Clean Energy and Smart Technology

THE APPLICATION OF XGBOOST CLASSIFICATION FOR FRAUD DETECTION IN CREDIT CARD TRANSACTIONS

Muhamad Fuat Asnawi — 2025-04-30

Credit card fraud detection remains a critical challenge due to the inherent imbalance in transaction datasets, where fraudulent transactions are significantly fewer than normal ones. This study investigates the application of the XGBoost classification algorithm to address this issue using the publicly available Kaggle Credit Card Fraud Detection dataset. The research incorporates data preprocessing techniques such as normalization and SMOTE to handle the dataset's imbalance. Hyperparameter tuning using GridSearchCV optimizes the model’s parameters, enhancing its performance. The results indicate that the model achieves an Area Under the Curve (AUC) of 0.97, demonstrating its high accuracy in distinguishing between fraudulent and normal transactions. The evaluation metrics reveal an F1-score of 0.77 for fraudulent transactions, showing the model's reasonable effectiveness in detecting fraud. While the model performs exceptionally well in identifying normal transactions, reducing false negatives remains a challenge. This study underscores the potential of combining advanced machine learning techniques with preprocessing and optimization strategies to develop robust fraud detection systems.

PRODUCT SALES PREDICTION SYSTEM AT REX COMPUTER STORE USING WEBSITE-BASED SINGLE EXPONENTIAL SMOOTHING METHOD

Rizqi Kafa Muntaqa — 2025-04-30

Estimating or predicting the amount of sales is one of the factors that determines whether a company's business is running well or not. The problem faced by Rex Computer is that it cannot predict product sales in the future with current sales data, so customers may run out of stock when they want to buy the items they want. This study aims to create a system that is able to predict sales and determine the level of accuracy of the system. This study will implement the single exponential smoothing method, which is one of the prediction algorithms. The method used is an interview with Rex Computer employees regarding product sales and sales data is obtained. As well as conducting a literature study to find data from various literatures about predictions using the single exponential smoothing method. This study produces a website-based prediction system that can predict with results for product sales in the USB Wifi category with an alpha value of 0.1, namely the prediction results of 6-7 products, MAD = 2.11, MSE = 8.16, RMSE = 2.85560831906761, MAPE = 18.52, and accuracy = 81%,

ABHIRAMA SPORTS CENTER WITH BIOPHILIC ARCHITECTURE APPROACH

Abimanyu Kusuma Nur Fitri — 2025-04-30

The planning of Abhirama Sports Center with a biophilic architecture approach is a study of how to combine sports needs with design concepts inspired by nature. This approach aims to create a sports center that promotes a harmonious relationship between humans and nature through the use of natural elements. In this planning, the main focus is on creating an environment that supports the health and physical fitness of users. The concept of biophilic architecture is applied by utilizing natural elements such as sunlight, fresh air, plants, and other natural elements. In addition, the use of the latest technology is also considered to enhance the sports experience for users. Through this planning, it is hoped that Abhirama Sports Center will become a place that not only facilitates sports activities, but also provides a pleasant and calming experience for users. School students, college students, and the general public are expected to be able to use this facility to improve their health, fitness, and happiness. In order to achieve this goal, this planning involves collaboration between architects, sports experts, and environmental experts. Through a holistic and integrated approach, Abhirama Sports Center is expected to become an example of an environmentally friendly sports center and contribute to the welfare of users and environmental sustainability.

RELOCATION OF REMBANG PEOPLE'S MARKET WITH A GREEN ARCHITECTURE APPROACH IN REMBANG DISTRICT

Hermawan Hermawan — 2025-04-30

Rembang is one of the regencies located in Central Java province. More precisely, it is located on the north side of Java Island, adjacent to East Java province. The area of Rembang Regency is 1036 km2 with most of the area being lowlands. Rembang Regency is divided into 14 sub-districts, 287 villages, and 7 urban villages. With the large number of residents divided into these areas, a market is needed to mediate the economic needs of the community. Rembang city market is located in Sumberjo Village, Rembang District, Rembang Regency. The design of the market reflects the traditional Central Javanese house, namely Joglo. This can be seen from the Joglo roof of the building. Although it displays regional diversity, the Rembang city market has not fully highlighted its design identity and spatial layout other than the Joglo roof. Therefore, it is necessary to carry out the relocation of the Rembang city market as well as a new building to further highlight diversity and spark people's purchasing power by increasing people's interest in the market. Green architecture has another term, namely ecological architecture or environmentally friendly architecture. This definition emphasizes development that refers to environmental conservation with the aim of producing energy-efficient and environmentally friendly buildings. In its construction, the building utilizes environmentally friendly materials and recycled materials that do not damage the surrounding environment. The positive impact obtained from the green architecture concept is the use of energy to be more efficient. In addition, green architecture is designed to be able to adapt to the environment. In addition, green architecture is identical to the use of light and solar energy, the use of openings such as windows to maximize natural air. Therefore, the relocation of the Rembang city market with a green architecture approach can increase public interest. In addition, a clean, organized, and comfortable market can make the Rembang city market competitive with modern markets.

EXPERIMENTAL TEST OF TURBO INSULATOR ON INTAKE MANIFOLD ON ENGINE PERFORMANCE

Sunaryo — 2025-04-30

Engine performance refers to the capability of an internal combustion engine to convert input energy, specifically fuel, into useful power. One method to enhance engine performance is to modify components of the intake system that affect airflow. A turbo insulator, which is a modified gasket connecting the carburetor to the intake manifold, is designed to generate turbulent airflow into the combustion chamber, thus improving combustion efficiency. This study aims to design and evaluate a turbo insulator on the intake manifold of a Suzuki Shogun NR-125 CC motorcycle through experimental testing of its impact on engine performance—specifically torque and power. A descriptive analysis method was employed for data analysis. Engine performance testing was conducted using an engine dynamometer, following ISO 1585 standards, within an engine speed range of 3,000 to 9,000 rpm, under standard factory conditions and with various turbo insulator configurations (5 and 7 blades, 45° and 60° blade angles, 4 mm and 8 mm thicknesses). The results indicate that the turbo insulator improves engine performance. The most optimal configuration, V-5 (5 blades, 45° angle, 8 mm thickness), achieved a maximum torque of 11.27 Nm at 3,500 rpm and a maximum power output of 10 HP at 7,750