Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Project QSUeVoto: distributed electronic voting system based on blockchain technology
Get PDFStudents' voting experience can be made far more secure, transparent, and effective with an electronic voting system based on blockchain. But for it to be implemented successfully, technological issues must be resolved, accessibility must be guaranteed, and student trust must be developed. Resilient security protocols, intuitive user interfaces, and unambiguous dissemination of the advantages and functionality of the system are vital for surmounting possible obstacles and optimizing favorable outcomes. System development techniques and a descriptive research design were used in this study. The developed systems are accepted and compliant as determined by the IT experts, as evidenced by the grand mean of 4.63 and the descriptive rating of conformity to a very high level. It can be deduced that the SG Advisor, SAS Director, students, and Canvasser Board from Maddela and Diffun Campus gave the generated application great approval and acceptance. This indicates that there is a notable discrepancy between the users' and IT specialists' perceptions of the system's adoption and compliance levels. This procedure can be made better with a safe voting system that has cutting-edge features. Blockchain technology is regarded as a disruptive breakthrough with substantial potential to improve the electronic voting system
Attention deficit and hyperactivity disorder classification in quantitative EEG signals using machine learning algorithms
Get PDFAttention deficit and hyperactivity disorder (ADHD) classification method as a quantitative observation has been continually improved to assist medical practitioners. Currently, machine learning algorithms such as k-nearest neighbors (KNN), multilayer perceptron (MLP), and support vector machine (SVM) are widely used. This study proposed a feature extraction method for quantitative electroencephalography (qEEG) data derived from the continuous wavelet transform (CWT) to classify children with ADHD versus healthy subjects. Subsequently, this study compared the performance of the classification pipeline before and after the implementation of principal component analysis (PCA) on the features prior to processing with machine learning algorithms. The results revealed that the overall performance of the classifiers consistently improved after the implementation of PCA. The results highlight the varying impact of PCA on classifier performance, with KNN showing an improvement in testing accuracy from 61.84% to 69.21% following PCA implementation, while the other classifiers showed deterioration in performance. These findings suggest that while PCA may be beneficial for some classifiers, its impact on performance varies depending on the specific characteristics of the dataset and the classifier utilized. Moreover, this study provides insight for future implementation of the classification method for ADHD patients across a more specific clinical range of the spectrum
Unveiling perceptions: aspect-based sentiment analysis of Malaysia’s e-hailing reviews
Get PDFThe growing demand for e-hailing services in Malaysia leads to increased competition among more than 20 licensed e-hailing service providers. Consumer satisfaction is a crucial factor influencing variables in the business organization, and understanding consumers’ perceptions is vital for service improvement. Reviews on e-hailing services are unstructured data and massive, making comparisons difficult. Thus, this study aims to classify Malaysia’s e-hailing service reviews from Google Play Store and X using latent Dirichlet allocation (LDA) and support vector machine (SVM). Aspect-based sentiment analysis (ABSA) was performed using a two-staged method, applying LDA for aspect category detection and SVM for aspect sentiment classification separately. Fare, availability, comfort, time, and convenience are five predetermined aspect categories in this study. The LDA for English and Malay achieved a perplexity of -7.31 and -7.49, respectively. Besides, the accuracy scores of SVM for English and Malay are 86.32% and 62.97%, respectively
Improving energy indicators of pulse converters
Get PDFAll rectifier circuits are divided into single-phase and three-phase, according to the number of phases of the supply network, single-cycle and two-cycle. Voltage conversion, which can vary in both frequency and amplitude, is carried out by two series-connected converters-a rectifier (AC/DC converter) and an inverter (DC/AC converter). Using simulation techniques in the MATLAB-based Simulink environment, the blocks used were taken from the sim power system/Simscape library. Models of semiconductor converters with pulse-width modulation based on one power thyristor switch and a semiconductor converter with pulse-frequency modulation based on four power thyristor switches have been developed. Experiments prove the correctness of the models. The results of a study of the developed models of semiconductor converters with pulse-width and pulse-frequency modulation are presented. The static and dynamic characteristics of pulsed semiconductor converters are presented. Analysis of the static characteristics of pulse converter circuits showed that the rigidity of the output characteristics of converters with pulse-frequency modulation is higher than that of converters with pulse-width modulation. The results of assessing the efficiency of pulsed semiconductor converters based on the analysis of static output characteristics allow us to conclude that the efficiency of a semiconductor converter with pulse-frequency modulation is more than one percent higher than that of a semiconductor converter with pulse-width modulation
Comparing machine learning models for Indonesia stock market prediction
Get PDFThe financial market hold a significant role in the economy and the ability to accurately predict stock prices poses a major challenge, particularly in volatile markets like Indonesia. This study investigates the application of three supervised machine learning algorithms: random forest (RF), support vector regression (SVR), K-nearest neighbor (KNN) to predict the closing prices of stocks. The data used in this research consists of BBCA, PWON, and TOWR stocks. This study adopted daily historical stock prices from March 2017 to February 2020, which were normalized and segmented into training and testing datasets. The models were trained using machine learning techniques, and their predictive accuracy was evaluated using root mean square error (RMSE) and mean absolute error (MAE). The historical stock data includes Open, High, Low, and Close prices. The result indicated that SVR consistently outperforms RF and KNN in terms of RMSE and MAE across different stocks. The SVR method produced RMSE values of 4.79% for BBCA stock, 10.61% for PWON stock, and 15.14% for TOWR stock, and produces MAE values of 3.52% for BBCA stock, 8.49% for PWON stock, and 13.78% for TOWR stock
Synergistic ensemble classification framework: utilizing a soft voting algorithm for enhanced prediction and diagnosis of diabetes mellitus
Get PDFDiabetes, a serious condition characterized by elevated blood glucose levels, can be effectively identified, and predicted early using machine learning (ML) algorithms. The research provides a comprehensive assessment of three ensemble ML models-stacking, soft voting, and hard voting-focused on enhancing diabetes diagnosis among Pima Indian women dataset taken from the National Institute of Diabetes and Digestive and Kidney Diseases, this study focuses on Pima Indian women aged 21 and older, with the dataset comprising critical diagnostic measurements. Two ensemble models were developed and evaluated on various evaluation parameters. The stacking model combines predictions from various classifiers using a meta-classifier, leveraging their strengths for final decision-making. In contrast, the voting model aggregates probability estimates from each classifier, providing nuanced predictions. Both models were rigorously evaluated on a validation dataset, emphasizing accuracy, specificity, sensitivity, and the receiver operating characteristic (ROC) area under the curve (AUC). Notably, the voting-based ensemble methods demonstrated superior performance in predicting diabetes for this cohort. However, their effectiveness heavily relies on preprocessing, base model selection, and hyperparameter optimization. This study underscores the potential of ensemble models in medical diagnostics, highlighting the critical role of data preprocessing, and configuration in enhancing predictive accuracy
Automated handwriting analysis and personality attribute discernment using self-attention multi-resolution analysis
Get PDFHandwritten document analysis is a method used in academia that examines the patterns and strokes of a person’s handwriting in order to get a deeper understanding of that person’s personality and character. In spite of the fact that there are a number of models and methods that may be used in the investigation of automated graphology, there are a few challenges that need to be solved. Among these challenges is the identification of efficient classification techniques that provide the highest possible degree of accuracy. Within the scope of this study, we propose automated handwriting analysis and personality attribute discernment using self-attention multi-resolution analysis (MRA) where the data is preprocessed using histogram equalization and the spurious line segment section is attached to the genuine line segment portion in order to segment the succeeding line from the authentic picture of the document. A deep dense network is combined with self-attention MRA in order to provide a novel approach to the investigation of authentic handwritten text. Using the most recent and cutting-edge standards that are currently in use, an evaluation is performed to determine whether or not the proposed strategy is feasible. It is observed that the proposed method obtained nearly 98% accuracy with precision of 99%
Neuro-adaptive hierarchical sliding mode control for a 3-wheeled mobile robot with disturbance rejection
Get PDFHigh tracking accuracy and fast convergence are essential features in the control of wheeled mobile robots for autonomous navigation applications. However, the design of a control system for these robots faces significant challenges due to the inherent complexity of their nonlinear dynamics and their non-holonomic underactuated nature. This article introduces a novel control framework for trajectory tracking of a three-wheeled mobile robot (3WMR), considering external and internal disturbances. To address the uncertain nonlinear and underactuated non-holonomic dynamics of the 3WMR, an adaptive hierarchical fast terminal sliding mode control (AHFTSMC) strategy is proposed. In this approach, an adaptive neural network scheme adjusts the sliding surface coefficients in real time to minimize tracking errors and mitigate the chattering phenomenon. In addition, a finite time disturbance observer (FTDO) is designed to accurately estimate and compensate for unknown lumped disturbances, which helps to improve the disturbance rejection capability. The stability of the closed-loop system is demonstrated using Lyapunov theory. The proposed control approach is validated by numerical simulations, and a comparative analysis of recent hierarchical sliding mode controllers (SMC) is performed. The results demonstrate that the proposed approach achieves superior performance in terms of fast convergence and tracking accuracy, which are crucial features for the autonomous navigation of mobile robots
Machine learning-based intelligent result compilation RPA bot for higher education institutions
Get PDFEducators are essential for societal progress, and well-educated students are pivotal for a promising future. Higher education faces challenges such as budget constraints, limited time, and a shortage of trained personnel, leading to faculty stress. Emerging technologies such as artificial intelligence (AI), machine learning (ML), and block chain provide solutions, with robotic process automation (RPA) bots a notable advanced AI subfield-automating repetitive tasks, thereby freeing teachers to focus on more essential responsibilities. RPA bots automate various educational processes, including examinations, admissions, marks updating, student record management, result compilation, human resources, resume screening, and administration. This research examines robotic automation in higher education institutions (HEIs), selecting and prioritizing RPA tasks through a survey involving subject matter experts (SMEs) from different HEIs, including professors and RPA experts. The research aims to develop a “virtual software bot” for automating “result compilation” post-examination. Using tools like XPATH, Whisper, and the web-based automation program Selenium web in Python, the bot automates this process. The ML library “Whisper” addresses the reCAPTCHA problem. The automated bot generates comma separated values (CSV) files in specific formats, completing the task 58 times faster than humans and saving 43 man-hours by compiling results for 653 students in 45 minutes
High-gain circularly polarized metasurface antenna for NR257 band millimeter-wave 5G communication
Get PDFA metasurface inspired circularly polarized (CP) compact patch antenna with high gain for fifth-generation communication systems is designed and implemented in this article. The proposed structure features a corner truncated patch antenna and a metasurface of 3×3 double sided identical circular metallic patches. The attribute that puts this design distinct is that it minimizes the impact of scattering and edge diffraction at millimeter wave frequencies. The metasurface above a patch with an air gap is designed using the similar substrate material with the same thickness, resulting in a simplified antenna design with high gain and low cost. The antenna’s overall dimension is , with a peak gain of 11.5 dBic and a 3-dB axial ratio bandwidth of 28.45 - 28.88 GHz. The simulated and experimental results show that the metasurface-inspired antenna has better impedance matching and radiation efficiency between 28.23 - 30.01 GHz. Additionally, the experimental results of the proposed antenna exhibits stable right-hand circular polarization in the desired frequency range and a flat gain response with a little variation. The proposed antenna design could be well suited for millimeter-wave communication systems, in scenarios requiring robust long-range performance and high data throughput