Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Novel entropy-based style transfer of the object in the content image using deep learning
Get PDFRecently neural style transfer (NST) has drawn a lot of interest of researchers, with notable advancements in color representation, texture, speed, and image quality. While previous studies focused on transferring artistic style across entire content images, a new approach proposes to transfer style specifically to objects within the content image based on the style image and maintain photorealism. Recent techniques have produced intriguing creative effects, but often only work with artificial effects, leaving real flaws visible in photographs used as references for styles. The suggested approach employs a two-dimensional wavelet transform (WT) to achieve style transfer by adjusting image structure with high-pass and low pass filters (LPF). Preserving the information content and numerical attributes of VGGNet19 through WT-based style transfer using the db5 WT at level 5, we can achieve a peak signal-to-noise ratio (PSNR) value of up to 96.76725. The qualitative result of the proposed methodology is compared with other existing algorithm. Also, the time complexity of the proposed methodology on different hardware platforms has been calculated and presented in the paper. The proposed methodology able to maintains appealing and precise quality of resultant image
A novel cost-effective power supply model for industrial appliances based on triangular magnetic shunt transformer design
Get PDFThis paper presents a new design of a magnetic shunt transformer for use in industrial microwave generators. The proposed transformer has a triangular shape and offers several advantages over existing transformer designs, including reduced volume and maintenance costs. We provide a detailed analysis of the transformer's dimensions and an equivalent model of the three-phase high voltage power supply system. The results of this study have significant implications for the field of industrial microwave generator design and could lead to the development of more efficient and costeffective systems. The resulting model is comprised of saturable inductors capable of accounting for the non-linear phenomena of saturation. The power supply is simulated using MATLAB/Simulink with a neuro-fuzzy ANFIS approach. The results are compared to experimental validations of a single-phase reference power supply for a magnetron, validating the proposed power supply. Additionally, the simulation results demonstrate the effectiveness of the proposed design, which outperforms existing transformers in terms of volume, energy efficiency and maintenance costs
A deep learning-based system for accurate diagnosis of pelvic bone tumors
Get PDFBone image analysis and categorizing bone cancers have both seen advancements thanks to deep learning (DL), more notably convolution neural networks (CNN). This study suggests a brand-new CNN-based methodology for categorizing pelvic bone tumors specifically. This work aims to create a pelvic bone computed tomography (CT) image categorization system based on deep learning. The proposed technique uses a convolutional neural network (CNN) architecture to automatically extract information from the CT images and classify them into distinct categories of tumors. A total of 178 3D CT pictures was discovered and added retroactively. DenseNet created the image-based model with Adam optimizer and cross entropy loss. The suggested system's accuracy is assessed using a variety of performance indicators, including sensitivity, specificity, and F1-score. As demonstrated by the experiment findings, the suggested deep learning based classification system has a high degree of accuracy (94%), making it useful for the diagnosis and treatment of pelvic bone tumors. Our promising results might hasten the use of DL-assisted CT diagnosis for pelvic bone tumors in the future
Controlling mobile robot in flat environment taking into account nonlinear factors applying artificial intelligence
Get PDFThe article shows how to build and identify intelligent automatic control problems for mobile robots in a flat surface environment at the workplace, with known and unknown obstacles. Research and develop programming and control methods as an operating system for mobile robots robot operating system (ROS). Update map data information, in the operating environment, robot position control process, obstacle overcoming process simultaneous positioning and mapping (SLAM). From there, we aim to calculate and determine the robot's motion trajectory to get a smart path. The positioning trajectory calculation system robots. The authors use actor-critic (AC) algorithm to research and develop control. Research results in simulations, in Gazebo environment and test runs on real mobile robots have shown high-quality practical performance of automatic navigation and control while using this algorithm
Internet of things-based rice field irrigation evaporation monitoring system
Get PDFThe urgency for efficient irrigation in Indonesia’s agriculture sector, particularly in paddy fields, is evident. However, existing methods for monitoring water levels are antiquated, often requiring manual measurements with a ruler. This research introduces a comprehensive “monitoring system for light intensity and water temperature as an analysis of evaporation for rice irrigation based on the internet of thingsâ€. The system integrates various sensors an anemometer for wind speed, an ultrasonic sensor for water level, a DS18B20 waterproof sensor for water temperature, and a GY-8511 sensor for sunlight intensity. All data are collected by an Arduino Mega controller, connected to an ESP32 for transmitting the readings to the Blynk app and an I2C 20×4 liquid crystal display (LCD) screen. The control mechanism employs a closed-loop system with a direct current (DC) motor actuator to operate the water gate, which can also be manually controlled via a cellphone. The system effectively meets daily evapotranspiration requirements of 1.44 mm, with optimal conditions yielding water levels of 3 cm, water temperatures of 38.53 °C, sunlight intensity of 4.59 mW/cm², and wind speed of 0.21 m/s
Active filter harmonic compensator with proportional resonant current controller for photovoltaic inverter
Get PDFThe strong development of renewable energy sources (RES), especially distributed energy sources, brings many benefits to the power system. Single-phase photovoltaic (PV) systems are the fastest growing type of distributed energy source worldwide today. Besides the beneficial factors for the distribution power system, the high penetration rate of solar power systems also causes negative impacts, especially power quality issues. PV inverters generate harmonics during the high-frequency switching of semiconductor elements. Traditionally available passive filters are not effective enough to ensure output power quality when the PV system generates power to the distribution grid. Therefore, this study presents the design of a proportional resonant current controller combined with active filter harmonic compensated (PR+HC) for a single-phase PV inverter. This controller, when integrated into traditional PV inverter, will provide better output power quality, contributing to reducing total harmonic distortion (THD) on the distribution grid. This study analyzes the parameters affecting the harmonic attenuation effect of the PR+HC controller, then simulates it on MATLAB Simulink to evaluate the results. The results of the study show that the PR+HC controller is not only effective in reducing the amplitude of odd harmonics, but also operates reliably even when the grid frequency fluctuates widely
A new approach to joint resource management in MEC-IoT based federated meta-learning
Get PDFMEC and IoT are rapidly expanding technologies that offer numerous opportunities to enhance efficiency and application performance. However, the huge volume of data generated by IoT devices, coupled with computational and latency constraints, poses data processing challenges. To address this within the MEC architecture, deploying computing servers at the network edge near IoT devices is a promising approach. This reduces latency and traffic load on the core network while improving the user experience. However, offloading computations task from IoT devices to MEC servers and efficiently allocating computing resources is a complex problem. IoT tasks may have specific requirements in terms of latency, bandwidth and energy efficiency, while computing resources and capacities maybe limited or shared between several users. We propose an approach called FedMeta2Ag, which we evaluate using the MNIST database. With 20 epochs, the training accuracy reached 91.5%, while the test accuracy achieved 92.0%. Performance consistently improved during the initial 20 iterations and gradually stabilized thereafter. Additionally, we compared the performance of our proposed model with existing methods, finding that our approach outperforms existing models in predicting performance more accurately. Thus, this approach effectively meets the demanding performance requirements of wireless communication systems
The effect of FeNi-AlN layer thickness on the response of magnetic SAW sensor by FEM simulation
Get PDFIn this study, we used simulation to investigate the optimal working point of a surface acoustic wave-magnetostriction sensor by varying the thickness of the magnetic sensitive layer using the finite elements method. We evaluated the sensor’s sensitivity by simulating the responses at the optimal point and changing the thickness of the magnetic sensitive layer (h3). Additionally, we reduced the piezoelectric substrate thickness (h1) at the optimal point to determine the limit point of the center frequency (f0) and improve the sensor sensitivity for low magnetic field intensity measurements by performing a wavelength reduction (λ). For the simulation, we selected a delay-line FeNi/IDT/AlN structure with specific materials and electrode parameters. Our results show that the optimal structure of the sensor is at h1=400 μm, λ=40 μm, and h3=1,060 nm, with a maximum f0 of 140.38493 MHz and maximum surface acoustic wave velocity of 5,615.4 m/s. At this optimal structure, the sensitivity reaches the maximum value of 10.287 kHz/Oe with a working range from 0 to 89 Oe. We also found that reducing the piezoelectric substrate thickness to 35 μm significantly reduces the manufacturing and simulation time, but the frequency response cannot determine the center frequency
Reconfiguration of the radial distribution network using an artificial rabbits optimization approach
Get PDFLowering system power losses along with improving voltage profile have been major concerns for researchers for the past few decades. The performance of an electrical distribution system (EDS) is dependent on these two factors. This work’s main emphasis is on reconfiguring the radial distribution network (RDN) to diminish system power losses and strengthen the voltage profile. The process of network reconfiguration (NR) involves state transitions of sectionalizing and tie switches while still adhering to the limitations. In this work, the optimal reconfiguration network is determined using the artificial rabbits optimization (ARO) approach. The adopted method is tested using IEEE 119 bus RDN under low, normal, and heavy load conditions. When compared to the current approaches, the adopted methodology produced favorable results
CMOS low noise amplifier technologies: trends for enhancing satellite receivers and mobile communications
Get PDFThe emerging demand for high-data-rate wireless communication systems and high-resolution radars, particularly in the millimeter-wave (mm-wave) spectrum, has captured significant attention within both the industrial and academic landscape. Recognized as the fundamental building block for satellite receivers, the low noise amplifier (LNA) plays a pivotal role in meeting these growing requirements. In Today's world a continuously increasing number of connected devices and resource-intensive digital content load to an incessant data being generated, transformed, and facilitated. In this paper, authors summarize the different technologies and techniques employed to design various LNAs with enhanced bandwidth, higher gain, low noise figure (NF), minimal power consumption, and less chip area