Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Virtual inertia evaluation for frequency instability in renewable energy integration
Get PDFIn recent trends, the increasing integration of renewable energy sources (RES) into grids has provides a transition in electricity generation and distribution in terms of frequency instability. Recently, the concept of virtual inertia (VI) has developed as a promising solution to minimize frequency instability in interconnected RES. Therefore, this research introduces VI evaluation technique to decrease the frequency instability. Advanced control algorithms are used to create VI, which simulates the stabilizing effect of traditional rotating mass in conventional power systems. The high penetration of RES based on power converters has suggestively decreased the VI which making them susceptible to frequency instability. This work recommends another use of VI control to further develop recurrence dependability of the connected power framework because of high entrance level of RESs. ∆f values differ between 17.4215 and 20.3621 with significant frequency variations due to conventional control. Equally, VI control exhibits a high level of efficiency in reducing frequency deviations; The ∆f values were consistently smaller between 0.0236 and 0.0369 than the conventional control. These findings signify the potential of VI control to improve frequency stability in power systems with RES
A three-phase model to keyword detection in Arabic corpora
Get PDFThe exponential growth of Arabic text data in recent years has created an urgent demand for sophisticated keyword detection techniques that are specifically tailored to the nuances of the Arabic language. This study addresses the critical need for efficient tools capable of swiftly and accurately identifying keywords within a collection of Arabic documents, particularly when analyzing multiple documents in a corpus. To meet this challenge, we present a novel corpus specifically designed for keyword detection in Arabic texts, along with an innovative approach that integrates three distinct candidate keyword lists: a frequency-based list, a vector space model list, and a machine learning-based list. This hybrid methodology leverages the strengths of each technique, enabling a more comprehensive and effective keyword identification process. We conducted extensive experimental validation to assess the performance and computational efficiency of our proposed pipeline. The results demonstrate that our approach consistently achieves robust performance across a variety of domains, with evaluation metrics indicating F1-scores that consistently surpass 91%. Overall, this study contributes to the advancement of automated keyword detection in Arabic, paving the way for enhanced information retrieval and text analysis capabilities
Single search investigation of various searches in recent swarm-based metaheuristics
Get PDFSwarm intelligence has become a popular framework for developing new metaheuristics or stochastic optimization methods in recent years. Many swarm-based metaheuristics are developed by employing multiple searches whether it is conducted through swarm split, serial searches, stochastic choose. Unfortunately, many existing studies that introduced new metaheuristic focused on assessing the performance of the proposed method as a single package. On the other hand, the contribution of each search constructing the metaheuristic is still unknown as the consequence of the missing of single or individual search assessment. Based on this problem, this work is aimed to investigate the performance of five directed searches that are commonly found in recent swarm-based metaheuristics individually. These five searches include: motion toward the highest quality member, motion relative to a randomly chosen member, motion relative to a random solution along the space, motion toward a randomly chosen higher quality member, and motion toward the middle among higher quality members. In this assessment, these five searches are challenged to find the optimal solution of 23 classic functions. The result shows that the first, fourth, and five searches perform better than the second and third searches
An enhanced predictive modelling framework for highly accurate non-alcoholic fatty liver disease forecasting
Get PDFNon-alcoholic fatty liver disease (NAFLD) is a chronic medical ailment characterized by accumulation of excessive fat in the liver of non-alcoholic patients. In absence of any early visible indications, application of machine learning based predictive techniques for early prediction of NAFLD are quite beneficial. The objective of this paper is to present a complete framework for guided development of varied predictive machine learning models and predict NAFLD disease with high accuracy. The framework employs step–by-step data quality enhancement to medical data such as cleaning, normalization, data upscaling using SMOTE (for handling class imbalances) and correlation analysis-based feature selection to predict NAFLD with high accuracy using only clinically recorded identifiers. Comprehensive comparative analysis of prediction results of seven machine learning predictive models is done using unprocessed as well as quality enhanced data. As per the observed results, XGBoost, random forest and neural network machine learning models reported significantly higher accuracies with improved ‘AUC’ and ‘ROC’ values using preprocessed data in contrast to unprocessed data. The prediction results are also assessed on various quality metrics such as ‘accuracy’, ‘f1-score’, ‘precision’, and ‘recall’ significantly support the need for presented methodologies for qualitative NAFLD prediction modelling
Information system success model: continuous intention on users’ perception of e-learning satisfaction
Get PDFThe information systems success strategy contributes to understanding of digitalization. This research aims to evaluate user satisfaction with the e-learning system continuously. The research method is hybrid, combining constructs of a unified theory of acceptance and use of technology, the technology acceptance model, and service quality (SVQ). Data collection was conducted through the distribution of questionnaires targeting instructors. Data analysis utilized structural equation modeling with partial least squares. This method was used to test the measurement model with factor loadings and average variance extracted (AVE) above 0.5. Meanwhile, validity testing on cross-loading had indicator values for each variable higher than other variables, with composite reliability above 0.7. These results were supported by hypothesis testing, which indicated that website quality positively influences user satisfaction, leading to sustained intention. The original sample obtained a value of 0.633; mean of 0.624; standard deviation of 0.105, and a p-value below 0.01. Additionally, user subjective norms have a strong relationship between sustained intention and system appropriateness, of 0.763 in using e-learning
Backstepping approach for the control of the double-fed asynchronous generator in a wind power system
Get PDFThis paper aims to model and control the dual-fed asynchronous generator (DFIG). The modeling and vector control were simulated using MATLAB, followed by the application of the Backstepping control strategy. A comparative study between two DFIG control strategies, fuzzy logic control (FLC) and Back-stepping control, was conducted. The results for the Backstepping approach are discussed and compared with FLC, highlighting that the Backstepping technique addresses robustness issues regarding variations in operating conditions and internal parameters. Both control strategies are applied to a wind turbine system, and the simulation results and robustness tests are analyzed
Designing fuzzy membership functions using genetic algorithm with a new encoding method
Get PDFThis article presents a new method for designing fuzzy membership functions using the genetic algorithm (GA) without the use of constraints. Conventional approaches to designing these functions often involve manual tuning or optimization techniques with limitations. However, this article introduces a constraint-free approach, as the GA requires all constraints to be met for a chromosome; if even one condition is not satisfied, the chromosome is discarded, regardless of its ideal values for other variables. Consequently, a high number of constraints, especially in the studied case, increases the likelihood of chromosome rejection, leading to a time-consuming design process and suboptimal results
Conception of speech emotion recognition methods: a review
Get PDFIn recent years, speech emotion recognition (SER) has emerged as a pivotal tool for understanding and enhancing human-computer interaction (HCI), thus garnering significant attention from researchers due to its diverse range of applications. However, SER systems encounter numerous challenges, particularly concerning the selection of appropriate features and classifiers for emotion recognition. This paper provides a concise survey of the field of speech emotion recognition, elucidating its classification algorithms and various feature extraction techniques across multiple languages. Additionally, it explores the limitations and weaknesses inherent in speech emotion recognition systems. Furthermore, the paper endeavors to categorize recent research endeavors in Arabic speech emotion recognition, employing diverse modeling approaches and extraction methods
A novel secure and energy aware LOADng routing protocol for IoT: an application to smart agriculture
Get PDFIn the burgeoning domain of the internet of things (IoT), efficient and secure communication protocols are crucial for the seamless operation of diverse applications. This paper proposes a novel routing protocol, termed secure and energy aware LOADng (SEA-LOADng), tailored for IoT deployments in the context of smart agriculture. The protocol is designed to address the unique challenges posed by agricultural environments, including limited energy resources and the need for robust security measures. The proposed protocol leverages LOADng, a lightweight and efficient routing protocol suitable for low-power and lossy networks characteristic of IoT deployments. Through innovative energy-aware mechanisms, it optimizes the power usage of IoT devices, thus prolonging their operational lifespan and reducing maintenance overhead. Moreover, stringent security measures are integrated into the protocol to safeguard sensitive data transmitted within the IoT network. To assess the efficacy of the proposed protocol, comprehensive simulations are carried out using realistic smart agriculture scenarios. The results demonstrate significant improvements in energy efficiency compared to LOADng protocol, while maintaining robust security against hello flood attack
Machine learning based optimized sea vessel location detection to identify illegal fishing
Get PDFIllegal fishing is a pervasive and destructive global issue that poses a significant threat to maritime ecosystems and the resilience of fisheries. Illegal, unregulated, and unreported (IUU) fishing leads to the extinction of the fishing population. Many researchers have presented various approaches to detect illegal fishing, for example, using sensors, image recognition, and convolutional neural networks (CNNs) but each one has some limitations. Our research aims to compare different vessel gear types to select the best vessel container that can be easily monitored and less prone to illegal activities. To achieve this, our research proposed an optimization method that involves hyperparameter selection using a genetic algorithm instead of a grid search. Using the crossover method of the genetic algorithm our model is compatible with larger datasets and unknown search space which is not possible in the baseline algorithm i.e. grid search. Moreover, after applying the genetic hyperparameter optimization technique, the overall accuracy, recall, and F1 score is increased for all vessel types significantly. While comparing our optimized model with the existing model with different evaluation metrics, our model’s performance is outstanding