Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
A transformer-based time series forecasting model with an efficient data preprocessing scheme
Get PDFTime series forecasting with cyclicality is key to the development of green energy, particularly wind energy, due to its high volatility. Accurate forecasting allows for optimal use of energy storage systems and balancing of power grids. In this article, the authors have developed a model for forecasting time series in wind energy through the combined use of Fourier transform and an adapted transformer architecture to solve the time series forecasting problem. The use of Fourier transform provided the ability to detect and account for hidden periodicities that may not be obvious in simple time series analysis, and allowed for the separation of random fluctuations from significant cyclical components, contributing to more accurate data analysis. The use of transformer architecture made it possible to effectively account for both short-term fluctuations and long-term trends in wind patterns, creating more accurate and reliable forecasts of wind energy production. The results show that the model outperforms methods such as transformers, long short term memory (LSTM), LSTM with Fourier transform, and DeepAR in forecast accuracy, taking into account seasonal, weather, and daily cycles of wind data
Multiwalled carbon nanotube/chitosan composite on quartz crystal microbalance for formaldehyde detection
Get PDFThis study introduces multi-walled carbon nanotubes (MWCNT)/chitosan (CS) composite as a potential new sensing material for quartz crystal microbalance (QCM) formaldehyde sensors. This sensing material selectively binds target molecules, causing a measurable frequency shift proportional to the added mass. CS, MWCNT, and the MWCNT/Cs composite samples were prepared for comparison via sonification, crosslinking and dispersion methods. The morphology character was studied using Raman spectroscopy, Fourier transform infrared (FTIR) spectroscopy, and field emission scanning electron microscopy (FE-SEM). Next the samples were drop cast on the QCM working electrode. An adsorption test was conducted to study the static and dynamic response for the formaldehyde detection. The frequency shift of the formaldehyde adsorption for the CS, MWCNT-COOH, and MWCNT/CS-based sensors were 114.98 Hz, 108.23 Hz, and 196.63 Hz respectively. The calculated sensitivity of 23.48 Hz/ppm and regression line R2 at 0.95076 were recorded shows that the MWCNT/CS can be a promising sensing layer to detect formaldehyde vapour
Transport of direct current electricity: research and prospects
Get PDFThe purpose of this study is to analyse the technical, economic, and environmental aspects of direct current electricity transport and to assess its potential in accordance with modern requirements for sustainable energy and infrastructure. The methods used include analytical method, classification, functional method, statistical method, synthesis. The study revealed that the use of direct current has the potential to increase the capacity of power transmission lines, which is especially important in a dynamically developing industrial sector. It should be noted that direct current networks have no phase shifts and no notions of static and dynamic stability, making them ideal for long-distance power transmission. As a result of the conducted research, it can be concluded that the use of direct current in technologies can increase the efficiency and reliability of energy systems, especially with an increase in consumption and load on the grid. Direct current power transmission technologies meet the requirements of sustainable energy supply, providing economic efficiency and reducing environmental impact
Event-driven integration of electronic medical records with blockchain and InterPlanetary file system
Get PDFThe integrity, security, and accessibility of electronic medical record (EMR) are often compromised by traditional systems, which struggle to ensure data integrity, transparent audit trails, and secure long-term storage. This research addresses these challenges by integrating EMR with a private blockchain and InterPlanetary file system (IPFS) cluster, using change data capture (CDC) for real-time updates and integrate with existing EMR systems, avoiding the need for building new EMR software. Implemented in the OpenEMR framework, the system's performance is evaluated across various processes, including document uploading, sharing, access, deletion, and integrity verification. Testing with anonymized medical records in PDF formats ranging from 1 MB to 100 MB shows that uploading to IPFS takes 0.7 seconds per MB, blockchain transaction processing averages 4.2 seconds, CDC time is 1.1 seconds per MB, and OpenEMR uploads average 0.98 seconds per MB. These results demonstrate significant improvements in data security, integrity, and availability, following the CIA triad principles. The system provides a traceable and secure solution for EMR management
A reliable unsupervised sensor data fusion method for fault detection in brushless direct current motors
Get PDFThis paper introduces an efficient and reliable unsupervised method for detecting faults in a brushless direct current (BLDC) motor based on abnormality identification in sensor-acquired vibration and sound signals through multi resolution decompostion and analysis. The research utilizes the double-density dual-tree complex wavelet transform (DD-DT-CWT) to extract important features from vibration signals, and incorporates audio feature extraction for the sound signals. The captured signals are divided into overlapping segments to improve fault localization, and the features of each segment are organized in a coefficient matrix. Subsequently, singular value decomposition (SVD) is applied to the resulting coefficient matrix from the vibration and audio signals. To effectively monitor the motor’s condition, the singular values from both sets of sensor data are combined. Analysing the decay patterns of the singular values enables the identification of faults in the BLDC motor under test. By establishing a suitable threshold for the decay slope of the singular values, the proposed method can accurately and precisely identify and categorize various faults in BLDC motors. This early fault detection can prompt predictive maintenance to ensure the optimal performance, reduced downtime and longevity of BLDC motors
Interference management based on clustering in RIS-aided ultra dense network under multicell scenario
Get PDFUltra dense network (UDN) and reconfigurable intelligent surface (RIS) are two latest technologies in encountering the increasing demands for network capacity and quality of service in wireless cellular networks. UDN is created by densely deploying femtocells in macrocells area. It causes complex interferences because distances among femtocells are likely very close. RIS provides solution in regulating the reflection of the signal emitted from the transmitter to the receiver to resolve the obstacles. However, RIS reflects the interference signals as well causing more complex interference problems. This paper proposes a solution using clustering method as interference management in RIS-aided UDN network. By clustering method, nearby femtocells are grouped and allocated different frequency channels among femtocells in a cluster. The performance of two systems–the baseline system and the one employing a clustering method–is evaluated based on signal to interference plus noise ratio (SINR), throughput, and bit error rate (BER). Simulation results indicate that SINR and throughput improved by 1.57% and 1.73%, respectively. Meanwhile, the BER for the baseline system is 5.78×10-8 and decreased when applying the proposed method system with a value of 2.26×10-8. The proposed clustering method is promising to confront the interference problems
Improving complex shear modulus imaging quality through enhanced frequency combination techniques
Get PDFThis study aims to improve the accuracy of complex shear modulus imaging (CSMI), a technique used to assess the elasticity and viscosity of soft tissues, essential for analyzing tissue structure and detecting tumors. CSMI methods are primarily divided into quasi-static and dynamic approaches, with the dynamic method estimating the complex shear modulus (CSM) by combining particle velocity measurements with force excitation. However, CSM estimation is vulnerable to errors from noise and the estimation method itself. To address noise, various filtering techniques are commonly applied. Additionally, errors from the estimation process can be minimized using approaches like frequency combination methods. In this research, we introduce an enhanced frequency combination method that substantially increases the accuracy of CSM parameter estimation, leading to higherquality CSMI outcomes. The proposed method achieves the lowest estimation error and the highest Q-index value compared to previous works. The proposed approach offers a valuable advancement in soft tissue imaging, supporting more reliable and precise diagnostic capabilities
Prediction of stock market price for investors using machine learning approach
Get PDFStock market price prediction is a challenging task that plays a crucial role in investment decision-making and financial risk management. Traditional approaches often rely on a single machine learning (ML) algorithm for predictive modeling. In this contribution, an innovative framework that integrates logistic regression (LR) with support vector machine (SVM) to improve the accuracy and reliability of stock market price prediction. Combining the strengths of both algorithms, the proposed model harnesses the interpretability of LR and the robustness of SVM to capture complex relationships in stock market data. Experiments conducted on publicly available Yahoo Finance stock dataset and the Dhaka dataset, the results show that the proposed model yielded accuracies of 97.15% and 98.86% respectively. In comparison with other models, the proposed method outperformed the other models in terms of root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), mean squared error (MSE), and accuracy. The contribution and importance of leveraging hybrid modelling techniques to enhance stock market price prediction and facilitate informed investment decision-making
Smart tourism application: towards software development for artificial intelligence in tourism management
Get PDFArtificial intelligence (AI) can manage tourism by optimizing, personalizing the experience, and enhancing user interactions. This research presents the Ayutthaya tourism platform independent model (ATPiM), an intelligent tourism application that integrates a domain-specific language (DSL) designed for chatbot development with machine learning algorithms that generate personalized recommendations based on user preferences, historical data, and real-time contextual influences. This pre-experimental design measures performance on parameters such as response time, recommendation accuracy, and system latency. The outcomes indicate that the mean time taken to respond to a user's query was 2.3 seconds, with 88.5% recommendation accuracy, and no latency. The AI-based recommendation system achieved 89.7% accuracy at destinations, 87.2% at accommodations, 90.3% at itineraries, and 85.6% at activities, with corresponding recalls of 85.4%, 83.5%, 88.1%, and 80.2% respectively. Although these results are promising, a 6.2% error rate for the advanced search, along with data security are some of the remaining issues. The findings reveal that the development of new user-centric and sustainable solutions for tourism, which leverage state-of-the-art natural language processing approaches, can enhance data security and provide additional new technologies, such as augmented reality (AR) and blockchain, for use in tourism
Improvement on the handover technique for 5G network using fuzzy logic algorithm
Get PDFBeyond 5G (B5G) networks require advanced handover algorithms to guarantee seamless connectivity and optimum quality of service. Traditional handover methods are not sufficient to meet the stringent latency and reliability requirements of next-generation networks. To meet these challenges, the integration of fuzzy logic into handover algorithms offers a viable solution. The proposed approach utilizes parameters such as reference signal received power (RSRP), reference signal received quality (RSRQ), signal-to-interference plus noise ratio (SINR), and user equipment (UE) speed as inputs, while dynamically adjusting the time-to-trigger (TTT) and handover margin (HOM) as outputs. To assess the effectiveness of this algorithm, handover latency (HOL) and handover interruption time (HIT) are evaluated and compared with existing algorithms in the literature. The results show better and more efficient performance in both terms of latency and interruption time