Journal of Informatics Information System Software Engineering and Applications (INISTA)

Classification of Package Delivery Duration Using Decision Tree Algorithm

2026-06-19T11:19:51+08:00

This study aims to classify package delivery duration based on the difference between shipping time and delivery completion time using the Decision Tree algorithm. The dataset used in this research was obtained from PT Idenative and consists of historical logistics data containing various shipment attributes such as number of items, destination location, delivery status, and time-related variables. Data preprocessing was conducted through cleaning, transformation, and categorization, where delivery duration was classified into four categories: Fast, Normal, Slow, and Very Slow. The classification model was developed using the Decision Tree algorithm due to its interpretability and ability to handle both categorical and numerical data. The dataset was divided into training and testing sets with an 80:20 ratio, and model performance was evaluated using confusion matrix, accuracy, precision, recall, and F1-score metrics. The results show that the model achieved an accuracy of 40.72%, with a macro precision of 0.62, recall of 0.35, and F1-score of 0.34, indicating moderate performance. The model faces challenges in distinguishing between similar classes, particularly Normal and Slow categories. Feature importance analysis reveals that the number of items and destination location are key factors influencing delivery duration. This study demonstrates that the Decision Tree algorithm can be applied to classify delivery duration in the logistics domain while providing interpretable insights for operational decision-making. However, further improvements are required, such as applying ensemble methods and data balancing techniques to enhance model performance.

Understanding the Effectiveness of Query Expansion in IndoSBERT-Based Semantic Retrieval

2026-06-19T11:20:08+08:00

The advancement of information retrieval systems has shifted from keyword-based approaches to semantic retrieval using transformer-based models such BERT and its variants. Despite their ability to capture contextual meaning, the vocabulary mismatch problem between queries and documents remains a key challenge. Query expansion (QE) is commonly used to address this issue, but its effectiveness in semantic retrieval is not always consistent. This study aims to analyze the impact of query expansion on a semantic retrieval system based on a fine-tuned IndoSBERT model using a dataset of undergraduate thesis titles and abstracts at repository UPN “Veteran” Jawa Timur. A hybrid QE approach is proposed by combining pretrained FastText and domain-specific Word2Vec embeddings, with and without filtering mechanisms. The system performance is evaluated using Precision@15, Recall@15, Mean Average Precision (MAP), and nDCG@15. The results show that QE can improve retrieval performance when properly controlled. The best performance is achieved by the hybrid QE with filtering, where MAP increases from 0.389 (without QE) to 0.483 and nDCG reaches 0.911. In contrast, FastText-based QE without filtering results in performance degradation due to query drift. It can be concluded that the effectiveness of QE in semantic retrieval is highly dependent on the quality of expansion terms and the application of filtering strategies. QE is not inherently beneficial, but requires careful design to improve retrieval performance.

Development and Evaluation of an Adaptive Scrum Model for Wedding Organizer Systems Using UML and ISO 25010

2026-06-19T11:20:23+08:00

This study proposes an adaptive Scrum model for developing a web-based Wedding Organizer system by integrating structured modeling and iterative development practices. Unlike conventional Scrum implementations, the proposed model incorporates Unified Modeling Language use case diagrams for defining product backlog, working hour-based effort estimation for sprint planning, and a client validation loop to enhance continuous user involvement. The system was developed through iterative sprints aligned with wedding preparation phases, ensuring better synchronization between development activities and real-world workflows. An analyst role within the development team was introduced to maintain consistency between system modeling and implementation. System evaluation was conducted based on ISO/IEC 25010, focusing on functional suitability and usability aspects. The results indicate that all system features operate as expected, and usability testing using the System Usability Scale achieved a score of 82.5, categorized as Excellent. The findings demonstrate that the proposed model improves requirement clarity, planning accuracy, and user involvement, leading to enhanced system usability and development efficiency. This study contributes a structured and practical approach to adapting Scrum for event-based application domains, particularly in Wedding Organizer systems.

Evaluation of Security Vulnerabilities in the Single Submission Pengangkut System Using OWASP Top 10

2026-06-19T11:20:45+08:00

International trade in the era of globalization has rapidly grown thanks to information and communication technology (ICT), but this also presents new challenges related to data security and user information protection. In Indonesia, the National Single Window (LNSW) utilizes the Single Submission Pengangkut web application to support international trade. Although this application plays an important role, potential security vulnerabilities could lead to data breaches and financial losses. This study aims to test the security vulnerabilities of the application using Penetration Testing methods based on the OWASP Top 10 standard. Testing was conducted using tools such as Nmap, Nessus, Kali Linux, and Burp Suite to identify and exploit vulnerabilities. The results of the testing revealed three vulnerabilities that did not pass the security test: Insecure Design, Vulnerable and Outdated Components, and Identification and Authentication Failures. Based on assessments using the Common Vulnerability Scoring System (CVSS), it was found that Insecure Design has a Medium vulnerability rating, while Vulnerable and Outdated Components and Identification and Authentication Failures fall under the info category, meaning they do not directly impact the application's security. To address these vulnerabilities, it is recommended to implement restrictions in the document input process, perform regular software updates, and implement multi-factor authentication (MFA). This study shows that applying the OWASP Top 10 as a guideline in penetration testing is effective for identifying and evaluating security vulnerabilities in the Single Submission Pengangkut web application.

IoT-Based Campus Parking Slot Monitoring System via Ultrasonic Sensors with Real-Time Web Visualization

2026-06-19T11:19:22+08:00

This research develops a campus parking slot monitoring system based on the Internet of Things (IoT) using the HC-SR04 ultrasonic sensor and the ESP32 DevKitC V4 module. The goal is to overcome parking space limitations by providing real-time information on slot availability thru an OLED display and web interface. The system is designed using a prototype development method consisting of ultrasonic sensors to detect vehicle distance, servo motors to operate automatic gates, and ESP32 as a processor and wireless data transmitter. The data from the sensor readings is processed to determine the status of the parking slots and communicated in real-time to the server. OLED displays real-time status on-site, while the web interface shows the overall parking conditions. The test results show the system is capable of detecting the presence of vehicles with high accuracy and stable data communication without significant delay. This system effectively improves parking space search efficiency and reduces congestion in the campus area. Its implementation supports the smart campus concept thru the digitalization of user-friendly, efficient, and scalable parking facility management, which can be developed into a data analysis-based system for smart parking management in the future.

Development of a Meeting Room Reservation System in the Food and Beverage Industry

2026-06-19T09:42:08+08:00

The manual process of meeting room reservations often takes considerable time and creates inefficiency, especially when coordinating schedules among multiple users. In addition, searching for meeting-related information is not yet integrated, and the absence of automatic reminders often causes users to miss scheduled meetings. To address these issues, a web-based system was developed to manage meeting room reservations digitally. The system includes an information search feature using a chatbot and automatic reminders integrated with Google Calendar or Outlook. The prototype method was applied in the development process. To ensure the system meets user needs, evaluations were carried out through functional testing, the User Experience Questionnaire (UEQ), and time efficiency testing. The functional testing results show that the system works properly and meets user requirements. Meanwhile, UEQ results indicate that all aspects Attractiveness, Perspicuity, Efficiency, Dependability, and Stimulation achieved the “Excellent” category. The highest score was for Stimulation at 2.531, suggesting the system provides an enjoyable, non-monotonous experience that fosters user engagement. In terms of efficiency, manual reservations required between 1,245 and 1,560 seconds, depending on the responsiveness of the admin or receptionist. After system implementation, booking time was reduced to 35 – 50 seconds. This shows an improvement in reservation efficiency of about 96%.