Jurnal | Eduelektromatika

OPTIMASI ALGORITMA NAIVE BAYES UNTUK KLASIFIKASI PASIEN DEMAM BERDARAH DENGUE DI RSU SEBENING KASIH

agus purniawan — 2025-12-31

Dengue Hemorrhagic Fever (DHF) remains a major public health issue in Indonesia, requiring rapid and accurate diagnosis to prevent severe complications. RSU Sebening Kasih, as a referral hospital in Pati Regency, faces challenges in classifying DHF patient care due to the presence of incomplete medical records (missing values). This study aims to optimize the Naive Bayes algorithm for DHF patient care classification by handling missing values using the Mean Imputation method. The dataset, obtained from the Hospital Management Information System (SIMRS) of RSU Sebening Kasih, consists of 635 patient records. The research process includes data preprocessing, handling missing values, data splitting into training and testing sets, and model evaluation using a Confusion Matrix based on accuracy, precision, recall, and F1-score metrics. After performing data cleaning, converting categorical attributes to numerical values, and imputing missing data, the Naive Bayes model was tested using an 80:20 stratified sampling ratio and evaluated with the aforementioned metrics. The results indicate excellent classification performance, achieving 98.43% accuracy in RapidMiner and 100% accuracy in Google Colab, with an average F1-score of 99.13% for inpatient cases and 91.67% for outpatient cases. These findings demonstrate that appropriate imputation methods can significantly enhance the performance of the Naive Bayes algorithm in classifying DHF patient care status. This research is expected to serve as a foundation for developing machine learning–based medical decision support systems at RSU Sebening Kasih and other hospitals to improve diagnostic effectiveness and healthcare service quality.

IMPLEMENTASI KONTROL SUARA DAN ALGORITMA A PADA GAME PLATFORMER 2D “KEBO BLAYON” MENGGUNAKAN UNITY

Ahmad Dani — 2025-12-31

The advancement of sensor technology, particularly voice sensors, offers innovative opportunities in the development of games. This study aims to design and develop a 2D platformer game titled Kebo Blayon, which implements voice control as the main interaction method and the A* algorithm for enemy (NPC) navigation. The game is developed using Unity and targeted for Android devices, following the Game Development Life Cycle (GDLC) method consisting of six development stages, from initialization to release. Voice input is utilized to control the main character—soft sounds trigger movement while louder sounds trigger jumping actions. Meanwhile, the A* algorithm is implemented to compute the optimal path for enemy characters to reach the player’s position. The testing results show that the voice control system functions responsively and the A* algorithm efficiently guides NPCs. Design and prototype validation by experts and general users both yielded feasibility ratings above 90%. Therefore, the implementation of voice control and the A* pathfinding algorithm in Kebo Blayon proves effective in enhancing interactive and inclusive gameplay within the 2D platformer genre.

PREDIKSI PENYAKIT JANTUNG MENGGUNAKAN ALGORITMA MULTIPLE LINEAR REGRESSION

Fahry Azkha — 2025-12-31

This research, titled "Heart Disease Classification Using Multiple Linear Regression Algorithm," aims to develop an effective predictive model for detecting the risk of heart disease. Coronary heart disease is one of the leading causes of death worldwide, making early detection crucial. The multiple linear regression method was chosen for its simplicity in modeling the relationship between independent and dependent variables. The dataset used is sourced from the UCI Machine Learning Repository, which includes demographic information and health risk factors. The findings indicate that the developed model achieves an accuracy of 80.33% with high sensitivity, although it faces challenges in terms of generalization to external data. This research is expected to contribute to the development of early detection tools for heart disease.

ANALISIS SENTIMEN ULASAN APLIKASI CANVA MENGGUNAKAN BIDIRECTIONAL LONG SHORT-TERM MEMORY UNTUK MENINGKATKAN PENGALAMAN PENGGUNA

Muhammad Yusuf — 2025-12-31

In the digital era, graphic design has become an essential skill in various fields, and the Canva app makes it easy to create creative designs online. However, user experiences with Canva vary and can be analyzed through reviews available on platforms such as the Google Play Store. This study aims to analyze the sentiment of Canva app user reviews using Long Short-Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) algorithms, and compare the performance of both methods in classifying positive, negative, and neutral sentiment. A total of 10,000 review data sets were obtained through web scraping. After preprocessing, 5,514 data sets remained, divided into training and testing data sets with an 80:20 ratio. Classification models were built using both deep learning algorithms and evaluated using accuracy, precision, recall, and F1-score metrics. The results showed that BiLSTM performed slightly better with an accuracy of 92.38%, a precision of 93.05%, a recall of 90.39%, and an F1 score of 91.53%, compared to LSTM with an accuracy of 92.29%, a precision of 91.48%, a recall of 91.39%, and an F1 score of 91.44%. This study shows that BiLSTM is more effective in analyzing sentiment due to its ability to capture sentence context bidirectionally.

PROTOTYPE SISTEM AKUAPONIK BERBASIS WEB DENGAN IMPLEMENTASI OPTIMASI PEMBERIAN NUTRISI MENGGUNAKAN ALGORITMA SIMPLE ADDITIVE WEIGHTING (SAW)

tiara sari — 2025-12-31

This study aims to develop a web-based aquaponics system prototype that implements the Simple Additive Weighting (SAW) algorithm for nutrient optimization. As an integrated farming system, aquaponics encounters challenges in controlling environmental parameters such as pH level, water temperature, Total Dissolved Solids (TDS), and water level, which are still managed manually. The research employs the Research and Development (R&D) method, which includes: (1) designing an Internet of Things (IoT)-based system consisting of pH sensor, TDS sensor, temperature sensor, ultrasonic sensor, and Arduino Uno microcontroller; (2) implementing the SAW algorithm for automated decision-making process; and (3) conducting system testing and validation. The results demonstrate that the developed system can monitor aquaponics parameters in real-time through a web interface with sensor accuracy showing an error rate below 5%. The SAW algorithm successfully calculates nutrient requirements based on parameter weighting, with expert validation indicating a system feasibility level of 77.6%, categorized as "Highly Feasible". Therefore, it can be concluded that this webbased aquaponics system prototype with the SAW algorithm is capable of optimizing automatic nutrient distribution, improving resource use efficiency, and supporting sustainable agricultural practices.

ANALISIS PERKEMBANGAN MIKROKONTROLER DARI AVR KE AI DALAM ERA KONEKTIVITAS

Muhammad Nathan Fuad — 2025-12-31

This change is influenced by the increasing need for smart devices capable of processing data in real-time and connected in the Internet of Things (IoT) ecosystem. AVR microcontrollers are an important foundation in understanding RISC architecturebased control systems, but the emergence of IoT and AI technologies has expanded the function of microcontrollers from mere instruction processors to devices capable of making adaptive decisions. This study analyzes the evolution of microcontrollers from AVR to AI and its impact on efficiency, flexibility, and the direction of future technological development. The results show that the future trend of microcontroller development will be towards increased connectivity, edge-AI-based processing, and the use of intelligent algorithms to support various industrial sectors

ANALISIS BAHASA PEMROGRAMAN C/C++ DAN PYHTON DALAM EKOSISTEM ROBOT

Rendy Tri Prasojo — 2025-12-31

Robot operating systems require programming languages capable of delivering high performance for real-time control and high flexibility for complex cognitive tasks. This study aims to systematically analyze and compare the optimal roles of C, C++, and Python in the current robotics ecosystem. The method used is a Systematic Literature Review (SLR), focusing on synthesizing findings from comparative studies (Ritonga & Yahfizham, 2023) and functional application journals (Surbakti et al., 2024; Imamuddin et al., 2021). The analysis is based on three main themes: quantitative performance, qualitative ease of development, and applicability in functional domains. The research findings clearly demonstrate that C/C++ is far superior in low-level control, real-time operations, and memory efficiency, thus playing a role as the core of system performance. On the other hand, Python excels in highlevel cognitive tasks, rapid prototyping, and complex data processing due to its simple syntax and rich library ecosystem (such as NumPy, Matplotlib). This research concludes that the best approach is a hybrid architecture, which leverages the speed of C/C++ for hardware interaction and the flexibility of Python for intelligence and application logic, thereby maximizing system performance and development efficiency.

ANALISIS PERFORMA KOMPONEN THROUGH - HOLE TEKNOLOGI (THT) DAN SURFACE MOUNT DEVICES (SMD) UNTUK RANGKAIAN MODERN

Zulfa Izzul — 2025-12-31

Today's electronics industry demands smaller, more functional, and more durable products. These needs are largely met by Surface Mount Technology (SMT) using Surface Mount Devices (SMD). However, Through-Hole Technology (THT) remains essential for applications requiring good heat distribution and mechanical strength. The shift to lead-free soldering brings new challenges related to joint reliability, particularly in terms of thermal fatigue. This study aims to review various ways to improve quality, reliability, and efficiency in modern electronics assembly processes through materials analysis, inspection development, and manufacturing process improvements.The research method used a qualitative analytical literature review, combining six scientific journals focused on three themes: solder reliability (Through-Hole Technology (THT) & Surface Mount Devices (SMD)), Automatic Optical Inspection (AOI), and manufacturing optimization. The main results of the study indicate: (1) To accurately estimate the lifespan of Surface Mount Devices (SMD) components, a Finite Element Analysis (FEA) model that takes into account uneven temperature distribution is required. (2) Difficult Through Hole Technology (THT) inspection can be improved with a 3D reconstruction-based AOI system capable of accurately measuring solder volume. (3) Surface Mount Devices (SMD) manufacturing process can be maximized by classifying five types of pick-and-place machines for efficient scheduling strategies. In addition, the innovation of Light Emitting Diode (LED) Surface Mount Devices (SMD) as light sources/filters in spectrophotometers shows potential for smaller and more cost-effective designs. The study recommends the development of Design for Manufacturing (DFM) standards that address leadless solder failure mechanisms as well as the adoption of 3D Automatic Optical Inspection (AOI) for Through Hole Technology (THT).