cover
Contact Name
Yaddarabullah
Contact Email
yaddarabullah@trilogi.ac.id
Phone
+62818749275
Journal Mail Official
jisa@trilogi.ac.id
Editorial Address
Jl. TMP Kalibata No.1 d.h STEKPI
Location
Kota adm. jakarta selatan,
Dki jakarta
INDONESIA
JISA (Jurnal Informatika dan Sains)
Published by Universitas Trilogi
ISSN : 27763234     EISSN : 26148404     DOI : https://doi.org/10.31326/jisa
JISA (Jurnal Informatika dan Sains) is an electronic publication media which publishes research articles in the field of Informatics and Sciences, which encompasses software engineering, Multimedia, Networking, and soft computing. Journal published by Program Studi Teknik Informatika Universitas Trilogi aims to give knowledge that can be used as a reference for researchers and can be useful for society. Accredited “SINTA 4” by The Ministry of Research-Technology and Higher Education Republic of Indonesia, Free of Charge (Submission,Publishing). JISA (Jurnal Informatika dan Sains) is scheduled for publication in June and December (2 issue a year) This Journal accepts research articles in these following fields: Software Engineering: Web Development, Mobile Apps Development, Database Management System Multimedia: Augmented Reality, Virtual Reality, Game Development Networking: Cloud Computing, Internet of Things, Wireless Sensor Network, Mobile Computing Soft Computing: Data Mining, Data Warehouse, Data Science, Artificial Intelligence, Decision Support System
Articles 187 Documents
Golden Goal Futsal Court Rental Mobile Application Using the First Come First Serve (FCFS) Algorithm and Payment Gateway Integration Sirajudin, Sirajudin; Sanjaya, Fadil Indra; Waluyo, Anita Fira
JISA(Jurnal Informatika dan Sains) Vol 8, No 2 (2025): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v8i2.2545

Abstract

The futsal pitch rental process at Golden Goal is still done manually through direct communication or text messages, which often results in various problems such as unstructured booking queues, schedule conflicts due to the lack of a clear queuing system, and late payments. These problems result in low operational efficiency and an increased potential for scheduling errors. This research aims to develop a mobile-based futsal pitch rental application equipped with the implementation of the First Come First Serve (FCFS) algorithm to ensure the booking process is carried out based on the user's arrival time in a fair and orderly manner. The system development method used is the Waterfall model, which includes requirements analysis, design, implementation, testing, and maintenance. The application was developed using the Flutter framework because it has the ability to produce Android and iOS applications with only a single codebase, faster development time, and stable and responsive interface performance. These advantages make Flutter suitable for building a real-time booking system that requires fast interaction and a consistent user experience. Furthermore, the application is integrated with Midtrans services as a payment gateway to facilitate automatic digital payment transactions. Testing results using the black-box method indicate that all key features, including schedule selection, FCFS-based queuing mechanism, payment processing, and rental data management, have run well as needed. The implementation of this system has proven to be able to reduce schedule conflicts, improve the accuracy of the booking process, and increase the efficiency of rental management at Golden Goal. Thus, this application can be an effective and modern solution to address the problem of futsal field rentals that have been handled manually.
Design and Construction of an System for Diagnosis of Online Game Addiction Using The Forward Chaining and Certainty Factor Methods Based on a Website (Case Study: RSU South Tangerang) Oktavia, Petricia; Ferdiansyah, Ferdiansyah
JISA(Jurnal Informatika dan Sains) Vol 8, No 2 (2025): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v8i2.2434

Abstract

 Online games are a type of game that provides a unique pleasure for players, as they can be played not only alone (singleplayer) but also with two or more people (multiplayer) from various locations and countries. Online games are a kind of game that gives players something special because they can be played either singleplayer or with two or more people from different places and countries. According to the APJII 2025 poll, 34.91% of participants spend one to two hours a day playing online games.  This suggests that playing online games has ingrained itself into people's daily lives.  Because of this, many people can become addicted to online games without realizing it. It might result in adverse bodily effects like exhaustion, weakened immunity, visual issues, anxiety, restlessness when not playing, diminished focus, and emotional shifts (irritability or sensitivity). Therefore, an expert system is needed to diagnose online game addiction as a means of determining the level of addiction. This website aims to determine the level of online game addiction, using the data and the forward chaining method, which aims to generate a conclusion from existing facts. With this method, a conclusion will be obtained, which is then further processed to determine the certainty value. And this expert system requires the certainty factor method to find this certainty value. Given the problems and needs at RSU Tangerang Selatan, this research has produced an expert system for diagnosing online game addiction, which provides ease of use because it is published on a website. This expert system generates output that includes conclusions based on existing facts, the level of online game addiction determined by the certainty factor method, a certainty value ranging from 0% to 100%, and solutions provided by experts.
The Effect of Online Adminduk Service Applications on the Number of Population Administration Applications ilahi, faidlul; saikin, saikin; ashari, maulana; fadli, sofiansyah
JISA(Jurnal Informatika dan Sains) Vol 8, No 1 (2025): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v8i1.2190

Abstract

This study aims to investigate the effect of using the population and civil registration office Online Service Application (SEMAIK) on the number of population administration (Adminduk) applications at the Population and Civil Registration Office (Disdukcapil) of Central Lombok Regency. The direct impact of the implementation of this application on the number of civil registration applications has not been widely studied empirically. Therefore, this research is important to determine the extent to which the use of the SEMAIK application has an effect on increasing applications for population administration services. The SEMAIK application, as an innovation of the Central Lombok Disdukcapil, is designed to make it easier for citizens to apply for civil registration documents online without the need to visit the Disdukcapil office directly. This research method uses the System Usability Scale (SUS) to assess the level of acceptance and satisfaction of application users. The study involved 48 respondents, resulting in an average SUS score of 73.9, which indicates that the application is in the “Acceptable” satisfaction category with a grade of C and a qualitative assessment between ‘Good’ to “Excellent”.”Data analysis shows that there is an increase in the number of Adminduk applications through the SEMAIK application during the 2021-2023 period, which is correlative with an increase in user satisfaction scores. This result confirms that the level of application acceptance is at a relatively good level. User satisfaction with the SEMAIK application has contributed to an increase in the number of Adminduk document submissions in Central Lombok Regency. This research provides important insights into the importance of usability in public service applications and its implications for the efficiency of population administration services.
Development of the 3D Game “Lavender's Warmth” Using the Collision Detection Method Nayottama, Nayaka Apta; Wahyuni, Febriana Santi; Zahro, Hani Zulfia
JISA(Jurnal Informatika dan Sains) Vol 8, No 2 (2025): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v8i2.2558

Abstract

This study presents the development of a 3D puzzle–adventure game titled “Lavender’s Warmth” using the Collision Detection and Finite-State Machine (FSM) methods. The use of Collision Detection is essential because the game relies heavely in physical interaction between puzzle pieces, slots, and environmental object. Without Collision Detection, the game would fail to validate puzzle placement. Meanwhile, the FSM approach is required to regulate enemy behaviour in structured manner. The Finite-State Machine was chosen because it is one of the most widely adopted approaches for modeling NPC behavior, offering deterministic transitions, low memory usage, and ease of debugging. Alternative techniques such as behavior trees or utility AI are more complex and unnecessary for the simple enemy mechanics in this game. Therefore, Finite-State Machine provides the most appropriate balance between functionality, performance, and development simplicity. The game was developed using Unity 3D and tested through functionality, method, and user evaluations. The results showed that all main features worked as expected, with 52.63% of users strongly agreeing and 40.64% agreeing that the game was engaging and enjoyable. The implementation of both methods successfully enhanced interactivity, responsiveness, and gameplay consistency. 
Interpretable Ensemble-Based Intrusion Detection Using Feature Selection on the ToN_IoT Dataset Sulaiman, Vaman Shakir; Mustafa, Firas Mahmood
JISA(Jurnal Informatika dan Sains) Vol 8, No 2 (2025): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v8i2.2487

Abstract

With With the rapid growth of IoT, securing interconnected devices against cyber threats has become critical. IoT datasets such as ToN-IoT are often high-dimensional, which poses challenges for efficient and accurate intrusion detection. Moreover, interpretable models are essential to help security analysts understand and trust automated decisions. Intrusion Detection Systems (IDS) powered by machine learning offer promising solutions, especially when trained on realistic datasets such as ToN_IoT. However, achieving a balance between high accuracy, computational efficiency, and model interpretability remains a challenge. This study proposes an efficient and interpretable IDS framework for binary classification using the ToN_IoT dataset, aiming to identify the optimal feature selection method and ensemble learning model while leveraging explainable artificial intelligence to interpret model decisions. A quantitative experimental approach was adopted, applying and comparing Principal Component Analysis (PCA) and Recursive Feature Elimination (RFE) for feature selection, and evaluating the performance of LightGBM, XGBoost, and Random Forest classifiers using Accuracy, F1-score, Precision, Recall, and training time. RFE outperformed PCA, identifying 11 key features, and LightGBM emerged as the top-performing model with an accuracy of 99.72%, demonstrating both speed and strong generalization. SHAP (SHapley Additive exPlanations) was used to generate summary plots for global feature importance, enhancing the transparency and interpretability of IDS decisions. Overall, the combination of RFE and LightGBM resulted in a high-performing and explainable IDS framework, underscoring the importance of strategic feature selection and model choice. Compared to existing IDS approaches on the ToN-IoT dataset, our proposed framework not only achieves higher accuracy but also provides a rapid and lightweight solution. Additionally, by incorporating SHAP for feature importance analysis, our approach ensures clear model interpretability, allowing security analysts to understand and trust the system’s decisions. This combination of high performance, efficiency, and explainability highlights the practical advantages of our method over previous work. Future research will extend this framework to support multiclass classification and online learning for real-time threat detection.
IoT Implementation for Hydroponic Water Monitoring Using Web-Based pH and TDS Sensors with Node-Red Faisal, Mochammad; Bachtiar, Adnan Nuur; Darwis, Muhammad
JISA(Jurnal Informatika dan Sains) Vol 8, No 1 (2025): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v8i1.2209

Abstract

Due to land scarcity, rapid urbanization, and shrinking agricultural space, urban environments such as Jakarta face increasing agricultural challenges. By enabling efficient, soil-free cultivation in limited areas, hydroponics has emerged as a promising solution to address these issues. However, ensuring the consistency of the quality of hydroponic water systems, especially in terms of pH and total dissolved solids (TDS), is often done manually, which is ineffective and prone to human error. Several IoT-based solutions have been proposed; however, many rely on cloud services or mobile platforms, which limit accessibility in offline environments. This study introduces a scalable, internet-independent hydroponic water quality monitoring system that uses pH and TDS sensors connected to an ESP32 microcontroller. A Node-RED dashboard, accessible by a browser on a local network, is used by the system to display data in real time, using the MQTT protocol. The system, developed using the IoT Platform Design Methodology, underwent black-box testing to ensure that its data acquisition, transmission, and visualization were accurate. The results showed reliable performance without any functional errors. Classified as a Level 2 IoT system, it allows real-time monitoring without automation and the possibility of future expansion such as data storage and actuator control. The proposed system provides a practical and scalable solution for urban hydroponic farmers working in areas with limited internet connectivity.
Hybrid Feature Combination of TF-IDF and BERT for Enhanced Information Retrieval Accuracy Aprilio, Pajri; Felix, Michael; Nugraha, Putu Surya; Fahmi, Hasanul
JISA(Jurnal Informatika dan Sains) Vol 8, No 1 (2025): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v8i1.2179

Abstract

Text representation is a critical component in Natural Language Processing tasks such as information retrieval and text classification. Traditional approaches like Term Frequency-Inverse Document Frequency (TF-IDF) provide a simple and efficient way to represent term importance but lack the ability to capture semantic meaning. On the other hand, deep learning models such as Bidirectional Encoder Representations from Transformers (BERT) produce context-aware embeddings that enhance semantic understanding but may overlook exact term relevance. This study proposes a hybrid approach that combines TF-IDF and BERT through a weighted feature-level fusion strategy. The TF-IDF vectors are reduced in dimension using Truncated Singular Value Decomposition and aligned with BERT vectors. The combined representation is used to train a fully connected neural network for binary classification of document relevance. The model was evaluated using the CISI benchmark dataset and compared with standalone TF-IDF and BERT models. Experimental results show that the hybrid model achieved a training accuracy of 97.43 percent and the highest test accuracy of 80.02 percent, outperforming individual methods. These findings confirm that combining lexical and contextual features can enhance classification accuracy and generalization. This approach provides a more robust solution for improving real-world information retrieval systems where both term specificity and contextual relevance are important.