SMATIKA JURNAL : STIKI Informatika Jurnal

Home Page SMATIKA Journal Volume 14 Number 02, Desember 2024

2025-01-06T08:36:52+00:00

Implementation of AHP and Topsis Method Selection of the Best iOS Gaming Smartphones

2024-12-16T09:42:31+00:00

In the current era, cell phones are an important component in everyday life. Rapid advances in smartphone technology are opening up new opportunities in various aspects of life, including in the world of gaming. Users are often confused when choosing an iOS model that meets the criteria for their gaming needs. In solving this problem, a system is needed to serve consumers to choose the top iOS smartphone for gaming needs based on predetermined criteria. Price, graphics capabilities, storage capacity, RAM, OS version, and battery life of the six available iPhone models are the criteria used in this research. The system implements the AHP (Analytical Hierarchy Process) method to get the criteria weighting numbers and TOPSIS (Technique for Others Preference by Similarity to Ideal Solution) to get the priority order of the highest to lowest numbers. From the calculations, the highest values obtained are iPhone 12 Pro Max (1), iPhone 12 Pro (0.528), iPhone 11 Pro (0.448), iPhone 12 (0.301), iPhone 11 Pro Max (0.222), and the lowest value is iPhone 11 ( 0.204). Based on these findings, consumers can make an informed decision regarding which iPhone is best for gaming. This system will make it easier for users to determine the best iOS smartphone for playing games.

Decision Support System In Selecting Automatic Motorcycles using the Preference Selection Index (PSI) Method

2024-12-24T09:01:36+00:00

This research aims to design a Decision Support System for selecting automatic motorbikes using the Preference Selection Index (PSI) Method. In the midst of the rapid development of the automotive industry, especially automatic motorbikes, the PSI method is applied without weighting criteria to help consumers choose motorbikes based on five main criteria. By normalizing data according to the type of cost or benefit criteria, the PSI method offers a simple and effective solution in decision-making processes involving various criteria. The system developed is expected to be able to provide recommendations for automatic motorbikes that suit the user's preferences and needs. The challenge in choosing an automatic motorbike lies in the complexity of considering various important criteria for consumers, such as price, completeness of documents, year of manufacture, condition and authenticity of spare parts. Therefore, this research aims to develop a decision support system that can provide effective motorbike recommendations based on these criteria without weighting. The PSI method is applied to achieve this goal by normalizing data according to the type of cost or benefit criteria, so that it is hoped that the resulting solution can meet the user's preferences and needs in choosing an automatic motorbike.

3D Adventure Game Design for Early Childhood Alphabet Recognition

2024-12-16T09:42:32+00:00

Since good practices in childhood will influence adult habits, dental health education should start early. Until recently, the only way to get information about dental health care and good and bad food choices for teeth was through lectures and pamphlets. The traditional approach is considered boring, unnecessarily visualized, and not difficult enough for children to understand. Dr. Rizza Dwi Prasetya from K24 Dental Care Lamongan says that one of the most important things to maintain good dental growth and health is to instill the value of dental care in children from an early age. One way to do this is by creating a 3D adventure game for Android smartphones that teaches about oral health. The Multimedia Development Life Cycle (MDLC) approach, which consists of six stages-ideation, design, material collection, assembly, testing, and distribution-was used in making this application. With an indicator of 81% "Very Good", this 3D adventure game about dental health has gone through user acceptability testing and black box testing. This means that this application is suitable for use as an educational tool for children to help them care for and maintain oral health.

Artikel Jurnal Interactive Mobile App UI/UX Design to Increase Promotion and Sales of F&B Products at Eatery Cafes

2024-12-16T09:42:34+00:00

In the digital era and advances in information technology, there is a great opportunity to utilize mobile apps as a solution to overcome challenges in the current digital era. The food and beverage (F&B) industry market is increasingly competitive with the presence of various new cafes and restaurants. To maintain and increase market prey, effective product promotion becomes very important. In this context, mobile applications are a potential tool for connecting customers with the products and promotions offered by a cafe. The aim of this research is to design an interactive mobile application interface for Eatery Cafe which focuses on increasing promotions and sales of F&B products. The method used is User Centered Design (UCD), where this method is able to place the user as the main focus in the design process. This design will then offer an intuitive and attractive user experience. In this design, it allows users to explore the menu, view product promotions, order online, and interact with Eatery Cafe through the feedback feature. Apart from that, the application is also equipped with payment features that make transactions easier for customers. Evaluation of the prototype through user trials shows that this application is successful in increasing user engagement and increasing awareness of F&B product promotions. Thus, it is hoped that this application can become an effective tool in strengthening the relationship between Eatery Cafe and customers and increasing product sales.

Utilization of OpenWRT as Portable Wi-Fi in Community Network Development: Affordable and Stable Internet Access

2024-12-16T09:42:34+00:00

This research aims to enhance internet access in rural areas by utilizing OpenWRT technology as a portable Wi-Fi. A case study was conducted in Bulupitu Village, Gondanglegi District, Malang Regency. The STB HG680P device was converted into a router with OpenWRT firmware (Helmiwrt), using non-regular internet packages such as ilmupedia. The results indicate that this system successfully provides stable and affordable internet access, with good signal strength and adequate internet speed. Positive impacts are observed in the improvement of accessibility, productivity, and social connectivity within the community. Challenges such as signal range limitations in enclosed areas are addressed through the use of additional repeaters and device maintenance training for network managers. This research provides a replicable model for other rural areas and offers practical solutions that can be widely implemented.

Product Recommendation System for Deem Clothing Using the Knowledge-Based Method

2024-12-16T09:42:35+00:00

Knowledge-based recommendation systems have become a crucial solution in assisting customers to select products that match their preferences, particularly in the garment industry. This study aims to develop a knowledge-based recommendation system for Deem Clothing's garment products, capable of addressing the challenges of direct product consultation. The study utilizes data obtained through interviews with the owner of Deem Clothing, direct business observations, and an analysis of the product catalog data. The method involves seven product criteria constraints: product type, material type, pattern, design details, color, additional accessories, and sleeve type. The recommendation process is conducted by implementing a simple constraint-based algorithm to generate product similarity scores and rank them from highest to lowest. The results indicate that the developed recommendation system can effectively and efficiently provide product recommendations that align with customer preferences. The conclusion of this study is that knowledge-based recommendation systems can reduce customer dependence on direct consultations, enhance the shopping experience, and optimize the sales process of garment products. The implications of this research for the field of knowledge are that knowledge-based approaches in recommendation systems can be widely applied across various industries to improve customer interaction and satisfaction.

Implementation of the Attendance System at PG-TK AISYIYAH VI as Teacher Absence Data Collection

2024-12-16T09:42:35+00:00

PG-TK AISYIYAH is a school with limited information system facilities, so an information system was created that refers to the method of recording attendance using a website with the aim of facilitating a more efficient and practical process when taking attendance. The purpose of this study is to design an attendance system that is applied to the website and automatically the attendance data will be listed, containing the name, time, minutes. In addition, an analysis was carried out at the school and data collection was carried out on teacher personal data. The research method used is through the stages of data analysis, design of the attendance system, implementation of the attendance system, testing and maintenance. At the testing stage using blackbox testing. The results of the study are that the attendance system shows that the application runs smoothly without errors. The admin confirms the attendance data and minutes provided by the teacher. All related entities in the application, with data from the teacher directly entering the admin system for confirmation.

Comparative Study of K-Nearest Neighbor and Naïve Bayes for Diabetes Risk Classification

2024-12-16T09:42:36+00:00

Diabetes mellitus is one of the fastest-growing health problems in the 21st century. One of the causes is the lack of public awareness for regular health check-ups, while the lifestyle being led is quite unhealthy. Hemoglobin A1c (HbA1c) examination is highly recommended to detect diabetes. However, this service is not yet available at Posbindu in Bulupitu Village. Therefore, another approach is needed to detect the risk of diabetes early, namely through data mining. The data mining methods used in this research are the Naïve Bayes and kNN classification methods. The variables to determine the risk of diabetes include gender, age, family history of diabetes, frequent urination, Body Mass Index (BMI), blood sugar levels, and diabetes risk output. The division of testing and training datasets uses cross-validation and ratio (60:40, 70:30, 80:20, and 90:10). The best accuracy of the Naïve Bayes method was obtained by dividing the dataset using k-fold cross-validation with k=2, achieving 96.1%. In the kNN method, the best results were obtained from the 80:20 dataset ratio. Manhattan distance was found to be the best distance calculation in this study compared to Euclidean distance and Chebyshev distance.

Information System Application Innovation Laundry Shoes Using The Waterfall Method

2024-12-16T09:42:37+00:00

The method of checking shoe clothing carried out by most clients is still conventional. Clients still got to check with the shoe clothing put to begin with. With this strategy, there are still a few issues that happen, particularly the time and vitality went through in carrying out the checking prepare gets to be incapable and wasteful. This inquire about points to plan and construct a web-based data framework utilizing the Waterfall strategy. The data framework that has been built can fathom and give development for issues that happen with respect to checking shoes that have not been or have been prepared rapidly and make it less demanding for clients to get data almost the shoe clothing process via the net. The data framework is outlined based on the stages contained within the Waterfall strategy. In the mean time, the data framework improvement handle employments the Visual Code Studio application and MySQL database.

Implementation Of Convolutional Neural Network (CNN) To Detect Hate Speech And Emotions On Twitter

2024-12-16T09:42:37+00:00

The research aims to develop an accurate and efficient hate speech detection model on Twitter's social media platform by leveraging the power of the Convolutional Neural Network. (CNN). The focus of this research is on identifying hate speeches that are loaded with negative sentiment, especially those related to racial, religious, and sexual orientation issues in the context of the Indonesian language. The research process involved collecting relevant Twitter datasets, preprocessing text to clear and compile data, and word representation using Word2Vec to capture contextual meanings. Specifically designed CNN models are then trained on that dataset. CNN's advantages in automatically extracting semantic features from text, coupled with the use of Word2Vec, allow the model to have high accuracy, which is 87%-99% for emotional assessment and 99% for hate speech assessment. This makes the model very effective in detecting subtle patterns in language that indicate the presence of hate speech. This research has made a significant contribution to the development of a better content moderation system on social media. With its ability to detect hate speech in real time, the model can help create a safer and more inclusive online environment. However, this research still has some limitations, such as limited data set size and variations of hate speech that are not fully represented. Therefore, further research is needed to overcome these limitations and improve the performance of the model.

Implementation Of The K-Nearest Neighbors (KNN) Algorithm For Malnutrition Prediction

2024-12-24T09:01:49+00:00

Malnutrition is a serious problem in developing countries, caused by a lack of food intake containing essential substances such as protein and energy. The implementation of machine learning algorithms can provide an accurate diagnosis of malnutrition health conditions in toddlers, facilitating early detection and appropriate interventions. The purpose of this study is to determine the performance of the K-Nearest Neighbors (KNN) algorithm in predicting malnutrition based on clinical characteristics possessed by toddlers. The data used are clinical characteristics of malnutrition sourced from a nutritionist. From the research results, the most optimal accuracy value in predicting malnutrition is 87%. With the existing dataset, it can be proven that the K-Nearest Neighbors (KNN) algorithm is able to classify malnutrition into 2 conditions, namely marasmus and kwashiorkor.

Black Box Testing Using Equivalence Partitions and State Transition Methods on the Angrem RSUD Campurdarat Application

2024-12-16T09:42:39+00:00

Application testing is important to ensure that the application can function properly without any bugs or errors from the application system. In this study, testing of the Angrem RSUD Campurdarat application needs to be done to ensure that the application can function properly without any bugs or errors when the application is used. This test uses two methods of black box testing, namely equivalence partitions and state transitions. The use of these two methods is necessary because they have different focuses. Equivalence partitions test the data input section from the user while state transitions test the flow or transition of the application. Equivalence partitions testing divides the input space into several partitions so that it can reduce the number of test cases. Based on the research that has been conducted on the Angrem RSUD Campurdarat application using the equivalence partitions and state transition methods, the test results show quite good application performance with some parts that need improvement. The results obtained are that in the equivalence partitions method from 44 test cases, there are 37 successful test cases and 7 failed test cases while in the state transition method there are 16 page transitions tested and all tests in this method are successful.

Emotion Detection on Facial Images Using Deep Learning as a Support Tool for Therapy for Individuals with Alexithymia

2024-12-16T09:42:40+00:00

Alexithymia is a condition characterized by difficulty in identifying and verbally expressing emotions, which can hinder an individual's ability to understand and manage their emotions. This study aims to implement and develop a model that can detect emotions using the MobileNetV2 architecture for therapy purposes for individuals experiencing alexithymia. The method uses the FER-2013 dataset, which consists of 35,887 grayscale facial images in 7 emotion categories: anger, disgust, fear, happiness, neutral, sadness, and surprise. Using a deep learning approach based on CRISP-DM, the research begins with normalization and data augmentation to improve the model's resilience to image variations. The developed model achieved a training accuracy of 67.7% and a validation accuracy of 65.3%, demonstrating significant capability in recognizing and classifying emotions from facial images. Evaluation using a confusion matrix showed that the model produced a precision of 64.9%, a recall of 65.4%, and an F1-score of 63.7% for each emotion class. This research implies the potential for developing systems that can support psychological therapy, especially to help individuals with alexithymia understand and manage their emotions through facial expression analysis, providing technology sensitive to emotional expressions.

Implementation of Data Mining using the Naïve Bayes Method on Drug Inventory at Kayuagung Regional Hospital

2024-12-16T09:42:40+00:00

Hospitals today have widely adopted inventory systems for managing drug supplies, which involve the process of big data analysis to identify relevant patterns, relationships, and trends in the drug inventory data. The goal is to optimize stock management, reduce waste, and ensure the availability of the right medications at the right time. Effective and efficient drug inventory management is a crucial aspect of hospital operations, ensuring timely availability of medications and minimizing the risks of shortages or overstocking. In this study, the Naïve Bayes method was chosen for its ability to handle large and complex datasets and produce accurate predictions. The research process involved several stages: problem identification, problem formulation, data collection, model classification creation, application development, model implementation, research testing, and report preparation. The findings of this study demonstrate the significant potential of data mining in inventory management within the healthcare sector.

Implementation of Web-Based Accounting Information System at Military Institutions in Kolatmar Puslatmar-8 Teluk Ratai

2024-12-16T09:42:41+00:00

This research aims to design a web-based Accounting Information System (SIA) to optimize cash book management in Kolatmar Puslatmar-8 Teluk Ratai. The method used is Rapid Application Development (RAD) which consists of four stages: needs planning, user design, construction, and cutover. The system was developed using PHP as a programming language and MySQL as a database management system. Research results show that the web-based SIA designed has features such as transaction data management, categorization, financial reporting, and debt-debt management. The system uses a three-tiered access structure consisting of the Treasury Staff, Administrator, and Chief. Black box testing shows that the system has met the basic needs of Kolatmar Puslatmar-8 Teluk Ratai in cash book management. Implementation of this system has the potential to improve efficiency and accuracy in the financial management of institutions. However, further development and testing are needed to ensure the reliability, security, and scalability of the system in the long term.

The Use of K-Means and K-Medoids Algorithms for Developing New Student Admissions Promotion Strategies

2024-12-17T06:12:13+00:00

New student admission is a crucial activity for universities, especially private universities, in obtaining new students. FTI Unmer Malang has implemented various promotional techniques, but still experiences obstacles in achieving student admission targets. The number of new students fluctuates, with a peak in admission in 2019 and a significant decrease of 23% in the last three years. One of the main problems is the lack of information dissemination to remote areas. To overcome this problem, this study applies a data mining method with clustering to group new student data based on their area of origin. Two clustering algorithms, namely K-Means and K-Medoids, are used to compare clustering results to find the optimal promotion strategy. The data used includes new students from the 2016 to 2022 academic years. The results of the study show that the K-Means algorithm shows better performance than the K-Means algorithm with DBI index accuracy level of 0.344. The results of the study are expected to help FTI Unmer Malang in determining a more effective promotion strategy based on the student's area of origin.

Implementation of Tsukamoto Fuzzy Inference System on Loan Eligibility Determination

2024-12-17T06:31:53+00:00

Loans are an important financial instrument in modern life for both individuals and business groups. Consideration of prospective borrowers is very important to reduce the risk of default. However, in Gapoktan Makmur Sejahtera the consideration process is still done manually. Therefore, it is necessary to develop a more systematic and measurable approach in assessing the feasibility of granting loans to minimize the risk of default. The data source of this research comes from loan data at the Makmur Sejahtera Farmer Group Association (Gapoktan). This research uses the Tsukamoto Fuzzy Inference System (FIS) method with 3 input variables, namely income, collateral, and character of prospective borrowers. The output variable in this study is eligibility in the form of a percentage of the results of the FIS Tsukamoto calculation. The application in this study was developed with the Python programming language and the Flask framework. The database used in this research is MySQL. The results showed that the application of determining the feasibility of granting loans was successfully made and could help in the process of determining prospective borrowers at Gapoktan Makmur Sejahtera so as to reduce the risk of default.

Modeling of a Malaria Parasite Detection System on Microscopic Images of Blood Cells Using Deep Learning Methods

2024-12-17T06:39:38+00:00

Microscopic examination is the most common malaria examination technique used in health facilities. However, microscopic examination requires special skills and quite a long time. This research aims to develop a malaria parasite detection system model in blood cell images using deep learning technology to increase the accuracy and speed of detection with the Convolutional Neural Network (CNN) algorithm. This research was carried out in several stages: data collection, image preprocessing, dividing training data and validation data, creating a model using CNN, and evaluating the model. A CNN model was created to classify blood cell images into two classes, namely infected and uninfected. The dataset used as a reference in forming a detection system model uses blood cell images from the open-source Kaggle as many as 11.312 images. The CNN model evaluation results obtained an accuracy value of 97.17% in detecting blood cell images. These results show that the CNN model created can be used to detect malaria parasites using blood cell images.

Design and Development of a Water Quality Recommendation System Prototype for Nila Aquaculture

2024-12-17T07:28:49+00:00

In fish farming, specific processes are required for fish intended for food or ornamental purposes. In addition to food and weather, water quality must also be considered. Water quality parameters include ammonia content, water temperature, pH, turbidity, and Total Dissolved Solids (TDS). Poor water quality can result in the presence of toxic compounds, leftover feed, organic materials, and substances that cause diseases in fish. Conversely, good water quality can reduce water turbidity, allowing sufficient sunlight penetration and potentially increasing fish productivity. This study discusses a water quality detection device using five sensors: a temperature sensor, pH sensor, ammonia sensor, TDS sensor, and turbidity sensor, all connected to an Arduino Nano ATmega-328 to read the sensor data. Testing was conducted under five different water conditions: tilapia pond water, clean water, tilapia pond water mixed with clean water, catfish pond water, and tilapia pond water mixed with catfish pond water. The standard deviation for temperature, pH, and ammonia for all water conditions was less than 0.1. The standard deviation for TDS in catfish pond water and tilapia pond water mixed with catfish pond water was less than 1.0, and the turbidity values were below 7.