Universitas Islam Kuantan Singingi: E-Journals
Not a member yet
1863 research outputs found
Sort by
Implementation of the Waterfall Method in the Lalungguh Ecoprint Website
Full text linkThe 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
Testing of Thesis Management Application Using STLC Framework and Automation Tools in Physics Study Program UPN “Veteran” Jatim
Full text linkThesis 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
An Integrated Machine Learning and Deep Learning Approach for Multiclass Flood Risk Classification with Feature Selection and Imbalanced Data Handling
Full text linkFloods are hydrometeorological disasters that often occur in tropical regions such as Indonesia and can have significant impacts on infrastructure, economy, and public health. This study aims to build and compare the performance of 21 artificial intelligence models, consisting of 15 Machine Learning algorithms and 6 Deep Learning architectures, in classifying flood risk levels based on multivariate tabular data. The dataset used includes 22 relevant environmental and social variables, with classification targets in four classes: Low, Moderate, High, and Very High. To improve data quality, feature selection was carried out using the LASSO method and class balancing with the SMOTEENN technique. The evaluation results showed that the C4.5, MLP, Random Forest, and Logistic Regression models obtained the highest accuracy (>94%), followed by deep learning models such as BiLSTM, CNN, and BiGRU with competitive accuracy (≥90%). Confusion matrix analysis confirmed the consistency of predictions across classes with a balanced distribution, especially in the decision tree and deep neural network models. This study emphasizes the importance of selecting a model that suits the characteristics of the data to achieve optimal predictions. The pipeline developed in this study is expected to be the basis for a more accurate and adaptive AI-based early warning system in mitigating flood risks in the future
Implementing TF-IDF and Logistic Regression for Sentiment Analysis of YouTube Comments on the iPhone 16
Full text linkSentiment analysis of user opinions on social media has become a crucial aspect in understanding public perception of technological products. This study specifically aims to classify and analyze public sentiment reflected in YouTube comments regarding the iPhone 16 by employing the Term Frequency-Inverse Document Frequency (TF-IDF) approach and the Logistic Regression algorithm. The data was collected from product review videos on the GadgetIn channel using web scraping techniques.The preprocessing stage included cleaning processes such as converting characters to lowercase (case folding), removing common words that do not carry sentiment meaning (stopword removal), and reducing words to their root forms (stemming). The feature extraction results obtained through TF-IDF were used as input for the Logistic Regression model to classify the comments into three categories of emotional expression: positive (supportive), neutral, and negative sentiments toward the discussed topic. The model’s effectiveness was evaluated using accuracy, precision, recall, and F1-score metrics. Based on the evaluation results, the model demonstrated a reasonably optimal performance in classifying user opinions. The findings indicate that the model performs with stability and accuracy in handling high-dimensional sentiment data. This research contributes to the development of text-based sentiment classification systems in the context of technology review analysis
House Price Prediction in Surabaya Using Backpropagation Neural Network
Full text linkThis research develops a house price prediction system in Surabaya using the Backpropagation Neural Network (BPNN) method. The dataset was obtained through web scraping of property listings, resulting in 3,435 records with 52 attributes. To improve stability, the target variable (house price) was transformed using natural logarithms. Several neural network architectures were tested, and the best configuration [32, 64, 32] achieved Mean Absolute Error (MAE) of 0.3125, Root Mean Squared Error (RMSE) of 0.4201, R² of 0.7138, and Mean Absolute Percentage Error (MAPE) of 1.46%. A multi-run evaluation of 20 iterations confirmed consistency of results. The model was implemented as a web-based application using Flask, allowing users to predict house prices in real-time. This research shows that BPNN is reliable for property price forecasting and can support decision-making in the housing market
Optimizing Prompt Engineering for AI-Based Logo Generation Using Response Surface Methodology
Full text linkThis research developed an optimized prompt engineering framework for AI-based logo generation using Response Surface Methodology (RSM) with Central Composite Design (CCD). Despite rapid AI adoption, users face challenges in communicating design intent effectively, leading to inconsistent outputs. This study systematically tested 47 prompt combinations across five variables: prompt clarity, detail level, thematic description, visual elements, and color specification. The optimization identified eight critical components forming a structured template: Main Design Focus, Detail Elements, Thematic Style, Primary Colors, Complementary Colors, Rewording, Layout Size, and Element Limit. Experimental validation with 30 graphic designers demonstrated substantial improvements over unstructured prompts: visual consistency increased from 65% to 87%, iteration efficiency improved by 48.5% (from 6.6 to 3.4 attempts), and user satisfaction rose from 58% to 82%. Both manual designers and AI-experienced users successfully applied the framework with comparable effectiveness. This research contributes a systematic, optimization-based approach to prompt engineering in creative AI applications and provides a practical framework enhancing accessibility for non-technical users while maintaining professional quality standards in logo desin
Design of Automatic Fan Base On Arduino Uno Microcontroler And DHT11 Sensor
Full text linkThe temperature of the human body can fluctuate depending on environmental conditions, particularly the surrounding room temperature. To maintain comfort, a cooling device capable of providing adequate airflow is required, and one commonly used solution is an electric fan. This study focuses on designing and implementing an automatic fan system controlled by an Arduino Uno microcontroller and a DHT11 temperature sensor. The system is programmed to activate the fan automatically when the detected room temperature exceeds a predetermined threshold. In the design phase, the Arduino Uno functions as the core controller due to its ability to process sensor input and manage hardware operations efficiently. The DHT11 sensor measures both temperature and humidity, transmitting the data to the microcontroller, which then delivers a control signal to the relay module. Following the design stage, system implementation is carried out using the C++ programming language through the Arduino IDE. The program continuously reads temperature values from the DHT11 sensor, enabling real-time decision-making. When the temperature reaches the specified limit, the microcontroller triggers the relay, causing the fan to operate automatically. The results of this study show that the fan responds accurately to temperature changes, providing a practical automatic cooling solution
Design and Implementation of a Web-Based RT/RW Service Information System and Resident Data Monitoring at Mekarsari Village Environment
Full text linkThis study aims to design and implement a web-based RT/RW service information and resident data monitoring system to improve the effectiveness, accuracy, and transparency of community services. RT/RW administrative services at Mekarsari Village area consist of 28 Neighborhood Associations (RT), 10 Community Associations (RW), and 5,842 residents. Currently, Mekarsari Village still uses a manual services system, which causes several problems such as delays in processing, data recording errors, and difficulties in monitoring resident data collection. The methodology used in this research is the Agile method, which includes an iterative and adaptive process to user needs. Each iteration involves planning, design, implementation, testing, and direct evaluation by users. The technologies used in the design and implementation of this system include the CodeIgniter framework for the backend, MySql as database, and Bootstrap for the user interface. The research data was obtained from direct observation and interviews with village officials, RT/RW, and local residents.
 
Web Based Archives at Pt Dupoin Palembang Branch As an Effort to Transform the Manual System To the Electronic System
Full text linkIn Indonesia, digital transformation has become a national strategy encouraging both public and private institutions to adopt information technology to improve efficiency and accountability. One important form of this transformation is the implementation of a web-based digital archiving system that enables centralized document storage, management, and access. Web-based systems are preferred due to their flexibility, multi-device accessibility, and cost efficiency. In the context of document management, such systems provide fast document retrieval, systematic classification, and enhanced data security through user authorization. This research identifies problems at PT DUPOIN Palembang Branch, where document archiving is still handled manually using physical filing cabinets, leading to inefficiency, risk of data loss, and human error. The purpose of this study is to transform the conventional archiving process into a web-based digital archive system to improve work effectiveness and service quality. Data were collected through observation, interviews, and documentation. The results are expected to show that the implementation of a web-based archive system allows documents to be accessed online anytime and anywhere, supports remote work conditions, and improves document traceability through metadata management. This system is anticipated to strengthen document governance and enhance organizational competitiveness
Analysis of the UI/UX of the Skylar Topup Website Information System Using the Usability Scale (SUS) System Method
Full text linkTechnological developments in the field of information systems have brought significant changes in the way we conduct transactions, communicate, and access services. One of the aspects that is focused on in the development of a website-based information system is the design of the user interface (UI) and user experience (UX). With technological advancements and wider adoption, intuitive, accessible, and user-friendly UI/UX design has become essential to ensure that information systems can meet users' needs efficiently and effectively. This study aims to evaluate user experience focusing on the ease of use and effectiveness of the user interface (UI) on the SkylarTopup information system. This process involves identifying challenges faced by users in interacting with the website, such as difficulties in navigation, slow response times, and design aspects that can be improved. Through SUS-based analysis, it is hoped that recommendations can be generated to improve the quality of UI/UX, so that SkylarTopup's information system can be more optimal, efficient, and better meet user needs. The results of the SUS score obtained show that although this system can be used quite well, there is potential for a significant improvement in terms of usability