JURNAL TEKNOLOGI DAN OPEN SOURCE

Implications of AI Technology on Higher Level Education Development in Batam

2025-06-01T15:06:46+07:00

This study examined artificial intelligence impact on higher education in Batam, focusing on its potential to improve teaching, learning, and administration while addressing concerns such as reduced human interaction and ethical dilemmas. The research aimed to provide insights into the effective integration of AI to enhance educational outcomes and promote innovation in Batam. Data from 331 college students in Batam were collected using Cluster Disproportional Random Sampling and analyzed through PLS-SEM, examining seven variables. Perceived Risk did not significantly impact Attitude, as students perceived AI uncertainty but remained unaffected, while Facilitating Conditions weakly influenced Behavioural Intention, likely due to students prioritizing other factors and having independent access to AI via personal devices. AI's impact on education showed that factors such as resources, ease of use, and performance shaped students perspective, although the study's limitations include a small sample size in each university and a lack of demographic diversity

Student Satisfaction and Continuance Intention of E-learning System: University Student Perspective

2025-06-01T15:06:55+07:00

The development of technology has also had an impact on changes in the digitalization of the world of education, which we know as online learning. Therefore, this study aims to examine the factors that influence student satisfaction and continuance intention in using the LMS-type e-learning system. This research uses ECM as model and quantitative approach by collecting questionnaires from 443 students in Batam City who come from different universities. After the questionnaire was collected, the research hypothesis variables were tested using SEM-PLS. The results of this study found that various indicators of interactivity, course content, and design quality positively significantly affect perceived usefulness, confirmation, and satisfaction, which then affects students continuance intention to continue to use the e-learning system to support the learning process. This research shows that students in Batam are satisfied and want to continue using the e-learning system as their learning support with interactivity and adequate course content and design quality. Even so, the development of e-learning systems must still be carried out in line with technological developments, and students need to maximize the results, satisfaction, and continuance of their intention towards the use of e-learning systems.

Implementation of Data Mining in Measuring Student Satisfaction at IAIN Kerinci

2025-06-01T15:07:03+07:00

Measuring student satisfaction is crucial, especially considering the increasing competition in the field of education along with the advancement of knowledge and technology. It is essential to assess whether the services expected by students align with the services they actually receive. Evaluating student satisfaction can significantly help higher education institutions improve service quality, which in turn may lead to an increase in student enrollment.This study employs a quantitative method using one of the data mining techniques—classification—through the C4.5 algorithm to measure student satisfaction levels. The population of this research includes active students at IAIN Kerinci, with a sample size of 100 respondents. The students serve as the subjects providing evaluations or opinions on variables characterized by Tangibles, Reliability, Responsiveness, Assurance, and Empathy.The data is processed using data mining classification techniques, with testing conducted through RapidMiner software. The results of the analysis and testing indicate that data mining effectively classifies the variables in measuring student satisfaction, generating 10 decision tree rules with an accuracy rate of 98.22%. These resulting rules are expected to serve as a foundation for making informed decisions on actions needed to enhance student satisfaction.

Database Consistency Improvement In Job Offering System Using Normalization Method

2025-06-01T15:07:10+07:00

The role of information systems in modern life today is very important, especially in a company to make strategic decisions or actions. Information systems must be free from data anomalies. Data anomalies can occur due to poor database structure design. This happens in job offering systems that still have data anomalies. This study uses the normalization method to verify the quality of the database in the job offering system. Normalization is a technique that focuses on grouping several attributes into an entity based on certain criteria to achieve normal form. Normalization aims to maintain data consistency and integrity. The job offering information system has two databases to carry out all its functions. The first database is for the needs of processing job offering information system data. The second database is for the needs of processing company organizational structure data. This study has identified both databases of the job offering system. There are 2 violations of the normalization provisions found. Violations occur in the employee and schedule_wwc tables which do not follow the 3NF normalization provisions. Improvements need to be made to the database to improve data consistency in the job offering system. This study has made improvements by modeling data according to the data needs of the job vacancy information system. The modeling produces a conceptual data model (CDM), a logical data model (LDM) and a physical data model (PDM). The modeling results have been reverified using the normalization method and are free from any violations.

Sentiment Analysis of Loudspeaker Regulations in Houses of Worship on Social Media Using Support Vector Machine Algorithm

2025-06-01T15:07:17+07:00

Social media is an online platform where users can share content or interact with each other through discussions and debates that involve sentiments, such as agreement or disagreement on various topics. User sentiments on social media can be utilized in multiple ways, such as to gauge public opinion regarding the issuance of Circular Letter Number SE 05 of 2022 by the Ministry of Religious Affairs, which provides guidelines for the use of loudspeakers in mosques and prayer rooms. Due to the high volume of comments on social media regarding this circular, a sentiment analysis system is necessary. The sentiment analysis system in this research employs the Support Vector Machine (SVM) algorithm to classify comments as positive or negative. A total of 350 comments were collected from each social media platform—Facebook, Twitter, YouTube, and Instagram—about the issuance of the circular. These comments were divided into 250 for training data and 100 for testing data on each platform. The training data from all platforms were combined, resulting in a total of 1000 training data. Based on system testing using the Support Vector Machine algorithm, the accuracy achieved was 72%. This result reflects the system's capability to analyze sentiments related to the guidelines for using loudspeakers in mosques and prayer rooms as stated in the circular

Analysis and Design of Monolithic System Architecture Migration to Microservices at PT. MALINDO Conceptual Approach

2025-06-01T15:07:28+07:00

This study analyzes the transition from a monolithic architecture to a microservices architecture within a corporate environment, specifically at PT.MALINDO. While the monolithic architecture was once effective, it now presents several challenges, including maintenance complexity, limited scalability, and frequent occurrences of deadlocks. The analysis highlights the growing need for a more adaptive and flexible system to respond to dynamic business requirements. In this context, a microservices architecture is proposed as a solution to overcome the limitations of the monolithic approach. Microservices break down applications into small, independent services, enabling easier and more efficient development, deployment, and maintenance. By using components such as an API Gateway and message brokers like Apache Kafka, inter-service communications can be managed more effectively, ensuring improved system performance and resilience. The findings indicate that transitioning to a microservices architecture can significantly enhance the system's performance, flexibility, and scalability. The resulting hypothesis suggests that adopting microservices will offer long-term benefits for PT.MALINDO, particularly in addressing system complexity and improving responsiveness to evolving business needs. Recommendations include implementation strategies and change management practices necessary to ensure a smooth and low-risk transit

Sentiment Analysis Related To Covid-19 Vaccination On Social Media Using The K-Nearest Neighbor (K-NN) Method

2025-06-01T15:07:38+07:00

Coronavirus 19 (COVID-19) has become a topic of great concern in the past two years. To anticipate the spread of the virus, the government has made various efforts, one of which is by procuring a COVID-19 vaccination to increase the body's immunity. In carrying out the program, the government urges the public to use social media as a means of disseminating information regarding the COVID-19 vaccination. Facebook is one of the most popular social media and is chosen by agencies as a medium of information. Information regarding the vaccination is shared by the Ministry of Health of the Republic of Indonesia through its Facebook Page and the public can provide opinions in the form of comments. Given that the comments are numerous and lengthy if you have to read the manual, it is difficult to classify which one corresponds to the positive, negative or neutral opinion class, so a system is needed to analyze them. This sentiment analysis system uses the K-Nearest Neighbor (K-NN) method to classify positive, negative and neutral opinions. This study uses 750 comments obtained from posts in November 2021 with the keywords 'vaccination' and 'vaccine', with the distribution of 700 training data and 50 test data. Furthermore, the comments are pre-processed with the stages of case folding, filtering, tokenizing, normalization, stopwords and stemming, then weighted using the TF-IDF feature. System testing is carried out using the K-Nearest Neighbor (K-NN) method with a value of k = 1, k = 3, k = 5, k = 7 and k = 9 . 1 and f-measure of 0.71428571428571. Meanwhile, the lowest accuracy value is at the value of k = 7 and k = 9 with an accuracy of 0.66 and an error rate of 0.34.

Implementation of Mobile-Based E-Kost System to Optimize Online Search, Booking, and Payment

2025-06-01T15:07:46+07:00

Rapid technological developments have changed the process of searching for boarding houses, which has been done manually through brochures, pamphlets, or banners. These conventional methods are considered inefficient because of their limited reach and the time required, especially for prospective tenants from outside the area. This study designs and develops a mobile-based e-boarding house application with features such as searching, booking, and digital payments, using the Rapid Application Development (RAD) methodology. This application makes it easier for users to find boarding houses that suit their wishes while making it easier for boarding house owners to manage room availability, tenant data, and payment history in a structured manner. The test results show that the e-boarding house application runs optimally without technical constraints and is effective in meeting user needs. By providing digital solutions, this application can increase the efficiency of searching and managing boarding houses, so that the process becomes faster, more practical, and more modern. Implementing this system provides significant benefits for prospective tenants and boarding house owners, namely increasing accessibility and management in the boarding house industry.

Application of COBIT 2019 Design Factors in Strengthening IT Governance in the Palm Oil Plantation Sector

2025-06-02T10:17:44+07:00

Application of Ensemble Machine Learning Methods for Aspect-Based Sentiment Analysis on User Reviews of the Wondr by BNI App

2025-06-02T10:31:18+07:00

This study analyzes user perceptions of the Wondr by BNI app using Aspect-Based Sentiment Analysis (ABSA) and a stacking ensemble learning approach on user reviews. Data were collected from the Google Play Store and App Store through scraping, then processed and labeled. The study involves two classification stages: aspect identification and sentiment classification for each aspect. The stacking ensemble model without resampling showed the best performance, with F1-scores of 99.4% for UI (User Interface), 99.3% for Authentication, and 99% for Transaction. For sentiment classification, F1-scores reached 82.2% User Interface (UI), 87.8% (Authentication), and 92.4% (Transaction). The use of LIME (Local Interpretable Model-Agnostic Explanations) improved model interpretability by highlighting keywords influencing the classification results. The final output of this research is a website capable of performing aspect-based sentiment classification

Design and Development of the Boarding House Management Information System (SIMKO) Using Laravel with Agile Methodology

2025-06-02T10:37:38+07:00

The manual management of boarding houses often causes various problems, such as inaccurate recording of transactions and tenant data, lack of information for prospective tenants, and unstructured booking and payment processes. This research aims to design and build a web-based Boarding House Management Information System (SIMKO) using the Laravel framework and the Agile development method. Data is collected through literature studies, interviews with boarding house owners, and direct observation of boarding houses in the Sedati area. The result of this research is an integrated information system with main features such as boarding house search, filing complaints, recording tenant and transaction data, booking rooms, financial reports, and digital payment support through Xendit. The development process is iterative and flexible to adjust to user needs. This system is expected to increase transparency, as well as the overall quality of boarding business management services.

Design of Web-Based Financial and Product Management System for Onemens Leather Admin Using the Agile Method

2025-06-02T10:46:29+07:00

This research aims to design and develop a web-based financial and product management system for Onemens Leather to address issues related to manual data management, which often leads to inefficiencies and errors in record-keeping. The system development employs the Agile Development methodology, which supports a flexible and adaptive software development process in response to user needs. The system is built using PHP programming language with the Laravel framework, and MySQL as the database management system. The outcome of this research is an interactive website providing key features such as a business performance dashboard, real-time product stock management, transaction recording, and automatic and structured reporting of inventory and financial data. The implementation of this system has proven to improve operational efficiency, accelerate data entry and reporting processes, enhance data accuracy, and support faster, more precise decision-making based on reliable data.

Analysis of MyPertamina Application Acceptance Using a Modified Technology Acceptance Model (TAM)

2025-06-05T09:04:03+07:00

The rapid development of digital technology has driven PT Pertamina to launch the MyPertamina application as a solution to support the efficient and transparent distribution of subsidized fuel. However, the implementation of this application has encountered various technical complaints from users, including bugs, registration difficulties, and transaction issues, raising concerns about public acceptance of the technology. This study aims to analyze the factors influencing the acceptance of the MyPertamina application using the Technology Acceptance Model (TAM), which is modified by incorporating external variables such as perceived trust, perceived risk, perceived security, and service quality. A quantitative approach using Partial Least Squares Structural Equation Modeling (PLS-SEM) was employed to analyze data from 391 respondents. The findings indicate that service quality, perceived usefulness, and perceived trust significantly affect the attitude toward use, which subsequently influences the intention to use the application. In contrast, perceived ease of use, perceived risk, and perceived security were found to have no significant effect on the attitude toward use. These results provide strategic insights for the development and improvement of MyPertamina's digital services to enhance public acceptance.

Frontend Design and Development of Thesis Management Application Using NextJS in Physics Study Program UPN “Veteran” Jatim

2025-06-05T09:20:46+07:00

In higher education institutions, managing undergraduate thesis administration remains a challenge, particularly in the Physics Study Program, which currently lacks an system that can manage the process of students thesis. To address this issue, the Thesis Management Application was developed as a solution to manage thesis administration through a web-based system accessible to Students, Lecturers, Thesis Coordinators, and Study Program Coordinator. This study focuses on frontend web development using the Next.js framework and APIs. The application offers key features including authentication, pre-proposal submission, thesis advisor assignment, seminar and examination management, and submission of graduation documents. The development process followed the Scrum methodology over six sprint iterations. The application was tested using both black-box testing and user acceptance testing. A total of 177 were tested using black-box testing, all of which received a passed status. User Acceptance Testing was conducted across the four user roles mentioned earlier, with all features receiving accepted status Finally, the system was deployed on the Vercel cloud hosting server, allowing public access for users.

Backend Design and Development of Thesis Management and Scheduling Application Using Rule-Based Algorithm in Physics Department UPN “Veteran” Jatim

2025-06-05T11:04:29+07:00

Thesis administration in higher education can be complex, especially in programs like Physics that previously lacked a structured system for managing thesis activities and seminar schedules. To address this, a backend system was developed to streamline these processes using a rule-based algorithm. The system supports multiple user roles—including students, lecturers, thesis coordinators, program coordinators, and administrators—by providing web-accessible API services. Key features include user authentication, pre-proposal submission, advisor assignment, seminar scheduling (proposal and final), oral examination coordination, and graduation document submission. The development followed the Scrum methodology over six sprint cycles, with each cycle aimed at improving functionality and ensuring system stability. To ensure the system met all functional requirements, black-box testing was conducted. The final version was deployed on a cloud hosting platform using Cloud Run, enabling public access to its API services. This solution is intended to enhance efficiency, reduce administrative workload, and provide a centralized, accessible platform for all stakeholders involved in the thesis process.

Real-Time Face Attendance System Using CNN Mobilenet and MTCNN

2025-06-05T11:08:23+07:00

This research presents the development of a real-time attendance system utilizing facial recognition, which incorporates three main components: the MobileNet Convolutional Neural Network (CNN) for classification, Multi-task Cascaded Convolutional Networks (MTCNN) for face detection, and Contrast Limited Adaptive Histogram Equalization (CLAHE) for image preprocessing. The model was trained on a curated subset of the Labeled Faces in the Wild (LFW) dataset, containing 20 categories with 50 images each, and evaluated using a locally captured dataset. Training was conducted on Google Colab using a pre-trained MobileNet model that was fine-tuned with 800 images, while 200 images were used for validation. System performance was assessed through several metrics, including accuracy, precision, recall, F1-score, and a confusion matrix. The model achieved a validation accuracy of 86% and an average F1-score of 0.85, reflecting high classification accuracy. To enhance usability, the system was implemented within a Python-based graphical user interface (GUI), which automates attendance tracking and records data directly into Excel spreadsheets. This study highlights the potential of integrating lightweight CNN architectures with effective preprocessing techniques and real-time GUI applications to create a reliable, efficient, and practical biometric attendance system

Creation of Appsheet-Based Vendor Database System at Savoy Homann Hotel Purchasing Division

2025-06-05T11:53:49+07:00

The tourism industry in Indonesia is experiencing rapid development. One of these industries is hospitality as a place for tourists to stay. In carrying out its operations, the hotel depends on vendors to meet the needs of goods and services. Therefore, the vendor selection stage needs to be done properly. An improper selection process can result in a mismatch between the goods received and the needs of the hotel. Based on these problems, this project was created with the aim of building an Appsheet-based vendor database system that contains complete information about vendor data and quality to support a better decision-making process. This project began with a needs analysis through interviews with Savoy Homann Hotel Purchasing. In addition, a literature study was conducted as a reference for designing solutions. Next, the system was developed and tested using the Blackbox Testing method and interviews. As a result, the system successfully fulfills all the company's needs, ranging from vendor data, product quality, to performance ratings. The test shows that the features run well and according to plan. In conclusion, this vendor database system effectively helps the Purchasing division in managing the procurement of goods and services more efficiently, structurally, and optimally.

Designing the UI/UX of the 'Skintopia' Skincare Application Using a User-Centered Design Approach

2025-06-05T12:16:37+07:00

In recent years, public interest in skincare has significantly increased, especially among younger generations. Although various skincare applications offering skin analysis features are already available, most of them still have limitations. These include product recommendations that are focused only on specific brands, the lack of validation by dermatologists, and the absence of a fully integrated skincare solution within a single platform. This study aims to develop a mobile skincare application called Skintopia, with a focus on user needs through the application of the User-Centered Design (UCD) method. The System Usability Scale (SUS) evaluation results showed scores of 92 from skincare users and 89 from dermatologists. Both scores fall under the “Excellent” category, receiving a grade of A and classified within the “acceptable” level of acceptability. These findings indicate that the UI/UX design of the Skintopia application successfully meets user needs and provides an intuitive and user-friendly experience.

Testing of Thesis Management Application Using STLC Framework and Automation Tools in Physics Study Program UPN “Veteran” Jatim

2025-06-05T12:44:44+07:00

Thesis administration at the higher education level, such as in the Physics Study Program, still faces challenges due to the absence of an integrated system. To address this issue, a web-based Thesis Management Application was developed to support five main user roles: Students, Lecturers, Thesis Coordinators, Program Coordinators, and Administrators. The system offers a comprehensive set of features including authentication, pre-proposal submission, advisor scheduling, seminar and exam management, publication submission, oral examinations, and final graduation requirements. This study focuses on the Quality Assurance (QA) process using the Scrum methodology and Software Testing Life Cycle (STLC) framework over six sprints conducted within three months. The process began with the mapping of 225 functional requirements on the Front-End and 206 on the Back-End, which were then translated into 1240 test cases derived from various usage scenarios, authorization validations, and interaction flow explorations. Non-functional testing was also conducted at the end of the sixth sprint, covering aspects such as portability, usability, performance, availability, and security. The results show that all system requirements were successfully met, indicating that the application is feasible for supporting a structured thesis administration process.

Implementation of Forward Chaining in a Web-Based Expert System for Passport Services

2025-06-12T21:06:08+07:00

In the digital era, technology has become a crucial component in public services. The Class I Immigration Office TPI Yogyakarta is experiencing an increase in passport applicants, necessitating more efficient service delivery. An Expert System, which simulates the knowledge of a human expert, can enhance the efficiency of passport services by gathering and organizing knowledge within a database. Expert Systems, which have been widely applied in the healthcare sector, also hold significant potential in passport services. Many passport applicants lack a clear understanding of the required information, leading to confusion and delays. An Expert System helps applicants access accurate information regarding passport types and provides recommendations for the most suitable option. It also improves service quality by reducing errors and saving time. The selection of an Expert System is based on its ability to effectively store and manage expert knowledge, while offering accurate and fast solutions and recommendations. This system benefits passport applicants, immigration officers, and the government by improving the efficiency and effectiveness of public services and increasing public satisfaction. Additionally, the Expert System is designed to be flexible and adaptable to changes in regulations or procedures.

Performance Comparison of K-Means Algorithm and BIRCH Algorithm in Clustering Earthquake Data in Indonesia with Web-Based Map Visualization

2025-06-12T21:19:26+07:00

This study applies the K-Means and BIRCH algorithms to cluster earthquake data in Indonesia based on geographic coordinates (latitude and longitude), depth, and magnitude from 2008 to 2023. Due to its position at the intersection of three major tectonic plates, Indonesia is highly prone to earthquakes, making the mapping of vulnerable regions essential for disaster risk reduction. K-Means is selected for its simplicity and clustering effectiveness, while BIRCH is known for its scalability and efficiency in processing large datasets. The clustering process involves data preprocessing and normalization, followed by determining the optimal number of clusters using the Elbow method. Initial findings indicate that K-Means produces more distinct and well-separated clusters than BIRCH, with Silhouette Scores of 0.3501 and 0.2247, respectively. However, after expanding the dataset to 121,123 records and incorporating additional attributes such as mag_type, phasecount, and azimuth_gap, BIRCH demonstrated a significant improvement in performance, achieving a Silhouette Score of 0.3489—surpassing K-Means, which dropped to 0.1293. These results suggest that BIRCH is more effective for clustering large and complex datasets. The final clustering results are visualized on a web-based map to support spatial analysis and the identification of earthquake-prone zones.

Rule-Based Expert System Model with Backward Chaining Algorithm for Symptom-Based Skin Disease Diagnosis

2025-06-12T21:29:38+07:00

A rule-based expert system was a computational model designed to emulate expert decision-making using a knowledge base and inference algorithms. This research developed a rule-based expert system model with a backward chaining algorithm to diagnose skin diseases based on clinical symptoms. Backward chaining, a goal-driven inference method, started with a disease hypothesis (e.g., psoriasis) and verified related symptoms (e.g., kemerahan, sisik keperakan), enabling efficient differentiation of skin diseases with overlapping symptoms, such as dermatitis, psoriasis, and scabies. The model provided advantages in handling uncertainty, produced accurate diagnoses, and supporting interactive symptom verification. Developed using a knowledge base from credible sources like WHO and AAD, the model was intended to assist in clinical decision-making. The results showed that the backward chaining algorithm effectively improved the accuracy and efficiency of diagnosing skin diseases based on patient-reported symptoms

Web-Based E-Commerce System Design Using RAD Method: A Case Study of PT Muda Jaya Export

2025-06-12T21:40:33+07:00

This study focused on the design and development of a web-based e-commerce information system for PT. Muda Jaya Export by employing the Rapid Application Development (RAD) approach. The company had been experiencing inefficiencies in handling transactions, inventory, and order management due to the reliance on manual tools such as Microsoft Excel and communication via WhatsApp. These outdated methods often led to data inconsistencies and delays in processing operations. To address these challenges, the new system was built to streamline and centralize various business functions, including sales transactions, pre-order handling, safety stock monitoring, and reorder point calculation. The platform featured capabilities such as online product ordering, real-time pre-order tracking, automated safety stock and reorder point computations, and secure payment integration through Midtrans. The system was implemented using modern web technologies, including React.js for the frontend, Express.js for the backend, and PostgreSQL for the database. To ensure functionality and user satisfaction, the system underwent testing through the Blackbox Testing technique as well as User Acceptance Testing (UAT). The testing outcomes demonstrated that the newly developed system significantly enhanced the accuracy and efficiency of the company’s sales and inventory operations. With this integrated solution, PT. Muda Jaya Export was better equipped to manage its business processes, reducing operational errors and delays. Furthermore, the system contributed to improved data reliability and provided valuable support for making informed decisions related to inventory levels and customer orders.

Acceptance Analysis and Application Success Bicarakan.id using Utaut and DeLone & McLean

2025-06-12T22:30:02+07:00

The development of digital-based mental wellbeing administrations gives viable and adaptable arrangements for the community, particularly the millennial era, in getting to mental administrations. One of the stages that give online counseling administrations in Indonesia is the application Bicarakan.id, which demonstrates a decently tall selection rate. Be that as it may, based on perceptions, it was found that different complaints from clients on a number of stages, such as less than ideal application execution and moderate reaction from benefit suppliers, hence preventing get to to the specified administrations. This consider points to analyze the components that influence the acknowledgment and effective utilize of the application Bicarakan.id by combining two approaches,namely the Unified Theory of Acceptance and Use of Technology (UTAUT) and DeLone & McLean model. The examination prepare was conducted utilizing Partial Least Square Structural Equation Model (PLS-SEM) through SmartPLS 4 computer program and included 403 respondents. The comes about appeared that the factors Information Quality, Service Quality, and Effort expectation desire have a positive and critical impact on User Satisfaction, which in turn too have a positive and critical impact on Continuance Intention. In the mean time, factors System Quality and Performance Expectancy desire don't have a critical impact on User Satisfaction, as prove by testing Path Coefficient based on the centrality criteria set.

Analysis of Factors Influencing the Acceptance of the Indodax Application Using the UTAUT 2 Model

2025-06-12T22:31:03+07:00

This study investigates the key factors influencing user acceptance of the Indodax application, a leading cryptocurrency trading platform in Indonesia, by employing the UTAUT 2 (Unified Theory of Acceptance and Use of Technology 2) framework. The model focuses on four core variables—Performance Expectancy, Effort Expectancy, Social Influence, and Facilitating Conditions—to assess their impact on users’ Behavioral Intention to adopt the platform. Data were collected from 417 respondents using an online questionnaire, and the relationships among variables were analyzed using SmartPLS 4.0 with the bootstrapping technique. The hypothesis testing results confirmed that all proposed hypotheses were supported, indicating that each of the identified factors significantly contributes to users' intentions to use the application. Among the variables, Performance Expectancy and Facilitating Conditions were found to have the strongest impact on users' Behavioral Intention. Nevertheless, Effort Expectancy and Social Influence also demonstrated significant positive effects. These outcomes emphasize the importance of improving user experience by enhancing system usability, leveraging social influence, and strengthening supporting infrastructure. Overall, the study offers valuable insights for developers, platform providers, and policymakers in developing strategies to encourage broader adoption of cryptocurrency platforms like Indodax and to support the growth of the digital asset ecosystem in Indonesia.

The Influence of Computer Use and Information Technology Literacy on Enhancing the Abilities of College Students at the Nahdlatul Ulama Institute of Technology and Science Lampung

2025-06-14T09:45:45+07:00

This study aims to determine the effect of computer use and understanding of information technology on improving the abilities of students in the Information Technology Study Program at the Nahdlatul Ulama Lampung Institute of Technology and Science. The main problem identified is the still low utilization of practical computer technology in the learning process, even though universities have made large investments in providing facilities. This study uses a qualitative approach with a data collection method through a questionnaire distributed to 102 students from the 2021 to 2024 intake. The results showed that most students preferred practice-based learning methods to theory, and more than half of respondents used computers or laptops in their daily activities. In addition, most students already had basic knowledge of technology, information, hardware, software, and networks before entering college. The conclusion of this study is that educational background, experience using computers, and practice-based learning methods significantly affect the improvement of students' abilities in the field of information technology. These findings reinforce the importance of implementing practice-based learning methods and optimizing computer laboratory facilities in order to produce graduates who are ready to compete in the digital era.

Implementation of the Waterfall Method in the Lalungguh Ecoprint Website

2025-06-14T09:56:14+07:00

The rapid development of the digital era has encouraged MSME (Micro, Small, and Medium Enterprises) owners to adopt technology to enhance business efficiency and effectiveness. Lalungguh Ecoprint, an MSME engaged in sustainable fashion through the use of natural-based ecoprint techniques, still encountered obstacles in product promotion and manual financial record-keeping. This study aimed to develop a website that integrates product catalog management with financial recording into a unified, more efficient system. The development process employed the Waterfall method to ensure a structured and systematic workflow. Laravel was chosen as the primary framework due to its support for the Model-View-Controller (MVC) architecture, which simplifies code organization and modular feature development. MySQL was utilized as the database management system for its reliability in managing complex data storage. The resulting website enables real-time, centralized management of product and financial data and is accessible across multiple devices. This system is expected to enhance operational efficiency, streamline business activities, and broaden Lalungguh Ecoprint’s marketing reach through a digital platform.

Transfer Learning Implementation with MobileNetV2 for Cassava Leaf Disease Detection

2025-06-14T10:07:48+07:00

Cassava (Manihot esculenta) is one of Indonesia’s key agricultural commodities but is vulnerable to various leaf diseases, such as Cassava Bacterial Blight (CBB) and Cassava Mosaic Disease (CMD). These diseases often exhibit similar visual symptoms, making it challenging for farmers to accurately identify them through manual observation. This study aims to develop an automatic cassava leaf disease detection system based on transfer learning, utilizing the MobileNetV2 architecture. The dataset used consists of 1,500 images, evenly distributed across three categories: CBB, CMD, and healthy leaves. The data underwent preprocessing, augmentation, and model training, including fine-tuning of the last 20 layers of the MobileNetV2 model. Evaluation results indicated that the model achieved an accuracy of 67% on the test set, with the highest performance in detecting Cassava Mosaic Disease, reflected by an F1-score of 0.75. These results demonstrate the potential of MobileNetV2 as a lightweight and efficient solution for detecting cassava leaf diseases, particularly when supported by a larger and more diverse dataset. This research serves as a foundation for developing mobile-based diagnostic tools to help farmers make faster and more accurate decisions in the field.

A Deep Learning-Based Sentiment Classification for Identifying Advertorial Content in Online News

2025-06-18T22:05:09+07:00

The rapid advancement of technology and the widespread use of the internet have brought significant positive and transformative impacts across various aspects of human life, including finance, healthcare, education, and the media industry. One notable consequence of information transparency is the vast availability and large-scale exchange of data. However, this also presents new challenges, particularly in the spread of misleading content such as disguised advertorials that resemble genuine news. This threatens the objectivity of the information received by the public. To address this issue, an automated solution is needed to identify the distinguishing characteristics of advertorials in online news content. This study proposes a deep learning approach using the Convolutional Neural Network (CNN) model to detect sentiment as an indicator of advertorial content. CNN is a widely used deep learning model for processing sequential and spatial data, capable of automatically learning features from text. The dataset comprises news articles categorized by advertorial traits, such as positive or neutral sentiment, persuasive language, and promotional content highlighting specific entities. The data undergo several processing stages, including text preprocessing, tokenization, padding, and CNN model training. Model performance is evaluated using accuracy, precision, recall, and F1-score. The experimental results show a validation accuracy of 84%, although overfitting issues were observed. Despite ongoing limitations, such as restricted data and suboptimal parameter tuning, the findings suggest that the CNN model has potential for automatically detecting advertorial content and can serve as a basis for future research using more advanced models and refined parameter adjustments.

Decision Support System For Submitting and Evaluating Web-Based Scholarships Using The Topsis Method at SMP Kusuma Raya

2025-06-18T22:41:21+07:00

This research aims to develop a web-based decision support system for the scholarship application and assessment process. The system is designed to improve efficiency, transparency, and objectivity of selection. The TOPSIS method is used to evaluate potential recipients based on a number of relevant criteria. The system was developed using PHP, MySQL, Visual Studio Code, and XAMPP as the development platform. System testing shows that this application is able to provide accurate scholarship recipient recommendations, so that it can help decision makers in determining recipients more fairly and systematically. With this approach, it is expected that the scholarship selection process will become more structured and reduce the potential for subjectivity in assessment. The results of this research contribute to the application of information technology in supporting a better selection system in the academic environment and scholarship granting institutions.

Optimization of Random Forest Model with SMOTE for Fetal Health Classification Based on Cardiotocography

2025-06-19T10:36:15+07:00

Fetal health during pregnancy is a crucial aspect in ensuring the optimal growth and development of a child, particularly during the golden period of life from the womb to the age of two. In the medical field, monitoring fetal conditions is vital to detect potential risks as early as possible. One of the tools commonly used in this process is cardiotocography (CTG), which provides essential data on fetal heart activity and movement. With technological advancements, machine learning-based approaches are increasingly being utilized to process CTG data more effectively. However, a major challenge in classifying medical data such as CTG lies in class imbalance, where the distribution between majority and minority classes is uneven. This study evaluates the effectiveness of the Synthetic Minority Over-sampling Technique (SMOTE) in addressing this imbalance and assesses the performance of the Random Forest algorithm in classifying fetal health conditions. The results show that the combination of SMOTE and Random Forest achieves the best performance compared to other methods, with an accuracy of 94.40%, precision of 94.45%, recall of 94.40%, and an F1-score of 94.38%. These findings indicate that SMOTE is effective in improving the representation of minority classes, while Random Forest demonstrates superior and consistent classification performance on CTG data