Jurnal Politeknik Negeri Batam (PoliBatam)
Not a member yet
3001 research outputs found
Sort by
Job Safety Analysis (JSA) untuk Pengoperasian Mesin Vadu pada Departemen SystemSoldering
No full textThe System Soldering department produces modules using the Vadu machine, which melts solder at specific temperatures to bond nutzen with the baseplate. Job Safety Analysis (JSA) is a method used to study jobs, identify hazards, and potential incidents related to each step of the job, and develop solutions to eliminate and control these hazards. The purpose of JSA is to understand the operation of the Vadu machine and analyze the dangers and risks associated with its use. This study employs a qualitative method by collecting information about job activities. The data collected is used to apply JSA to identify hazards and develop measures to reduce risks, considering factors such as the likelihood of accidents occurring (Likelihood) and the severity of risks if an accident happens (Severity). The data analysis aims to identify hazards and risks in job activities and provide recommendations for improvement. The results indicate that implementing JSA is crucial for managing risks in the workplace. Moreover, employing Personal Protective Equipment (PPE) is essential for safeguarding workers and minimizing related risks. Despite the company’s risk assessment and danger control measures, accidents can still happen in the workplace. Increasing understanding of JSA implementation and the importance of using appropriate PPE is expected to reduce risks and improve workplace safet
Analisis Penambahan Efek Partikel dan Suara yang Indah dan Bervariasi Untuk Meningkatkan Pengalaman Pemain Pada "Game VR Mahakarya”
Get PDFVirtual Reality (VR) technology has brought significant changes to the gaming industry, offering more interactive and immersive experiences. The integration of precise audio-visual elements can further enrich these experiences. While previous studies have examined audio-visual elements in VR games, most have not specifically addressed the impact of particle effects and sound in enhancing player immersion. Therefore, this study incorporates varied particle and sound effects to explore their influence on player immersion in the "Mahakarya VR Game." The research employs a qualitative method, including semi-structured interviews, participatory observation, and thematic analysis to explore players’ subjective experiences. The findings indicate that the addition of varied particle effects, such as crystal glows and visual explosions, along with responsive sound design, can significantly enhance player immersion and overall gameplay satisfaction. This study provides recommendations for VR game developers to more effectively integrate multimedia elements to create more engaging gaming experiences.Teknologi Virtual Reality (VR) telah membawa perubahan besar dalam industri game, memberikan pengalaman yang lebih interaktif dan imersif, dan pengintegrasian elemen-elemen audio-visual yang tepat dapat memperkaya pengalaman tersebut. Meskipun beberapa penelitian sebelumnya telah mengkaji elemen audio-visual dalam game VR, sebagian besar belum membahas secara spesifik dampak efek partikel dan suara dalam meningkatkan imersi pemain. Oleh karena itu, penelitian ini menambahkan efek partikel dan suara yang bervariasi terhadap pengalaman imersi pemain dalam "Game VR Mahakarya." Metode yang digunakan ialah kualitatif meliputi wawancara semi-terstruktur, observasi partisipatif, dan analisis tematik untuk mengeksplorasi pengalaman subjektif pemain. Hasil penelitian menunjukkan bahwa penambahan variasi efek partikel, seperti kilau kristal dan ledakan visual, serta desain suara yang responsif, dapat meningkatkan imersi pemain, dan meningkatkan kepuasan bermain. Penelitian ini memberikan rekomendasi bagi pengembang game VR untuk mengintegrasikan elemen multimedia secara lebih efektif demi menciptakan pengalaman bermain yang lebih menarik
Performance Comparison of Random Forest, SVM, and XGBoost Algorithms with SMOTE for Stunting Prediction
Get PDFStunting is a growth and development disorder caused by malnutrition, recurrent infections, and lack of psychosocial stimulation in which a child’s length or height is shorter than the growth standard for their age. With a prevalence of 21.5% in Indonesia by 2023, stunting is a global health problem that requires technology-based detection approaches for early intervention. This study evaluates the performance of three machine learning algorithms: Random Forest (RF), Support Vector Machine (SVM) and eXtreme Gradient Boosting (XGBoost) in predicting childhood stunting, and applying the SMOTE technique to handle data imbalance. The evaluation results show that XGBoost with SMOTE achieves the best performance with 87.83% accuracy, 85.75% precision, 91.59% recall, and 88.57% F1-score, superior to RF (84.56%) and SVM (68.59%). These results show that the combination of XGBoost and SMOTE is the best solution for an accurate and effective machine learning-based stunting detection system, so it can be used in public health programs to accelerate stunting risk identification
Minimalist DevStack Deployment: An Analysis of Performance and Swap Utilization
Get PDFCloud technology offers significant advantages; however, its high implementation costs and high hardware requirements pose barriers to small-scale deployments and educational institutions. This study addresses these challenges by investigating the performance of OpenStack deployed via DevStack on a single-node server equipped with an Intel Core i7 processor, 16 GB of RAM, and a 500 GB solid-state drive (SSD) under resource-constrained conditions. We implemented a resource tuning approach by turning off non-essential services (including Cinder, Heat, and Tempest) and adjusting Nova\u27s memory configurations to minimize overhead. Real-time system monitoring was performed using Prometheus and Grafana to examine trends in CPU, memory, and swap utilization across three configurations: default, optimized (RAM=1024 MB), and minimalist (RAM=512 MB). Our empirical results show that the optimized setup enhances system efficiency, decreasing CPU use and memory usage from 86% to 70.90% while maintaining the ability to run up to ten virtual machines with varying operating systems (e.g., CirrOS, Ubuntu 24.04 Server LTS). However, the minimalist configurations, which aim for aggressive swap utilization and reach 100% swap saturation when running 8 VMs under idle workloads, consequently compromise overall system responsiveness despite lower CPU usage. Efficiency in this context is defined as conserving RAM and CPU usage without degrading basic system responsiveness. This highlights a critical trade-off between RAM conservation and overall system responsiveness. This research provides practical insights into designing cost-effective and lightweight OpenStack environments. It establishes a crucial threshold for memory optimization, preventing performance degradation caused by excessive swap usage, particularly in resource-constrained research settings
Classification of the Number of Malaria Cases in Asahan Regency Using Random Forest Application
Get PDFThis study aims to classify the number of malaria cases in Asahan Regency using the Random Forest method. This method was chosen because it is able to handle data with many and complex variables and reduce the risk of overfitting. Data were collected from the Asahan Regency Health Office. The research stages include data collection, preprocessing, model training, and model evaluation. The dataset used consists of 568 malaria case data from 25 sub-districts. The data is divided into 80% for training and 20% for testing. Of the total data, there are 109 data 19.2% in the low category, 334 data 58.8% in the medium category, and 125 data 22.0% in the high category. This classification aims to assist in mapping the level of malaria risk in the area. In this study, several variables were used for model training, including health centers, sub-districts, age, month, and gender. The results of the analysis showed that the most influential variables were health centers 47.53%, followed by sub-districts 43.77%, age 6.07%, months 2.18%, and gender 0.45%. The Random Forest model built was evaluated using accuracy, precision, recall, and F1-Score metrics. The evaluation results showed that the model was able to classify the number of malaria cases well, with an accuracy value of 0.97. With these results, Random Forest has proven effective as a classification method in malaria cases in Asahan Regency
IoT-Based Prediction of Ornamental Plant Water Needs Using Sugeno Fuzzy Algorithm
Get PDFUrban plant care is increasingly important amid growing concerns about air pollution and limited time for manual maintenance. In Indonesia, air quality has deteriorated significantly, with PM2.5 pollution levels exceeding World Health Organization standards, particularly in major cities like Jakarta. Ornamental plants play a crucial role in improving air quality; however, urban residents often struggle to consistently water them. This study addresses that problem by developing an Internet of Things (IoT)-based smart irrigation system that utilizes the Sugeno fuzzy algorithm to predict the water needs of ornamental plants. The system combines a capacitive soil moisture sensor and a DHT11 temperature-humidity sensor with an ESP8266 microcontroller to monitor environmental conditions. Data is transmitted to Firebase and visualized in an Android application, which provides real-time monitoring and specific volume recommendations ranging from 10 ml to 240 ml, calibrated for medium-sized plant pots which is also based on 27 fuzzy rules derived from three input parameters: air temperature, humidity, and soil moisture. Real-world testing with the Aglaonema Snow White plant confirmed that the system functions reliably, helping users optimize water usage and support sustainable, data-driven plant care in urban environments. The system achieved an average prediction accuracy of 89.14% and a mean absolute error of 7.6% in guiding soil moisture toward a 70% target, confirming its practical effectiveness. While the system was tested on Aglaonema Snow White, the fuzzy rule base can be recalibrated for other ornamental plant species with different water needs
Sensor Fusion – Based Localization for ASV with Linear Regression Optimization
Get PDFASV (Autonomous Surface Vehicle) is one of popular innovations in the maritime field that is widely used for various missions on the water surface. The ASV itself has the ability to operate automatically without human intervention. Therefore, ASV requires an accurate and reliable localization system. This research focuses on developing an ASV localization system using waterflow sensors optimized through linear regression and integrated with orientation data from an IMU sensor through sensor fusion to obtain global coordinate position estimation. The experiments conducted showed a significant improvement in accuracy after optimization, with the Root Mean Square Error (RMSE) of the waterflow sensor data decreasing from 161.65 meters to 0.28 meters. Moreover, the yaw data reading by IMU achieved accuracy with RMSE 1.54 degrees. The localization system in the final test achieved RMSE values of 0.07 meters for the X-axis, 0.14 meters for the Y-axis, and 1.9 degrees for yaw during the ASV global positioning experiment. In addition, a GUI (Graphical User Interface) was developed for visualization with average communication latency of 113.6 milliseconds. This localization system is a promising solution in stable water condition
Comparison of Hyperparameter Tuning in Decision Tree and Random Forest Algorithms for Song Genre Classification
Get PDFThis research applies Decision Tree and Random Forest algorithms for music genre classification based on audio numerical features such as tempo, energy, loudness, and valence. The dataset used comes from Kaggle and consists of 7,958 song entries from eight genres. The data was processed through pre-processing stages that included duplication removal, empty value handling, normalization, outlier removal, and class balancing using the SMOTE technique. In the initial test, Random Forest showed an accuracy of 85%, higher than Decision Tree which recorded 76%. After hyper parameter tuning using GridSearchCV, Decision Tree\u27s accuracy increased to 79%, while Random Forest experienced a slight decrease to 84%. This decrease does not reflect a decrease in performance, but rather a more balanced redistribution of predictions to minor classes, as reflected by the stable F1-score macro value at 0.84. In terms of efficiency, tuning the Random Forest took much longer (806.81 seconds) than the Decision Tree (17.42 seconds), indicating that model complexity has a direct impact on training time. These findings suggest that data quality, tuning strategy and time efficiency are important factors in building a reliable and balanced music genre classification system
Carrier Performance Evaluation at PT. XYZ Based on Vendor Performance Indicator (VPI) with the Analytical Hierarchy Process (AHP) Method
Get PDFXYZ is a manufacturing company in the household electronic appliance industry that collaborates with several carrier vendors to support smooth goods delivery. These carriers include CMA, MAERSK, COSCO, HMM, and SEALAND ASIA. The problem occurring in PT. XYZ\u27s shipping process is that some containers owned by the carriers do not meet the quality standards used by the company. This study aims to determine the performance of carriers used by PT. XYZ and the criteria used in evaluating carrier performance based on the Vendor Performance Indicators (VPI) framework, which includes Quality, Cost, Delivery, Flexibility, and Responsiveness (QCDFR), using the Analytical Hierarchy Process (AHP) method. This type of research is descriptive quantitative research. The research data was obtained from questionnaire responses from 5 experts in the SCM Shipping department of PT. XYZ. The results of this study indicate that the most influential criterion in evaluating carrier performance is quality, with a weight of 0.424, while the least influential criterion is cost, with a weight of 0.048. The carrier with the best performance is CMA, with a weight of 0.953, while the carrier with the lowest performance is SEALAND ASIA, with a weight of 0.535.
 
The When Prices Stay the Same, but Contents Shrink: Shrinkflation and Consumer Behavior
No full textShrinkflation is the practice of reducing the quantity of a product while maintaining its price, has become a prevalent strategy for manufacturers to deal with escalating production expenses. This research explores consumer perceptions and behavior toward shrinkflation through a qualitative approach. Data was collected through semi-structured interviews with consumers of fast-moving consumer goods, aiming to understand their awareness, emotional responses, and decision-making processes regarding shrinkflation. The results reveal that many consumers initially overlook reductions in product size, but once they realize the change, they experience feelings of distrust and dissatisfaction. Additionally, shrinkflation impacts brand loyalty, with several consumers showing a tendency to switch to alternative products or brands. This study highlights the importance of transparency and clear communication in maintaining consumer trust. It provides valuable insights for manufacturers and policymakers in developing strategies that address consumer concerns while promoting fair market practice