cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Rio Andriyat Krisdiawan
Contact Email
rioandriyat@uniku.ac.id
Phone
+6285224064393
Journal Mail Official
nuansa.informatika@uniku.ac.id
Editorial Address
Kampus 1 UNIKU. Jl. Cut Nyak Dhien No.36A, Cijoho, Kec. Kuningan, Kabupaten Kuningan, Jawa Barat 45513 Kampus 2 UNIKU. Jl. Pramuka No.67, Purwawinangun, Kec. Kuningan, Kabupaten Kuningan, Jawa Barat 45512
Location
Kab. kuningan,
Jawa barat
INDONESIA
Nuansa Informatika
Published by Universitas Kuningan
ISSN : 18583911     EISSN : 26145405     DOI : https://doi.org/10.25134/nuansa
Core Subject : Science,
Computer Science & IT
NUANSA INFORMATIKA adalah jurnal peer-review tentang Informasi dan Teknologi yang mencakup semua cabang IT dan sub-disiplin termasuk Algoritma, desain sistem, jaringan, game, IoT, rekayasa Perangkat Lunak, aplikasi Seluler, dan lainnya
Arjuna Subject : Ilmu Komputer (semua kategori) - Aplikasi Ilmu Komputer
Articles 87 Documents
 5   6   7   8   9 
A Bidirectional GRU Approach with Hyperparameter Optimization for Sentiment Classification in Game Reviews : Pendekatan GRU Dua Arah dengan Optimasi Hiperparameter untuk Klasifikasi Sentimen dalam Ulasan Game Alamsyah, Nur; Titan Parama Yoga; Budiman; Imannudin Akbar; Hendra, Acep; Januantara Prima, Alif
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.399

Abstract

Sentiment analysis plays a vital role in understanding user perspectives, especially in domains such as game reviews where user feedback influences product perception and engagement. This study presents a comparative approach using Gated Recurrent Unit (GRU), hyperparameter-tuned GRU, and Bidirectional GRU models to classify sentiments in a dataset of game reviews. The experiment begins with standard preprocessing and tokenization steps, followed by vectorization and supervised training. Hyperparameter optimization is conducted using Keras Tuner to identify the most effective configuration of embedding dimensions, GRU units, dropout rates, and learning rates. The best model, a Bidirectional GRU with tuned parameters, achieves a validation accuracy of 85.37% and shows superior performance across key metrics such as precision, recall, and F1-score. Despite the relatively small and imbalanced dataset, the Bidirectional GRU model demonstrates robust generalization. This study also highlights future directions, including class balancing techniques and the integration of pretrained word embeddings to further improve model performance.
The Implementation of the TOPSIS Method in Determining Stunting Toddlers: Penerapan Metode TOPSIS dalam Penentuan Balita Stunting Umi Khultsum; F. Lia Dwi Cahyanti; Elly Firasari
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.400

Abstract

Stunting is a growth disorder in children due to chronic malnutrition and recurrent infections, especially in the first 1,000 days of life. Assessment of stunting status that only relies on height and weight measurements is considered ineffective because it does not cover all aspects that affect a child's nutritional status. At Posyandu Bougenvile, stunting identification is still done manually and is at risk of causing errors in decision making. This study aims to develop a web-based Decision Support System (DSS) using the Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method to assist Posyandu cadres in determining toddler stunting status quickly, accurately, and efficiently. This system processes data from four main anthropometric indicators, namely Height/Age, Weight/Age, Weight/Age, and BMI/Age. The results of the system calculations show agreement with manual calculations, which proves that the system is working optimally. An example of the results shows that toddlers with code A1 (Rafasya Malik) have the lowest preference value of 0, followed by A4 (Ihsan Dwi Hanggoro) with a value of 0.4022149 which is included in the high stunting risk category. This system has proven to be able to help Posyandu cadres in prioritizing the handling of at-risk toddlers, as well as supporting the stunting monitoring process in a more structured and data-based manner.
Predicting the Happiness Index Based on the HDI Indicator in Indonesia Using the Ensemble Learning Approach: Prediksi Indeks Kebahagiaan Berdasarkan Indikator IPM di Indonesia Menggunakan Pendekatan Ensemble Learning Pane, Syafrial Fachri; Zain, Rofi Nafiis; Setiawan, Iwan; Putratama, Virdiandry
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.410

Abstract

Machine Learning is used to analyze complex data in various fields of research. In this study, we applied an ensemble learning approach consisting of Random Forest Regression (RF), XGBoost Regression (XGB), Decision Tree Regression (DT) and Pearson correlation analysis as well as Shapley Additive Explanations (SHAP) to analyze the relationship between the HDI and Happiness indicators in Indonesia. Second, building a prediction model with an ensemble learning approach, namely stacking, which consists of several algorithms including RF, XGB, DT. The results of this study, one, based on the results of Pearson correlation analysis, Permutation Importance (PI), and SHAP, show that the happiness score of Indonesian people has a strong correlation with the Human Development Index variable. The Pearson correlation result shows a value of 0.88, which indicates a very strong positive relationship between HDI and happiness. In addition, the Permutation Importance and SHAP analysis also confirms that HDI is one of the most influential variables in predicting happiness scores in Indonesia. Second, the performance model for predicting happiness using stacking regressors with an R-Squared value of 97.68\%, MAE 0.002900, MSE 0.000021, and RMSE 0.004604.
A Data-Driven Approach to Comparative Evaluation of Regression Models for Accurate House Price Prediction: Pendekatan Berbasis Data untuk Evaluasi Komparatif Model Regresi untuk Prediksi Harga Rumah yang Akurat Permata Hati, Tiara; Budiman, Budiman; Akbar, Imannudin; Alamsyah, Nur
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.411

Abstract

This study aims to develop and evaluate a property price prediction model in Bandung by applying machine learning (ML) algorithms. The need for more accurate property price predictions is increasing due to fluctuations in the property market. This study analyzes property characteristics, including the number of bedrooms, bathrooms, land area, building area, and location, as well as their impact on house prices. The study evaluates four regression algorithms, including linear regression, K-Nearest Neighbors (KNN), Random Forest, and XGBoost. Finally, this study proposes price_per_m2 and building_land_ratio as new features recommended for improvement in accuracy. The bottleneck method is derived from the data collection area of the Rumah123.com website, encompassing data preprocessing and data exploration. The following metrics will be used to evaluate each model: Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²). Based on our study, we conclude that both Random Forest Regression and XGBoost Regression achieve the highest accuracy, with R² values of 0.9941 and 0.9955, respectively, after adjustment. Conversely, Linear Regression and KNN Regression have the lowest accuracy, with KNN Regression being the least accurate. The primary contribution of this study is the development of a more accurate house price prediction model that can be applied in cities with similar market characteristics. These findings provide practical insights for property developers and buyers when making investment decisions.
Development Of A 2d Educational Animal Card Game Using Unity: Pengembangan Game Kartu Hewan Edukatif 2D Menggunakan Unity Sulaiman, Alma; Mamay Syani
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.423

Abstract

This research focuses on the development of Game Kartu Hewan, a 2D educational game for kindergarten children at TK Assalam Parongpong, using Unity and the Multimedia Development Life Cycle (MDLC). The study aimed to create an engaging learning tool for animal recognition (names and sounds). The MDLC method guided the game's creation through concept, design, material collection, assembly, and testing phases. Testing involved 90 kindergarten children (aged 3–6 years) and 10 teachers through game interaction, observation, interviews, and pre-test/post-test analysis. Results showed a significant improvement in animal recognition ability, with the average score increasing from 58.4 (pre-test) to 84.7 (post-test). A total of 85% of students completed all levels of the game, and 91% successfully identified animal names and sounds. The majority of children reported enjoying the game and found it easy to play. Teachers' feedback also emphasized the game's effectiveness as an educational tool. This study underscores the efficacy of Unity-based 2D games developed via MDLC in fostering engaging and effective learning experiences for young children.  
Performance and Efficiency Testing Analysis of Database Systems in Academic Information Systems: Analisis Pengujian Kinerja dan Efisiensi Sistem Basis Data dalam Sistem Informasi Akademik Kusuma Dewi, Utami; Lingga Wicaksono, Ryan; Dwifebri Purbolaksono, Mahendra; Satria, Villy
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.438

Abstract

This study examines the performance and efficiency of database systems within academic information systems, acknowledging the increasing demand for responsiveness and reliability in managing complex academic data. As educational institutions increasingly rely on digital systems, performance testing becomes essential to ensure that these systems continue to support the learning environment effectively. Guided by the ISO/IEC 25010 standard, the research focuses on evaluating three key aspects of performance efficiency: time behavior, resource utilization, and capacity. Using JMeter, a range of user load scenarios were simulated, and the results were examined through Control Quality Charts and Nelson Rules to detect underlying issues affecting system performance. The findings reveal that 82.5% of queries demonstrated good time behavior, and 80% performed well in resource usage. However, half of the tests related to capacity highlighted the need for further improvements. Some queries experienced delays and consumed excessive CPU and memory resources, indicating areas where optimization is required. These insights highlight the importance of refining queries and managing resources more effectively to ensure a seamless user experience. Future research should consider automated optimization, machine learning-based performance prediction, and system scalability, especially in more dynamic and distributed academic environments.
Fuzzy-Driven Adaptive NPC Behavior in a Meme-Based Platformer Game for Android Mobile: Perilaku NPC Adaptif Berbasis Fuzzy dalam Game Meme Platformer Berbasis Ponsel Android Encep Sayid Amrulloh; Andriyat Krisdiawan, Rio; Lesmana, Iwan; Rohmawati, Lutfi
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.440

Abstract

Game-based applications are increasingly used beyond entertainment to deliver adaptive, engaging user experiences. Yet, many mobile platformer games still rely on static enemy behaviors, leading to repetitive gameplay. This study introduces Pepe the Ponderland Warrior, a 2D platformer for Android that incorporates culturally relevant meme characters and dynamic NPC behavior using fuzzy logic. Developed with the Game Development Life Cycle (GDLC), the game uses the Fuzzy Sugeno inference system to adapt NPC responses based on player distance, health, and damage received. UML modeling guided the system design, while testing included black-box, white-box, and User Acceptance Testing (UAT). The fuzzy-based system enabled real-time, context-aware NPC decisions, creating more varied and challenging gameplay. The game passed functional and logical testing, with UAT from 30 users producing a high feasibility score of 81.2%, reflecting satisfaction in design, gameplay, and difficulty balance. By integrating fuzzy logic with meme-inspired content, this study offers a novel and efficient AI approach for mobile games, highlighting potential for expansion across platforms and with more adaptive inputs.

Page 9 of 9 | Total Record : 87

 5   6   7   8   9 

Filter by Year

2023 2025


Reset
Filter By Issues
All Issue Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025 Vol. 19 No. 1 (2025): Nuansa Informatika 19.1 Januari 2025 Vol. 18 No. 2 (2024): Nuansa Informatika 18.2 Juli 2024 Vol. 18 No. 1 (2024): Nuansa Informatika 18.1 Januari 2024 Vol. 17 No. 2 (2023): Volume 17 No 2 Tahun 2023