Implementation of Finite State Machine in Role Playing Game Fighting System

Fauzi Anggi Ariesta — 2025-03-01

The gaming industry has experienced rapid development, particularly in the evolution of combat mechanics within Role-Playing Games (RPGs). One of the main challenges in combat system development is creating enemies that adapt and respond to player strategies. The Finite State Machine (FSM) is widely used to dynamically manage enemy behavior. This study aims to compare combat systems with and without FSM to analyze their impact on gameplay quality.

The research employs the Game Development Life Cycle (GDLC) method with the Doppler Interactive approach, covering planning, design, development, testing, and evaluation stages. To assess the effectiveness of the developed combat system, an evaluation is conducted using Heuristic Evaluation for Educational Games (HEEG), which measures gameplay aspects and player enjoyment based on severity rating.

The results indicate that the FSM-based combat system achieved a 41% score in gameplay aspects, while the enjoyment aspect received a 71% score. Additionally, 78% of respondents agreed that FSM improved enemy AI adaptability, creating a more dynamic and engaging gameplay experience. This study is expected to serve as a reference for game developers, particularly RPG Maker MV users, in optimizing combat mechanisms to enhance overall game quality.

IMPROVING SALES CLASSIFICATION OF FASHION PRODUCTS AT SABHIRA OFFICIAL WITH RANDOM FORES

Nazwa Arraudhah — 2025-03-01

Abstract

This research focuses on improving the accuracy of the fashion product sales classification model at Sabhira Official Store by applying the Random Forest algorithm. The approach used follows the stages of Knowledge Discovery in Database (KDD), which includes data selection, preprocessing, transformation, data mining, and evaluation. The research data consisted of 1,559 transactions in the period August to October 2023, with attributes such as product category, number of items sold, price, and sales category (low, medium, high). The model was developed using RapidMiner software, with a data split of 70% for training and 30% for testing. The analysis results show that the Random Forest algorithm is able to achieve an accuracy rate of 99.81%, with precision for the “High” category reaching 100%, while other categories have values above 99%. Evaluation using confusion matrix shows a very low prediction error rate, so this model can classify sales levels more accurately. The results of this study provide useful insights for Sabhira Official Store in stock management and data-driven promotion strategies.

Keywords— Random Forest, sales classification, fashion products, KDD.

Jurnal Dinamika Informatika

Implementation of Finite State Machine in Role Playing Game Fighting System

IMPROVING SALES CLASSIFICATION OF FASHION PRODUCTS AT SABHIRA OFFICIAL WITH RANDOM FORES