Jurnal Sistemasi (OJS FTIK - UNISI, Fakultas Teknik dan Ilmu Komputer Universitas Islam Indragiri)
Not a member yet
946 research outputs found
Sort by
User Behavior Analysis of E-Wallet Usage Among Generation Z using the Theory of Planned Behavior
Full text linkWith the rapid advancement of digital technology and the growing demand for fast and practical transaction systems, the use of digital wallets (E-Wallets) among the younger generation—particularly Generation Z—has significantly increased. This study aims to identify the behavioral factors influencing E-Wallet usage among Gen Z by applying the Theory of Planned Behavior (TPB). This theoretical framework includes three main constructs believed to influence Behavioral Intention (BI) and actual user behavior: Attitude Toward the Behavior (ATB), Subjective Norm (SN), and Perceived Behavioral Control (PBC). The study involved 100 Gen Z university students in Pekanbaru, selected through purposive sampling. A quantitative research method was employed, and data were analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). Instrument validity was tested through discriminant validity, while reliability was assessed using Cronbach’s Alpha and Composite Reliability. The findings reveal that all three variables—Attitude Toward the Behavior, Subjective Norm, and Perceived Behavioral Control—have a significant influence on Behavioral Intention to use E-Wallets among Gen Z in Pekanbaru. Furthermore, both Behavioral Intention and Perceived Behavioral Control significantly affect the actual usage behavior of E-Wallets. Theoretically, these results support the applicability of the TPB framework in the context of digital payment systems. Practically, E-Wallet providers are advised to focus on enhancing users’ positive attitudes, leveraging social influence, and improving ease of use for Gen Z. However, this study is limited by its exclusion of external factors beyond the TPB model that may also influence E-Wallet usage behavior
Development of an AHP Model for Evaluating WiFi Quality based on Multicriteria
Full text linkWi-Fi service quality not only supports academic and administrative activities, but also significantly impacts user productivity and satisfaction. The criteria examined in this study regarding Wi-Fi services include ease of access, network stability, connection speed, coverage, and security. This research is based on questionnaire data collected from 100 Wi-Fi users at the Faculty of Information Technology, Satya Wacana Christian University (FTI UKSW), which was used to determine the relative importance of each criterion. The main objective of this study is to determine the weight of each Wi-Fi service criterion using the Analytic Hierarchy Process (AHP) method. Based on the AHP analysis, the criterion with the highest priority is ease of access, with a weight of 0.417087. The weights for the other criteria are as follows: network stability at 0.259637, connection speed at 0.165161, coverage at 0.104853, and security at 0.053262, making security the lowest-priority criterion. From these findings, it can be concluded that ease of access to Wi-Fi has a significant influence on user satisfaction. This insight can serve as a recommendation for the university to improve its services—for instance, by adding more access points or implementing a single sign-on system for Wi-Fi access
Assessing Academic Information System Performance Through Sentiment Analysis
Full text linkThe Academic Information System (SIMAK) at Sriwijaya University plays a crucial role in facilitating student academic activities; however, it faces several technical issues that affect user satisfaction, including server outages and challenges in data access. This dissatisfaction serves as a vital metric for evaluating the system's effectiveness. This study aims to analyze student sentiment regarding SIMAK utilizing the Naïve Bayes method. A total of 92 tweets were gathered from Twitter through web scraping, which were then categorized into manually labeled training and test datasets for model validation. The data underwent processing that included text cleaning and the application of Term Frequency-Inverse Document Frequency (TF-IDF) to assess the significance of words within a collection of documents. The evaluation results indicated that the model achieved an accuracy of 65%, with a precision of 63% for negative sentiment and a recall of 100%. In contrast, positive sentiment exhibited a low precision of 12.5% and an F1-score of 22.2%, highlighting difficulties in identifying positive sentiment due to data imbalance. The model demonstrated greater effectiveness in identifying user grievances, particularly concerning server disruptions, data delays, and challenges in completing Study Plan Cards and accessing grades. These findings provide valuable insights for SIMAK maintainers to enhance system reliability and user experience. Future research should aim to broaden data coverage and explore alternative analytical methods to yield more representative outcomes
Smart Clove Oil Distillation System using IoT and Ultrasonic Sensors
Full text linkTraditional clove essential oil distillation remains inefficient due to manual labor dependency, imprecise oil-water separation, and inconsistent product quality. Addressing these limitations, this study aims to design and develop a smart, Internet of Things (IoT)-based system named AquaClove to automate and optimize the distillation process. The system integrates an ESP32 microcontroller, ultrasonic sensors, and solenoid valves, enabling precise fluid level detection and automated oil-water separation. Using the Arduino IoT Cloud, the system supports real-time monitoring and remote control, enhancing operational transparency and scalability. results indicate that the system achieved a 32% reduction in total distillation time (from 4.2 to 2.9 hours), 66.7% reduction in labor requirements (from 3 to 1 personnel), and 66.7% reduction in oil loss per 10-liter batch (from 0.6 L to 0.2 L). The ultrasonic sensors consistently detected liquid levels with an average measurement deviation of less than ±2 mm, while solenoid valves responded within 0.8 seconds of command input. These outcomes demonstrate significant improvements in process efficiency, separation precision, and system responsiveness. Furthermore, the modular container design promotes gravity-assisted separation, enhancing energy efficiency and reducing mechanical complexity. The remote monitoring feature allows users to access real-time data on fluid levels and system status, ensuring reliable operation with minimal manual supervision. AquaClove thus demonstrates how integrating ultrasonic sensing and IoT technologies can modernize traditional agricultural processes. This study contributes a scalable and sustainable solution to the essential oil industry, particularly in small- and medium-scale clove oil production
Implementation of a Network Security System using an Intrusion Prevention System with Machine Learning
Full text linkThis research develops a machine learning-based Intrusion Prevention System (IPS) to automatically detect and prevent network attacks. The system was designed using the Random Forest algorithm, trained on the CICIDS2017 and CICIDS2019 datasets—standard benchmarks developed by the Canadian Institute for Cybersecurity, widely used in cybersecurity research for their realistic network traffic and diverse attack types. The system focuses on three common attacks: SYN Flood, Port Scanning, and SSH Patator. After preprocessing, training, and evaluation, the model was integrated into the IPS, enabling real-time network monitoring, attacker IP blocking, and automated notifications via Telegram. Testing results indicate that the system achieves high detection accuracy while delivering fast and efficient responses. This system simplifies the work of network administrators by detecting and responding to attacks without the need for manual log monitoring. Through its automated and adaptive approach, the IPS makes a significant contribution to enhancing network security and can be directly implemented in organizational or institutional network environments to substantially reduce the risk of cyberattacks
The use of iTCLab Kit as a Learning Media for Dynamic Systems and Control
Full text linkThe Internet-Based Temperature Control Lab (iTCLab) kit is an instructional tool designed to facilitate the understanding of fundamental concepts in dynamic systems and control, particularly Proportional-Integral-Derivative (PID) controllers. The background of this study lies in the gap between students’ theoretical knowledge and its application in real-world systems, which often poses a challenge in learning Dynamic Systems and Control courses. This research aims to evaluate the effectiveness of using iTCLab in improving students’ understanding of both PID control theory and its practical applications. The study was conducted in three stages: development of learning modules, implementation, and evaluation involving 30 Informatics students. Assessment was carried out through knowledge tests (pre-test and post-test) and perception surveys. The results indicated an increase in the average score from 52.30 to 76.48 (+46.26%, p < 0.001, Cohen’s d = 1.86), along with positive evaluations in terms of theory–practice integration (4.30), ease of use (4.10), content relevance (4.40), and learning satisfaction (4.20) on a 1–5 scale. These findings suggest that iTCLab is effective in strengthening students’ conceptual understanding and technical skills. From a practical standpoint, iTCLab is suitable for integration into Semester Learning Plans (RPS) and further development to support Internet of Things (IoT)-based distance learning
The Best Nurse Performance Recommendation Model with Integration of AHP and Weighted Product Methods
Full text linkThis study aims to develop a recommendation model for identifying the best nurse performance by integrating the Analytical Hierarchy Process (AHP) and Weighted Product (WP) methods. Nurse performance plays a vital role in determining the quality of healthcare services; however, existing performance evaluations are often subjective and lack transparency. This situation leads to dissatisfaction among nurses and reduces work motivation. Therefore, a system that provides objective and fair evaluation is needed. The AHP method is employed to determine the priority weights of nurse performance criteria through pairwise comparisons, while the WP method is applied to rank nurses based on the assigned weights. The criteria used include Technical Competence, Professional Attitude, Teamwork, and Patient Satisfaction. This research adopts a Research and Development (R&D) approach, which involves data collection, criteria identification, AHP weighting, web-based system development, and model validation and evaluation. The results indicate that integrating the AHP and WP algorithms can produce a comprehensive and practical nurse performance recommendation model that enhances decision-making efficiency and accuracy in hospitals. The best nurse performance recommendation resulted in Wulandari achieving the highest score of 0.3251
Analysis of Student Job Readiness in Facing AI Transformation Towards Society 5.0 in XYZ University Students
Full text linkThis study analyzes the factors influencing job readiness among XYZ University students in the context of Society 5.0. The novelty of this research lies in its application of Soft Systems Methodology (SSM) combined with quantitative questionnaire analysis, enabling both systemic and measurable problem identification—an approach still rarely applied in studies of student job readiness in Indonesia. A survey was conducted with 355 active students across five study programs and analyzed using IBM SPSS 2.5 to ensure data reliability. The findings reveal that AI literacy, psychological readiness, and the use of digital technologies have a significant impact, while human-centered skills such as communication and empathy serve as key reinforcing factors. Practically, this study encourages universities to integrate technology-based technical skills with soft skills in their curricula and training programs to produce graduates who are more adaptive, competitive, and prepared for the demands of Society 5.0. The study’s contribution lies in its use of SSM to map complex issues and formulate strategies for improving job readiness. The implication is that universities should embed technical competencies, soft skills, and AI-based training into adaptive learning ecosystems to better prepare graduates for the challenges of Society 5.0
Performance Comparison of ResNet50, VGG16, and MobileNetV2 for Brain Tumor Classification on MRI Images
Full text linkBrain tumor classification using MRI images is a significant challenge in medical diagnosis, requiring models with high accuracy and efficient training. This study aims to compare the performance of three Convolutional Neural Network (CNN) models—ResNet50, VGG16, and MobileNetV2—for brain tumor classification based on MRI images. The dataset consists of four brain tumor categories: glioma, meningioma, pituitary, and no tumor, with data split into training, validation, and testing sets. Each model was evaluated using metrics including accuracy, precision, recall, F1-score, specificity, and training time to assess their effectiveness in predicting brain tumors with optimal accuracy and efficiency. Experimental results indicate that VGG16 achieved the best overall performance, with an accuracy of 94.93%, precision of 94.68%, and specificity of 98.33%, while also having the shortest training time of 47.15 minutes. MobileNetV2 demonstrated strong performance with a recall of 94.08% but required a longer training time of 79.53 minutes. ResNet50 recorded the lowest accuracy (91.67%) despite excelling in precision (91.79%), but it underperformed in recall (91.25%) and specificity (97.2%). Overall, this study confirms that VGG16 is the most efficient and effective model for MRI-based brain tumor classification
Kit iTCLab Application as a Learning Tool for the Internet of Things
Full text linkThe rapid advancement of the Internet of Things (IoT) has created opportunities for transformative innovations in various technology-based learning sectors, particularly through Smart Kits. This study aims to develop and implement the Internet-Based Temperature Control Lab (iTCLab) Kit as an interactive learning tool for IoT. The iTCLab application is designed to enable users to monitor and control temperature in real-time via an internet-based platform. The system utilizes temperature sensors, heating actuators, an ESP32 microcontroller, and an internet connection. Testing was conducted through the Microcontroller course in the Informatics Study Program. The results indicate that the iTCLab Kit significantly enhances students' understanding and mastery of practical IoT programming. Thus, the iTCLab Kit serves as an innovative solution to support more effective and efficient IoT learning