Articles
64 Documents
Search results for
, issue
"Vol 29, No 3: March 2023"
:
64 Documents
clear
Optimization of location and rating of unified power flow controllers for congestion management
Vengadesan Alagapuri;
Ashok Bakkiyaraj Radhakrishnan;
Sakthivel Sithangkathan;
Jayanthi Kalikrishnan
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1258-1267
Large number of contracted power exchanges among sellers and purchasers, in a deregulated power market causes transmission line congestion. Congestion of lines undermines the security and economy of power networks. Flexible AC transmission system (FACTS) devices are introduced at appropriate spots to change the power flow in order to keep the flow of the lines within their capability. In this work, the most commonly used unified power flow controller (UPFC) is proposed for achievement of changing the line flow and for easing congestion from the over loaded lines. The size and site of UPFC controllers significantly impact their performance in congestion management task. The location and size of the UPFC devices are to be optimized by using an optimization algorithm. Whale optimization algorithm (WOA) is exploited in this effort for realizing the aim of determination of site and size of the FACTS converters. The present method has lesser quantity of variables which are tuned to get best outcomes. The suggested WOA based technique is executed on the IEEE 57 bus system. The outcomes comparison is made with particle swarm optimization algorithm (PSO) and firefly algorithm (FFA) and the better improved outcomes are found.
Optimization of retinal blood vessel segmentation based on Gabor filters and particle swarm optimization
Ahmad Fauzi;
Lukmanda Evan Lubis
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1590-1596
The structure of the retinal blood vessels can be obtained by segmenting the fundus images. A fundus image can be gained through color fundus photography or fluorescein angiography (FA). The fundus image produced by the camera can cause noise which can reduce the quality of the fundus image. To reduce the noise, this research uses the non-local means filter (NLMF). For texture analysis, the study uses Gabor filters due to the frequencies of this filter as the same as the human visual system. The segmenting process of the retinal blood vessel is performed using K-means optimized by particle swarm optimization (PSO). The accuracy of 0.9525, the precision of 0.8330, the sensitivity of 0.5817, and the specificity of 0.9880 are obtained using the proposed method.
COVID-19 classification using hybrid deep learning and standard feature extraction techniques
Hassan Ahmed El Shenbary;
Ebeid Ali Ebeid;
Dumitru Baleanu
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1780-1791
There is no doubt that COVID-19 disease rapidly spread all over the world, and effected the daily lives of all of the people. Nowadays, the reverse transcription polymerase chain reaction is the most way used to detect COVID-19 infection. Due to time consumed in this method and material limitation in the hospitals, there is a need for developing a robust decision support system depending on artificial intelligence (AI) techniques to recognize the infection at an early stage from a medical images. The main contribution in this research is to develop a robust hybrid feature extraction method for recognizing the COVID-19 infection. Firstly, we train the Alexnet on the images database and extract the first feature matrix. Then we used discrete wavelet transform (DWT) and principal component analysis (PCA) to extract the second feature matrix from the same images. After that, the desired feature matrices were merged. Finally, support vector machine (SVM) was used to classify the images. Training, validating, and testing of the proposed method were performed. Experimental results gave (97.6%, 98.5%) average accuracy rate on both chest X-ray and computed tomography (CT) images databases. The proposed hybrid method outperform a lot of standard methods and deep learning neural networks like Alexnet, Googlenet and other related methods.
On image restoration problems using new conjugate gradient methods
Basim A. Hassan;
Haneen A. Alashoor
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1438-1445
The nonlinear conjugate gradient algorithm is one of the effective algorithms for optimization since it has low storage and simple structure properties. The coefficient conjugate is the basis of conjugate gradient algorithms with the desirable conjugate property. In this manuscript, we have derived a new second order information for the Hessian from objective function, which can give a new search direction. Based on new search direction, we have proposed the update formula interesting and nonlinear conjugate gradient method. Under wolfe line search and mild assumptions on objective function, the method possess sufficient descent property and are always globally convergent. Numerical results show that the method is effective and competitive to recover the original image from an image corrupted by impulse noise.
Hybrid agile development phases: the practice in software projects as performed by software engineering team
Norzariyah Yahya;
Siti Sarah Maidin
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1738-1749
The combination of scrum and waterfall is one of the software engineering teams that preferred hybrid agile models. The purpose of combining the two models is to leverage the advantages of each also to tailor the hybrid agile model to the needs of the project. However, to what extent are the phases, stages, and features of scrum and waterfall implemented in a software project remains unclear. Additionally, which phase will employ scrum, and when will waterfall be deemed optimal is also the arising question. This research adopted a qualitative study, and interviews are used as a data collection instrument. The interview is conducted based on an interview protocol, and thematic analysis is utilized to extract the themes from the interviews. This study investigates how the scrum and waterfall models are utilized in a software project, and three themes were identified in answering the research question. The findings indicate five development phases in a hybrid agile project and that waterfall is the preferable model in planning, while development is on scrum, and project testing and deployment could be either waterfall or scrum.
Prediction of movie success based on machine learning and twitter sentiment analysis using internet movie database data
Jyoti Tripathi;
Sunita Tiwari;
Anu Saini;
Sunita Kumari
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1750-1757
Nowadays, predicting the success of a new movie is a crucial task. In this work, the hybrid approach considers the movie features as well as sentiment expressed in the movie review to predict the success rate of a movie. Multiple movie features such as title, director, star cast, and writer. Are considered for prediction. The related raw data is collected from the internet movie database (IMDb) website and after pre-processing, the collected data is used to generate the supervised machine learning model. Different supervised learning models are compared and the one with the best results is used further. The mean squared error, root mean squared error and r2 score of the models generated are comparable with existing models. Further, sentiment analysis of the movie-related tweets is performed. The accuracy of best sentiment analysis model is 88.47%. Finally, the two models are combined to give the success prediction rating of new movies and the results of the hybrid model are encouraging. The proposed model may be used to find the top-rated movies of a particular calendar year.
The application of multi-layer phosphor-in-glass sheets in boosting white light emitting diodes chromaticity
Ha Thanh Tung;
Huu Phuc Dang;
Nguyen Le Thai
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1318-1325
With the use of phosphor-in-glass (abbreviated as PiG), it is possible to make alterations for the remote adjustment incorporated with a diode that generates blue light emitting diode (LED) and acquire remarkably superior light output at considerable temperatures of color compared to standard structures of LED devices. It should be noted that the imbrication of emission spectra in phosphor substances, as well as the forfeited, amount of light caused by reabsorption appear to be the primary problems stemming from the model of multi-color phosphor. The earlier study came up with the method of creating various phosphor-in-glass (PiGs) by slicing and reconstruction, which remedied certain aspects of the flaws mentioned. Practically speaking, the light amount forfeited occurs in the linking zones in the middle of the color phosphor and will be a subject of the research. We can see for certain that it is necessary to come up with a means of preparation to deal with the issues of the interfacial layer. Therefore, the low sintering of PiGs at 600 °C was considered an appropriate procedure, as it could create a double-layer PiG in a lying direction as well as a triple-layer PiG yielding superior optical efficiency when compared to equivalent versions.
Smart fuzzy logic control of photovoltaic system: case study Kingdom of Saudi Arabia
Taha A. Khalaf;
Khalid Alshahrani;
Obaid Alsubaie;
Anas Aljohani;
Waleed AlAnzi;
Mahmoud Aref
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1412-1422
Robust controls of photovoltaic (PV) system applications that include modular multilevel inverter (MMI) for interfacing stand-alone and gridconnected operating modes are investigated in this paper to overcome interfacing problems of two-level and three-level inverters. The MMI provides high-quality voltage, current, and power signals without additional filters, which reduces complexity and cost of interface circuits. A new control method of active and reactive power has been introduced for PV systems to get maximum power point (MPP) in various climatic circumstances. The steady-state and dynamic performances of MMI are investigated using MATLAB/Simulink. A fuzzy logic control is proposed to track the MPP utilizing the perturb and observe (P&O) technique. A fair comparison between fuzzy logic control and proportional integral (PI) control was conducted using MATLAB/Simulink. The fuzzy logic controller for obtaining MPPT by P&O method is proposed to get fast and accurate results. The obtained results obvioused that the fuzzy logic controller is quick accessing MPP than PI controller. A simple LC filter can achieve minimum harmonics provided by total harmonic distortion (THD) of MMI within IEEE limit. The PV system for standalone and grid-connected modes is being tested under climatic conditions in the city of Tabuk, Kingdom of Saudi Arabia (KSA).
Adaptation issues of machine learning in safety digitization
Gyana Ranjana Panigrahi;
Nalini Kanta Barpanda;
Komma Anitha;
Shanti Rathore;
Preesat Biswas;
Prabira Kumar Sethy
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1802-1808
The internet community is the only set of irreplaceable spaces in today’s world and is used by millions for knowledge acquittance via the digital exchange between the landed gentry. The torrent of available e-contents in the Internet community attracts corporates and researchers to find the factual weightage of formed data. It is high time for digital diversification, which is the objective of using various learning-based machine learning (ML) systems for hands-on fortification. The main idea is to make stylistic communication more understandable. Here, the authors try to adapt the factual weightage procedure of formed data through the Internet community using machine learning schemes. Hence, the authors have chosen to emphasize cyber security, which is not well discussed and concerned with ethical contemplation from hackers' forums amidst internet communities. There are disparities in the continual growth of connotations, acronyms, spellings, and even technical jargon, which need periodic re-learning and their prototype implications through the proposed model.
Smart power switch using internet of things
Abdulaziz Khalid Eid Abougamea;
Siow Chun Lim
Indonesian Journal of Electrical Engineering and Computer Science Vol 29, No 3: March 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v29.i3.pp1809-1816
The increase in electricity consumption coupled with the lack of a convenient way to assist the consumers to lower their electricity consumption is a growing concern. Smart internet of things (IoT)-based devices has been developed in this regard. However, no specific standards were followed, and this is a problem for the consumer as they have to own different smart device from different brands which results in higher cost. To solve these issues, a smart power switch using IoT is proposed. The system consists of microcontroller (ESP32), relay and current sensor (ACS712). The ACS712 measures the current of the appliance. The ESP32 then send these readings to server. Whenever the ESP32 receives switching commands from the cloud platform, ESP32 will activate the relay and hence switching the appliance. The cloud platform is linux based virtual private server (VPS) running on Django Python and structured query language (SQL) ite database. The mobile application built using flutter to allow both iOS and android users to use the app to control and monitor the normal appliances. The server, circuit and mobile application have showed a real-time data exchange, fast response, numerical, graphical consumption presentation and capable of setting energy or power limit for the appliance to not exceed.