this system has been proven to increase administrative efficiency, simplify the guidance process, and provide a structured thesis repository that supports academic transparency and accountability. Thus, this information system is expected to be a sustainable solution in the management of final projects as well as a model for the development of academic digitalization in higher education.

This study addresses the inefficiencies in the manual student payment administration system currently used at SMK Bina Insan Nusantara, which relies on handwritten ledgers and Microsoft Excel spreadsheets, leading to frequent data errors, delayed reporting, and difficulties in retrieving payment records. The research aims to design a web-based information system to streamline the recording, monitoring, and reporting of student payments. A descriptive research approach was employed, with data collected through direct observation, semi-structured interviews with administrative staff, and literature review. System analysis was conducted using the PIECES framework, and system design followed the Unified Modeling Language (UML) methodology. The proposed system features user authentication, student data management, real-time payment input, digital receipt generation, and automated reporting (daily, monthly, and yearly). Black-box testing confirmed that the system functions as intended, validating inputs, processing transactions accurately, and generating reliable outputs. Findings indicate that the web-based system significantly improves data accuracy, operational efficiency, accessibility, and service quality compared to the existing manual process. The implementation of this system enables school administrators to manage payments more effectively, provides students and parents with timely access to payment information, and supports faster, data-driven decision-making by school leadership and the foundation. Future enhancements could include mobile integration and online payment gateways.

The purpose of this research is to create an interactive Augmented Reality (AR)-based educational application that can display the Indonesian folktale "Keong Mas" using Unity 3D and Vuforia SDK. Due to the dominance of modern digital entertainment that is more visually appealing, the younger generation's interest in traditional folktales is declining. The choice of AR technology is based on its ability to combine three-dimensional virtual objects with the real environment in real-time, resulting in an interactive, engaging, and memorable learning experience. The research process used is the Life Cycle of Multimedia Development (MDLC), which consists of six stages: ideation, design, material collection, compilation, testing, and deployment. 3D character models, background environments, and interactive stories appear in the application when the camera detects certain markers. Testing was conducted using the black-box method to ensure all functions, including marker tracking, scene transitions, and narration playback, run smoothly. The test results show that the AR application "Keong Mas" successfully displays the folktale interactively and engagingly, thereby increasing the learning interest of children and adolescents. This application not only serves as an innovative learning medium but also contributes to the preservation of local culture through the integration of digital technology.

The Student Evaluation of Lecturers (EDOM) at the Faculty of Engineering, Universitas Dr. Soetomo has historically been conducted via Google Forms and processed manually, resulting in slow response times, repetitive recap procedures, and insufficiently documented reporting validity. This study aims to design, build, and evaluate a web-based EDOM system using the Prototype Model (MODEL PROTOTYPE) to improve data collection efficiency, recap accuracy, and the effectiveness of feedback for teaching quality assurance. The development method comprises requirements elicitation with the Quality Assurance Unit through a review of SPMI documents and brief interviews, architectural and interface design (Laravel, MVC pattern, and MySQL), staged prototyping, and rapid iterations based on stakeholder feedback until functional conformity is achieved. The resulting system provides authentication and role-based authorization (Admin, GPM, Lecturer, Student), odd/even period management, a question bank employing a Likert scale, anonymous questionnaire submission, score recap per lecturer and per category (pedagogical, professional, personal, social), dashboard visualizations, and report export to support governance needs. Functional evaluation was conducted through black-box testing on core scenarios (login, period scheduling, submission, recap, and export) and indicated conformance to specifications. User acceptance evaluation employed the Technology Acceptance Model (TAM) to examine perceived usefulness, perceived ease of use, attitude toward use, and behavioral intention; the results indicate positive acceptance and potential for operational adoption. Practically, the prototype approach accelerates requirement alignment, reduces the risk of mis-specification, and facilitates change control, while the Laravel-based implementation supports maintainability, role-based access security, and further feature development. The study is limited to a single faculty; future work may include SSO integration, audit trails, and longitudinal, cross-semester analytics for more comprehensive monitoring of lecturer performance.

State Senior High School 7 Surakarta is one of the public schools located in Surakarta City. The library activities, including member data management, book processing, and book borrowing and returning, are still conducted manually using physical logbooks. This manual process is considered inefficient and prone to errors. The purpose of this study is to develop a book borrowing system at State Senior High School 7 Surakarta that serves as a tool to assist officers in recording, loans, and returning books. This system is designed using the CodeIgniter framework to support WEB displays, programming in PHP, and using MySQL for database management. This system is created using the System Development Life Cycle (SDLC) method with a waterfall model that includes the stages of analysis, design, implementation, testing, and maintenance. System testing was conducted using Black-Box Testing and the System Usability Scale (SUS). The Black-Box Testing results showed that all features and functions operated correctly. The SUS evaluation produced a score of 75.68%, indicating that users generally agreed with the implementation of the system, which falls under the "acceptable" classification.

Manual inventory management at Toko Terang Abadi presents various challenges, including delays in reporting and high recording errors. This study aims to improve accuracy and efficiency in stock management by creating a web-based inventory information system using the Waterfall method. Data collection was conducted through interviews, direct observation of store activities, and literature review. The system was designed and implemented using PHP and MySQL, and tested using black-box testing methods to ensure all functions work according to user needs. Implementation results show that recording efficiency increased by 50% and input errors decreased by 90%. These findings support previous research highlighting the importance of digitalizing inventory systems in the SME and retail sectors to improve effectiveness and accuracy in managerial decision-making.

The advancement of information technology has encouraged companies to enhance operational efficiency through computerized systems, particularly in human resource management. PT Volar Mekanikal Teknologi x Luminous Creation faces challenges in manual attendance recording, unsystematic leave management, and a payroll system that lacks integration. Therefore, this study aims to design and implement a web-based Employee Management Information System using the Extreme Programming (XP) methodology. The system focuses on three main features: attendance tracking using GPS and selfie verification, online leave applications, and automated payroll calculation integrated with attendance data. The system development process includes planning, design using Unified Modeling Language (UML), coding with the Laravel framework and MySQL database, and testing through the Black-Box method. The implementation results show that the system effectively improves efficiency and accuracy in employee management, while also supporting the company’s operational activities in a more professional and structured manner.  

The development of e-learning platforms has transformed the landscape of education by providing flexible and accessible learning methods. However, security threats targeting web-based applications pose significant risks to the confidentiality, integrity, and availability of academic data. This research aims to analyze the security vulnerabilities of the ILMU2 e-learning website at UPN “Veteran” Jawa Timur using the Web Application Security Project Zed Attack Proxy (OWASP ZAP) methodology. The study applies a black-box testing approach to simulate attacks and identify potential weaknesses in the website's security mechanisms. Expected findings include the identification of vulnerabilities such as cross-site scripting (XSS), SQL injection, and security misconfigurations. The results are intended to provide insights for improving the security posture of the ILMU2 platform and contribute to the broader discourse on securing educational technology in higher education institutions.

Employee performance represents the ability to fulfill tasks and responsibilities according to organizational standards. At UPTD Puskesmas Kosambi, the evaluation of Non-Civil Servant (Non-ASN) healthcare workers is still done manually and tends to be subjective, primarily based on attendance. This study aims to address the issue by developing a decision support system using the MOORA (Multi-Objective Optimization on the Basis of Ratio Analysis) method. A descriptive-applied approach and the waterfall development model were employed. Five evaluation criteria were used: attendance (25%), service quality (35%), report timeliness (20%), patient complaints (10%), and lateness (10%). Data from 20 Non-ASN healthcare workers in April 2025 were analyzed, with Anis Julianti achieving the highest MOORA score of 0.3839. The system underwent validation through black-box testing and user acceptance testing (UAT), both confirming its accuracy and usability. The findings were compared with previous studies. Harningsih et al. (2024) used the MOORA method for promotion evaluations at the North Sumatra Provincial Inspectorate Office and recorded a top score of 0.3616. Dewi Yohana br Ginting et al. (2024) applied the method at a beauty clinic and found a top score of 0.3747. These comparisons indicate that the MOORA results in this study fall within a consistent and valid range. The developed decision support system is expected to enhance the objectivity, transparency, and accountability of performance evaluations for Non-ASN employees in primary healthcare services, offering a more comprehensive alternative to manual assessment methods.

The rapid growth of the fashion industry in Indonesia, particularly in Bandung, has increased the demand for structured and efficient sewing course management. Bandung Vision Center, as one of the institutions providing sewing training, faces significant administrative challenges due to the continued use of manual registration and attendance monitoring systems. These conventional processes result in data inaccuracies, slow information retrieval, limited transparency, and difficulties in monitoring participant progress across multiple training waves. This study aims to design and develop a web-based application to optimize participant registration and attendance monitoring processes at Bandung Vision Center. The research adopts an Agile software development methodology to ensure iterative development, flexibility, and responsiveness to user requirements. The system is implemented using the Laravel framework for backend development, ReactJS for frontend interface design, and MySQL as the relational database management system. System modelling is conducted using UML diagrams, and functionality testing is performed using the black-box testing method. The results indicate that the developed application significantly improves administrative efficiency, enhances data accuracy, and enables real-time monitoring of participant attendance. Additionally, the system increases transparency, facilitates structured data management, and supports better decision-making for course administrators. The implementation of this web-based application demonstrates its effectiveness in modernizing administrative processes and strengthening institutional competitiveness in the local fashion education sector. Future enhancements may include integration of online payment features, automated notifications, and advanced data analytics to further improve service quality and user satisfaction.

Software testing is a critical phase in information system development to ensure the system's quality and reliability. This study aims to evaluate the reliability and functionality of PT Perta Sakti Abadi's financial information system using the black-box testing method with the Equivalence Partitioning (EP) technique. This technique allows input data to be grouped into valid and invalid categories, minimizing test cases without reducing testing coverage. The testing focuses on the login feature as the system's primary component by evaluating various input combinations. The testing scenarios include boundary conditions to ensure the system handles inputs correctly in various situations.The results indicate that the system successfully verifies valid credentials, rejects access with invalid data, and provides informative error messages. Additionally, the system demonstrates resilience in handling testing scenarios, including inputs with special characters and empty fields. Input validation mechanisms function optimally, supporting secure user access and ensuring the login feature aligns with functional specifications. This successful testing forms a strong foundation for testing other modules, such as multi-level authentication and data encryption. Thus, the Equivalence Partitioning technique within the black-box testing method proves effective in enhancing the quality of web-based financial information systems.