Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
An efficient intrusion detection systems in fog computing using forward selection and BiLSTM
Get PDFIntrusion detection systems (IDS) play a pivotal role in network security and anomaly detection and are significantly impacted by the feature selection (FS) process. As a significant task in machine learning and data analysis, FS is directed toward pinpointing a subset of pertinent features that primarily influence the target variable. This paper proposes an innovative approach to FS, leveraging the forward selection search algorithm with hybrid objective/fitness functions such as correlation, entropy, and variance. The approach is evaluated using the BoT-IoT and TON_IoT datasets. By employing the proposed methodology, our bidirectional long-short term memory (BiLSTM) model achieved an accuracy of 98.42% on the TON_IoT dataset and 98.7% on the BoT-IoT dataset. This superior classification accuracy underscores the efficacy of the synergized BiLSTM deep learning model and the innovative FS approach. The study accentuates the potency of the proposed hybrid approach in FS for IDS and highlights its substantial contribution to achieving high classification performance in internet of things (IoT) network traffic analysis
Definite time over-current protection on transmission line using MATLAB/Simulink
Get PDFThis paper has investigated the application of the definite time over-current (DTOC) which reacts to protect the breaker from damage during the occurrence of over-current in the transmission lines. After a distance relay, this kind of over-current relay is utilized as backup protection. The overcurrent relay will provide a signal after a predetermined amount of time delay, and the breaker will trip if the distance relay does not detect a line failure. As a result, this over-current relay functions with a time delay that is just slightly longer than the combined working times of the distance relay and the breaker. This DTOC is tested for various types of faults which are 3- phase fault occurring at load 1, 3-phase fault occurring at load 2, a 3-phase fault occurring before primary protection, and the behaviour of voltage and current with a failed primary protection. All the results will be obtained using the MATLAB/Simulink software package
A system for monitoring human postures, seizures, and falls from bed using radio and surface electromyography signals
Get PDFIn this work, a system for monitoring human postures, seizures, and falls from bed using received signal strength indicator (RSSI) and surface electromyography (sEMG) signals is studied through experiments. In this proposed system, a person who is located inside a wireless link is monitored by considering the change in measured RSSI signals as the 2.4 GHz IEEE 802.15.4 signals received at a receiver. Human motions in bed that affect RSSI levels can be captured. Thus, with this technique, it does not raise a privacy concern compared with vision-based technology. Additionally, sEMG signals associated with muscle movements from human postures are recorded from the human body’s abdominal muscles. Eight different activities, including normal and critical events, are tested and evaluated. Experimental results indicate that the proposed system could automatically monitor different human postures in real-time. RSSI and sEMG signals correlated to each posture have their own patterns. Furthermore, the relationship between human behaviors and RSSI and sEMG levels is summarized
Description and analysis of Sigfox received signal strength indicator dataset by using statistical techniques
Get PDFLow power wide area network (LPWAN) technology has expanded and is essential in the development of applications for the internet of things (IoT). The Sigfox LPWAN network is characterized by its long-range coverage, low cost and power consumption. In this article, a set of 5174 values is analyzed, containing 1606 null RSSI data, obtained with the Sipy module and MicroPython, which provide a coverage map of several points with a resolution of 200 meters deployed in Quito–Ecuador. It is evaluated the type of distribution to which the set of network measurements is adjusted and an optimal 900 MHz propagation model in suburban environments is determined from the measurements obtained from the known base station. As a result, the lost values of RSSI were predicted using the inverse normal distribution method in the original values, observing that they conform to a logistic distribution. The data from the base station were subjected to a data augmentation algorithm designed in MATLAB, determining that the stanford university interim (SUI) model reduces the precision error in the trend of the curve by not presenting changes greater than 5 dB, achieving a precision of 97% with respect to the fit of the curve of the data
A deep learning based architecture for malaria parasite detection
Get PDFDuring last decade, medical imaging has attracted great deal of research interests. Deep learning applications has revolutionized medical image analysis and diseases diagnosis. Convolutional neural networks (CNNs)-a class of deep learning-have been widely used for classification and feature extraction, and they revealed good performance for various imaging applications. However, despite the advances in medicine, malaria remains among the world’s deadliest diseases. Only in 2020, malaria recorded 241 million clinical episodes, and 627,000 deaths. The disease is examined visually through a microscope, which depends on the pathologists experience and skills and results may vary in different laboratories. This paper proposes an efficient CNN architecture that could be used in diagnosing of malaria disease. By processing on 27,558 red blood smear cell images with balanced samples of parasitized and unparasitized cells on a publicly available malaria dataset from the National Institute of Health, the proposed model achieves high accuracy rate with 99.8%, 98.2, and 97.7% for training, validation and testing sets. Furthermore, the statistical results approve that the proposed model is outperforming the state-of-the-art models
Advanced spatial adaptive channel estimation for efficient mmWave communication
Get PDFThis study explores the intricacies posed by the unique features of 5G/6G wireless sensor networks (WSNs) to guarantee dependable and long-lasting connectivity. The increasing energy consumption in 5G/6G networks due to higher data rates and more complex architectures emphasizes the necessity for energy-efficient techniques. The WSN resources are limited, specially designed resource allocation and management techniques are essential. In this paper, a unique analogue combining design called advanced spatial adaptive channel estimation (ASACE) and an optimization model for channel state information (CSI) estimation that takes use of the low-rank characteristics of channel matrix sparsity are presented. Gradient descent (GD) optimization is incorporated to improve the suggested approach, demonstrating improvements in residual errors and computing complexity. The optimization problem aims to find the gains and orientations of wideband channel paths. Moreover, a comparative analysis is conducted between the suggested model and many cutting-edge methods, emphasizing error minimization. This thorough analysis offers a nuanced viewpoint on the effectiveness and efficiency of the suggested ASACE approach in the context of wideband cross-entropy (CE) and optimization, which makes a significant contribution to the area
Development of stability charts for double salience reluctance machine modeled using hill’s equation
Get PDFThe paper presents a novel algorithm for the development of stability charts. The second-order differential homogeneous equation describing a double salient reluctance machine with a capacitance connected to its stator winding is transformed into hill’s equation. The circuit components are the stator coil time-varying inductance of a double salient reluctance machine, capacitance and resistance. All these are modeled by hill’s equation. The double salient reluctance machine acts as an energy conversion system. The maximum and minimum inductance of the energy conversion system is measured in laboratory by inductance, capacitance, and resistance (LCR) meter. These values help to determine the inductance modulation index. The inductance modulation indetx, the characteristic constant and the characteristic parameter obtained from modeling equations are used in the MATLAB/Simulink model. The MATLAB/Simulink simulations generate stable and unstable oscillations to form stability charts. The proposed stability charts are in good agreement with the Ince-Stritt stability chart, which is widely applied in physics, mechanics and in electrical engineering, especially where the state of stability of a system or an electric oscillatory circuit is to be determined
Wastewater monitoring system in the textile industry
Get PDFRecently, a problem which often experienced by the Environmental Agency is to monitor the quality of industrial waste. The problem comes from manual monitoring of wastewater and the high cost of laboratory tests for each variable for the waste. This system is intended to develop a wastewater monitoring system considering the state of the environment and technology. This system uses 5 types of sensors to measure the quality of wastewater. The sensor will display measurement data both offline via liquid crystal display (LCD) and online via the website. For the pH sensor test, we obtained an error value approximately of 1.32% and accuracy of 98.68%. For the oxidation reduction potential (ORP) sensor test, we obtained an error value of 1.4% with 98.6% accuracy. We obtained an error value of 0.22% with 99.78% accuracy for the temperature sensor test. For the total dissolved solid (TDS) sensor test, we obtained an error value of 1.02% with 98.98% accuracy. The color sensor is validated using a spectrometer to measure the variation of color in remazol waste concentration. For the Client - Server communication test, the system has a delay of 2 seconds. One of the advantages of using a web server is the system has minimum network traffic
Accident black spots identification based on association rule mining
Get PDFThis paper presents an analytical approach to identifying the important characteristics of accident black spots on Moroccan rural roads. An association rule mining method is applied to extract road spatial characteristics associated with fatal accidents. The weighted severity index was calculated for each section, which was then used to determine the severity levels of black spots. The apriori algorithm is applied to find the correlation between road characteristics and the severity levels of black spots. Then, a general rule selection method is proposed to identify the rules strongly associated with each severity level. The results show that the proposed approach is effective in identifying the most important factors contributing to accidents. Furthermore, it shows that the combination of several road characteristics, such as road width, road surface, and bridge presence, may contribute to fatal accidents. The general rule selection found that wet, bad surfaces, and narrow shoulders were significantly associated with accidents on rural roads. The findings of the present study can help develop effective strategies to reduce road accidents and thus improve road safety in the country
Identifying deoxyribonucleic acids of individuals based on their chromosomes by proposing a special deep learning model
Get PDFOne of the most significant physiological biometrics is the deoxyribonucleic acid (DNA). It can be found in every human cell as in hair, blood, and skin. In this paper, a special DNA deep learning (SDDL) is proposed as a novel machine learning (ML) model to identify persons depending on their DNAs. The proposed model is designed to collect DNA chromosomes of parents for an individual. It is flexible (can be enlarged or reduced) and it can identify one or both parents of a person, based on the provided chromosomes. The SDDL is so fast in training compared to other traditional deep learning models. Two real datasets from Iraq are utilized called: Real Iraqi Dataset for Kurd (RIDK) and Real Iraqi Dataset for Arab (RIDA). The results yield that the suggested SDDL model achieves 100% testing accuracy for each of the employed datasets