Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Modeling two loops RLC circuit AC power source using symbolic arithmetic differential equations
Get PDFAs oscillator applications, resistance-inductor-capacitor (RLC) circuits are employed in a diversity of settings. A low-pass, band-stop, band-pass, or high-pass filters can all be designed using an RLC circuit. A two-loop RLC circuit could not be represented mathematically in prior studies. Laplace transform is one type of integral transformation, which is able to resolve both second order non-uniform and uniform linear differential equations. This work solves the differential equations (DEs) of a two loops RLC circuit of an alternating voltage source by using two alternative approaches, Laplace transform (LT) and deep learning convolutional neural network (DLCNN). Initially, two DE have been declared. Next, Laplace transform is computed to solve these equations with symbolic variables for the first loop current and capacitor charge. Finally, we substitute the numerical values of the circuit elements for the symbolic variables. The charge and current initially decline exponentially. On the other hand, they oscillate over a long period of time. The capacitor charge and current initially decline exponentially and oscillate over a long period of time. The qualities of the result can be examined with a symbolic result, which is not possible with a numeric result
Handwritten Arabic words detection using Faster R-CNN in IFN/ENIT dataset
Get PDFRecognizing Arabic offline handwritten words still faces various challenges because of the diversity of writing styles and the overlap between the words and characters. Therefore, building an effective system to solve these challenges has always been difficult, which has led to a lack of published research in this field. This study introduces two new models to recognize handwritten Arabic words based on the Faster region-convolution neural network (Faster R-CNN). These models employ two pre-trained networks during the feature extraction phase: The visual geometry group-16 (VGG-16) network and the residual network (ResNet50) network. To help with overlapping detections and make localization more accurate, a soft non-maximum suppression (Soft-NMS) strategy is used in post-processing. Models are independently trained and tested on two groups of data from the Institut Für Nachrichtentechnik/Ecole Nationale d’Ingénieurs de Tunis (IFN/ENIT) dataset. The first group includes one word in each image, while the second contains multiple words. Test results showed that the proposed models give excellent results compared to others. The results of VGG16 and ResNet50 with the first dataset reached accuracy rates of 100% and 99.5%, respectively. Meanwhile, the accuracy of the second group reached 91.4% and 100% with VGG16 and ResNet50, respectively
Enhancing Arabic offensive language detection with BERT-BiGRU model
Get PDFWith the advent of Web 2.0, various platforms and tools have been developed to allow internet users to express their opinions and thoughts on diverse topics and occurrences. Nevertheless, certain users misuse these platforms by sharing hateful and offensive speeches, which has a negative impact on the mental health of internet society. Thus, the detection of offensive language has become an active area of research in the field of natural language processing. Rapidly detecting offensive language on the internet and preventing it from spreading is of great practical significance in reducing cyberbullying and self-harm behaviors. Despite the crucial importance of this task, limited work has been done in this field for nonEnglish languages such as Arabic. Therefore, in this paper, we aim to improve the results of Arabic offensive language detection without the need for laborious preprocessing or feature engineering work. To achieve this, we combine the bidirectional encoder representations from transformers (BERT) model model with a bidirectional gated recurrent unit (BiGRU) layer to further enhance the extracted context and semantic features. The experiments were conducted on the Arabic dataset provided by the SemEval 2020 Task 12. The evaluation results show the effectiveness of our model compared to the baseline and related work models by achieving a macro F1- score of 93.16%
Enhancing classification in high-dimensional data with robust rMI-SVM feature selection
Get PDFDealing with high-dimensional datasets presents notable challenges for classification modelling, primarily due to complexity and susceptibility to overfitting. Traditional feature selection methods frequently struggle to guarantee improved classification performance by including more features. Instead, they often rely on utilising the entire feature set. To address these challenges, a robust feature selection algorithm known as ranked mutual information for support vector machines (rMI-SVM) has been introduced. This approach mitigates the risk of overfitting by selecting features that augment the classification model with additional information, thereby ensuring enhanced performance as more features are selected. rMI-SVM can accommodate datasets with missing values regardless of data linearity as it does not require additional parameters or preset the number of features needed. The proposed method offers a solution to the challenges posed by high-dimensional data, and explicitly identifies the optimal number of features required for a classification model, thus circumventing the necessity of using the full feature set. These findings are supported by receiver operating characteristic (ROC) curves, which highlight the effectiveness of rMI-SVM in outperforming existing baselines and delivering a superior classification model performance
Pre-trained Bi-LSTM model for automated classification of ventricular arrhythmias using 1-D and 2-D ECG
Get PDFNumber of cardiac conditions have been associated with abnormal heartbeat (arrhythmia) such as ventricular fibrillation (Vfib), ventricular flutter (Vfl), and ventricular tachycardia (Vta). This is a difficult and essential job for timely clinical assessment and identification of these potentially life-threatening heart arrhythmias. With the aid of a one-dimensional electrocardiogram (ECG) signal and its associated two-dimensional image, the suggested method provides a strategy for the detection of time-frequency interpretation (Vfib, Vfl, and Vta). A four-stage cascaded Savitzky-Golay (SG) filter is used after a 2-stage median filter to preprocess the ECG signal. This technique employs z-score normalisation after brief (2 sec) ECG readings. The classification of these ECG segments (1-D) and associated time-frequency representation pictures (2-D) was explored separately using a bi-directional long short-term memory-based network. Eight distinct categorization scenarios were examined, and then an average accuracy of 99.67% for 1-D ECG and 99.87% for 2-D ECG signal was attained
Effective capacity analysis of configurable intelligent surface-assisted NOMA communications systems
Get PDFThis paper investigates the integration of configurable intelligent surfaces (CIS) into relay radio networks, focusing on communication system enhancement. Towards this end, we propose CIS-assisted non-orthogonal multiple access (NOMA) communication systems to improve direct connections between a base station and two destination nodes. Our primary objective is to assess the net-work’s overall capacity, considering critical factors like signal-to-noise ratio, the number and placement of CIS components, quality of service exponent, and power distribution coefficients. Analytical equations developed in this research closely align with simulation results, validating our theoretical analysis. This study underscores the growing significance of CISs in modern communication systems, introducing adaptability and optimization to wireless networks. By exploring CIS-assisted NOMA communication systems, we contribute to dis-cussions about the evolving landscape of wireless communication technologies, poised to revolutionize information transmission and reception in the digital age
Frequency response of microgrids with PV power generation and energy storage system (battery and supercapacitor)
Get PDFSince renewable energy sources (RES) have almost little inertia, an increase in their electricity might harm the power system's ability to run steadily and dependably. Numerous solutions to the issue mentioned above are offered. This paper aims to assess the technological possibility of using energy storage system (ESS) devices built from batteries and supercapacitors to enhance the interia response of sources in microgrids with a large amount of PV power penetration. The microgrid's inertia was altered by varying the penetration level of RES. To obtain a rigid microgrid, batteries and supercapacitors are suggested in this study to enhance frequency stability and droop control is utilized to complete this assessment. The model of the on-grid power network was designed using Simulink in MATLAB to evaluate the high level of RES penetration impact on the frequency stability of the system. Results verify that the microgrid stiffness is significantly enhanced when the suggested storage elements are incorporated. The findings show that the rate of change of frequency (RoCoF) is reduced when the size of the ESS increases and vice versa. The supercapacitor energy storage system (SCESS) can increase the stability of the system's frequency more effectively than the battery energy storage systems (BESS) with a slower time response
Robust hybrid control strategy for active power management in Kabertene wind farm within Algeria’s PIAT grid
Get PDFThe paper introduces a hybrid control strategy for optimised active power management in Algeria's Kabertene wind farm, crucial for the pole insalah-adrar-timimoune (PIAT) grid's stability. This strategy merges simultaneous interconnection and damping assignment (SIDA) passivity theory, passivity-based control (PBC), and multivariable proportional-integral-derivative (PID) controllers. This combined approach ensures frequency and voltage stability within the PIAT grid, which encompasses various elements like wind farms, solar plants, gas turbines, and dynamic impedance (Z), current (I), and active power (P) (D-ZIP), load model. By tailoring controllers for doubly fed induction generators (DFIGs) using SIDA-PBC principles and optimising internal parameters, the strategy achieves precise control of active power output. Additionally, particle swarm optimisation (PSO) refines power scheduling, which is especially beneficial for intermittent renewable sources like DFIGs. This comprehensive strategy offers numerous advantages: improved network stability, minimized voltage deviations, reduced frequency fluctuations, and enhanced integration of renewable energy sources. The paper emphasises practical implementation considerations, providing valuable guidance for efficient Kabertene wind farm operation and integration. This research contributes significantly to fostering cleaner and more reliable energy systems, facilitating the PIAT grid's transition towards sustainable energy generation
Risk analysis and prevention in computer security in institutional servers, a systematic review of the literature
No full textIn recent years, computer attacks on the server infrastructure in organizations have been increasing, and the pandemic of covid-19 and remote work have been the main causes for this massive wave of large-scale attacks, small businesses are especially vulnerable because to optimizing resources they leave aside the cyber security in their network infrastructure. The present research is a systematic review that compiles 58 articles where policies, techniques, and infrastructure for the prevention of threats in enterprise servers have been implemented and raised, these articles have been collected from major databases such as IEEE Xplore, SAGE, Science Direct, Scopus, and IOP Publishing. The results show that one of the most effective methods in preventing communications between institutional servers is public key infrastructure/SSL-TLS encryption. Most research claims that it is the most effective method as it provides a central certifier and manages the certificates for the servers allowing each of the modules or attachments within the infrastructure to identify and validate other members and to proceed with the encryption of network traffic, Finally, a security implementation model is proposed
A survey to build framework for optimize and secure migration and transmission of cloud data
Get PDFIn the recent era of computational technologies, the internet is needed daily. The data generated is enormous and primarily stored on dedicated servers or clouds. Data migration and transfer are significant tasks for maintaining consistency and updating data. The data is the most critical component in any cloud service. There are various methods to protect data, like secure transfer, encryption, and authentication. These techniques are used as per need and transmission of the data. As data grows on a server or cloud, it must be migrated securely. Here, the exhaustive survey is provided for building a framework for migrating and transmitting cloud data. The framework should be sustainable and adaptable for load-balancing recovery and secure transmission. Various security load balancing parameters must be considered to obtain these state-of-the-art functionalities in the framework. The existing similar frameworks are studied, and findings are proposed in the paper to develop the framework