Journal of Applied Informatics and Computing

Design and Development of a Mobile-Based Water Reminder Application on the iOS Platform

Supardianto Supardianto — 2023-11-29

Lifestyle encompasses the various ways in which individuals, groups, and nations are influenced by geography, economy, politics, history, culture, and religion. It reflects the characteristics of residents, including their daily behaviors in work, activities, and health. Maintaining a healthy lifestyle is crucial for overall well-being, and one key aspect is ensuring an adequate intake of water. Water constitutes the primary component of the human body, comprising an average of 70-80 percent of an individual's body weight. Factors influencing water consumption behavior include knowledge and preferences for other beverages. To address the challenge of promoting water consumption and advocating for its importance, this study proposes the development of a mobile application system capable of reminding individuals to drink water based on personalized needs, considering factors such as gender, age, weight, height, and activity level. The research aims to leverage and advance existing technology, specifically by creating a mobile application on the iOS platform. The objective is to enhance and reinforce individuals' discipline in maintaining proper water intake. Targeting users from middle-class to affluent social conditions, the application is tailored for the iOS platform. The study involves testing the functionality of the water reminder system software developed for mobile devices running on the iOS platform. The ultimate goal is to create an information system that not only exhibits maximum aesthetics and functionality but also adheres to the principles of interface design, including the application of the eight golden rules.

Real-Time Visitor Counting with Dynamic Facial Recognition using Python and Machine Learning

I Made Bhaskara Gautama — 2023-11-29

Visitor data or the number of visitors at a particular location is crucial information to be obtained. This data can serve various purposes, particularly in enhancing customer satisfaction. For instance, predicting the number of visitors at tourist destinations enables tourism management to be better prepared for welcoming and providing optimal services to arriving visitors. Visitor count data can also be employed to automatically restrict visitors during the COVID-19 pandemic, ensuring a safe and comfortable environment with limited attendees. To acquire visitor data, a system capable of accurate visitor detection is required. This research utilizes computer vision to detect visitor faces. The developed system, programmed in Python, functions by detecting visitor faces and conducting a count based on the detected faces. To prevent the same visitor from being detected multiple times, a facial recognition method with dynamic facial data collection is implemented in this study. The constructed system successfully counted 27 out of 28 visitors over a two-day period. However, the system has limitations, particularly in terms of the restricted detection area. Therefore, a physical mechanism mandating visitors to undergo facial scanning and registration needs to be established, ensuring recorded data corresponds to the actual visitor count.

Geohash-Based Maize Plant Monitoring System Ulitizing Drones

Muhammad Habib Algifari — 2023-11-29

Corn is one of the important food crops in the world. To ensure optimal results, farmers usually monitor crop conditions manually. Unfortunately, manual monitoring can take time and effort due to the large area of maize fields (approx.: 1 ha). In addition, corn plants are also susceptible to diseases and pests which often result in corn farmers experiencing losses due to crop failure. This can be supported by several cases of corn crop failure in Lampung caused by pests and water shortages, such as in Bumidaya Village, South Lampung. Therefore, this research will develop a corn crop monitoring system using geohash and drones. The primary objective of this research is to develop a comprehensive design for a corn crop monitoring system, leveraging the capabilities of machine learning for corn plant recognition. The application of geohash is expected to assist farmers in handling and early detection of plants that experience a decrease in health quality before it spreads to all other maize crops. The results of the model training carried out with the R-CNN are that the detection model is able to detect with an accuracy of 88.9% with a low distance of the drone in taking pictures or close to plants.

Comparative Analysis of OpenMP and MPI Parallel Computing Implementations in Team Sort Algorithm

Eko Dwi Nugroho — 2023-11-29

Tim Sort is a sorting algorithm that combines Merge Sort and Binary Insertion Sort sorting algorithms. Parallel computing is a computational processing technique in parallel or is divided into several parts and carried out simultaneously. The application of parallel computing to algorithms is called parallelization. The purpose of parallelization is to reduce computational processing time, but not all parallelization can reduce computational processing time. Our research aims to analyse the effect of implementing parallel computing on the processing time of the Tim Sort algorithm. The Team Sort algorithm will be parallelized by dividing the flow or data into several parts, then each sorting and recombining them. The libraries we use are OpenMP and MPI, and tests are carried out using up to 16 core processors and data up to 4194304 numbers. The goal to be achieved by comparing the application of OpenMP and MPI to the Team Sort algorithm is to find out and choose which library is better for the case study, so that when there is a similar case, it can be used as a reference for using the library in solving the problem. The results of research for testing using 16 processor cores and the data used prove that the parallelization of the Sort Team algorithm using OpenMP is better with a speed increase of up to 8.48 times, compared to using MPI with a speed increase of 8.4 times. In addition, the increase in speed and efficiency increases as the amount of data increases. However, the increase in efficiency that is obtained by increasing the processor cores decreases.

Re-Calibration of Model-Based Capacitive Sensor for IoT Soil Moisture Measurements

Iman Setiawan — 2023-11-30

Low-cost automatic irrigation systems require quality calibrated soil moisture sensors. The sensor is an indirect method of soil moisture measurement. The sensor works based on the change in the dielectric constant. So, it requires to be calibrated in terms of the soil water content. Polynomial and linear models are frequently used to calibrate soil moisture sensor data in the gravimetric test method. However, computational effort is required. This study aims to obtain a sensor calibration application that can provide the best model of the available models for model-based capacitive soil moisture sensor. This research was conducted using primary data from gravimetric test experiment on Internet of things (IoT) based soil moisture sensor. Web-based re-calibration application produced best model based on adjusted R Squared. Finally, model-based capacitive soil moisture sensor set up using best model coefficient. The results show that the web-based re-calibration application can provide the best model for model-based capacitive soil moisture sensor. Based on gravimetric test experiments and web applications, the best model is a polynomial regression model order 3 with 0.945 adjusted R Squared. The model predicted value for soil moisture is in the range 0 – 1.2 for raw sensor data values of 100 – 530. When the model coefficient configured in capacitive soil moisture sensor and Blynk application, soil moisture measurement can be done via mobile phone in real time.

Optimizing Driving Completeness Prediction Models: A Comparative Study of YOLOv7 and Naïve Bayes at Institut Teknologi Sumatera

Muhammad Habib Algifari — 2023-11-30

The number of vehicles in Indonesia is increasing every year. The number of motor vehicle accidents in 2022 will be more than 100,000. It is hoped that several regulations regarding motorbike rider equipment will increase awareness of rider safety. By utilizing image recognition technology developed with artificial intelligence, it is possible to create digital image processing models or images that are fast and accurate for detecting driving equipment. The object detection model developed uses a dataset in the form of images of motorists who want to enter ITERA through the main gate. The object detection model will also be integrated with the classification model to create a program that can detect motorbike rider equipment, such as mirrors, helmets, not wearing a helmet, shoes, not wearing shoes, open clothes, and closed clothes. After detecting motorized rider equipment in the classification area, the results will be transferred to a classification model to determine the level of safety for motorized riders, either insufficient or sufficient safety. The test results show that the optimal object detection model was found at an epoch value of 70 with a batch-size of 16, producing a mAP value of 0.8914. The optimal classification model uses the naive Bayes method which has been trained with a dataset of 62 data and achieves an accuracy of 94%.

Comparison of Naive Bayes Method with Support Vector Machine in Helpdesk Ticket Classification

Arief Wibowo — 2023-11-30

The technical support department or helpdesk department is a unit that requires a quick response in handling its tasks. The company's helpdesk team can consist of several individuals who know specific or specialized issues. Typically, technical problems are handled with an application that can track issues based on tickets. Ticket queue systems are used to facilitate control over the actions of the service or repair provided by the team. Helpdesk applications assist in addressing issues reported by users and then help upper-level management distribute tasks and monitor the helpdesk team's performance, including providing solutions to users' various problems. This research aims to predict the placement of fields that serve assistance based on the corpus users provide in the natural language. Prediction modelling is done using the Naïve Bayes and Support Vector Machine algorithms. The modelling results show that the accuracy rate of helpdesk service prediction with the Naïve Bayes algorithm reaches 82.06%, while the accuracy rate of prediction with the Support Vector Machine algorithm reaches 85.30%.

Emotion Classification of Indonesian Tweets using BERT Embedding

Muhammad Habib Algifari — 2023-11-30

Twitter is one of the social media that has the largest users in the world. Indonesia is one of the countries that has the 5th largest number of Twitter users in the world which causes a high possibility of conflict between Indonesian Twitter users due to emotional tension in tweets. In this paper, we will compare the BERT embedding method with CNN and LSTM. The results of this experiment are BERT-CNN has the best performance results which has an accuracy of 61% compared to BERT-LSTM. In the experiment several stages of data preprocessing, data cleaning, data spiting and data training were carried out and the results were evaluated using confusion metrics.

Performance Analysis of Family Welfare Empowerment Application: A Kanban Method Approach

Zaidir Zaidir — 2023-11-30

This research examines the application of the Kanban method in testing a family welfare empowerment application. The Kanban method, initially developed by Toyota in manufacturing, has been effectively applied in software development. This study involves a series of tests involving various features within the application, such as user registration, village data collection, processing of the family welfare empowerment data at the Village/District level, and more. The test results show that most tests were successful, highlighting the application's success in executing essential functions such as user registration and event scheduling. However, some tests failed, primarily in inputting village, hamlet, and community unit data. These results indicate that using the Kanban method in testing a family welfare empowerment application can potentially enhance development and testing efficiency. Metrics such as testing time, test success, and time efficiency have provided valuable insights into the application's performance. In conclusion, this testing provides a foundation for further application development, focusing on improving the areas that experienced testing failures. This research also opens up opportunities for further studies on using the Kanban method in software testing in various other application development contexts.

Hyperparameter Tuning on Graph Neural Network for the Classification of SARS-CoV-2 Inhibitors

Salamet Nur Himawan — 2023-11-30

COVID-19 is caused by the SARS-CoV-2 virus, which results in a range of symptoms, from mild to severe, and can lead to fatalities. As of October 2023, WHO has recorded 771 cases of COVID-19 globally. Various efforts have been made to control the spread of the virus, including vaccination, isolation measures, and intensive medical care. The emergence of new SARS-CoV-2 variants has led to the ongoing evolution of virus transmission. Continued research is essential to understand this virus and develop strategies to address the pandemic. Inhibitors of SARS-CoV-2 play a crucial role in the vaccine development process. Inhibitors can impede the virus's development, helping reduce disease severity and control the pandemic. The classification of inhibitors is expected to serve as a foundation for selecting compounds that can be developed into vaccines. This research develops a Graph Neural Network model for inhibitor classification and uses the random search method for hyperparameter tuning. Graph Neural Networks are chosen due to their excellent performance in modelling graph data. This study demonstrates the success of hyperparameter tuning in improving the performance of the Graph Neural Network for accurate classification of SARS-CoV-2 inhibitors.

Catfish Fry Detection and Counting Using YOLO Algorithm

Takyudin Takyudin — 2023-11-30

The development of computer vision technology is growing very fast and penetrating all sectors, including fisheries. This research focuses on detecting and counting catfish fry. This research aims to apply deep learning in detecting catfish fry objects and counting accurately so as to help farmers and buyers reduce the risk of loss. The detection system in this research uses digital image processing techniques as a way to obtain information from the detection object. The research method uses YOLO Object Detection which has a very fast ability to identify objects. The object detected is a catfish puppy object that is given a bounding box and the detection label displays the class name and precision value. The dataset amounted to 321 images of catfish puppies from internet and photography sources that were trained to produce a new digital image model. The number of split training, validation and testing datasets is worth 831 annotation images, 83 validation images and 83 images for the testing process. The value of the training model mAP 50.39 %, Precision 61.17 % and Recall 58 % Detection test results based on the YOLO method obtained an accuracy rate of 65.7%. The avg loss value in the final model built with YOLO is 4.6%. Based on the results of tests carried out with the number of objects 50 to 500 tail size 2-8 cm using video, objects in the image are successfully recognized with an accuracy of 63% to 70%. Calculations using the YOLO algorithm show quite good results.

Optimization of ACS712 Sensor Current Measurement in Solar Power System through Regression Modeling

Lantana Dioren Rumpa — 2023-11-30

This study aims to improve the accuracy of current measurements in solar power systems using the ACS712 sensor and linear regression modeling. While the ACS712 sensor is commonly used for current measurement in solar systems, it often faces accuracy issues. In this research, we measured current using the ACS712 sensor alongside a validated reference device and applied a linear regression model to correct any inaccuracies. The results show that our linear regression model significantly boosts the accuracy of ACS712 sensor current measurements. We also conducted performance tests with the model on the Arduino Uno platform, which revealed increased measurement accuracy in various testing scenarios. Before implementing the model, the average difference between ACS712 sensor measurements and reference device readings was 0.364. After implementing the model, this difference dropped substantially to just 0.044.

Sentiment Analysis of the Top 5 E-commerce Platforms in Indonesia using Text Mining and Natural Language Processing (NLP)

R. A. E. Virgana Targa Sapanji — 2023-11-30

This research attempts to depict a sentiment comparison of the top 5 E-commerce platforms in Indonesia by gathering the emotional tone behind sentence contents related to customer sentiments, customer experiences, and the brand reputation of E-commerce. Data were collected using Python 3.11.4 with the google-play-scraper library, extracted from user reviews/comments on each play store page of the top 5 E-commerce platforms in Indonesia. A sampling of 10,000 records was taken to form a long document term matrix (DTM) of 59,981,785 due to the limitation of CPU capacity for data matrix size. R Programming version 4.3.1 was employed for sentiment analysis in this study. It can be concluded that user comments or reviews on the top five (5) E-commerce platforms in Indonesia show positive sentences indicating user satisfaction (3664 sentences), neutral sentences indicating average user appreciation (2282 sentences), and negative sentences indicating user dissatisfaction (4054 sentences). At least with more positive and neutral sentences, it is indicated that 59.64% of E-commerce users in Indonesia express a positive opinion on the performance of the top 5 E-commerce platforms in the country.

Implementation of Apriori Algorithm for Determining Spare Parts Product Recommendation Packages

Yumaris Alfi Alhillah — 2023-11-30

The aim of this research is to determine recommended product packages for spare parts from an automotive parts supplier. Shop owners have faced challenges in meeting customer demands over the past few months, experiencing frequent stockouts of spare parts due to a manual transaction recording system and a manual checking system for spare parts storage. This inefficiency and lack of accuracy in managing in-demand spare parts prompted the application of the apriori algorithm, a data mining method. Data was collected from the total sales over the past three months, subsequently cleaned and transformed for manual and Python-based apriori calculations. The results, obtained through both manual and Python implementations of apriori, indicate that the two frequently occurring item sets are oil filters with a confidence value of 68% and air filters with a confidence value of 63%. Based on these findings, the study recommends spare parts stores to maintain higher stock levels of oil filters and air filters compared to other spare parts.

Sales Analysis Using Apriori Algorithm in Data Mining Application on Food and Beverage (F&B) Transactions

Sonia Marselina — 2023-11-30

The current business landscape has compelled many companies to compete in boosting their company's revenue, particularly in the F&B sector. Existing sales transaction data has not been fully maximized in determining the business strategy of companies. Therefore, the implementation of data mining is necessary to analyze and explore available data to discover new information that is more beneficial for the company. In this study, we analyze sales transaction data using the a priori algorithm method because this algorithm efficiently handles the data mining process on a large scale with a substantial amount of data. The results of this study indicate that the formed association rules can determine patterns of product purchases that are frequently bought together. The established association rules successfully combine sales transaction data into two-item combinations, namely green tea latte and french fries, with a support value of 16% and a confidence level of 83%. These rules can be used as a reference in determining the company's business strategy.

Implementation of Information Gain for Sentiment Analysis of PSE Policy using Naïve Bayes Algorithm

Stevanus Ertito Pramudja — 2023-11-30

The Ministry of Communication and Information Technology of Indonesia (Kominfo) has established the Penyelenggara Sistem Elektronik (PSE) policy as a mandatory registration requirement for both domestic and foreign Electronic Systems (ES). As a result, Kominfo will impose sanctions on all ES by temporarily suspending their access if they fail to register by July 29, 2022, at 23:59 WIB. This policy has sparked both support and opposition among the Indonesian public, and it has become a topic of discussion, including among Twitter users. Therefore, sentiment analysis is employed as a solution to identify public concerns or issues regarding the policy based on negative and positive tweets. The objective of this research is to evaluate the results of feature selection using Information Gain and the Naïve Bayes Classifier algorithm in analyzing Twitter users' sentiment towards the policies of the Information and PSE of the Ministry of Communication and Information Technology. A total of 1153 lines of tweets were collected from the Twitter platform using the keyword "PSE Kominfo," which were then analyzed using the Naïve Bayes Classifier algorithm and Information Gain feature selection with three scenarios: 90:10, 80:20, and 70:30. Based on the evaluation using the confusion matrix, overall, Scenario 1 with a 90:10 ratio and Information Gain feature selection performed the best, achieving an accuracy of 79.7%, recall of 85%, and an F-1 score of 88%. However, the best precision was observed in Scenario 2 with an 80:20 ratio, reaching 92% due to the higher proportion of positive predictions made by the model compared to other scenarios.

K-Means Clustering with KNN and Mean Imputation on CPU Benchmark Compilation Data

Rofiq Muhammad Syauqi — 2023-12-05

In the rapidly evolving digital age, data is becoming a valuable source for decision-making and analysis. Clustering, as an important technique in data analysis, has a key role in organizing and understanding complex datasets. One of the effective clustering algorithms is k-means. However, this algorithm is prone to the problem of missing values, which can significantly affect the quality of the resulting clusters. To overcome this challenge, imputation methods are used, including mean imputation and K-Nearest Neighbor (KNN) imputation. This study aims to analyze the impact of imputation methods on CPU Benchmark Compilation clustering results. Evaluation of the clustering results using the silhouette coefficient showed that clustering with mean imputation achieved a score of 0.782, while with KNN imputation it achieved a score of 0.777. In addition, the cluster interpretation results show that the KNN method produces more information that is easier for users to understand. This research provides valuable insights into the effectiveness of imputation methods in improving the quality of data clustering results in assisting CPU selection decisions on CPU Benchmark Compilation data.

Sentiment Analysis on Fuel Purchase Policy Through MyPertamina Application Using NB and SVM Methods Optimized by PSO as Weight Optimation

Rousyati Rousyati — 2023-12-05

Sentiment analysis on the MyPertamina application can serve as a means to extract customer opinions about the application. This method involves collecting reviews from users who have utilized the MyPertamina application and classifying these reviews as positive or negative using sentiment analysis algorithms. After the reviews are classified, themes discussed in positive and negative reviews can be extracted, such as ease of use, payment speed, or technical issues. This provides a general overview of user expectations for the MyPertamina application and areas that may need improvement. Sentiment analysis of MyPertamina application comments using Naïve Bayes (NB) and Support Vector Machine (SVM) methods is a process to evaluate whether user comments on the MyPertamina application are positive or negative. NB and SVM are machine learning methods used to predict the category of an input based on given training data. In this study, user comments on the MyPertamina application are used as input and classified as positive, negative, or neutral based on previous training data. The goal of this sentiment analysis is to understand user perceptions of the MyPertamina application and enhance its quality. The research concludes that the implementation of data mining can assist in categorizing sentiments of MyPertamina reviews. The NB algorithm with the addition of Particle Swarm Optimization (PSO) proves to be the most effective method in this study compared to NB alone, SVM, and SVM + PSO. The NB algorithm with PSO optimization yields an accuracy of 79.49%, the highest precision of 79.57%, recall of 79.38%, and the highest AUC of 95.30%, falling into the category of excellent classification.

Comparison of Hierarchical, K-Means and DBSCAN Clustering Methods for Credit Card Customer Segmentation Analysis Based on Expenditure Level

Hafid Ramadhan — 2023-12-05

The amount of data from credit card users is increasing from year to year. Credit cards are an important need for people to make payments. The increasing number of credit card users is because it is considered more effective and efficient. The third method used today has a function to determine the effective outcome of credit card user scenarios. In this study, a comparison was made using the Hierarchical Clustering, K-Means and DBSCAN methods to determine the results of credit card customer segmentation analysis to be used as a market strategy. The results obtained based on the best silhouette coefficient score method is two cluster hierarchical clustering with 0.82322 score. Based on the best mean value customers are divided into two segments, and it is suggested to develop strategies for both segments.

Improving Helpdesk Chatbot Performance with Term Frequency-Inverse Document Frequency (TF-IDF) and Cosine Similarity Models

Gede Herdian Setiawan — 2023-12-05

Helpdesk chatbots are growing in popularity due to their ability to provide help and answers to user questions quickly and effectively. Chatbot development poses several challenges, including enhancing accuracy in understanding user queries and providing relevant responses while improving problem-solving efficiency. In this research, we aim to enhance the accuracy and efficiency of the Helpdesk Chatbot by implementing the Term Frequency-Inverse Document Frequency (TF-IDF) model and the Cosine Similarity algorithm. The TF-IDF model is a method used to measure the frequency of words in a document and their occurrence in the entire document collection, while the Cosine Similarity algorithm is used to measure the similarity between two documents. After implementing and testing TF-IDF and Cosine Similarity models in the Helpdesk Chatbot, we achieved a 75% question recognition rate. To increase accuracy and precision, it is necessary to increase the knowledge dataset and improve pre-processing, especially in recognition and correct inaccurate spelling

Clustering Balinese Language Documents using the Balinese Stemmer Method and Mini Batch K-Means with K-Means++

Made Agus Putra Subali — 2023-12-05

Clustering aims to categorize data into n groups, where data within each group exhibits maximum similarity, while the similarity between groups is minimized. Among various clustering methods, k-means is widely employed due to its simplicity and ability to yield optimal clustering results. However, the k-means method is susceptible to slow processing in high-dimensional datasets and the clustering outcomes are sensitive to the initial selection of cluster center values. In addressing these limitations, this study employs the k-means mini-batch method to enhance processing speed for high-dimensional data and utilizes the k-means++ method to optimize the selection of initial cluster center values. The dataset for this research comprises 300 news articles in Balinese sourced from the https://balitv.tv/ website. Prior to the clustering process, a stemming procedure is applied using the Balinese stemmer method to enhance recall. The obtained results reveal that a majority of the 300 data instances exhibit a high degree of similarity, as indicated by the clustering results. If the number of clusters (n) exceeds two, the data fails to be distinctly separated due to the high structural similarity among the data instances. This can be attributed to the relatively small number of words or attributes produced. In future research, feature reduction will be implemented, and a clustering method capable of addressing data overlap will be explored.

Rental Price Prediction of Boarding Houses in Batam City Using Linear Regression and Random Forest Algorithms

Jerry Jerry — 2023-12-05

Boarding houses, commonly known as "kost," are residential places typically rented by individuals, serving a function similar to hotels, but with more affordable pricing. With the proliferation of boarding house businesses, residents and newcomers in Batam city face challenges in selecting suitable accommodation based on both price and amenities. Leveraging machine learning, a branch of artificial intelligence (AI), and incorporating various algorithms, a system can be developed to predict the rental prices of boarding houses. This helps individuals make informed decisions regarding the suitability of a boarding house based on their preferences and budget. The algorithms utilized in this study are Linear Regression and Random Forest. The modeling process resulted in R2 Scores, with Linear Regression achieving a score of 64%, while Random Forest outperformed with an impressive 99% R2 Score. Due to the higher R2 Score of Random Forest, this model was selected for the development of a website using the Scrum framework. The outcome of this research is a predictive pricing website for boarding houses, offering a valuable tool for residents and visitors in Batam when seeking to rent or lease a boarding house.

Improvement of Spelling Correction Accuracy in Indonesian Language through the Application of Hamming Distance Method

Mudawil Qulub — 2023-12-06

Spelling correction is a critical feature in software to reduce typing errors, commonly found in document processing software and smartphone keyboards. This research aims to evaluate the accuracy of the Hamming Distance method in correcting words in the Indonesian language, both standard and non-standard forms. The research data is derived from a previous study and comprises 60 standard and non-standard Indonesian words. Typos are generated by considering the layout of letters on the QWERTY keyboard. Typing error data is divided into two groups, namely words with 1 and 2 character differences. The first test is conducted on standard words, achieving an accuracy rate of 98.33% for 1 and 2 character differences. Subsequent testing on non-standard words shows an accuracy rate of 100% for 1 character difference and 96.67% for 2 character differences. The results of this research highlight the potential of the Hamming Distance method in improving the quality of spelling correction in the Indonesian language.

Implementation of Finite State Machine Algorithm for Interactive Physics Learning in a 3D Game

Nur Budi Nugraha — 2023-12-06

Physics is a subject taught in high schools as per the established curriculum. Teachers often employ traditional teaching methods where students study independently without active participation, leading to boredom and reduced enthusiasm for learning. Physics is frequently perceived as difficult and perplexing by most students, and the utilization of 3D games as a learning tool can help overcome these challenges. This research aims to integrate the Finite State Machine (FSM) algorithm into a 3D game to create a more effective and engaging learning experience for students. The study employs the waterfall method in application development, encompassing stages such as needs analysis, application design, FSM implementation in games, and game testing and evaluation. 3D physics games have been successfully developed and tested for their feasibility. This game serves as an effective means of entertainment and learning, aiding students in enhancing their understanding of physics subjects. According to the results of a questionnaire with 50 respondents, it is evident that this 3D game is quite user-friendly (90%) and possesses a very good user interface (89%). Approximately 78% of respondents stated that their experience in using the game was very good. Moreover, 82% of respondents found that this educational physics game was highly beneficial for learning physics material.

Non-Playable Character (NPC) based on Behaviour Tree for Enhanced Immersive Experience in the Serious Game "Warik's Adventure"

Tandicha Marchelputra Siswoko — 2023-12-06

Video games, or digital games, have transcended their traditional role of mere entertainment and are now being leveraged for more serious purposes, such as education and cultural preservation. Serious games offer the advantage of presenting content in an interactive and enjoyable manner. A crucial element in gameplay for creating interactivity and a pleasurable experience is the non-playable character (NPC). In serious games, replayability is pivotal for optimizing the comprehension of learning content, with the gameplay experience being a key factor influencing replayability. While games are known for their entertaining aspects, immersion design in serious games often falls short, resulting in a subpar experience. The NPC design in this study is grounded in appreciative learning, emphasizing positive outcomes such as possibilities, peak successes, exploration, and future optimism. The reward activity is structured across four levels: Discovery, Dream, Design, and Destiny. Behaviour Tree is employed to govern NPC behavior throughout all four stages. To evaluate the effectiveness of the immersive design, the Game Experience Questionnaire (GEQ) is employed, measuring three primary components—sensory, imaginative, and challenge-based immersion. The GEQ result indicates a score of 3.2, showcasing a slight improvement from the previous version's score of 3.07. This research contributes to the enhancement of serious game design by focusing on NPC behavior and immersive experiences, ultimately fostering more effective and engaging learning environments.