Jurnal Teknik Informatika dan Sistem Informasi

Applying Pathfinding in Firefighter Adventure Game Using Learning Instructional Design Method

Dede Kurniadi — 2025-04-17

Firefighters have responsibilities in fire and rescue incidents that do not exist in fire incidents, such as evacuating wasp nests, rescuing animals trapped in trees or wells, and so on. The importance of understanding the duties of a fire extinguisher is to
provide awareness to the public that with the existence of a fire extinguisher, the management of environmental resources is better maintained to realize environmental safety and security from the dangers of fire disasters. With very rapid technological information, presenting firefighting duties can be more interesting if presented with an adventure-themed 3D educational game. This research uses the Digital Game-Based Learning Instructional Design (DGBL-ID) method and applies a pathfinding algorithm to the path that
will be taken. This research produces an Android-based firefighting adventure game application. Testing the level of user satisfaction
obtained very satisfactory results, which were measured based on Black Box testing with the Guttman Scale method calculation.

Design and Implementation of E-Commerce Corrugated Carton Box Using Rapid Application Development

Tevin Takasili — 2025-04-17

PT Hora Cipta Jaya is a company specializing in the sale of corrugated cardboard boxes. PT Hora Cipta Jaya typically uses corrugated cardboard boxes to package goods or products for shipping. Due to their strength, durability, and recyclability, many industrial companies use them to package their products. PT Hora Cipta Jaya still conducts sales processes manually, starting from transactions, marketing, to recording and reporting. Employees still need to manually record all company data during sales using Excel. Errors often occur during the purchase and sale of products, such as mistakes in recording and pricing calculations, as well as errors in order data entry and shipping. The aim of this research is to assist the company in managing data and designing a system that features online ordering, payment, shipping, reporting, and product promotion. We developed this system using the RAD method, utilizing PHP programming language and MySQL database. The system development process is divided into four stages: requirements analysis, system design, system implementation, and application feasibility analysis. The research resulted in an e-commerce system that helps the company manage data, facilitates online product sales transactions and broader product marketing, and automatically records invoices and reports. All features of this system are now operational after successfully completing testing phases for both admin and customer parts using the black box testing method. The system scored 78 for the admin section and 79.5 for the customer section from each respondent using the System Usability Scale, achieving a class B rating (good category).

Indonesian Sign System Introduction Application with Tensorflow Lite and Firebase Authentication

Rozali Toyib — 2025-04-17

Deaf and mute individuals often face communication barriers with the general public due to limited understanding of sign language. This leads to a gap in social interaction and access to various public services. Government efforts to enhance social inclusion through various policies and programs need to be accompanied by practical solutions that can help the deaf and mute interact more easily with society. This study aims to develop a mobile application that can recognize and translate Indonesian Sign Language System (SIBI) into text or speech in real-time, thus helping the deaf and mute communicate more effectively with the general public. The application is designed using TensorFlow Lite for sign language recognition and Firebase Authentication for user authentication. The application was evaluated through questionnaires involving respondents from the general public and mobile experts. The results of the general user questionnaire showed an average satisfaction percentage of 86.65%, with positive ratings for ease of use, benefits, and application interface. Meanwhile, the results of the expert mobile questionnaire showed full satisfaction with an average percentage of 100%, indicating that all application features functioned well. The findings indicate that this application is effective in recognizing and translating sign language and is well-received by the deaf, mute, and the general public.

Performance Comparison of Word Embedding in Travel App User Review Sentiment Analysis

Muhammad Agung Maugi Pahendra — 2025-04-17

Traveloka, as one of the leading travel booking platforms, has achieved more than 50 million downloads on Google Play Store. This achievement shows the high interest and trust of users in the services offered. However, user reviews indicate that there are some issues with the app's performance and stability that need to be taken into account. This research compares the performance of the Word2Vec and ELMo word embedding methods using the BiLSTM model in sentiment analysis of Traveloka application reviews. The research results show that the BiLSTM model with Word2Vec has an accuracy of 76.13%, precision 75.22%, and F1-measure 76.58%, better than the model with ELMo which has an accuracy of 74.38%, precision 70.49%, and F1-measure 74.40%. The BiLSTM model with Word2Vec is more effective in sentiment analysis of Traveloka reviews, helping identify and address user issues to improve service quality and user satisfaction.

Integration of Convolutional Autoencoder with Support Vector Machine for Almond Varieties Classification

Rizal Fadlullah — 2025-04-17

This research aims to optimize almond variety classification by integrating Convolutional Autoencoder (CAE) as a feature extraction method and Support Vector Machine (SVM) for classification. The research process includes data collection from available datasets, preprocessing, and splitting data for training and testing. Features from almond images are extracted using CAE, which are then used in the SVM model for classification. Model evaluation shows a classification accuracy of 97% on the test data, a significant increase compared to the 48% accuracy of conventional SVM. The CAE-SVM approach offers more compact and informative feature representations, effectively improving almond variety recognition. This study highlights the potential of combining CAE and SVM advantages to enhance plant image analysis and encourages further advancements in machine learning applications in agriculture.

Implementation of Bidirectional Long Short-Term Memory for Stock Entity Identification

Akmalia Fatimah — 2025-04-17

One of the financial products in the capital market that is in great demand is stock. Shares are proof of ownership of a company that fluctuates and tends to have a high level of risk and nonlinear price changes. To make the right investment decision, investors are required to be able to analyze the abundant stock information carefully and quickly. In facing this challenge, Named Entity Recognition (NER) can be a potential solution in analyzing stock information by recognizing stock entities and grouping them into certain labels. In this research, NER is developed with the Bidirectional Long Short-Term Memory algorithm, which is used to identify five stock entities: company name, stock code, stock index, industry sector, and sub-sector. With an accuracy of 99.81% on the test data, the Bi-LSTM algorithm can identify the entities well and group each token into the five entities.

Economic Data Forecasting Using Hybrid Vector Autoregressive-Long Short Term Memory Model

A. Gilang Aleyusta Savada — 2025-04-17

Fluctuations in stock prices and the Rupiah exchange rate create uncertainty for investors in their investment decision-making. One approach to minimizing investment risk is through forecasting utilizing a reliable method. Traditional forecasting models, such as Vector Autoregressive (VAR), are effective in capturing linear patterns but struggle to accommodate more complex patterns. On the other hand, modern deep learning models like Long Short Term Memory (LSTM) can handle dynamic patterns (both linear and nonlinear) but have limitations in consistently processing simultaneous relationships among variables. This research aims to develop a Hybrid forecasting model by integrating VAR and LSTM approaches to predict the Composite Stock Price Index (IHSG) and the Rupiah exchange rate against the US Dollar. The Hybrid VAR-LSTM model leverages the strengths of VAR for linear patterns and LSTM for nonlinear patterns in multivariate time series data. Using the OSEMN framework (Obtain, Scrub, Explore, Model, iNterpret), this study ensures a systematic and comprehensive analysis process. Data from January 2004 to December 2023 is used to build the model, while data from January to July 2024 is used for validation. The model's performance is evaluated using Mean Absolute Error (MAE) to measure the prediction error. The results indicate that the Hybrid VAR-LSTM model significantly improves prediction accuracy compared to the VAR model used independently, as evidenced by a reduction of 42.72 points in MAE for IHSG predictions and 55.82 points for Rupiah predictions.

Keywords — Composite Stock Price Index; Hybrid VAR-LSTM; OSEMN Framework; Rupiah Exchange Rate; Time Series Forecasting.

Design Of Automatic Parking Barrier System With Face Recognition Using Eigenface Method

Yulius Dani Eko Saputro — 2025-04-17

The main problem in this study is that the parking system on the campus of the Catholic University Of Darma Cendika still relies on manual methods, such as the use of cards and physical tickets, which are prone to human error, inefficient, easily misused, and raise security concerns. The main objective of this study is to improve the security and efficiency of parking area management by reducing dependence on card-based methods or physical tickets. This study collects facial data from individuals with various angles and facial positions, then the data is further processed to improve image quality. By applying the Eigenface model, the system is able to recognize faces with 100% accuracy under certain lighting and distance conditions. However, the performance of facial recognition is still affected by the quality of lighting and the distance between the camera and the object, indicating that further optimization is needed. Recommendations proposed include adjusting the lighting and camera position to obtain better facial image results. The Eigenface-based facial recognition technology applied in this study has great potential in improving the efficiency of the automatic parking barrier system. However, to achieve optimal results in various environmental conditions, further development is needed. Thus, it is expected that this system will not only be able to recognize faces accurately, but also be able to operate effectively and efficiently in real environments. In addition, this system also uses the Convolutional Neural Network method to distinguish between real faces and facial images from the cellphone screen, thereby increasing the overall security of the system.

YOLOv5 Implementation for Image Classification in Indonesian Cuisine Calorie Estimation System

Maximus Aurelius Wiranata — 2025-04-17

In this era of continuously evolving technology, calorie counting applications have become crucial for individuals who are concerned about their eating habits and health. However, most of these applications have not fully accommodated the variety of dishes commonly consumed in Indonesia, especially the popular dishes in Java Island, which has the largest population in Indonesia. To address this limitation, this research introduces an innovative solution in the form of an Indonesian Cuisine Classification and Calorie Content Estimation System using YOLOv5 technology. In this approach, the YOLOv5 object classification technology is used to identify various types of Indonesian dishes, including eight classes such as satay, meatball soup, traditional soup, fried rice, mixed vegetables salad, fried chicken, beef soup, and beef stew. This system is not only capable of accurately classifying dishes but also provides calorie content estimation based on the composition of the classified food ingredients. The implementation of this research combines YOLOv5 to apply the Indonesian cuisine classification model using the nutrition API from API Ninjas to obtain the required nutrition data. This research uses datasets obtained from Kaggle website, Mendeley Data, and Roboflow, with a total of 303 images for each class of dishes. As a result, the model achieved an accuracy score of 94.2%, precision of 94.3%, recall of 93.8%, and an F1 Score of 93.8%.

Designing Index Learning Style for Developing Personalization Learning Management System Moodle-Based

Helen Anjelica Sianipar — 2025-04-17

Differences in students' learning styles often pose challenges in online learning, particularly in personalizing learning materials to meet individual needs. This study developed an Index Learning Style (ILS) plugin based on the Felder-Silverman Learning Style Model (FSLSM) to support personalized learning on the Moodle Learning Management System (LMS). The plugin is designed to identify students' learning styles through 44 questions measuring four main dimensions: processing, perception, input, and understanding. The system development involved algorithms for learning style analysis, integration with Moodle's restricted access feature, and implementation in an Internet of Things (IoT) course. The implementation results show that the ILS plugin can effectively map students' learning styles to relevant Learning Object Materials (LOM). Moreover, personalized learning materials increase student engagement and facilitate material comprehension, particularly for those with dominant learning styles such as Active, Sensitive, Visual, and Sequential. The development of the ILS plugin provides a practical solution for enhancing the online learning experience to make it more adaptive. This plugin has the potential for widespread implementation in various technology-based education contexts to support more personal and effective learning.