Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

25,002 Article Results

A novel global maximum power point tracking based on flamingo search algorithm for photovoltaic systems

10.11591/ijece.v15i1.pp1015-1026
Abdelghani Draoui , Ahmed Saidi , Boumediene Allaoua , Abdrabbi Bourezg
Due to the high dependency of photovoltaic (PV) solar cell’s output on solar irradiance and, the ambient temperature. Maximum power point tracking (MPPT) algorithms are used extensively to operate the system at its full potentials. Moreover, being installed in outdoor spaces, PV modules are inevitably subjected to partial shading conditions, where different parts of the system are receiving different amounts of solar irradiance. In case of occurrence of partial shading conditions on a PV module that is equipped with bypass diodes, the power-voltage (P-V) curve will have multiple peaks. This multi-peak curve requires using an advanced algorithm which track the global maximum power point (GMPP) instead of being deceived and trapped in a local maximum power point. In this paper, the flamingo search algorithm (FSA) is adapted for GMPP tracking for a PV system under partial shading conditions. The FSA algorithm fetch for the GMPP by reading the PV panel power and setting accordingly the duty cycle of the buck converter. To investigate model validity, simulation is performed using the MATLAB/Simulink platform and results demonstrate good tracking performance and fast response that prove the robustness of the system against rapid variations in solar irradiance levels.
Volume: 15
Issue: 1
Page: 1015-1026
Publish at: 2025-02-01

Seasonal auto-regressive integrated moving average with bidirectional long short-term memory for coconut yield prediction

10.11591/ijece.v15i1.pp783-791
Niranjan Shadaksharappa Jayanna , Raviprakash Madenur Lingaraju
Crop yield prediction helps farmers make informed decisions regarding the optimal timing for crop cultivation, taking into account environmental factors to enhance predictive accuracy and maximize yields. The existing methods require a massive amount of data, which is complex to acquire. To overcome this issue, this paper proposed a seasonal auto-regressive integrated moving average-bidirectional long short-term memory (SARIMA-BiLSTM) for coconut yield prediction. The collected dataset is preprocessed through a label encoder and min-max normalization is employed to change non-numeric features into numerical features and enhance model performance. The preprocessed features are selected through an adaptive strategy-based whale optimization algorithm (AS-WOA) to avoid local optima issues. Then, the selected features are given to the SARIMA-BiLSTM to predict the coconut yields. The proposed SARIMA-BiLSTM is adaptable to handling a widespread of various seasonal patterns and captures spatial features. The SARIMA-BiLSTM performance is estimated through the coefficient of determination (R2), mean absolute error (MAE), mean squared error (MSE), and root mean square error (RMSE). SARIMA-BiLSTM attains 0.84 of R2, 0.056 of MAE, 0.081 of MSE, and 0.907 of RMSE which is better when compared to existing techniques like multilayer stacked ensemble, convolutional neural network and deep neural network (CNN-DNN) and autoregressive moving average (ARIMA).
Volume: 15
Issue: 1
Page: 783-791
Publish at: 2025-02-01

Human motion classification by micro-doppler radar using intelligent algorithms

10.11591/ijece.v15i1.pp455-466
Andres Felipe Arias Ballen , Edith Paola Estupiñan Cuesta , Juan Carlos Martinez Quintero
This article introduces a technique for detecting four human movements using micro-doppler radar and intelligent algorithms. Micro-doppler radar exhibits the capability to detect and measure object movements with intricate detail, even capturing complex or non-rigid motions, while accurately identifying direction, velocity, and motion patterns. The application of intelligent algorithms enhances detection efficiency and reduces false alarms by discerning subtle movement patterns, thereby facilitating more accurate detection and a deeper understanding of observed object dynamics. A continuous wave radar setup was implemented utilizing a spectrum analyzer and radio frequency (RF) generator capturing signals in a spectrogram centered at 2,395 MHz. Six models were assessed for image classification: VGG-16, VGG-19, MobileNet, MobileNet V2, Xception, and Inception V3. A dataset comprising 500 images depicting four movements-running, walking, arm raising, and jumping-was curated. Our findings reveal that the most optimal architecture in terms of training time, accuracy, and loss is VGG-16, achieving an accuracy of 96%. Furthermore, precision values of 96%, 100%, and 98% were obtained for the movements of walking, running, and arm raising, respectively. Notably, VGG-16 exhibited a training loss of 4.191E-04, attributed to the utilization of the Adam optimizer with a learning rate of 0.001 over 15 epochs and a batch size of 32.
Volume: 15
Issue: 1
Page: 455-466
Publish at: 2025-02-01

Innovative power sharing and secondary controls for meshed microgrids

10.11591/ijece.v15i1.pp99-113
Youssef Amine Ait Ben Hassi , Youssef Hennane , Abdelmajid Berdai
In alternating current (AC) microgrids, the prevalent approach for controlling the power distribution between generators and loads is droop control. This decentralized technique ensures accurate power sharing; however, its utility is restricted by significant drawbacks. Notably, in scenarios involving dissimilar power sources, mismatched impedance lines, or meshed microgrids, conventional droop control fails to ensure effective reactive power sharing among inverters, often leading to notable circulating currents. Hence, the primary objective of this paper is twofold: firstly, to examine limitations inherent to conventional droop control; secondly, to introduce a robust power-sharing methodology for AC microgrids. This novel approach is specifically designed to achieve consistent sharing of active and reactive power across meshed topology microgrids. The technique considers the presence of distributed power loads and the dynamic nature of the topology. Despite the attainment of satisfactory active and reactive power sharing, deviations in voltage and frequency occasionally manifest. To address this issue, a supplementary control mechanism is proposed as a third phase. This secondary control method focuses on reinstating the microgrid's voltage and frequency to rated values, all while upholding the precision of power sharing. The efficacy of this multi-stage methodology is rigorously validated through simulations using MATLAB/Simulink and practical experimentations.
Volume: 15
Issue: 1
Page: 99-113
Publish at: 2025-02-01

Intellectual mapping of the sign language role in deaf education: forecasting future reforms

10.11591/ijere.v14i1.28265
Rona Almos , Alies Poetri Lintangsari , Herry Nur Hidayat
Over the five decades, debatable approaches on deaf education are tangled in the issues of oralism and manualism. The later has valued sign language as the significant factor in the effort of providing quality deaf education. This research aims at mapping the intellectual reports on sign language position in deaf education from 1972 until 2023 including 1,000 documents from Web of Science database. This research use VOS Viewer by implementing co-citation analysis, bibliographic coupling and co-occurrence analysis to see the development of the research, the network and the emerging topical focus. The results suggest that sign language plays the pivotal role in deaf education that predict the future reforms of education for the deaf in form of bilingual education and technology integration. Other significances related to the top discussed themes, the leading authors, the influential publishers are also discussed to seek the interweaving connection among the subemergent research foci.
Volume: 14
Issue: 1
Page: 146-156
Publish at: 2025-02-01

Factors affecting environmental ethics behavior of undergraduate students

10.11591/ijere.v14i1.28443
Junkaew Likhit , Wongchantra Prayoon , Ongon Suparat , Sookngam Kannika , Uraiwan Praimee
The research aimed to investigate the variables affecting undergraduate students’ environmental ethical conduct as well as the variables influencing the environmental ethical behavior of undergraduate students of various genders and academic years. In the topic of environmental education, year 1-4 pupils made up the research sample. A total of 231 people from Mahasarakham University’s Faculty of Environment and Resource Studies freely provided information. A survey was used as the research method to assess the variables influencing undergraduate students’ ethical conduct in the environment. Frequency, percentage, mean, standard deviation, and one-way ANOVA testing of hypotheses are the statistics used for the study. The factors affecting the undergraduate students’ overall environmental ethical behavior were found to be at the highest level, equal to 4.04. After examining each item, it was found that serving the public and keeping promises was equal to 4.86, followed by upholding universal ideals (¯x=4.22), a factor that involves avoiding punishment. fear of criminal and disciplinary penalty (¯x=4.11), conformity factor (¯x=4.02), reward-seeking factor (¯x=3.97), social responsibility compliance factor (¯x=3.74), and personal qualities (¯x=3.41) were the factors that had the smallest effect on the student’s environmental ethical behavior, in that order. At the 05 levels, several factors influenced learners of different genders’ environmental ethical behavior, and various factors affected the environmental.
Volume: 14
Issue: 1
Page: 557-565
Publish at: 2025-02-01

Pyramidal microwave absorbers: leveraging ceramic materials for improved electromagnetic interference shielding

10.11591/ijece.v15i1.pp435-447
Nur Shafikah Rosli , Hasnain Abdullah , Linda Mohd Kasim , Samihah Abdullah , Mohd Nasir Taib , Shafaq Mardhiyana Mohamat Kasim , Norhayati Mohd Noor , Azizah Ahmad
This study presents the development and optimization of pyramidal microwave absorbers designed for efficient electromagnetic interference (EMI) reduction in anechoic chambers. Based on prior research, this work transitions from conventional flat cement-carbon absorbers to a novel pyramidal design, incorporating silicon carbide (SiC) as ceramic materials. Introducing ceramic materials into the cement-carbon composite aims to enhance absorption across a broader frequency range while maintaining structural integrity. The study evaluates five sets of pyramidal absorbers with varying SiC content within the 1–12 GHz frequency range. Reflectivity performance was assessed using the naval research laboratory (NRL) Arch free space method at a 0° incidence angle. Among the tested absorbers, the set containing 10% SiC demonstrated superior performance, achieving minimum and maximum reflectivity values of -26.6215 and -55.2752 dB, respectively, particularly in the C-band. The findings highlight the significant impact of material composition and porosity on the absorber's effectiveness, providing valuable insights for the future design of high-performance EMI absorbers.
Volume: 15
Issue: 1
Page: 435-447
Publish at: 2025-02-01

Comparison of machine learning algorithms to identify and prevent low back injury

10.11591/ijece.v15i1.pp894-907
Christian Ovalle Paulino , Jorge Huamani Correa
With the advancement of technology, remote work and virtual classes have become increasingly common, leading to prolonged periods in front of computers and, consequently, to discomfort and even lower back pain. This study compares machine learning algorithms to identify and prevent low back pain, a common health problem. A predictive model for early diagnosis and prevention of these injuries was developed using datasets from open data repositories. Six machine learning models were used to train the data. Results showed that logistic regression was the most effective model, with performance curves of 70%, 90%, and 99%. Performance metrics indicated 86% accuracy, 85% recall, and 86% F1-score. Accuracy of 70%, recall of 71%, and F1-score of 63% reflect the robust ability of the model to address the problem. In addition, an intuitive interface was implemented using Gradio Software to improve data visualization.
Volume: 15
Issue: 1
Page: 894-907
Publish at: 2025-02-01

Higher order thinking skills research trends: a bibliometric analysis in selected journals (2014 to 2023)

10.11591/ijere.v14i1.29590
Lilis Lismaya , Hartono Hartono , Bambang Subali , Woro Sumarni , Saiful Ridlo , Murbangun Nuswowati
This article aims to analyze the trend of higher order thinking skills (HOTS) research in selected journals, namely Journal of Research in Science Teaching (JRST), International Journal of Science Education (IJSE) and Review of Educational Research (RER) through bibliometrics on the Scopus database from 2014 to 2023. The articles consist of a total of 947, then divided into 333 articles analyzed, with details of JRST 113 articles, IJSE 130 articles and RER 90 articles. The method used in this research is article analysis using bibliometric stages, followed by keyword search, initial search results, correction of search results, initial data compilation and data analysis. The results showed that the publication of scientific articles in selected journals on HOTS varied from year to year. The results of this study are expected to help other researchers who are interested in reviewing and researching research trends related to HOTS in selected journals and to recommend further research directions.
Volume: 14
Issue: 1
Page: 695-707
Publish at: 2025-02-01

Bitcoin volatility forecasting: a comparative analysis of conventional econometric models with deep learning models

10.11591/ijece.v15i1.pp614-623
Nrusingha Tripathy , Debahuti Mishra , Sarbeswara Hota , Sashikala Mishra , Gobinda Chandra Das , Sasanka Sekhar Dalai , Subrat Kumar Nayak
The behavior of the Bitcoin market is dynamic and erratic, impacted by a range of elements including news developments and investor mood. One well-known aspect of bitcoin is its extreme volatility. This study uses both conventional econometric techniques and deep learning algorithms to anticipate the volatility of Bitcoin returns. The research is based on historical Bitcoin price data spanning October 2014 to February 2022, which was obtained using the Yahoo Finance API. In this work, we contrast the efficacy of generalized autoregressive conditional heteroskedasticity (GARCH) and threshold ARCH (TARCH) models with long short-term memory (LSTM), bidirectional LSTM (Bi-LSTM), and multivariate Bi-LSTM models. Model effectiveness is evaluated by means of root mean squared error (RMSE) and root mean squared percentage error (RMSPE) scores. The multivariate Bi-LSTM model emerges as mostly effective, achieving an RMSE score of 0.0425 and an RMSPE score of 0.1106. This comparative scrutiny contributes to understanding the dynamics of Bitcoin volatility prediction, offering insights that can inform investment strategies and risk management practices in this quickly changing environment of finance.
Volume: 15
Issue: 1
Page: 614-623
Publish at: 2025-02-01

Analytic hierarchy process geographic information system based model for sustainable construction and demolition waste landfill site selection

10.11591/ijece.v15i1.pp803-816
Mohamed Ayet Allah Bilel Soussi , Nermine El Madsia , Chamseddine Zaki , Alaaeddine Ramadan , Louai Saker , Moustafa Ibrahim
Properly managing waste generated by buildings and public works is a significant challenge in Tunisia, particularly in the city of Bizerte. The inadequate disposal of such waste can cause substantial harm to human life, property, and the environment. This paper proposes an multi-criteria decision making (MCDM) that utilizes the analytic hierarchy process (AHP) decision support tool to identify suitable landfill sites for construction and demolition waste (CDW) in Bizerte. The AHP method is widely used in MCDM applications. The approach involves classifying different scenarios based on various exclusion and appreciation criteria to determine the optimal locations for future landfills. Furthermore, the paper develops a conceptual approach for identifying better sites for the disposal of CDW, resulting in a comprehensive database capable of storing, accessing, and extracting information at both conceptual and operational levels. The proposed model considers spatial, technical, and environmental criteria in the selection of a suitable landfill site. The proposed methodology offers an effective and practical solution for properly managing CDW waste in Bizerte, Tunisia, and can be applied to other regions facing similar challenges.
Volume: 15
Issue: 1
Page: 803-816
Publish at: 2025-02-01

Hybrid optimization algorithm for analysis of influence propagation in social network

10.11591/ijece.v15i1.pp624-634
Akshata Sandeep Bhayyar , Kiran Purushotham
Influence maximization(IM) is defined as the problem of identifying a node subset in a social network which increases the spread of influence. IM plays a crucial role in social networks by catalyzing the dissemination of influence, resulting in an augmented count of influenced nodes following the propagation process. The existing researches mainly concentrated on increasing the spread of influence, but did not consider the running time of the network. In this manuscript, the salp swarm algorithm (SSA) and bi-adaptive strategy particle swarm optimization (BiAS-PSO) algorithms are integrated and named as SS-BiAS-PSO algorithm to increase the spread of influence based on the IM problem to minimize the running time of the network. The datasets utilized for the research are Ego-Facebook, Epinions, Gowalla, and HepTh, while linear threshold (LT) is utilized as a diffusion method. Then, the proposed SS-BiAS-PSO algorithm is deployed for the analysis of influence propagation. The proposed algorithm reaches a high influence spread of 645, 680, 715, and 750 with less running times respectively for 10, 20, 30, and 40 seed set sizes in Ego-Facebook. The proposed algorithm proves more effective than the existing techniques like traditional SSA and particle swarm optimization (PSO).
Volume: 15
Issue: 1
Page: 624-634
Publish at: 2025-02-01

Negative-sequence current filter based on inductance coils

10.11591/ijece.v15i1.pp24-35
Mark Kletsel , Bauyrzhan Mashrapov , Rizagul Mashrapova , Alexandr Kislov
The construction of new relay protection systems without the use of current transformers is a fundamental problem of electro energetics, which has not yet been solved. This works suggests a negative-sequence current filter which receives information from inductance coils (ICs) mounted at a safe distance in the magnetic field of phase currents. This filter does not require current transformers, thus saving high-quality copper, steel, and expensive high-voltage insulation in amount unprecedented for relay protection (a 6 to 110 kV current transformer has 19 to 480 kg in weight). A circuit (including functional diagnostics) and a technique for selecting the parameters of filter components and the points where ICs should be fixed are presented; a structure for IC fastening is described. Computer simulation and experiment were used for data collection. The data show that i) the filter conversion coefficient m= 1.6, and imbalance increases by 7% at the network frequency f= 48–52 Hz; ii) protections based on this filter should have a time delay; iii) the filter is not inferior to well-known well-tested filters with current transformers; and iv) it is functional, but can only be used for single-standing electrical installations.
Volume: 15
Issue: 1
Page: 24-35
Publish at: 2025-02-01

Hybrid long short-term memory and decision tree model for optimizing patient volume predictions in emergency departments

10.11591/ijece.v15i1.pp669-676
Ahmed Abatal , Mourad Mzili , Zakaria Benlalia , Hajar Khallouki , Toufik Mzili , Mohammed El Kaim Billah , Laith Abualigah
In this study, we address critical operational inefficiencies in emergency departments (EDs) by developing a hybrid predictive model that integrates long short-term memory (LSTM) networks with decision trees (DT). This model significantly enhances the prediction of patient volumes, a key factor in reducing wait times, optimizing resource allocation, and improving overall service quality in hospitals. By accurately forecasting the number of incoming patients, our model facilitates the efficient distribution of both human and material resources, tailored specifically to anticipated demand. Furthermore, this predictive accuracy ensures that EDs can maintain high service standards even during peak times, ultimately leading to better patient outcomes and more effective use of healthcare facilities. This paper demonstrates how advanced data analytics can be leveraged to solve some of the most pressing challenges faced by emergency medical services today.
Volume: 15
Issue: 1
Page: 669-676
Publish at: 2025-02-01

Enhancing sentiment analysis through deep layer integration with long short-term memory networks

10.11591/ijece.v15i1.pp949-957
Parul Dubey , Pushkar Dubey , Hitesh Gehani
This involves studying one of the most important parts of natural language processing (NLP): sentiment, or whether a thing that makes a sentence is neutral, positive, or negative. This paper presents an enhanced long short-term memory (LSTM) network for the sentiment analysis task using an additional deep layer to capture sublevel patterns from the word input. So, the process that we followed in our approach is that we cleaned the data, preprocessed it, built the model, trained the model, and finally tested it. The novelty here lies in the additional layer in the architecture of LSTM model, which improves the model performance. We added a deep layer with the intention of improving accuracy and generalizing the model. The results of the experiment are analyzed using recall, F1-score, and accuracy, which in turn show that the deep-layered LSTM model gives us a better prediction. The LSTM model outperformed the baseline in terms of accuracy, recall, and f1-score. The deep layer's forecast accuracy increased dramatically once it was trained to capture intricate sequences. However, the improved model overfitted, necessitating additional regularization and hyperparameter adjustment. In this paper, we have discussed the advantages and disadvantages of using deep layers in LSTM networks and their application to developing models for deep learning with better-performing sentiment analysis.
Volume: 15
Issue: 1
Page: 949-957
Publish at: 2025-02-01
1 2 3
...
1666 1667
Show 45 of 1667

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration