J-INTECH ( Journal of Information and Technology)

Application for Mental Health Consultation with Scheduling Function at the Counseling Guidance of Universitas Teknologi Yogyakarta

2025-06-19T02:23:31+00:00

This study developed a mobile-based mental health consultation application at Universitas Teknologi Yogyakarta (UTY) to offer both online and offline counseling services for students. The tool incorporates two primary features online consultations and offline consultation scheduling, designed to improve students' access to mental health support. The system utilizes Flutter for cross-platform mobile application development, Firebase for data management, and Node.js for backend services. The study employs a Research and Development (R&D) methodology encompassing needs analysis, system design, implementation, and testing. The results indicate that the application successfully mitigates obstacles such time limitations, stigma, and restricted accessibility, hence enhancing student involvement with mental health services. The Self-Reporting Questionnaire 20 (SRQ-20) serves as a mental health screening instrument within the application, enabling students to evaluate their mental health status. This program aims to deliver a thorough and accessible solution for mental health counseling at UTY and may serve as a prototype for other universities.

Application of the A-Star Method for Evacuation Routes Using the Long-Range Wide Area Network (LoRaWAN)

2025-06-19T02:23:30+00:00

Optimal evacuation route planning is a crucial factor in disaster mitigation, especially in areas with limited communication infrastructure. This study proposes the application of the A-Star method for evacuation route optimization, supported by the Long-Range Wide Area Network (LoRaWAN) as an emergency communication system. The research methodology includes the development of an A-Star algorithm optimized with an adaptive heuristic function, integration with LoRaWAN-based sensors for real-time road condition monitoring, and simulations in various disaster scenarios. The results show that the developed system can reduce evacuation time by up to 31.4% compared to conventional methods and maintain communication connectivity up to 95% even under emergency conditions. Furthermore, the dynamic adaptation mechanism allows for automatic route changes based on current field conditions, enhancing the effectiveness of the evacuation process. Therefore, the integration of the A-Star method and LoRaWAN network proves to be a reliable and efficient solution for improving public safety during disasters.

Application of Honeypot in Network Security for Detecting Cyber Attacks on IT Infrastructure

2025-06-19T02:23:29+00:00

The high security risks that are susceptible to hacking and exploitation by malicious actors to steal data or information often arise due to a lack of awareness regarding the critical importance of implementing deceptive network security using honeypots. Negligence can create vulnerabilities that are easily exploited, allowing attackers to initiate breaches. A notable network security approach involves using Honeypots, a method that creates a decoy server to mimic an authentic one. Honeypots are deliberately engineered to attract the attention of cyber attackers and facilitate their access to the trap server, thereby enabling the monitoring and analysis of their activities without compromising the integrity of the primary server. To achieve optimal network security, comprehensive testing of Honeypots is essential. This testing process serves as a fundamental metric in evaluating the efficacy and performance of Honeypot systems in mitigating cyber threats.

Combination of Response to Criteria Weighting Method and Multi-Attribute Utility Theory in the Decision Support System for the Best Supplier Selection

2025-06-24T02:24:46+00:00

Choosing the right supplier is a strategic factor in supporting operational efficiency and a company's competitive advantage. This process requires a decision support system that is able to assess various alternatives objectively and in a structured manner. This study aims to develop a decision support system in the selection of the best supplier by combining the Response to Criteria Weighting (RECA) and Multi-Attribute Utility Theory (MAUT) methods. The RECA method is used to objectively determine the weight of each criterion based on the variation of data between alternatives, so as to reduce subjectivity in the weighting process. Meanwhile, the MAUT method functions to calculate the total utility value of each supplier based on the normalization value and weight that has been obtained. The results of the RECA method show the objective weight of each criterion, which is then used in the MAUT calculation process. The results of the analysis, obtained in the best supplier selection based on the total score of each candidate, it can be seen that PT Global Niaga Mandiri ranks first with the highest score of 0.6512, this shows that this company is the best choice in the supplier selection process. In second place is UD Anugrah Bersama with a score of 0.399, followed by PT Indo Logistik Prima in third place with a score of 0.3451. The combination of the RECA and MAUT methods has been proven to be able to produce accurate, rational, and accountable decisions. This system provides a measurable approach in filtering supplier alternatives efficiently and is relevant to be applied to various other multi-criteria decision-making contexts.

Analysis of the Effectiveness of Traditional and Ensemble Machine Learning Models for Mushroom Classification

2025-06-24T02:24:45+00:00

The classification of edible versus poisonous mushrooms presents a critical challenge in the domains of applied biology and public health, particularly due to the serious implications of misidentification. This research employs the UCI Mushroom Dataset to evaluate and compare the effectiveness of several machine learning models, including traditional algorithms like Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, K-Nearest Neighbors and Naïve Bayes, as well as advanced ensemble techniques such as Stacking and Voting Classifier. Notably, both Random Forest and Stacking achieved flawless accuracy, reaching 100%, underscoring the high predictive capacity of these models in complex categorical scenarios. Conversely, Naïve Bayes exhibited significantly weaker performance—achieving only 59.8% accuracy—likely due to its underlying assumption of feature independence, which does not hold for this dataset. The ensemble learning approaches, including the combination of Stacking and Bagging, not only preserved but also enhanced model robustness and generalization. These methods effectively leverage the complementary strengths of individual learners to yield more accurate and stable predictions while mitigating overfitting risks. Comparative analysis with previous research confirms the consistency of these findings and reinforces the viability of ensemble strategies for handling intricate classification tasks. Overall, this study highlights the importance of algorithm selection tailored to data characteristics and supports the use of ensemble learning to boost predictive reliability.

Decision Support System for Selecting BPS Central Tapanuli Partners Using the SMART Method

2025-06-24T02:24:42+00:00

The selection of partners at the Central Statistics Agency (BPS) of Central Tapanuli is a very important process because it determines the quality of supporting staff in census and survey activities. One of the core stages in the selection process is the interview, which functions to directly evaluate the abilities and character of prospective partners. The assessment in the interview covers several main aspects, namely analytical skills, communication, appearance, and politeness. This study aims to design a decision support system based on the SMART (Simple Multi Attribute Rating Technique) method that can help process interview results systematically and objectively. Each criterion in the interview is given a weight based on the level of importance, then the value of each candidate is processed through mathematical calculations that produce a final score. This score is used to determine the candidate's ranking and provide recommendations to the selection committee. The system is developed in the form of a web-based application with a user-friendly interface, and supports data input, value processing, and automatic presentation of results. The implementation results show that the SMART method is able to improve assessment accuracy, reduce subjectivity, and accelerate the decision-making process in partner selection. With this system, the interview process is not only a fairer and more transparent means of assessment, but also supports work efficiency and consistency of selection results in the BPS environment.

Analyzing Students' Interest in Mathematics Through the Implementation of the K-Means Clustering Algorithm

2025-06-25T02:24:50+00:00

This Research is motivated by the importance of understanding students' interest in mathematics, especially in State Junior High School 193 East Jakarta, considering that mathematics is often considered a difficult and frightening subject for some students. Learning interest, which is defined as the tendency of students to pay attention with a feeling of pleasure, has a significant influence on the process and results of student learning. This study aims to identify the level of student interest in mathematics using the K-Means algorithm. This method is used to group students into several clusters based on their level of interest. The results showed that students were divided into three clusters, namely the first cluster with very high interest totaling 193 students with an average Final Semester Exam score of 91.920, the second cluster with low interest totaling 18 students with an average score of 52.333, and the third cluster with high interest totaling 66 students with an average score of 87.606.