Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Comparative field assessment of grounding enhancement material for electrical earthing system
Get PDFGrounding enhancement material (GEM) is used to lower the earthing resistance value of a given earthing system. In this paper, a commercially available GEM is experimented at the field alongside with Sodium Chloride, Copper II Sulphate and planting soil. The well established Wenner’s 4 pole method and fall of potential method was employed to measure the soil resistivity and earthing resistance respectively. It was found that the salts i.e., Sodium Chloride and Copper II Sulphate are superior in reducing the earthing resistance as reduction of more than 85% were observed. However, the commercial GEM has exhibited the most stable earthing resistance value over a period of 101 days, exhibiting the lowest standard deviation. This seems to suggest that the commercial GEM has superior moisture retention capability. This study also proven that Sodium Chloride can be dissolved by heavy downpour and replenishing it periodically is needed in a tropical country like Malaysia with regular thunderstorms and heavy downpours
Speed synchronization of two DC motors with independent loads based on the higher load torque
Get PDFDual-motor and multi-motor electric drive systems have been used in many industrial applications, and speed synchronization of the motors can always get worse by system parameter uncertainties and load torque perturbations. This work focuses on the application of adjustable speed double-direct current (DC) motor drive control systems. In this paper, a system of two DC motors with armature control at different load conditions has been built. The synchronization of these motors was set basing on the higher torque of the two motor shafts. When two DC motors operate at different shafts a challenge appears in synchronization of their speeds, particularly with the existence of load difference allocated on their shafts. This work paid special attention to this problem. It presents a dynamic simulation of speed control and synchronization of dual DC motor drive. The results show the advantages of the used technique in terms of steady-state and transient performance
Glaucoma detection in retinal fundus images using residual network architecture
Get PDFGlaucoma is a significant eye disease that can lead to irreversible vision loss if not detected and treated early. This research focuses on developing an automated glaucoma detection system using a combination of a convolutional neural network (CNN) with the residual network 18 (ResNet18) architecture, locality sensitive hashing (LSH), and Hamming distance calculation. The CNN model is trained to extract meaningful features from retinal images, while LSH enables efficient indexing and retrieval of similar images. Hamming distance calculations are utilized to measure the dissimilarity between binary codes obtained from LSH. A dataset of 506 retinal images, consisting of 117 glaucoma images, 19 glaucoma suspect images, and 370 healthy images. The proposed glaucoma detection system achieved an average accuracy of 99.96%, sensitivity of 99.97%, and specificity of 99.94% during training, and 82.37% accuracy, 86.78% sensitivity, and 73.55% specificity during testing. Comparative analysis demonstrated its superiority over traditional methods. Further research should focus on larger datasets and explore multi-class classification for different glaucoma stages. The proposed system has potential for early glaucoma detection, facilitating timely intervention, and preventing vision loss
The effect of thickness of a conductive nanocomposite ink printed on textile co-planar waveguide antenna
Get PDFIn the area of wearable technology an enhancement of basic microstrip antenna is evolution of wearable textile antenna. A new development of wearable antenna is the incorporated of conductive plane using nanocomposite ink that embedded onto the fabric. In this paper, the performance of variety thickness of conductive Graphene-Ag-Cu ink on a drill fabric is presented. The performances include its resistivity and conductivity measurement. By performing a measurement using scanning electron microscopy, energy-dispersive X-ray spectroscopy, and four-point probe, it can obtain and measure the composition and thickness of nanocomposite layered on a fabric and resistivity respectively. Hence, it can provide detailed information about the surface morphology, roughness, and thickness of the nanocomposite coating on the fabric as well as the electrical conductivity. Finally, the electrical conductivity increased to the fifth layered from 0.1473×104 S/cm up to 0.5393×104 S/cm
Enhanced multi-lingual Twitter sentiment analysis using hyperparameter tuning k-nearest neighbors
Get PDFSocial media is a medium that is often used by someone to express themselves. These various problems on social media have encouraged research in sentiment analysis to become one of the most popular research fields. Various methods are used in sentiment analysis research, ranging from classic machine learning (ML) to deep learning. Researchers nowadays often use deep learning methods in sentiment analysis research because they have advantages in processing large amounts of data and providing high accuracy. However, deep learning also has limitations on the longer computational side due to the complexity of its network architecture. K-nearest neighbor (KNN) is a robust ML method but does not yet provide high-accuracy results in multi-lingual sentiment analysis research, so a hyperparameter tuning KNN approach is proposed. The results showed that using the proposed method, the accuracy level improved to 98.37%, and the classification error (CE) improved to 1.63%. The model performed better than other ML and even deep learning methods. The results of this study indicate that KNN using hyperparameter tuning is a method that contributes to the sentiment analysis classification model using the Twitter dataset
A novel energy-efficient dynamic programming routing protocol in wireless multimedia sensor networks
Get PDFWireless multimedia sensor networks (WMSNs) have characteristics that may influence the routing decisions, such as limited energy resources, storage and computing capacity. Therefore, a routing optimization needs to be done to match the characteristics of the WMSNs. Existing routing protocols only consider energy efficiency regardless of energy threshold, maximum energy, and link cost collectively as the primary basis of routing. In this work, the energy-efficient dynamic programming (EEDP) protocol is proposed to optimize routing decisions that take into account the energy threshold, the maximum energy, and the link cost. Then, the protocol is compared with the dynamic programming (DP), and the ant colony optimization (ACO) protocol. The simulation results show that the EEDP protocol can improve energy efficiency of nodes and network lifetime of the WMSNs. Then, the EEDP protocol is also implemented into a network topology of 10 NodeMCU ESP32 devices. As a result, the EEDP protocol can work very well by selecting routes based on nodes that have the remaining energy above 50 and has the shortest distance. The average delay in sending data for the entire route for the 10 iterations of sending data is 3.99 seconds
Prediction of global ionospheric TEC using attention based bidirectional long short-term memory and gated recurrent unit
Get PDFAn accurate prediction of ionospheric total electron content (TEC) at the primary stage is essential for applications related to global navigation satellite systems (GNSS) under varying weather conditions. The previous TEC prediction schemes contribute for each time step that increases the prediction time. The eye contact phenomenon establishes a metaphorical connection which intends to capture and emphasize the attention worthy elements in a sequence. This research introduces a deep learning approach which is a combination of attention-based bidirectional long short-term memory and gated recurrent unit (Bi-LSTM GRU) to predict TEC in the ionosphere. Bidirectional LSTM is the better option for achieving durability when combined with a gated recurrent unit (GRU) to predict TEC in the ionosphere. The proposed approach is evaluated with the existing LSTM approach for root mean square error (RMSE) during training and validation. The RMSE while predicting the global ionospheric delay using the existing LSTM for 20 epochs is seen to be 0.004, whereas the existing approach achieves a training error of 0.003
Design optimization and trajectory planning of a strawberry harvesting manipulator
Get PDFThis paper presents a systematic approach to optimizing the structural parameters of a 4-degree-of-freedom (DoF) strawberry harvesting manipulator to minimize its workspace. Unlike previous research that primarily concentrated on the spatial needs related to fruit distribution areas, this work addresses the spatial dynamics of different stages of the fruit-picking process. This is achieved by combining the workspace model method, mathematical modeling, and the GlobalSearch algorithm in the optimization process. A comprehensive verification was conducted using the Denavit-Hartenberg method to simulate the workspace of the optimal manipulator structure. This ensured that the manipulator effectively covered the entire harvesting space. The research design involves exploring an optimal trajectory planning method by adopting a modified sine jerk profile that minimizes overall trajectory duration while maintaining good smoothness. The effectiveness of this method is demonstrated through a simulation of the trajectory of the four joints to drive the end effector from the initial position to the position of the strawberry. This approach yields execution times up to 27% shorter than in previous studies. The proposed method is useful for optimizing the physical and trajectory design of the harvesting manipulator that operates in confined and restricted environments to enhance efficiency, adaptability, and safety in harvesting operations
Evaluation of the performance of the vehicular ad hoc network protocols in the case of V2I and EV2I communications
Get PDFVehicular ad hoc network (VANET) is an intelligent technology that enables efficient communication, secure data transmission, and traffic management. The purpose of routing protocols in the VANET network is to route data between vehicles (V2V) and vehicles-to-infrastructure (V2I). Recently, researchers have shown interest in designing effective routing protocols for the VANET network, as not all existing protocols are suitable for all traffic scenarios. Electric vehicles (EVs) are increasingly being adopted and integrated into intelligent transportation systems (ITS). Developed countries are actively promoting sustainable transportation solutions to increase energy efficiency and reduce carbon emissions. Therefore, this research presents an EV charging station (CS) management scheme based on communication between EVs and RSUs, with performance evaluation simulated using VANET network protocols. In this study, the G-MDORA, MDORA, and geographical routing protocol (GRP) protocols were modified to accommodate V2I communication, and RSUs were distributed along the roadmap. Additionally, a scheme for managing electric vehicle CS was presented, focusing on the communication between electric vehicles and RSUs in the EV2I context. Performance was evaluated using the G-MDORA, GRP, and MDORA protocols, considering factors such as throughput, communication overhead, packet delivery ratio, and end to end delay
Hybrid RNNs and USE for enhanced sequential sentence classification in biomedical paper abstracts
Get PDFThis research evaluates a number of hybrid recurrent neural network (RNN) architectures for classifying sequential sentences in biomedical abstracts. The architectures include long short-term memory (LSTM), bidirectional LSTM (BI-LSTM), gated recurrent unit (GRU), and bidirectional GRU (BI-GRU) models, all of which are combined with the universal sentence encoder (USE). The investigation assesses their efficacy in categorizing sentences into predefined classes: background, objective, method, result, and conclusion. Each RNN variant is used with the pre-trained USE as word embeddings to find complex sequential relationships in biomedical text. Results demonstrate the adaptability and effectiveness of these hybrid architectures in discerning diverse sentence functions. This research addresses the need for improved literature comprehension in biomedicine by employing automated sentence classification techniques, highlighting the significance of advanced hybrid algorithms in enhancing text classification methodologies within biomedical research