cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Ridwan Sanjaya
Contact Email
ridwan@unika.ac.id
Phone
+62818298462
Journal Mail Official
sisforma@unika.ac.id
Editorial Address
Jl. Pawiyatan Luhur IV/1, Bendan Dhuwur, Semarang
Location
Kota semarang,
Jawa tengah
INDONESIA
Sisforma: Journal of Information Systems
Published by Universitas Katolik Soegijapranata
ISSN : 23558253     EISSN : 24427888     DOI : 10.24167
Core Subject : Science, Education, Engineering,
Computer Science & IT Education Engineering Library & Information Science
SISFORMA journal published by the Information Systems Studies Program Faculty of Computer Science Soegiapranata Semarang. to accommodate the scientific writings of the ideas or studies related to information systems. Scope journal Sisforma: Topics that will be published in the journal SISFORMA include (but not only in the limit in these topics only): Education and Curriculum, Game Theory and Game Technology, General topic in Information System, E-business, ERP, CMS, Artificial Intelligence and Enterprise System Information, Network and Computer Security, and Information Technology
Arjuna Subject : Ilmu Komputer (semua kategori) - Sistem Informasi
Articles 13 Documents
 1   2 
Search results for , issue "vol 13, no 1: may 2026" : 13 Documents clear
Topic Analysis Using LDA-LSTM on Shopee User Comment Shannon Dominique Saputra; Albertus Dwiyoga Widiantoro Dwiyoga Widiantoro
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.15534

Abstract

Shopee's growth has also shaped online shopping in Indonesia. This study analyzed user reviews to measure satisfaction and identify key service issues using a hybrid framework: LDA for topic modeling and LSTM for sentiment classification. Class imbalance was addressed using a combination of Random Oversampling and Neighborhood Cleaning Rule (ROS-NCL).The results showed that LSTM + ROS-NCL outperformed ROS, NCL, and SMOTE, with 95% accuracy and a precision, recall, and F1-score of 0.94 each. These findings demonstrate that oversampling combined with noise cleaning effectively improves performance on imbalanced data, while also providing practical insights for feature development, logistics improvements, and Shopee's promotional strategy.
Analyzing Teachers' Digital Literacy and Students' Computational Thinking Using the Streamlit Dashboard: A Case Study of PPKS Foundation Schools Vanditya Maharani P. K.; Bernardinus Harnadi
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.15554

Abstract

Teachers’ digital literacy and students’ computational thinking (CT) skills are increasingly important in 21st-century education. Secondary data from the Assessments of “Profil Kepala Sekolah dan Guru (PPKS)” and the Bebras Challenge were used to examine the link between the two. In addition, this study develops an interactive Streamlit-based dashboard for data visualization and evaluates user perceptions of the dashboard interface. A quantitative design was used by gathering secondary data from schools connected to the PPKS Foundation. Descriptive statistics was used to summarize data of the dataset and then, correlation analysis together with simple linear regression were performed to observe the association among variables. The findings indicate that the teachers’ LD is correlated with the students’ CT skills; however, a weak to moderate relationship between them appears. The implementation of interactive visualization tool like the Streamlit dashboard helped for easy interpretation of data to be made in education. This is also supported by feedback in user interviews that described the dashboard as accessible and providing assistance to comprehend complex data.
Product Demand Analysis Using the XGBoost Algorithm at PT Atmadjaya Sembada Anugerah Okky Julian Atmajaya Tarmoko; Rinabi Tanamal
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.13650

Abstract

PT Atmadjaya Sembada Anugerah is a frozen food manufacturing company that faces challenges in stock management due to unpredictable daily fluctuations in product demand. Inaccurate demand forecasting can lead to inefficiencies in distribution and storage operations. This study aims to apply the Extreme Gradient Boosting (XGBoost) algorithm to forecast product demand using historical daily sales data. The process involves exploratory data analysis, data cleaning, feature engineering for time and statistical variables, and time-based data splitting. The model is trained using features selected through Recursive Feature Elimination and optimized using hyperparameter tuning with Optuna. Evaluation is conducted through TimeSeriesSplit cross-validation and assessed using three standard performance metrics. The results indicate that the model effectively captures seasonal patterns and general demand trends, although it remains limited in responding to sudden demand spikes. These findings support the use of XGBoost as a foundational approach for demand forecasting systems in stock planning, with potential for further improvement through the integration of external data and expanded feature sets.
Enhanced Validator Trust Metrics using SCP Log Analytics Erdhi Widyarto Nugroho
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.15535

Abstract

Validators in Federated Byzantine Agreement (FBA) systems, such as the Stellar network, are essential to guaranteeing transaction security and network liveness. However, the metrics currently used to determine validator trust are based on aggregated data (active rate, agreement rate, latency) that may not reflect the detailed behavioral changes required for accurate reputation assessment. This paper analyzes a dataset of 7,150 observations from 55 Stellar validators spanning 133 days and identifies five fundamental limitations of aggregated metrics: parameter poverty, zero variance in agreement rate, minimal variance in active rate, temporal insensitivity, and live data sparsity. Based on these findings, this paper proposes a framework for extracting 12 behavioral parameters from SCP.log files including ballot consistency, nomination success rates, timeout frequency, and equivocation attempts for enhanced EigenTrust-based reputation assessment. While full implementation requires continuous SCP.log collection, the proposed framework addresses the identified limitations by specifying the behavioral parameters necessary for dynamic validator trust assessment in FBA systems.
Design and Development of an Employee Attendance and Performance Evaluation Application Based on Mobile and Web with Face Recognition, Geolocation, and the SAW Method at Toll Road Company PT XYZ Krisna Restu Dewanta; Ahmad Habib
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.14797

Abstract

This research aims to design a mobile-based attendance app for the toll road company in East Java, PT XYZ.Using Face Recognition and Geolocation to simplify employee attendance. The app features an employee performance evaluation system based on the Simple Additive Weighting (SAW) method via a web admin interface. Employees can clock in using real-time facial recognition and location validation, while admins can monitor attendance and performance. Developed using Extreme Programming (XP) and tested through User Acceptance Testing (UAT), the app enhances efficiency, accuracy, and transparency in managing attendance and performance across multiple locations.
Development of a Family Meal Plan Application with Voice Recognition, Siri Integration, and Nutrition Management Using Data-Driven Approach Livanty Efatania Dendy; Celinka Eira Jove; Rinabi Tanamal
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.14489

Abstract

Maintaining a healthy diet has become increasingly important as fast-food consumption rises and nutritional balance is often overlooked. This research proposes a technology-based Family Meal Plan Application equipped with voice recognition, Siri integration, nutrition management, and automated grocery lists to assist home cooks in planning healthier meals more efficiently. The application was designed using Figma, developed with Flutter, and integrated with the Siri API to provide a seamless hands-free experience during cooking. A nutrition prediction model was also developed using a Kaggle dataset and deployed locally to generate real-time nutritional analysis. The final results of this study show that the application prototype successfully meets user needs in simplifying weekly meal planning, providing accurate voice-based cooking guidance, and offering automated nutrition calculations for each family member. User testing involving home cooks indicated increased efficiency in meal preparation, reduced cognitive load during recipe execution, and improved awareness of daily nutritional intake. The voice command system operated with high accuracy and responsiveness, while the automated grocery list feature significantly streamlined weekly shopping activities. Overall, the application demonstrates strong potential to support healthier family eating habits through an intelligent, data-driven, and user-friendly solution.
A Prototype of IoT-Based Indoor Hydroponics Using MQTT for Sustainable Urban Housing Andre Kurniawan Pamudji; Cindy Fiolita Graciela; Stephani Inggrit Swastini Dewi; Marcella Adelia Putri; Vincenzhea Chrissa Siwi; Nesia Rani Wijaya
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.15545

Abstract

Urban population growth significantly reduces the availability of open land for household farming, thus threatening urban food security. Indoor hydroponics offers a space-efficient solution, but manual maintenance often lags behind in addressing water quality fluctuations. Although IoT solutions have been widely developed, they generally still rely on rigid local servers or hardcoded Wi-Fi configurations, thus limiting multi-device scalability. This research aims to develop an indoor hydroponic automation and monitoring system using a hybrid communication architecture to support remote deployment without complex configuration. Adopting the Prototyping Software Development Life Cycle (SDLC) model, this research integrates Information Systems with green architecture. The hardware side is based on a WeMos D1 R32 microcontroller connected to an analog pH sensor, a water level sensor, and a 4-channel active-low relay module to control LED growlights and three mini submersible pumps in separate water and nutrient tanks. The HiveMQ Cloud Broker infrastructure was used to facilitate asynchronous telemetry over TCP port 1883 and data delivery to the browser via WebSockets port 8000 using the Eclipse Paho JavaScript library. Results: A physical prototype was successfully realized in the form of a compact vertical rack. The Trimmed Mean Filter algorithm in the firmware indicated reliable performance under the tested scenario in stabilizing the noise of analog pH readings. The web dashboard successfully processed JSON and updated the telemetry graph responsively during functional testing. The automatic extraction of the device's MAC Address successfully isolated MQTT topics to prevent data collisions between devices. Conclusion: This system effectively addresses the limitations of urban residential space through a biophilic design approach while providing an adaptive smart living solution for urban communities.
A Comparative Performance Evaluation of Real-Time Communication Architectures for ESP32-Based Chatbot Systems Ridwan Sanjaya; Christin Wibhowo
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.15565

Abstract

ESP32-based devices are widely used as a low-cost and resource-constrained platform for Internet of Things (IoT) applications that require responsive communication. However, real-time chatbot systems need higher requirements regarding delays that can reduce the perception of responsiveness, conversation continuity, and user trust. This study evaluates the use of WebSocket, Hybrid MQTT-WebSocket, Hybrid MQTT-Server-Sent Events (SSE), and Cloudflare as four real-time communication architectures for an ESP32-based chatbot system. This study used a systematic literature review on ESP32 communication models and experimental performance evaluation using Sovi Lau 2.0 logs. This dataset consists of 400 communication logs from the performance of the four architectures. The four metrics analyzed were latency, throughput, packet loss, and power consumption. One-way ANOVA was used to compare the architectures, followed by Tukey's HSD for significant metrics. The results show that Cloudflare has the lowest average latency and the highest throughput, while Hybrid MQTT-SSE produces the lowest packet loss and the lowest power consumption. The ANOVA test showed that of the variables tested, only latency had a significant difference between the architectures. The Tukey HSD test confirmed that the Cloudflare architecture had the significantly lowest latency.
Analysis of Academic Scheduling Management Using ISO/IEC 27001:2022 People Controls Yolan Dita Dewi Pramudita; Wiwin Sulistyo; Irwan Sembiring
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.14531

Abstract

User behaviour plays a critical role in determining the effectiveness of academic information system management, particularly in processes requiring high data accuracy and timeliness, such as academic scheduling. Despite system support, inconsistencies in data provision and updates indicate that information reliability is influenced by how users perform their responsibilities. This study evaluates People Controls based on ISO/IEC 27001:2022 Annex A.6 and integrates COBIT–CMMI to measure capability levels from a behavioural perspective. A qualitative approach was employed through observation and structured interviews with key stakeholders involved in academic scheduling. User activities were mapped to Annex A.6 controls to identify implementation gaps, followed by capability level assessment using COBIT–CMMI. The results show that control implementation is largely informal and habit-based, with an overall capability level of Level 2 (40%). User behaviour demonstrates basic control execution but lacks consistency and standardization, particularly affecting data accuracy and timeliness, which leads to misalignment between data availability and operational needs. These findings emphasize that improving information security requires strengthening consistent user behaviour, role accountability, and structured practices, alongside technical system support.
Optimizing YOLOv11 for Accurate Car Parts Segmentation in Automotive Industry Applications FX Hendra Prasetya
SISFORMA Vol 13, No 1: May 2026
Publisher : Soegijapranata Catholic University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24167/sisforma.v13i1.15499

Abstract

We study the application of the YOLOv11 (You Only Look Once version 11) model for automotive component segmentation. Computer vision technologies are becoming increasingly important to the automobile industry. They help to improve manufacturing, improve quality control and make inventory management easy. To automate these operations, it is required to be able to segment automotive parts accurately. This means you can correctly identify and sort out parts in images. The proposed study uses a dataset of different images of car parts with annotations for training the YOLOv11 model. The research aims to improve the architecture and training parameters of the model to achieve high accuracy and efficiency in the segmentation of various automotive parts including engine, wheels and body panels. We can see how well the model works using performance metrics like Intersection over Union (IoU), precision, recall and F1-score. Expected results of this study are a powerful segmentation model which can be integrated into existing automotive systems to improve operational efficiency and reduce human error in recognition of car parts.

Page 1 of 2 | Total Record : 13

 1   2 

Filter by Year

2026 2026


Reset
Filter By Issues
All Issue Vol 13, No 1: May 2026 Vol 12, No 1: May 2025 Vol 11, No 2: November 2024 Vol 11, No 1: May 2024 Vol 10, No 2: November 2023 Vol 10, No 1: May 2023 Vol 9, No 2: November 2022 Vol 9, No 1: May 2022 Vol 8, No 2: November 2021 Vol 8, No 1: May 2021 Vol 7, No 2: November 2020 Vol 7, No 1: May 2020 Vol 6, No 2: November 2019 Vol 6, No 1: May 2019 Vol 5, No 1 (2018): May 2018 Vol 5, No 2: November 2018 Vol 4, No 2 (2017): November 2017 Vol 4, No 1 (2017): May 2017 Vol 3, No 2 (2016): November 2016 Vol 3, No 1 (2016): May 2016 Vol 2, No 2 (2015): November 2015 Vol 2, No 1 (2015): May 2015 Vol 2, No 1 (2015) Vol 1, No 2 (2014): November 2014 Vol 1, No 1 (2014): May 2014 Vol 1, No 2 (2014) Vol 1, No 1 (2014) More Issue