cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Tole Sutikno
Contact Email
ijece@iaesjournal.com
Phone
-
Journal Mail Official
ijece@iaesjournal.com
Editorial Address
-
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
International Journal of Electrical and Computer Engineering
Published by Institute of Advanced Engineering and Science
ISSN : 20888708     EISSN : 27222578     DOI : -
Core Subject : Science, Engineering,
Computer Science & IT Electrical & Electronics Engineering
International Journal of Electrical and Computer Engineering (IJECE, ISSN: 2088-8708, a SCOPUS indexed Journal, SNIP: 1.001; SJR: 0.296; CiteScore: 0.99; SJR & CiteScore Q2 on both of the Electrical & Electronics Engineering, and Computer Science) is the official publication of the Institute of Advanced Engineering and Science (IAES). The journal is open to submission from scholars and experts in the wide areas of electrical, electronics, instrumentation, control, telecommunication and computer engineering from the global world.
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 6,301 Documents
 569   570   571   572   573 
Feature selection using non-parametric correlations and important features on recursive feature elimination for stock price prediction Priyatno, Arif Mudi; Ramadhan Sudirman, Wahyu Febri; Musridho, Raja Joko
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 2: April 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i2.pp1906-1915

Abstract

Stock price prediction using machine learning is a rapidly growing area of research. However, the large number of features that can be used can complicate the learning process. The feature selection method that can be used to overcome this problem is recursive feature elimination. Standard recursive feature elimination carries the risk of producing inaccurate algorithms because the top-ranked features are not necessarily the most important features. This research proposes a feature selection method that combines important features and nonparametric correlation in recursive feature elimination for stock price prediction. The data features used are technical indicators and stock price history. The recursive feature elimination method is modified with important features and nonparametric correlation features. The strategy for combining important features and non-parametric features is average weight, 25:75% weight, 75:25% weight, maximum weight, and minimum weight. The performance evaluation results show that the proposed feature selection method succeeded in obtaining small error values. The proposed method for predicting PT Bank Rakyat Indonesia Tbk (BBRI) stock prices obtains mean squared error, root mean square error, mean absolute error, and mean absolute percentage error evaluation values of 0.0000336, 0.00577, 0.00459, and 1.78%, respectively. This shows that recursive feature elimination with feature selection that combines important features and non-parametric correlation works better than the original recursive feature elimination at predicting stock prices.
Geographic information system-based spatio-temporal detection and mapping of COVID–19 hot/cold spots in Oman Al-Mulla, Yaseen; Al–Muqaimi, Mohammed; Ali, Ahsan; Al-Badi, Taif; Parimi, Krishna; Chowdary, Anusha
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 5: October 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i5.pp5779-5801

Abstract

Infected COVID-19 patients, especially after March 11, 2020, grew drastically in Oman. Hence, a variety of measures were issued to restrict all social gatherings, commercial activities, and mandating preventative health practices. This study aimed to i) understand distribution patterns and impact of decisions and responses at the spread of confirmed cases; ii) highlight and verify most concentrated regions with infections; and iii) overview spatial changes of cases overtime. The analysis was carried out using inverse–distance-weighted interpolation and hotspot (Getis–Ord GI*) techniques. Results showed a substantial relationship between spatial structure of COVID–19 and population distribution and density. COVID–19 has increased by 11.5% weekly in the capital, which were locked down since April 2020. However, after health quarantine was lifted on May 29, 2020, weekly cases surged in the capital. Al-Batinah-North and Dhofar recorded an increase of 32.1% and 30.5%, respectively, after restrictions had eased. The analysis illustrated that spread of COVID–19 was shifting from Northeast to Southeast and later shifted back to the Northeast of the country at the end of year 2022. This study is beneficial for pertinent organizations to perform detailed studies for developing and monitoring disease systems and dominating relevant factors.
Efficient network management and security in 5G enabled internet of things using deep learning algorithms Poojari Thippeswamy, Sowmya Naik; Raghavan, Ambika Padinjareveedu; Rajgopal, Manjunath; Sujith, Annie
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 1: February 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i1.pp1058-1070

Abstract

The rise of fifth generation (5G) networks and the proliferation of internet-of-things (IoT) devices have created new opportunities for innovation and increased connectivity. However, this growth has also brought forth several challenges related to network management and security. Based on the review of literature it has been identified that majority of existing research work are limited to either addressing the network management issue or security concerns. In this paper, the proposed work has presented an integrated framework to address both network management and security concerns in 5G internet-of-things (IoT) network using a deep learning algorithm. Firstly, a joint approach of attention mechanism and long short-term memory (LSTM) model is proposed to forecast network traffic and optimization of network resources in a, service-based and user-oriented manner. The second contribution is development of reliable network attack detection system using autoencoder mechanism. Finally, a contextual model of 5G-IoT is discussed to demonstrate the scope of the proposed models quantifying the network behavior to drive predictive decision making in network resources and attack detection with performance guarantees. The experiments are conducted with respect to various statistical error analysis and other performance indicators to assess prediction capability of both traffic forecasting and attack detection model.
Personalized diabetes diagnosis using machine learning and electronic health records S., Gowthami; Reddy, R. Venkata Siva; Ahmed, Mohammed Riyaz
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 4: August 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i4.pp4791-4801

Abstract

Diabetes mellitus (DM) poses a significant health challenge globally, necessitating accurate and timely diagnosis for effective management. Conventional diagnostic methods often struggle to address the multifaceted nature of diabetes and the requisite lifestyle adjustments. In this study, we propose a data-driven approach utilizing machine learning techniques to enhance diabetes diagnosis. By leveraging extensive patient attributes and medical records, machine learning algorithms can uncover intricate patterns and correlations. Our methodology, validated on the PIMA India dataset, demonstrates promising results. The random forest model achieved the highest accuracy of 87%, followed closely by gradient boost at 90%. Notably, XGBoost and CATBoost models attained a peak accuracy of 90.9%. These findings underscore the potential of machine learning in transforming diabetes diagnosis. Beyond improving diagnostic accuracy, our approach aims to guide individuals towards healthier lifestyles. Intelligent systems driven by machine learning hold promise for revolutionizing diabetes management, ultimately leading to better patient outcomes and more effective health care delivery.
Coffee bean graded based on deep net models Balakrishnan Jayakumari, Bipin Nair; Koovamoola Mambilamthoda, Abrav Nanda; Stephen, Shalwin Ambalamoottil; Venkitesan, Pranav; Raghavendra, Venkatesh
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 3: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i3.pp3084-3093

Abstract

Coffee is a widely consumed beverage, and sorting coffee beans is a critical process that ensures high-quality graded coffee products. Coffee beans were graded into nine grades in robusta types. To automate the grading process, a deep learning-based approach was developed using a large dataset of high-resolution images and data augmentation techniques. In contrast to previous studies focusing on robusta type graded into six coffee bean grads, our research extends this framework by employing robusta type into nine grades with an outperformed accuracy. The proposed work uses four deep learning models, namely residual network 34(Resnet34), inception version 3 (Inception v3), efficient network bayesian optimization (EfficientNet-B0), and visual geometry group-16(VGG-16), where trained and evaluated for coffee bean classification into nine grades. The EfficientNet-B0 model exhibited outperformed accuracy, achieving 100% in distinguishing good and bad coffee beans, even in challenging lighting and background conditions.
Optimal model of vehicular ad-hoc network assisted by unmanned aerial vehicles and information-centric networking to enhance network performance Houari, Abdeslam; Mazri, Tomader
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 2: April 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i2.pp1788-1796

Abstract

Vehicular ad-hoc network (VANET) is a promising project related to intelligent transportation systems (ITS), which aims at connecting vehicles and providing a set of functionalities for the efficient management of the network. However, the high mobility of the network nodes is considered a significant challenge for implementing a reliable, secure, and efficient exchange system. Furthermore, VANET faces the issue of packet delivery due to the high mobility of the nodes and packet collisions complicate the process of sending and receiving packets. We propose to combine two technologies which are unmanned aerial vehicle (UAV) and information centric networks (ICN) and apply it in VANET architecture as supporting technology. The UAV are more reliable and less affected by channel fading. And can be used in areas where we cannot install network infrastructure. The UAV has many advantages that we have cited in this article and can solve many issues of VANET. Using ICN can solve some of the problems of VANET since ICN has many strategies to capture and retrieve data. This study proposes a new VANET model based on an UAV and ICN, to reduce the overload of the vehicles, which in most cases require more resources and have a limited time to process and act especially in case of an accident or emergency.
Investigation of auto-oscilational regimes of the system by dynamic nonlinearities Siddikov, Isamidin; Khalmatov, Davronbek; Alimova, Gulchekhra; Khujanazarov, Ulugbek; Feruzaxon, Sadikova; Usanov, Mustafaqul
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 1: February 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i1.pp230-238

Abstract

The paper proposes a method for the analysis and synthesis of self-oscillations in the form of a finite, predetermined number of terms of the Fourier series in systems reduced to single-loop, with one element having a nonlinear static characteristic of an arbitrary shape and a dynamic part, which is the sum of the products of coordinates and their derivatives. In this case, the nonlinearity is divided into two parts: static and dynamic nonlinearity. The solution to the problem under consideration consists of two parts. First, the parameters of self-oscillations are determined, and then the parameters of the nonlinear dynamic part of the system are synthesized. When implementing this procedure, the calculation time depends on the number of harmonics considered in the first approximation, so it is recommended to choose the minimum number of them in calculations. An algorithm for determining the self-oscillating mode of a control system with elements that have dynamic nonlinearity is proposed. The developed method for calculating self-oscillations is suitable for solving various synthesis problems. The generated system of equations can be used to synthesize the parameters of both linear and nonlinear parts. The advantage is its versatility.
Comparison of proposed electricity billing mechanism for residential clients of Maharashtra Belge, Archana Talhar; Bodkhe, Sanjay; Alegavi, Sujata; Ravankar, Arpit; Kasturiwale, Hemant; Ranjan, Alok
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 5: October 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i5.pp4815-4826

Abstract

The comparison of three modified electricity billing mechanisms (model I, model II, and model III) for low tension (LT-I) residential consumers of Maharashtra, India, is presented in this paper. Models I and II are presented in detail along with the results in the previous version of this paper in the year 2020 and year 2022. In continuation of this work, model III is presented in this paper in the year 2023. The main components of this mechanism are traditional billing, time-of-day billing, and an optional facility to use renewable energy by implementing net metering. The combination of these elements generates three distinct billing mechanisms. These have several advantages, like the profits of the existing mechanism, renewable integration, grid stability, demand management, cost saving, environmental benefits, and customer empowerment. The projected billing mechanism is developed and implemented in MATLAB software, and a real-time application is created. The comparison between these three mechanisms helps in giving the best mechanism with respect to residential consumers. Lastly, the philosophy for the future extension to this work is presented which is based on the concept of overseas billing mechanism i.e., seasonal time of day tariff of Sacramento Municipal Utility District and Arizona Public Service.
Advanced particle swarm optimization for efficient and fast global maximum power point tracking under partial shading conditions El Moujahid, Yassine; El Harfaoui, Nadia; Hadjoudja, Abdelkader; Benlafkih, Abdessamad
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 4: August 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i4.pp3570-3579

Abstract

Partial shading (PS) is a common issue in photovoltaic systems (PVs), and it can significantly reduce the system's output power. This paper presents the advanced particle swarm optimization (APSO) algorithm. APSO is designed to alleviate the challenges posed by PS in PVs in from where of effectiveness and stability speed so that it works to achieve and maintain the global maximum power point (GMPP) under PS conditions. It leverages persistent variables to store and track system states and iterations; it also includes checks to ensure that the duty cycle remains within specified bounds facilitating more effective optimization. Additionally, APSO optimizes solar panel duty cycles and velocities to converge toward an optimal solution to improve overall power generation efficiency and settling time. The results evaluation involves testing the performance of photovoltaic panels under three different shading scenarios and comparative analysis against recent Heuristic-optimization-based GMPP techniques, this study and comparative analyses demonstrate APSO's effectiveness and superiority in terms of high efficiency that reaches 99.85% and fast settling time of GMPP at less than 0.01 second across all test cases. APSO presents a promising solution for maximizing PV power output in the presence of partial shading.
Detecting and resolving feature envy through automated machine learning and move method refactoring Al-Fraihat, Dimah; Sharrab, Yousef; Al-Ghuwairi, Abdel-Rahman; AlElaimat, Majed; Alzaidi, Maram
International Journal of Electrical and Computer Engineering (IJECE) Vol 14, No 2: April 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v14i2.pp2330-2343

Abstract

Efficiently identifying and resolving code smells enhances software project quality. This paper presents a novel solution, utilizing automated machine learning (AutoML) techniques, to detect code smells and apply move method refactoring. By evaluating code metrics before and after refactoring, we assessed its impact on coupling, complexity, and cohesion. Key contributions of this research include a unique dataset for code smell classification and the development of models using AutoGluon for optimal performance. Furthermore, the study identifies the top 20 influential features in classifying feature envy, a well-known code smell, stemming from excessive reliance on external classes. We also explored how move method refactoring addresses feature envy, revealing reduced coupling and complexity, and improved cohesion, ultimately enhancing code quality. In summary, this research offers an empirical, data-driven approach, integrating AutoML and move method refactoring to optimize software project quality. Insights gained shed light on the benefits of refactoring on code quality and the significance of specific features in detecting feature envy. Future research can expand to explore additional refactoring techniques and a broader range of code metrics, advancing software engineering practices and standards.

Page 571 of 631 | Total Record : 6301

 569   570   571   572   573 

Filter by Year

2011 2026


Reset
Filter By Issues
All Issue Vol 16, No 1: February 2026 Vol 15, No 6: December 2025 Vol 15, No 5: October 2025 Vol 15, No 4: August 2025 Vol 15, No 3: June 2025 Vol 15, No 2: April 2025 Vol 15, No 1: February 2025 Vol 14, No 6: December 2024 Vol 14, No 5: October 2024 Vol 14, No 4: August 2024 Vol 14, No 3: June 2024 Vol 14, No 2: April 2024 Vol 14, No 1: February 2024 Vol 13, No 6: December 2023 Vol 13, No 5: October 2023 Vol 13, No 4: August 2023 Vol 13, No 3: June 2023 Vol 13, No 2: April 2023 Vol 13, No 1: February 2023 Vol 12, No 6: December 2022 Vol 12, No 5: October 2022 Vol 12, No 4: August 2022 Vol 12, No 3: June 2022 Vol 12, No 2: April 2022 Vol 12, No 1: February 2022 Vol 11, No 6: December 2021 Vol 11, No 5: October 2021 Vol 11, No 4: August 2021 Vol 11, No 3: June 2021 Vol 11, No 2: April 2021 Vol 11, No 1: February 2021 Vol 10, No 6: December 2020 Vol 10, No 5: October 2020 Vol 10, No 4: August 2020 Vol 10, No 3: June 2020 Vol 10, No 2: April 2020 Vol 10, No 1: February 2020 Vol 9, No 6: December 2019 Vol 9, No 5: October 2019 Vol 9, No 4: August 2019 Vol 9, No 3: June 2019 Vol 9, No 2: April 2019 Vol 9, No 1: February 2019 Vol 8, No 6: December 2018 Vol 8, No 5: October 2018 Vol 8, No 4: August 2018 Vol 8, No 3: June 2018 Vol 8, No 2: April 2018 Vol 8, No 1: February 2018 Vol 7, No 6: December 2017 Vol 7, No 5: October 2017 Vol 7, No 4: August 2017 Vol 7, No 3: June 2017 Vol 7, No 2: April 2017 Vol 7, No 1: February 2017 Vol 6, No 6: December 2016 Vol 6, No 5: October 2016 Vol 6, No 4: August 2016 Vol 6, No 3: June 2016 Vol 6, No 2: April 2016 Vol 6, No 1: February 2016 Vol 5, No 6: December 2015 Vol 5, No 5: October 2015 Vol 5, No 4: August 2015 Vol 5, No 3: June 2015 Vol 5, No 2: April 2015 Vol 5, No 1: February 2015 Vol 4, No 6: December 2014 Vol 4, No 5: October 2014 Vol 4, No 4: August 2014 Vol 4, No 3: June 2014 Vol 4, No 2: April 2014 Vol 4, No 1: February 2014 Vol 3, No 6: December 2013 Vol 3, No 5: October 2013 Vol 3, No 4: August 2013 Vol 3, No 3: June 2013 Vol 3, No 2: April 2013 Vol 3, No 1: February 2013 Vol 2, No 6: December 2012 Vol 2, No 5: October 2012 Vol 2, No 4: August 2012 Vol 2, No 3: June 2012 Vol 2, No 2: April 2012 Vol 2, No 1: February 2012 Vol 1, No 2: December 2011 Vol 1, No 1: September 2011 More Issue