Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Fifth generation core: the performance enhancement of virtual private server and bare metal
Get PDFThe fifth generation (5G) architecture represents the most recent advancement in mobile networks and is presently operational in various global places. Several new use cases and applications have been introduced, with a specific focus on improving throughput, reducing latency, minimising packet loss, optimising CPU usage, and maximising memory utilisation. In order to effectively address each scenario, it is necessary to integrate the most advanced technology, putting in significant effort to optimise resources and ensure system adaptability. This strategy will establish an architecture capable of accommodating many scenarios of a shared physical infrastructure by using techniques such as virtualization and cloud-based service deployment. Therefore, in this study, a test was carried out related to the performance of the 5G core network (CN) on bare metal servers and virtual private servers (VPSs). The quality of service (QoS) using Wireshark and Iperf3 is tested by utilizing ‘cpustat’ and free tools. The results of performance comparisons of these two methods on the 5G CN shows throughput values of ≥10 Gbps ≤20 Gbps, latency values of ≤4 ms, and packet loss values of 0%, in accordance with IMT 2020 standards. Thus, the ideal 5G CN services can be realized
Random-guided optimizer: a metaheuristic that shifts random search to guided search through iteration
Get PDFThis study offers a new swarm-based metaheuristic: random-guided optimizer (RGO). RGO has novel mechanics in shifting the random motion into a guided motion strategy during the iteration. In RGO, the iteration is divided into three equal size phases. In the first phase, the unit walks randomly inside the search space to tackle the local optimal problem earlier. In the second phase, each unit uses a unit selected randomly among the population as a reference in conducting the guided motion. In the third phase, each unit conducts guided motion toward or surpasses the best unit. Through simulation, RGO successfully finds the acceptable solution for 23 benchmark functions. Moreover, RGO successfully finds the global optimal solution for four functions: Branin, Goldstein-Price, Six Hump Camel, and Schwefel 2.22. RGO also outperforms slime mold algorithm (SMA), pelican optimization algorithm (POA), golden search optimizer (GSO), and northern goshawk optimizer (NGO) in solving 12, 20, 12, and 1 function consecutively. In the future, improvement can be made by transforming RGO into solid multiple-phase strategy without losing its identity as a metaheuristic with multiple strategy in every iteration
Ageing durability of SiR under prolonged voltage stress, contaminant flow and contaminant concentration: a statistical approach
Get PDFSilicone rubber (SiR) has become a reliable choice for outdoor high voltage (HV) insulation in recent years. However, the durability of these polymeric materials is affected by both electrical and environmental stresses, leading to aging. While prior research aimed at enhancing performance, little focus was placed on identifying the major root causes of aging in these insulators. To delve into the causes, we conducted inclined plane tracking (IPT) tests, varying voltage, flow rate, and contamination concentration. Samples with consistent alumina trihydrate (ATH) filler content were tested under the BSEN 60587 standard. The voltage ranged from 3.5-5.5 kV, flow rate from 0.3-0.9 ml/min, and contamination concentration from 500-4500 µS/cm. A Two-Level Factorial analysis with a design of experiment (DOE) approach was used. The study revealed that contaminant concentration significantly impacted leakage current (LC), followed by contamination flow rate and voltage. Additionally, optimization techniques are used to determine ideal LC values under specific conditions. This study explains how each factor affects LC values, allowing for predictive modelling, which improves our understanding of SiR insulators' durability, optimizes LC in real-world situations, and improves their performance and lifespan
Ultrasonic sensor decision-making algorithm for mobile robot motion in maze environment
Get PDFAn autonomous mobile robot is one that can move from one location to another without the intervention of a human. A maze environment is a complex environment since it contains many obstacles and the major problem is moving through it. To avoid obstacles while moving through the maze, the mobile robot must be designed with an algorithm. This work proposes a decision-making system with an ultrasonic sensor to allow the developed autonomous mobile robot to avoid obstacles in any maze setting through its movements. The maze was designed with a size of 100×200 cm2 for the case study. Due to the height dimension of the barrier (20 cm) and the height dimension of the mobile robot including the ultrasonic sensor (20 cm), a distance of 20 cm was taken between the wall (obstacle) and the sensor. The result distance between the (wood wall) object and the sensor indicates that it is a reasonable distance chosen for the mobile robot to move and turn with flexibility as it travels through the maze environment from 0 cm to 300 cm. This mobile robot path took 1 minute to finish at a speed of 5 cm/sec, indicating that it is a quick algorithm as compared with related work
Machine learning-based detection of fake news in Afan Oromo language
Get PDFThis paper presents a machine learning-based (ML) approach for identifying fake news on web-based social media networks. Data was acquired from Facebook to develop the model which was used to identify Afan Oromo's false news. The system architecture uses algorithms, such as support vector machines (SVM), k-nearest neighbor (KNN), and convolutional neural networks (CNNs) to detect and classify fake news. Existing models have limitations in understanding reported news accuracy compared with verified news. This study successfully resolved the challenges in the detection of social media fake news detection for the Afan Oromo language with the use of ML models and natural language processing (NLP) techniques. The results show that the SVM approach achieved a precision, recall, and F1-score, of 0.92, 0.92, and 0.90
Optimal placement of wind turbine in distribution grid to minimize energy loss considering power generation probability
Get PDFThis research proposes an algorithm to determine the optimal position of wind turbines in a distribution grid for minimizing its annual energy loss. In this paper, the probability distribution of power generation at each wind turbine node is considered and the nonsimultaneous occurrence of the power generation at wind turbine nodes is also interested. Moreover, we also consider the wind energy exploitability at each node in the grid. This algorithm is coded in MATLAB environment and it is verified via a sample IEEE 33 bus distribution grid with a sample data of power generation probability. The verifying results indicated that the optimal number of wind turbines at each node to obtain a minimal annual energy loss. Results also indicated that the node voltage is varied because of the change of power generation; however, the voltage at all nodes is in normal operation range and its median value is between about 1.01 pu to 1.05 pu. The power factor of wind turbines has an impact on the optimal number of wind turbines at nodes and the efficiency of wind turbine installation
Performance comparison of state-of-the-art deep learning model architectures in Indonesian food image classification
Get PDFFood image recognition is essential for developing an elderly-friendly daily food recording application in Indonesia. However, existing datasets and models are limited and do not cover the diversity and complexity of Indonesian food. In this paper, we present a new dataset of 24,427 images of 160 types of Indonesian food with higher variety and quality than previous datasets. We also train and compare the performance of 67 models based on 16 state-of-the-art deep learning architectures on this dataset. We find that efficientnet_v2_l provides the best accuracy of 85.44%, followed by other models such as convnext_large and swin_s. We also discuss the trade-off between model size and performance, as well as the challenges and limitations of food image classification. Our dataset and models can serve as a basis for developing a user-friendly and accurate food recording application for the elderly population in Indonesia
Application of neural networks ensemble method for the Kazakh sign language recognition
Get PDFSign languages are an extremely important means of communication in many cases, especially for deaf and hard of hearing people. But the same gesture can convey different meanings in different countries, so many different sign languages have been developed all over the world. In this study, a convolutional neural network (CNN) model was developed based on an ensemble method containing the ResNet-50 and VGG-19 architectures, which will be able to classify the Kazakh sign language (KSL) consisting of 42 Kazakh alphabet signs (classes). A proprietary data set of 57,708 images for 42 signs of the KSL has been formed. The ensemble model was compared with ResNet-50 and VGG-19 by evaluation metrics such as accuracy, precision, recall, f1-measure, and loss function. The recognition accuracy of the ensemble method reached 95.7%, exceeding the performance of ResNet-50 and VGG-19. The developed method was also tested on test data, where 35 out of 42 gestures were recognized completely correctly. The reliability of the proposed approach and the classification results obtained by using preprocessing methods and data augmentation techniques to expand the data set was confirmed by a computational experiment
An Adam based CNN and LSTM approach for sign language recognition in real time for deaf people
Get PDFHand gestures and sign language are crucial modes of communication for deaf individuals. Since most people can't understand sign language, it's hard for a mute and an average person to talk to each other. Because of technological progress, computer vision and deep learning can now be used to count. This paper shows two ways to use deep knowledge to recognize sign language. These methods help regular people understand sign language and improve their communication. Based on American sign language (ASL), two separate datasets have been constructed; the first has 26 signs, and the other contains three significant symbols with the crucial sequence of frames or videos for regular communication. This study looks at three different models: the improved ResNet-based convolutional neural network (CNN), the long short-term memory (LSTM), and the gated recurrent unit (GRU). The first dataset is used to fit and assess the CNN model. With the adaptive moment estimation (Adam) optimizer, CNN obtains an accuracy of 89.07%. In contrast, the second dataset is given to LSTM and GRU and a comparison has been conducted. LSTM does better than GRU in all classes. LSTM has a 94.3% accuracy, while GRU only manages 79.3%. Our preliminary models' real-time performance is also highlighted
The scheduling techniques in the Hadoop and Spark of smart cities environment: a systematic review
Get PDFProcessing extensive and diverse data in real-time is a significant challenge in the context of smart cities. Timely access to information and efficient analytics is essential for smart city services to make data-driven decisions and enhance urban living. Scheduling algorithms play a crucial role in ensuring the prompt delivery of services and efficient task completion. This paper explores various scheduling techniques, including static, dynamic, and hybrid schedulers, and compares their objectives and performance. Additionally, the study examines two prominent data processing frameworks, Hadoop and Spark, and compares their capabilities in handling big data in smart cities. With its ability to process large amounts of data quickly and efficiently, Spark has shown superiority over Hadoop in real-time data processing and performance optimization. The paper concludes by highlighting the strengths and limitations of each framework. It discusses the need for further research in optimizing scheduling techniques and exploring hybrid artificial intelligence scheduling for Spark. Overall, the findings contribute to a better understanding of data processing in real-time and provide insights for researchers and practitioners in smart cities