Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Cascaded H-bridge 7-level inverter application for air exhaust fan drive control of Thu Thiem road tunnel
Get PDFThe Thu Thiem road tunnel in Vietnam is crucial in reducing traffic congestion and ensuring the safety of those passing through, thanks to its ventilation system that generates clean air. This fresh air production is primarily supported by two exhaust fans at both ends of the tunnel in the eastern and western towers. However, the fans have a power capacity of several hundred kW and operate at kilovolt-level voltage, which is unsuitable for conventional inverters. Therefore, this paper proposes a 7-level inverter to feed the exhaust fan drive motor. The 7-level inverter improves the output voltage quality, and the output current and voltage have reduced the harmonic distortion significantly. The outstanding advantages of this inverter are verified through MATLAB/Simulink simulation software compared to a 3-level inverter
Fault diagnosis of power transformer using random forest based combined classifier
Get PDFIn the power system, transformers are crucial electrical equipment that require an insulator or dielectric material, such as paper immersed in insulating oil, to prevent electrical contact between components. The dissolved gas analysis (DGA) test is important for diagnosing and determining the maintenance recommendations for transformers. The duval triangle method (DTM) is commonly used to identify faults in transformers. The data used in this article are from DGA test of power transformers in East Java and Bali transmission main unit (UIT JBM). The DGA data were analyzed based on the IEEE C57.104-2019 standards, and by using the developed random forest (RF) classifier-based DTM for easier software implementation and better accuracy. The results of fault identification in 6 transformers case study showed a low-thermal fault (T1)300 °C in transformer 1, where methane gas increased, stray gassing (S) in transformer 5 due to escalating hydrogen gas production, overheating (O)≤250 °C indicated in transformers 2 and 6 due to rising ethane gas production. Transformers 3 and 4 were found in normal condition. This fault identification is done to enhance the accuracy of maintenance recommendation action based on DGA
KawanSurya: an Android-based mobile app for assessing the techno-economic potential of rooftop photovoltaic
Get PDFMany developing countries, including Indonesia, are progressing poorly in residential rooftop photovoltaic (PV) adoption, including on-grid systems. On the customer side, the decision to implement on-grid rooftop PV or rely only on power from the utility grid has often been made without appropriate knowledge of techno-economic considerations. This includes the impression of high system costs. This paper introduces KawanSurya: PV calculator, a solar rooftop PV techno-economic application for Android mobile phones, designed to help residential customers assess the potential of installing on-grid rooftop PV systems. The tool allows users to select a specific geographic location, calculate daily load profiles, and determine available roof areas. It uses irradiance data from the PVGIS API and HOMER’s solar PV output equation to determine hourly PV output power. Simulation results for a typical 2,200 VA household show a payback period of 9.44 years or beyond, significantly influenced by electrical load profiles and bill reduction factors. A 65% bill reduction factor and similar load profile prolong the payback period, while a 0% billing reduction factor or uncompensated electricity sales may exceed the project’s lifetime
Utilizing virtual reality for real-time emotion recognition with artificial intelligence: a systematic literature review
Get PDFEfficiency and optimization in virtual reality (VR) technology is an urgent need, especially in the context of optimizing algorithms to recognize user emotions while using VR. Efficient VR technology can improve user experience and enable more immersive and responsive interactions. This study adopts the preferred reporting items for systematic reviews and meta-analyses (PRISMA) (2020) method to identify and analyze gaps in the existing literature, focusing on the optimization of electroencephalogram (EEG) signal classification algorithms to recognize VR users' emotions. The literature search was conducted through the Scopus database, with article selection based on the type of emotion classified, the classification method used, the limitations of the research, and the results obtained. Of the 1478 articles found, 74 articles passed the initial selection stage, and the final stage 13 articles were selected for further analysis. The selected articles provide important insights into the development of EEG classification algorithms for VR users, especially in multi-user settings. The findings identify potential and opportunities in the development of more efficient and accurate EEG signal classification algorithms for VR users. By focusing on emotion classification in a multi-user VR environment, this research contributes to improving the efficiency of VR technology and supporting a better and more responsive user experience
Predicting player skills and optimizing tactical decisions in football data analysis using machine learning methods
Get PDFThis study investigates the integration of machine learning (ML) techniques into football analytics to predict player skills and optimize tactical decisions. A dataset of over 150,000 professional match actions from various leagues and seasons was analyzed using deep neural networks, convolutional neural networks (CNNs), and gradient boosting machines (GBM) algorithms on biometric, contextual, and match data. The valuing actions by estimating probabilities (VAEP) metric indicated scores from +1.8 to +3.0 for key players, enabling detailed performance evaluation. CNN models achieved up to 91% precision, 88% recall, and a receiver operating characteristic – area under the curve (ROC-AUC) of 0.94, confirming their effectiveness in predicting player actions and contributions. Injury risk prediction using eXtreme gradient boosting (XGBoost) reached an F1-score of 0.87 and a ROC-AUC of 0.92, offering actionable insights for injury prevention and optimal player rotation. The findings highlight artificial intelligences (AI)’s capacity to support individualized preparation, tactical adjustments, and cost-effective recruitment strategies. While computational demands and data quality remain challenges, the results demonstrate the transformative potential of AI in modern football, providing a practical framework for data-driven decision-making to enhance team performance and strategic plannin
Cross-cultural prediction of marital satisfaction using machine learning algorithms and generic needs
Get PDFMarital satisfaction is crucial for individual well-being and family stability. Prior research has predominantly focused on Western contexts using traditional statistical models, limiting the generalizability of findings across cultures. This study addresses a significant gap by employing machine learning algorithms Naive Bayes, support vector machine (SVM), random forest (RF), and extreme gradient boosting (XGBoost) on a diverse dataset comprising responses from 7,178 participants across 33 countries. Our methodology includes a robust data preprocessing pipeline, feature selection, and algorithm evaluation, emphasizing their practical application in relationship interventions. Using predictors derived from Maslow's generic needs, including love, respect, and pride in one's spouse, we demonstrate that these factors are significant cross-cultural predictors of marital satisfaction. Our results show that pride in spouse, love, and respect for spouse are the most significant predictors of marital satisfaction across cultures. This demonstrates the effectiveness of machine learning in capturing complex relationships, offering more accurate predictions than traditional methods. These findings suggest that fostering love, respect, and sacrifice in early relationships can significantly enhance marital satisfaction across diverse cultural contexts
Meta-learning for malaria diagnosis: evaluating stacking models for enhanced classification performance
Get PDFAccurate malaria detection is crucial for effective disease management, particularly in regions with limited medical resources. Deep learning models have shown promising results in automated diagnosis, yet real-world deployment often faces challenges such as computational cost and model interpretability. This study evaluates multiple deep learning architectures—VGG16, ResNet50, InceptionV3, MobileNetV2, and DenseNet121—on the publicly available National Institutes of Health (NIH) malaria cell image dataset (27,558 images), and enhances their performance using stacking ensemble learning with different meta-learners. Among individual models, DenseNet121 achieved the highest accuracy of 88.00%, while MobileNetV2 had the lowest at 84.80%. Implementing stacking with logistic regression as the meta-learner improved accuracy to 89.40%, while random forest increased it to 90.10%. The best performance was achieved with XGBoost as the meta-learner, attaining an accuracy of 91.20%, precision of 92.10%, recall of 90.80%, and an F1-score of 91.40%—representing a 3.2% accuracy improvement over the best individual model. The classification report further confirms superior performance in distinguishing infected and uninfected cases. These results highlight the potential of stacking with advanced meta-learners to support health workers in rapid, reliable malaria diagnosis, ultimately aiding timely treatment, and improving patient outcomes in clinical and field settings
Low-cost internet of things system for water metering in smart campus
Get PDFInternet of things (IoT) technologies are transforming the monitoring of water distribution networks (WDN) and urban water infrastructure (UWI), as well as smart campus infrastructures, which has the same problems as an urban water network, such as leaks, inaccurate readings, and unnecessary expenses. Smart water meters (SWM) represent an economical IoT solution for remotely monitoring system parameters such as flow rate, pressure, and water quality to reduce losses. This paper introduces an IoT-based smart water metering solution employing message queuing telemetry transport (MQTT), long range (LoRa), a middleware for IoT, and low-cost sensors, implemented at the Federal Institute of Para´ıba, Brazil, as an initial effort toward establishing a smart campus. The evaluation of the IoT device showed a measurement performance index (MPI) of 97.83%, with a flow sensor error margin (FS400A) below 2% for calibrated ranges. The quality of the wireless link yielded an average RSSI of-89 dBm and a packet error rate of 0.35%. The IoT system demonstrated potential as a feasible smart campus applicatio
Feature selection to predict COVID-19 new patients in the four southern border provinces of Thailand
Get PDFThis paper presents a machine learning-based prediction framework that utilizes ensemble feature selection techniques to accurately forecast the number of new coronavirus disease (COVID-19) infections in Thailand’s four southern border provinces. The framework used include multiple linear regression (MLR), mul tilayer perceptron neural networks (MLP-NN), and support vector regression (SVR), to classify short-term trends in new patient cases. The study evaluates the effectiveness of these models across different provinces and demonstrates how integrating feature selection methods: forward selection (FS), backward elimination (BE), and genetic algorithms (GA) enhances prediction accuracy. The findings highlight the adaptability of the models, with each province ben efiting from tailored model-feature selection strategies. The results show that the predictive models align closely with real patient data, enabling authorities to anticipate outbreaks and implement timely interventions. Moreover, the pro posed methodology can be applied to other epidemics, making it a valuable tool for public health planning and preparedness. The study offers actionable in sights for decision-makers, emphasizing the importance of predictive modeling in community-level outbreak management
Beyond a simple filter: transient and steady state analysis of first-order resistor-resistor-capacitor circuits
Get PDFThis paper presents a quantitative analysis of a first-order resistor-resistor-capacitor (RRC) circuit, detailing its transient, steady state, and frequency-domain behaviors through computational modeling. The study confirms that the circuit's time constant (Ï„) governs its dynamic response, with the capacitor charging to 63.2% of its final voltage in one Ï„. The key finding is the circuit's fundamental distinction from a simple resistor-capacitor (RC) filter: under a 100 V step excitation, the RRC topology stabilizes with a non-zero steady-state current of 0.35 A, following a controlled transient inrush of 1.0 A. Frequency analysis further characterizes the circuit as a stable low-pass filter with a predictable -20 dB/decade roll-off. This work elucidates a critical engineering trade-off, demonstrating that the RRC's components dually define its transient speed and its final steady state operating point, providing a quantitative framework for advanced power management and signal conditioning applications