Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Citrus leaf disease detection through deep learning approach
Get PDFThe majority of people in the world directly or indirectly depend on agriculture. Plant diseases are a significant threat to agricultural production and food security. Due to its high nutritional value, citrus fruit is one of the most abundant fruits in the world. However, different diseases are responsible for degraded citrus production as well as financial losses to the farmers. Traditionally, visual observation by experts has been attended to diagnose plant diseases. Usually, plant leaf disease recognition methods mainly rely on expert experiences to manually extract the colour, composition, and other features of diseased leaf images. Black spot, greening, canker, and melanoses are four common citrus leaf diseases. Rapid and accurate diagnosis of these diseases is a demand of time. Deep learning is a promising solution to these problems. There are different types of deep learning architecture like ImageNet, GoogleNet, VGG16, ResNet50, and InceptionV3, which show promising results in different object detection. Though most of these benchmark models give almost similar accuracy. However, this paper uses two deep learning models to find the better ones for the detection of citrus leaf disease detection. Hence, InceptionV3 outperforms VGG16 in terms of accuracy
Nonlinear control of three level NPC inverter used in PV/grid system: comparison of topologies and control methods
Get PDFWith the passage of time, the importance of using renewable energy systems to overcome energy consumption and improve the quality of the grid has emerged through the use of nonlinear control techniques and reliance on advanced types of inverters such as multi-level inverters. This research is focused on comparing two grid-connected converter topologies in a photovoltaic (PV) generation system connected to a three-phase grid that serves a non-linear load. Additionally, the study explores two different control techniques applied to this converter, evaluating their effects on the total harmonic distortion coefficient. A comparison has been made between the traditional inverter and the three-level inverter type neutral point clamped (NPC) inverter, with the use of integral backstepping (IBS) technique which was also compared with the proportional integral (PI) controller. The simulation results in MATLAB/Simulink are presented illustrating the performances and the strong effectiveness of the three-level NPC inverter controlled by the proposed technique (IBS)
Accurate classification of forest fires in aerial images using ensemble model
Get PDFThis paper proposes a method to identify forest fires in aerial images using three different convolutional neural networks (CNNs). Unlike general approaches that make use of a single CNN to classify the images, the proposed solution uses the outcomes of different CNNs and considers the most predicted class. This method overcomes the problems associated with using a single CNN, such as low accuracy due to the drawbacks associated with that model. The three different classifiers used here are InceptionV3, VGG-16, and ResNet50. Classification is carried out based on the presence of fire or smoke features in the images. The individual predictions are combined using max-ensembling. The performance is analyzed using metrics like precision, recall, accuracy and F1-score. From the work, it was found that the combined model resulted in an accuracy of 95.8%. The results confirm that the final model provides greater classification accuracy than the individual models. The proposed method can be used to predict forest fires from live aerial images more accurately and help reduce the damage caused
Integral-proportional derivative approach for brushless direct current motor speed control
Get PDFis paper proposed the integral-proportional-derivative (I-PD) as an extension of the conventional proportional-integral-derivative (PID) method that has been used in many brushless direct current (BLDC) applications to control the BLDC motor that can deal with desired speed (reference) changes. It has elucidated a comprehensive comparative analysis between PID, intending to delineate the most efficacious control approach based on a thorough evaluation. This paper scrutinizes four principal methods: proportional-integral (PI), integral-proportional (I-P), PID, and I-PD. Our findings indicate that in the presence of voltage spike constraints, I-P or I-PD emerges as the optimum choice for both four-pole and six-pole motors. Where maximum difference (MaxDiff) is the principal consideration, PI, and I-P are identified as the most suitable methods. Conversely, when the primary objective is to minimize root mean square error (RMSE), PI proves superior for four-pole motors, while PID is preferable for six-pole types. Notably, I-P demonstrates excellent performance in terms of settling time for both motor types. In summation, I-P stands out as the preeminent choice if the objective is to select a singular method that ensures optimal performance across all parameters for a four-pole or six-pole motor
Enhancing radar applications: FPGA-driven phase estimation with floating point arithmetic
Get PDFThis article introduces a paradigm shift in radar technology with field programmable gate array (FPGA)-driven Phase estimation using floating point arithmetic (FPA). Leveraging FPGA’s parallel processing and the precision of FPA, this work promises enhanced accuracy and efficiency. The proposed system’s key performance metrics include the following: number of slices: 20,941, number of look-up tables (LUTs): 22,371, number of digital signal processing (DSP) blocks: 2, delay: 112.9 ns, and power consumption: 7.2 mw. A comparative analysis showcases advantages in area utilization, LUT, and DSP blocks despite a trade-off with delay. The presented methodology and results demonstrate the feasibility of real-time phase estimation at GHz rates, positioning this approach as transformative for next-gen radar systems
Experimental study the performance of a 6-bladed Savonius vertical axis wind turbine using polyvinyl chloride material
Get PDFThe Savonius U type wind turbine is a vertical axis turbine that can operate at low wind speeds. In general, the performance of this turbine is influenced by several factors, one of which is the shape of the turbine blade. This research aims to test the design results of a 6 blade Savonius turbine with a blade length of 50 cm made from polyvinyl chloride (PVC) by varying the dimensions of the blade diameter. The variables that vary between blade length and blade diameter are D/L=0.10, D/L=0.13, D/L=0.18, and D/L=0.20. The aim of this research is to determine the effect of variations in the parameters above on turbine rotation and the electrical power produced in a direct current (DC) generator at each variation in wind speed. From the research results, it is known that the trend graph of the relationship between turbine rotation and wind speed has a linear correlation. In simple terms, this turbine can be applied to DC voltage loads such as lighting using light emitting diode (LED) lamps with a maximum power capacity of ± 16 watts, while the overall efficiency (OE) is 50.25%
A comprehensive review on different types of fuel cell and its applications
Get PDFThis review article provides an overview of various types of fuel cells that are currently being researched and developed. Fuel cells are electrochemical devices that convert chemical energy directly into electrical energy, making them a promising technology for clean and efficient energy production. The review covers the principles of operation and key characteristics of proton exchange membrane fuel cells (PEMFCs), solid oxide fuel cells (SOFCs), alkaline fuel cells (AFCs), direct methanol fuel cells (DMFCs), and microbial fuel cells (MFCs). The article also discusses the advantages and limitations of each type of fuel cell, as well as the current research and development efforts aimed at improving their performance and reducing their costs. Overall, this review provides a comprehensive understanding of the various types of fuel cells and their potential applications in the field of energy production
Prediction of ionospheric total electron content data using NARX neural network model
Get PDFSuccessful prediction of ionospheric total electron content (TEC) data will help in correction of positioning errors in global navigation satellite systems (GNSS) caused by the ionosphere. This research paper proposes a prediction model for ionospheric TEC using a nonlinear autoregressive with exogenous inputs (NARX) neural network that utilizes past TEC data alongwith solar and geomagnetic indices namely F10.7, disturbed storm (Dst), Kp, Ap, and time of the day. We assess the prediction capability of our model at different latitudes during different solar activity years. We compare our results with another NARX model which uses previous TEC data along with time of the day, day of the year and season as exogenous parameters. The results show that for the solar minimum year the TEC prediction accuracy improves by 35.71% and for the solar maximum year it improves by 31.20%. The results using root mean square error (RMSE), mean absolute error (MAE), correlation coefficient, and symmetric mean absolute percentage error (sMAPE) clearly indicate that solar and geomagnetic indices along with time of the day help in enhancing prediction accuracy of TEC across different latitudinal regions during both solar minimum and maximum years
Authentication with privacy-preserving scheme for 5G-enabled vehicular networks
Get PDFThe 5G-enabled vehicular network is an innovative technology that has promise for intelligent transportation systems. It enables the transmitting of messages about traffic that deliver the most recent information on congestion, road conditions, and driving surroundings. The communication channel used by vehicle networks is inherently open, which unfortunately exposes the system to privacy and security concerns. To solve the problems of deploying a safe vehicular network, some academics have put forth plans. However, a number of current methods have significant computational or communication overhead costs. To solve this problem, an efficient and secure authentication with a privacypreserving (ES-APP) scheme established elliptic curve encryption is introduced. With the proposed ES-APP, the data signed and verified for vehicle-to-vehicle and vehicle-to-infrastructure modes in the 5G-based vehicular network are more effective. The ES-APP scheme’s goal is to meet the criteria for the security and privacy of the 5G-enabled automotive network. Ultimately, this work discusses the critical survey of the existing studies and the expected outcome for the ESAPP scheme and further works in the 5G-enabled vehicular network
On the development of an autonomous hexacopter drone for animal detection and collision avoidance system
Get PDFTraffic accidents caused by collisions with animals are a significant global concern for authorities. The economic impact is substantial, including costs for treating injuries, rehabilitating victims, repairing vehicle damage, and addressing fatalities. As a contribution towards finding a solution, a wireless sensor network (WSN) and an autonomous, power-efficient, and economically feasible drone are presented. WSN is responsible for acquiring relevant information from the farm and communicating the data to the aerial drone denoted as a hexacopter; which is functioning as a mobile roadside device for transferring the warning information to the passing drivers so as to avoid any collision with animals. The proposed system involves the design of a lightweight camel-based sub-system to trigger drones for monitoring herds, a drone-based sub-system for tracking and ensuring safety in agricultural areas, and a vehicle-based sub-system to communicate collision warnings where an alarming protocol has been developed. The whole system has been designed, implemented, tested, and verified in an actual flight test. Experimental results indicate that the system has a unique capability. It can mitigate the number of accidents involving vehicles and animals, especially camels, and thus reduce the economic cost of damages associated with the problem