Journal of Informatics Information System Software Engineering and Applications (INISTA)

Design and Building A 2D Game as Educational Media for The Babad Pasirluhur Folklore Using Construct 3

2024-12-29T16:06:44+08:00

Folklore can also be called a part of Indonesian culture that tells about entertainment, history and culture from a region in Indonesia. Indonesian folklore has educational value and cultural elements that can be studied. One way of learning about folklore can be implemented through games. Games can be used as an educational media because apart from producing information they can also be entertainment for those who play them. Based on the background, we have conducted interviews with teachers at Public Elementary School 2 Purwokerto Lor and obtained results regarding the need for media to introduce folklore. In this elementary school, the folklore about Babad Pasirluhur is not yet understood by students. So we propose to design a 2D game as an educational media for the Babad Pasirluhur folklore implemented into adventure genre. Therefore, the aim of this research is to design an educational adventure game for the Babad Pasirluhur folklore using the Game Development Life Cycle (GDLC) method. This game was build using the Construct 3 game engine because suitable for simple adventure game. The resutls obtained were that black box method functional with a success score of 100% from 5 testers. Meanwhile, the UAT test obtained results of 84,7% from 33 grade 4 students at Public Elementary School 2 Purwokerto Lor. The UAT test results stated that it was included in the “strongly agree” category. These results have been tested using the normality test and one sample t-test and the concluesion is that H0 is rejected and H1 is accepted. So the results of this game can be accepted as a learning media for the Babad Pasirluhur folklore by grade 4 students at Public Elementary School 2 Purwokerto Lor. Suggestions for further development are needed to improve the design to suit the character of grade 4 students based on the results of the UAT testing on the design section which got the lowest score is 84%.

Implementation of The Weighted K-Nearest Neighbors Algorithm in The Classification of Beef and Pork Images

2024-12-29T16:06:44+08:00

The demand for meat in Indonesia is still high, especially for the consumption of beef and pork, which are important commodities in the market. Although meat provides essential nutrients, pork has health risks because it contains more than 40 dangerous pathogens and various bacteria. In traditional markets in Indonesia, the fraudulent practice of mixing pork and beef to gain greater profits is a serious problem. This is very detrimental to consumers, especially Muslims who do not consume pork. The study used machine learning, the Weighted K-nearest neighbor (WKNN) algorithm, to classify meat based on color features. The stages used began with collecting a dataset of 400 images and divided into 200 images of pork and beef for each. Images were taken using a Canon EOS Kiss X50 DSLR camera at ISO 100-200 for good image quality. Feature extraction uses HSV and RGB algorithms that focus on color. Furthermore, the data is divided into 70% for training and 30% for testing. The model was evaluated with a confusion matrix, namely accuracy, precision, and F1 score, which each produced an accuracy of 85%, 86%, and 80%. The research is updated on the application of WKNN for meat classification in traditional markets.

Deep Learning Model Based on Particle Swam Optimization for Buzzer Detection

2024-12-29T16:06:45+08:00

Along with the development of the internet, the presence of buzzers is increasingly widespread on social platforms, especially on Twitter. Buzzers have played an important role in influencing and spreading misinformation, manipulating public opinion, and harassing and intimidating online social media users. Therefore, an effective detection algorithm is needed to detect buzzer accounts that endanger social networks because they affect neutrality. In this research, we propose a Deep Neural Network model to detect buzzer accounts on Twitter. We conducted experiments on 1000 datasets using PSO-based Deep Neural Network models and Ada Boost-based Deep Neural Networks to obtain the best model in detecting buzzer accounts. The results show that the performance of the PSO-based Deep Neural Network is the best with 98.90% accuracy compared to Ada Boost-based Deep Neural Network 95.30% or without feature weight and boosting algorithms with 46.60% accuracy. This clearly shows the superiority of our proposed method. These results are expected to help maintain neutral information on social media and minimize noise in the data that will be used for sentiment analysis research.

Expert System for Diagnosing Diseases in Coffee Plants Using Forward Chaining and Classic Probability Algorithms

2024-12-29T16:06:45+08:00

Coffee is a highly demanded product and a key commodity in Indonesia due to its significant market value and contribution to the country's foreign exchange. The majority of coffee plantations are found in highland areas, particularly in West Lampung Regency, which produced approximately 56,054 tons of coffee in 2022. However, coffee production has been declining due to low productivity and quality. One major issue is the limited knowledge of coffee farmers in West Lampung about diseases affecting coffee plants, leading to improper treatment. Another challenge is the lack of experts to guide farmers in managing and treating coffee diseases effectively. To address these problems, an expert system is needed to provide information and solutions for dealing with coffee diseases. This system incorporates expert knowledge into a computerized platform to assist in diagnosing coffee plant diseases. The system is developed using the waterfall method and employs forward chaining and classic probability algorithms to diagnose diseases and calculate the accuracy of results. Users can diagnose based on symptoms and receive treatment recommendations. This web-based expert system aims to assist farmers in early disease diagnosis and provide appropriate solutions for managing coffee diseases

Design and Implementation KP-SPAMS Transaction Information System utilizing Laravel Framework and Extreme Programming Methodology

2024-12-29T16:06:45+08:00

The Community-Based Drinking Water and Sanitation Management Group (KP-SPAMS) oversees the Community-Based Drinking Water and Sanitation Provision Program (PAMSIMAS), which is essential for providing clean water services to rural areas. Nevertheless, KP-SPAMS continues to face challenges related to operational transaction management, such as the documentation of customer data, water usage, invoicing, and financial reporting. This research aims to develop a web-based transaction information system, utilizing the Laravel framework and the Extreme Programming methodology, to meet the specific requirements of KP-SPAMS Sumber Waras located in Ngenep Village, Malang Regency. The Extreme Programming methodology facilitates adaptable and cooperative software development, enabling quick responses to evolving customer requirements. The system's primary functionalities are customer registration, water usage recording, automatic billing, and payment reporting. The implementation results indicate that this system may enhance operational efficiency, accountability, and traceability of all transaction processes in KP-SPAMS, facilitating improved decision-making and superior service quality for the community. User Acceptance Testing results show that 80% of users rated the system positively, with 53.33% agreeing and 26.67% strongly agreeing that the system meets their needs and provides a satisfactory experience. Only 6.67% of responses indicated dissatisfaction, and no respondents strongly disagreed, demonstrating that the system aligns well with user expectations and offers a solid foundation for future improvements.

User-Centered Design for E-commerce Prototyping

2024-12-29T16:06:46+08:00

Re.wood is a wooden furniture business located in Tinggarjaya Village, Jatilawang District, Banyumas Regency that offers a variety of furniture products, ranging from chairs to wall hangings, to beautify interior and exterior spaces, but still has a limited market share. Re.wood currently uses a conventional sales process that is less effective and lacks information for customers, which causes a lack of sales levels for Re.wood. Designing a system before entering the system development stage is a must because it ensures that the resulting solution is relevant and effective in overcoming the problems users face. The problem can be solved by designing User Interface and User Experience of web-based e-commerce applications. The design method used by researchers is the user-centered design method. User-centered design is a method of focusing on the needs of potential users in the system design stage or process. The results of designing the user interface and user experience only include the user interface developed using Figma. The resulting website produces menus such as Home Page, login, Shop, Cart, Search, and Profile. This evaluation utilized the User Experience Questionnaire (UEQ) methodology to assess various aspects of the system. The resulting values (1.55 for Efficiency, 1.54 for Attractiveness, 1.49 for Clarity, 1.33 for Accuracy, 1.5 for Stimulation, and 1.15 for Novelty) represent the average UEQ calculation figures for each dimension. In other words, these numbers correspond to the results obtained through the UEQ, which helps evaluate user experience in terms of efficiency, attractiveness, clarity, accuracy, stimulation, and novelty. UEQ uses a Likert scale to measure user experience, and the resulting values show that the system performs well in most aspects. These findings indicate that the prototype meets the needs and provides a satisfying user experience.

Analysis and Design of UI/UX Sepran Application Using Design Thinking Method

2024-12-29T16:06:46+08:00

Abstract

Finance is something that must be thought about from a broader perspective. A low level of financial literacy can result in individuals making financial decisions using only speculation, not according to financial analysis sourced from historical data. If the decision taken turns out to be wrong or inappropriate, it will have an impact on financial health in the future. This statement can be overcome by using several financial management applications that provide features to view historical financial expenses and income in a certain period, one of which is the Sepran application: Expenses Manager. However, this Sepran application still has several shortcomings, such as not being able to connect to an e-wallet so that it can only be input manually, the font size and some icons that still look small, and the colours used in expenses. From these problems, a redesign of the Sepran application will be carried out using the design thinking method approach and the System Usability Scale (SUS) to measure the success rate of the designed interface. Design thinking has 5 stages, namely Empathize, Define, Ideate, Prototype, and Test. The first stage, empathize, is the stage of extracting problems. Define is the stage of defining problems, and ideate is the stage of determining ideas from problems that have been defined at the ideate stage. Furthermore, the prototype is a stage where ideas that have been determined at the ideate stage are implemented into low- and high-fidelity designs. The last is the test stage, where this stage will test using SUS through a prototype to get feedback and find out whether the design objectives have been achieved. The purpose of this research is to redesign the Sepran application to meet user needs and analyze the success rate of the interface using SUS. The results obtained an average score of 93.25 and a grade of A. This score indicates that the redesign of the Sepran application is in accordance with user needs.

Implementation of Agile Methodology in the Design and Development of Web-Based New Student Admission Information System

2024-12-29T16:06:47+08:00

The infrastructure supporting communities and educational institutions is necessary for the Industry 4.0 era to increase the productivity of educational institutions. The new student registration process at TK Al-Fath is still traditional. It has several shortcomings, such as repeated visits by parents during registration, repetitive information delivery, and unorganized documents, leading to difficulties in data summarization. A web-based system is required to assist TK Al-Fath and prospective students' parents in the new student admission process. This information system will be developed using the Agile development methodology, which will include stages of planning, implementation, software testing, documentation, and deployment. By applying the Agile methodology, the developed information system meets user needs and can be quickly adapted according to changes and feedback received during the development process. This system is limited to serving as an information and registration center, developed from observation, discussion, and literature study. In the final stage, Blackbox testing and User Acceptance Testing (UAT) were conducted. In the Blackbox testing, there were nine functionality testing scenarios, all of which resulted in a 'Successful' status after being tested by 20 respondents. The design and development of the Web-Based New Student Admission Information System at TK Al-Fath were completed and accepted by users, with a total UAT percentage of 93.58%, falling into the 'Very Good' category.

The Application of LSTM in the AI-Based Enhancement of Classical Compositions

2024-12-29T16:06:47+08:00

Music enhancement through deep learning methodologies presents an innovative approach to refining and augmenting classical compositions. Leveraging a comprehensive dataset of classical piano MIDI files, this study employs LSTM networks with attention mechanisms for music refinement. The model, trained on diverse compositions, demonstrates proficiency in capturing tempo nuances but faces challenges in replicating varied pitch patterns. Assessments by 28 individuals reveal positive reception, particularly in melody integration, scoring notably high at 8 out of 10. However, while praised for cohesion, bass lines received slightly lower scores, suggesting opportunities for enhancing originality and impact. These findings underscore the LSTM model's capability to generate harmonious melodies and highlight refinement areas, particularly in innovating bass lines within classical compositions. This study contributes to advancing automated music refinement, guiding further developments in LSTM-based music generation techniques.

MSME Digitalization Using Point of Sale Calculator to Improve Efficiency and Productivity

2024-12-29T16:06:48+08:00

Digitalization of Micro, Small, and Medium Enterprises (MSMEs) in Indonesia is crucial to increase competitiveness in the era of globalization. Due to cost considerations, many MSMEs continue to rely on conventional methods to manage their businesses, leading to inefficiencies in transaction handling and sales data analysis. This traditional approach often results in errors, reporting delays, and suboptimal decision-making, which can hinder growth and productivity. This study focuses on the implementation of a free cloud-based Point of Sale (POS) calculator application as a digital solution to address these challenges. The POS application streamlines the transaction process and generates real-time sales reports, ultimately improving operational efficiency and strategic decision-making. The development method used in this study is the System Development Life Cycle method. The POS application development process includes comprehensive Requirements Analysis, System and Software Design, Implementation, Testing, and Maintenance. User feedback was collected through structured interviews and surveys to evaluate the application's ease of use and its benefits in improving MSME operations. The findings showed significant improvements in operational efficiency, as the POS application speeds up transaction processing and provides timely, data-driven insights for decision-making.

Implementation of Random Forest Classification and Support Vector Machine Algorithms for Phishing Link Detection

2024-12-29T16:06:48+08:00

This research compares two machine learning methods, Support Vector Machine (SVM) and Random Forest Classification (RFC), in detecting phishing links. Phishing is an attempt to obtain sensitive information by masquerading as a trustworthy entity in electronic communications. Detecting phishing links is crucial in protecting users from this cyber threat. In this study, we used a dataset consisting of features extracted from URLs, such as URL length, the use of special characters, and domain information. The dataset was then split into training and testing data with an 80:20 ratio. We trained the SVM and RFC models using the training data and evaluated their performance based on the testing data. The results show that both methods have their respective advantages. SVM, known for handling high-dimensional data well and providing optimal solutions for classification problems, demonstrated a high accuracy rate in detecting phishing links. However, SVM requires a longer training time compared to RFC. On the other hand, RFC, an ensemble method known for its resilience to overfitting, showed performance nearly comparable to SVM in terms of accuracy but with faster training time and better interpretability. This comparison indicates that RFC is more suitable for scenarios requiring quick results and easy interpretation, while SVM is more appropriate for situations where accuracy is critical, and computational resources are sufficient. In conclusion, the choice of phishing link detection method should be tailored to specific needs and available resource constraints. This research provides valuable insights for developing more effective, efficient, and relevant phishing detection systems.