Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Design and simulation of a double boost switched capacitor multilevel inverter
Get PDFThis article presents an innovative boost inverter configuration that produces a nine-level double voltage augmentation waveform. A significant drawback of conventional multilevel inverters (MLIs) lies in their dependence on conversion for elevating the voltage, particularly applied in conjunction with renewable energy sources. The proposed methodology, characterized by its double voltage boosting capacity, mitigates this challenge by automatically enhancing the input voltage. Switched-capacitor multilevel inverters (SCMLIs) represent a prevalent category within the realm of MLIs. This paper presents a double boost switched capacitor inverter (DB-SCI) designed to address critical issues involving the increased use of semiconductor switches, DC sources, and capacitors. The proposed DB-SCI achieves a nine-level resultant voltage utilizing a single DC source, 8 switches, and 3 capacitors. It can amplify the output voltage with a gain of two. Moreover, the DB-SCI employs a level-shifted pulse width modulation (PWM) approach to augment the resultant voltage and enhance the output voltage's quality. The article assesses the effectiveness and feasibility of the DB-SCI under various modulation indices using MATLAB/Simulink. The comparison study of MLI topologies is presented
Performance evaluation of distribution network with change of load by connecting wind DG
Get PDFThe aim of this research is to determine the optimal location and size of a minimum number of distributed generators (DGs) needed to maintain the stable operation of an IEEE 85-bus distributed network. The main objective is to ensure the stability of the distribution network by optimizing the placement and capacity of DGs. This is accomplished through the utilization of particle swarm optimization (PSO). The stability of the distribution network is checked by evaluating the voltages and power losses using load flow. The stability of the distribution network is assessed using boundary criteria that are not altered by more than 5% of the nominal voltage value. The distribution network voltage stability is assessed using various case studies, one of that involves a change in load driven by connecting WDG and the other by a change in power supply from wind DGs due to varying wind speed. The PSO is implemented in IEEE-85 bus distribution network using MATLAB software
Identification and segmentation of tumor using deep learning and image segmentation algorithms
Get PDFBrain tumor is a typical mass of tissue that develops when cells proliferate and divide excessively. Brain tumor perception requires a great deal of work and experience from the medical professional in order to identify the tumor's precise location. If a brain tumor is not discovered in a timely manner, it affects a person's ability to function normally and raises the death rate. This study focuses on tumor segmentation and tumor detection using magnetic resonance imaging (MRI) images. This work helps the medical professional to precisely identify the tumor location and segmentation process provides cost effective data storage. The YOLOv8s model is utilized for tumor identification, while the image segmentation technique is employed for tumor segmentation. The images come from an open-source dataset used for research, and Roboflow 100 transforms them into .yaml files that are congenial with YOLOv8s. To train the model the dataset is split into training, validation and testing. Proposed model consist of dataset which comprises 639 images, of which 453 are utilized for training, 122 for validation, and 64 for testing, resulting in a ratio of 71:19:10. The dataset is subjected to preprocessing and augmentation. The suggested model performance is assessed depending on the parameters like precision, recall, mAP50 and mAP50-95
DigiScope: IoT-enhanced deep learning for skin cancer prognosis
Get PDFIn dermatology, early identification and intervention are crucial for optimizing patient outcomes in skin cancer care. Recent technological advances, particularly in the internet of things (IoT), have led to significant growth in telemedicine. This study introduces a cutting-edge system that proactively predicts the emergence of skin cancer by combining deep learning algorithms, IoT devices, and sophisticated medical imaging techniques. The experimental setup leverages a high-resolution mobile camera for dermoscopy, associated with a cloud-integrated machine learning framework. The proposed algorithm comprehensively examines lesion characteristics, Utilizing color, texture, and shape characteristics to evaluate the probability of malignancy. Subsequently, a cloud-hosted machine learning model analyzes and scrutinizes the collected data, yielding a thorough diagnostic evaluation. Initial results reveal that this system achieves an impressive predictive accuracy rate exceeding 97.6%, enabling swift and efficient skin cancer detection. These promising findings emphasize the potential for rapid, efficient, and proactive diagnosis, significantly improving patient prognosis and reinforcing the value of telemedicine in contemporary healthcare
Analyzing and clustering students admission data in Yala Rajabhat University Thailand
Get PDFThis research explores the use of clustering techniques to analyze student admission data at Yala Rajabhat University, Thailand, aiming to enhance recruitment strategies and understand student profiles. Employing K-means, Hierarchical Clustering, and Density-based spatial clustering of applications with noise (DBSCAN), the study groups admission data based on factors like educational institution, geographic location, and program chosen. The methodology incorporates normalization and principal component analysis (PCA) to ensure data quality, while the Elbow Method determines the optimal number of clusters for effective data segmentation. The davies-bouldin index (DBI) evaluates the clustering configurations, ensuring that clusters are well-separated and cohesive. The results reveal distinct student profiles that can inform targeted marketing and improve recruitment strategies. This study not only provides strategic insights into student recruitment but also contributes to the literature on the use of data science in educational settings, highlighting the transformative impact of advanced analytics on institutional effectiveness. The research emphasizes the importance of data-driven approaches in adapting to the changing dynamics of student admissions and the competitive landscape of higher education
Enhancing Qur'anic recitation through machine learning: a predictive approach to Tajweed optimization
Get PDFThe human voice is a powerful medium for conveying emotion, identity, and intellect. Arabic, as the language of the Qur'an, holds deep spiritual and linguistic importance. Reciting the Qur'an correctly involves following Tajweed rules, which ensure phonetic precision and aesthetic quality. However, mastering these rules is challenging due to complex pronunciation and articulation variations, often requiring expert guidance. Traditional learning methods lack personalized feedback, making it difficult for learners to identify and correct errors. With the rise of machine learning, new opportunities have emerged to support Qur’anic recitation through intelligent analysis of Tajweed patterns and error prediction. This study presents a predictive model that identifies Qur’an reciters using ensemble learning techniques. By incorporating deep learning models like gated recurrent units (GRUs), long short-term memory (LSTM), and recurrent neural network (RNN), the system effectively captures the vocal features unique to each reciter. The model achieves an accuracy rate of 88.57%, demonstrating its potential to support Qur’anic learning and preservation. Nonetheless, its performance may be affected by audio quality and limited training data diversity. To improve adaptability and robustness, future work will focus on enriching the dataset and optimizing the model to generalize better across a broader range of reciters
CriteriaChecker: a knowledge graph approach to enhance integrity and ethics in academic publication
Get PDFAcademic writing is an integral part of scientific communities. This is a formal style of writing used by researchers and scholars to communicate critical analysis and evidence based arguments. This work showcased a graph-based approach for scraping, extracting, representing and evaluating the available academic writing forgery detection criteria and further enhancing the model by proposing a set of new age criteria. The proposed work is based on knowledge graphs and graph analytics capable of selecting subset of 16 criteria from the available superset of a cent of criterias provided by Bealls, Cabells, Shreshtha, and Think.Check.Submit, Scopus, and other relevant authors. The process for detecting the influencial parameters consists of 04 phases: dataset preparation, knowledge graph representation and making inferences through graph analytics and evaluation of results. The experimental results are then compared to the retraction database that consisting of information about retracted articles. The work enables the construction of an experiential knowledge graph that effectively identifies influential criteria, enhancing this list by incorporating new age criteria into current influential set and concluding in result by successfully detecting the academic predatory behavior
Extended Kalman filter based unconstrained model predictive control of a complex nonlinear system: the quadruple tank process
Get PDFThis paper proposes the model predictive controller (MPC) based on the Kalman filter for a complicated nonlinear system—the quadruple tank process (QTP). The control of a multivariable and nonlinear system like a QTP is a difficult job. A number of nonlinear design techniques are implemented to ameliorate the pursuit performance of the QTP, however, the nonlinear techniques make implementation composite and computationally unsuitable. In this work, an unconstrained MPC is planed for the QTP experiences and it is controlled for both minimum and non-minimum sentence configurations in order to follow the wanted track. Its performance can be damaged once system is pass from minimum to non-minimum phase region and inversely. The unknown states required for model predictive control design are rebuilt using an extended Kalman filter. The design of model predictive control and extended Kalman filter is based on the QTP and the achievement of the proposed controller is checked for the monitoring of references. All results of simulation are affected using the MATLAB software. The results of the simulation show the capability and power of the suggested controller in respect of monitoring the trajectory and state estimation
Date fruit classification using CNN and stacking model
Get PDFIn North Africa and the Middle East, the date is the most popular fruit, with millions of tons harvested annually. They are a crucial component of the diet due to their exceptional content of essential vitamins and minerals, which confer a high nutritional value. The ability to accurately identify and differentiate between date varieties is therefore of paramount importance in agriculture. It is crucial for improving agricultural practices, ensuring harvest quality, and contributing to the economic development of date-producing regions. In this paper, we propose a hybrid method for classifying date fruit varieties based on two stages. In the first stage, we select the two best-performing pre-trained models from six experimented deep learning models, and we concatenate the feature maps extracted from these two models. In the second stage, we apply different classification methods, including artificial neural networks (ANN), support vector machines (SVM), and logistic regression (LR). The performance achieved by these methods is 97.22%, 98.46%, and 99.07%, respectively. Then, with the stacking model, we combined these methods, and the performance result was increased to 99.38%. This result demonstrates the effectiveness of the hybrid model for identifying date fruit varieties
Phasor measurement unit optimization in smart grids using artificial neural network
Get PDFThe wide area measurements systems (WAMS) play a vital role in the operation of smart grids. The phasor measurement units (PMU) or synchrophasors are one of the principle components under WAMS. PMU in a smart grid converts power system signals into phasor from voltage and current which enhances the observability of the power system. A variety of operations is performed by the PMUs such as adaptive relaying, instability prediction, state estimation, improved control, fault and disturbance recording, transmission and generation modeling verification, wide area protection and detection of fault location. The PMUs can improve the performance of grid operations and monitoring. Thus, PMU optimization is very necessary to achieve the desired power system observability. The performance of the PMUs can be optimized using artificial intelligence (AI) technologies. The novice method of monitoring maximum power transfer using PMUs equipped with artificial neural networks has been discussed in this paper. In this paper, a two-bus system model is developed that can be generalized to multiple bus systems. The proposed method is novel, simple, feasible, and cost effective for smart grids