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

28,428 Article Results

Five-Tier BI architecture with tuned decision trees for e-commerce prediction

10.11591/ijeecs.v39.i3.pp1633-1641
Thiruneelakandan Arjunan , Umamageswari A.
In recent times, remarkable performance has been shown by large language models (LLMs) in a range of natural language processing (NLP) such as questioning, responding, document production, and translating languages. In today's competitive business landscape, understanding consumer behaviour in online buying is crucial for the success of e-commerce platforms. The work proposes a novel Five-Tier service-oriented BI architecture (FSOBIA) that leverages advanced tuned decision tree (ATDT) techniques for predicting online buying behaviour. The proposed FSOBIA offers e-commerce platforms a scalable and adaptable solution for gaining insights into consumer preferences and making informed business decisions. The goal of FSOBIA's design and implementation is to meet the needs of evolving users and quicker service. Experimental evaluations on real-world datasets in FSOBIA achieved over 95% prediction accuracy, outperforming traditional models: Decision trees (82%), and XGBoost (91%), while offering better scalability and computational efficiency.
Volume: 39
Issue: 3
Page: 1633-1641
Publish at: 2025-09-01

A new approach for optimal sizing and allocation of distributed generation in power grids

10.11591/ijpeds.v16.i3.pp1598-1607
Hudefah Alkashashneh , Ayman Agha , Mohammed Baniyounis , Wasseem Al-Rousan
This paper presents a methodology for optimizing the allocation and sizing of distributed generators (DG) in electrical systems, aiming to minimize active power losses on transmission lines and maintain bus voltages within permissible limits. The approach consists of two stages. First, a sensitivity based analysis is used to identify the optimal candidate bus or buses for DG placement. In the second stage, a new random number generation method is applied to determine the optimal DG sizing. Moreover, a ranking for the optimal locations and sizes is given in case the optimal location is unavailable in real-world scenarios. The proposed methodology is demonstrated through a straightforward algorithm and tested on the IEEE 14-bus and IEEE 30-bus networks. Numerical simulations in MATLAB illustrate the effectiveness of the proposed approach in finding the optimal allocation of DG and the amount of active power to be allocated at the candidate buses, considering the inequality constraints regarding voltage limits and DG allowable power. The paper concludes with results, discussions, and recommendations derived from the proposed approach.
Volume: 16
Issue: 3
Page: 1598-1607
Publish at: 2025-09-01

Modeling and simulation of klystron-modulator for linear accelerators in PRTA

10.11591/ijpeds.v16.i3.pp1822-1831
Wijono Wijono , Dwi Handoko Arthanto , Galih Setiaji , Angga Dwi Saputra , Taufik Taufik , Andang Widi Harto
Approximately 70% of commercial industries worldwide use electron accelerator technology for various irradiation processes. The advantages of irradiation processes compared to thermal and chemical processes are higher output levels, reduced energy consumption, less environmental pollution, and producing superior product quality and having unique characteristics that cannot be imitated by other methods. Research Center for Accelerator Technology (PRTA), BRIN, Indonesia is developing standing wave LINAC (SWL) for food irradiation applications at S-band frequencies (±2856 MHz), electron energy of 6-18 MeV, and an average beam power of 20 kW. This paper aims to model, simulate, and analyze the klystron modulator in the RF linear accelerator (LINAC). The klystron modulator is the main component of the RF LINAC, which functions to supply klystron power with the order of megawatt peak DC, so that the klystron can amplify the low-level RF signal from the RF driver into a high-power RF signal with a power of 2-6 MW peak. The klystron modulator modeling is carried out based on mathematical modeling, then simulated using LTspice to analyze the system performance of the klystron modulator. The results of the klystron modulator modeling simulation show stable system performance and dynamic response. So that it meets the specifications of the 6-18 MeV SWL LINAC being developed by PRTA-BRIN.
Volume: 16
Issue: 3
Page: 1822-1831
Publish at: 2025-09-01

Torque sharing function optimization for switched reluctance motor control using ant colony optimization algorithm

10.11591/ijpeds.v16.i3.pp1537-1551
Dhiyaa Mohammed Ismael , Thamir Hassan Atyia
Switched reluctance motors (SRMs) are gaining popularity in industrial and automotive applications due to their robust design, fault tolerance, and high torque density, particularly in wide-speed-range operations. However, SRM performance is often limited by torque ripple, speed oscillations, and inefficiencies, which can lead to mechanical stress, vibration, and acoustic noise. Addressing these challenges requires the effective optimization of control strategies. This study aims to enhance the performance of SRM drives by employing an ant colony optimization (ACO) algorithm to optimize the torque sharing function (TSF). The proposed method iteratively tunes TSF parameters to minimize torque ripple and improve speed stability under varying operating conditions. Simulation results demonstrate significant improvements: torque ripple is reduced from a range of –20 Nm to 10 Nm without optimization to below 10 Nm with ACO-based optimization. Similarly, current peaks decrease from 60 A to 5.5 A, ensuring smoother motor operation and enhanced efficiency. Comparative analysis confirms that the ACO-based TSF provides superior tracking of speed set points, reduced mechanical stress, and improved reliability, making it well-suited for high performance applications in both industrial and automotive sectors.
Volume: 16
Issue: 3
Page: 1537-1551
Publish at: 2025-09-01

Investigation of optimal tilt, orientation, and tracking of a solar PV system in Iraq

10.11591/ijpeds.v16.i3.pp1914-1925
Ahmed Zurfi , Ali Abdul Razzaq Altahir , Ali Ibrahim
This paper examines the effect of tilt angle and tracking modes on energy performance of a PV system under Iraqi weather conditions. A 5-kWdc rooftop residential PV system is modeled and simulated using system advisor model (SAM) to investigate its optimal configuration of tilt angle and tracking axes for maximum energy extraction. The system is simulated with meteorological datasets for all 18 Iraqi provinces. The effect of soiling losses due to dust accumulation on incident irradiance and energy generation is considered as most Iraqi territories suffer from frequent dust storms yearly. The system annual AC energy and optimal tilt angles are evaluated and compared in five different scenarios including fixed-axis with tilt at latitude, fixed-axis with tilt at annual optimal angle, fixed-axis with tilt at monthly annual angle, one-axis tracking and dual-axis tracking. The results showed that considerable amount of energy is left unharnessed in fixed-axis scenarios when tilt angles are adjusted at latitude and optimal annual values. Using optimal monthly tilt with fixed-axis improved energy extraction by 5-6% for all locations. Energy performance is further improved with one axis tracking. Dual-axis tracking achieved highest energy yield compared to other scenarios. Overall, mid-south provinces provided highest energy opportunities among others.
Volume: 16
Issue: 3
Page: 1914-1925
Publish at: 2025-09-01

Advancing power quality via distributed power flow control solutions

10.11591/ijpeds.v16.i3.pp1801-1811
Abdelkader Yousfi , Fayçal Mehedi , Khelifa Khelifi Otmane , Youcef Bot
The growing demand for enhanced power quality and reliable transmission has driven advancements in power flow control technologies. The distributed power flow controller (DPFC) represents an advancement over the unified power flow controller (UPFC). In contrast to the UPFC, the DPFC removes the DC link connecting the shunt and series converters, and redistributes the series converters along the transmission line as single-phase static series compensators. This modification enhances grid performance while maintaining full power flow control capabilities. The DPFC offers several advantages over the UPFC, including higher reliability, improved controllability, and greater cost-effectiveness. The system comprises a shunt converter in conjunction with multiple series converters, each with its own control circuit, all managed by a central control unit. This article presents the implementation of a DPFC model in MATLAB/Simulink. The simulation outcomes indicate that the DPFC significantly contributes to improved voltage stability and enhanced power transfer capability, thereby reinforcing system performance and reliability.
Volume: 16
Issue: 3
Page: 1801-1811
Publish at: 2025-09-01

Photovoltaic energy harvesting for the power supply of medical devices

10.11591/ijpeds.v16.i3.pp1962-1969
Hamza Abu Owida , Basem Abu Izneid , Nidal Turab
The increasing demand for sustainable and reliable power sources in portable and implantable medical devices has led to growing interest in photovoltaic (PV) energy harvesting. Traditional power sources, such as batteries, are limited by finite energy capacity and frequent replacement or recharging needs, particularly in implantable devices where surgical intervention is required for battery replacement. Photovoltaic energy harvesting, which converts light into electrical energy, offers a promising alternative, especially in environments with consistent light exposure. This review provides an in-depth analysis of the advancements in PV technologies for powering medical devices. It covers various types of PV materials, design innovations, and the integration of energy storage systems. Additionally, the review highlights the application of PV systems in both external and implantable medical devices, while addressing critical challenges such as ensuring biocompatibility, optimizing performance in low-light conditions, and miniaturizing PV systems for implantation. The potential of PV energy harvesting to improve device longevity and reduce the need for invasive procedures is emphasized. This review concludes by outlining the current challenges and future directions needed to achieve widespread clinical adoption, aiming to contribute to the development of sustainable power solutions in healthcare.
Volume: 16
Issue: 3
Page: 1962-1969
Publish at: 2025-09-01

Comparative of prediction algorithms for energy consumption by electric vehicle chargers for demand side management

10.11591/ijece.v15i4.pp4192-4201
Ayoub Abida , Redouane Majdoul , Mourad Zegrari
This study focuses on demand side management (DSM), specifically managing electric vehicle (EV) charging consumption. Power distributors must consider numerous factors, such as the number of EVs, charging station availability, time of day, and EV user behavior, to accurately predict EV charging demand. We utilized machine learning algorithms and statistical modeling to predict the energy required by EV users for a specific charger and compared algorithms like K-Nearest Neighbors, XGBoost, random forest regressor, and ridge regressor. To contribute to the existing literature, which lacks studies on future energy prediction for a specific period, we conducted predictions for the next year 2024 on the energy consumption of electric vehicles for an electric vehicle charging point in a Moroccan city. These predictions can be generalized to other chargers as well. Our results showed that K-nearest neighbors (KNN) outperformed other algorithms in accuracy. This study provides valuable insights for distribution operators to manage energy resources efficiently and contributes to the DSM field by highlighting the effectiveness of KNN in predicting EV charging demand.
Volume: 15
Issue: 4
Page: 4192-4201
Publish at: 2025-08-01

Numerical modelling of photocurrent for CuInxGa1-xSe2-based bifacial photovoltaic cell

10.11591/ijece.v15i4.pp3649-3659
Seloua Bouchekouf , Hocine Guentri , Liamena Hassinet , Amina Merzougui , Farida Kebaili
Research on thin-film solar cells based on CuInSe2 has demonstrated the potential of this compound for photovoltaic conversion. The introduction of gallium as a substitute for indium has led to the creation of the CuInxGa1-xSe2 (CIGS) structure, which could serve as one of the foundational materials for high-performance solar cells. This paper focuses on modelling the bifacial back surface field (BSF) solar cell. We took the CdS/CIGS thin-film structure as an application example to optimize, through simulation, the physical-electronic and geometric parameters of the various layers of the cell. Our study has led us to interesting results that clearly show that the performance of the cell is precisely controlled by the space charge region associated with the CIGS absorber layer, which is promising for research in photovoltaics due to its high absorption coefficient and the ability to vary its bandgap, allowing for increased conversion efficiency. The high-doped P+ layer (Wbsf) enhances the total photocurrent of the bifacial.
Volume: 15
Issue: 4
Page: 3649-3659
Publish at: 2025-08-01

Enhancing anomaly detection performance using ResNet50 and BiLSTM networks on benchmark datasets

10.11591/ijece.v15i4.pp3727-3736
Dipak Ramoliya , Amit Ganatra
Detection of abnormal activity from large video sequences is one of the biggest challenges because of ambiguity in different activities. Over the last many years, several cameras have been placed to cover the public and private sectors to monitor abnormal human activity and surveillance. In recent years, deep learning and computer vision have significantly impacted this kind of surveillance. Intelligent systems that can automatically identify unusual events in video streams are currently in high demand. A deep learning-based combinational model has been proposed to detect abnormal activity from input video streams. The proposed study uses a combination of convolution and sequential models. A ResNet50 network with a residual connection was used for initial feature extraction. The proposed bidirectional long short-term memory (BiLSTM) network has improved the extracted ResNet50 features. Simulation of the proposed model was experimented on two benchmark datasets for anomaly detection UCF Crime and ShanghaiTech. Simulation of proposed architecture has achieved 97.55% and 91.94% remarkable accuracy for UCF Crime and ShanghaiTech datasets respectively.
Volume: 15
Issue: 4
Page: 3727-3736
Publish at: 2025-08-01

DriveGuard: enhancing vehicle breakdown assistance through mobile geolocation technology

10.11591/ijece.v15i4.pp3957-3964
Mohamed Imran Mohamed Ariff , Abdul Hadi Abdul Halim , Samsiah Ahmad , Mohammad Nasir Abdullah , Zalikha Zulkifli , Khairulliza Ahmad Salleh
The DriveGuard mobile application addresses the growing demand for efficient vehicle breakdown assistance by connecting users to nearby workshops using advanced geolocation technologies. With the rise in private vehicle ownership, sudden breakdowns are increasingly common, necessitating quick access to assistance. DriveGuard utilizes GPS, GSM/CDMA Cell IDs, and Wi-Fi positioning for precise location tracking, enabling users to locate assistance rapidly and accurately. Developed through the waterfall model, the application offers a user-friendly interface built with the Flutter framework. Test results indicate high functionality and user satisfaction, achieving usability ratings between 88% and 90%. DriveGuard’s design improves road safety by reducing waiting times for emergency services, alleviating the stress often associated with breakdown situations. Future work will focus on expanding service options, enhancing security, and refining user interactions to provide a more comprehensive roadside assistance tool. DriveGuard demonstrates the potential of mobile technology in promoting safe and efficient transportation.
Volume: 15
Issue: 4
Page: 3957-3964
Publish at: 2025-08-01

Low-cost portable potentiostat for real-time insulin concentration estimation based on electrochemical sensors

10.11591/ijece.v15i4.pp3683-3695
Fitria Yunita Dewi , Harry Kusuma Aliwarga , Djati Handoko
Administering incorrect insulin dosages to diabetic patients can be fatal, leading to severe health consequences. Insulin detection, in conjunction with blood glucose monitoring, can significantly enhance diagnostic accuracy. Electrochemical methods for insulin detection offer a low-cost and portable solution. This study presents an insulin concentration estimation system using a customized electrochemical potentiostat operating in real-time via Bluetooth low energy (BLE). Conventional electrochemical sensing, which relies on calibration curves to determine concentration, poses accuracy limitations in portable devices. To address this, we implement a multiple- predictor approach that incorporates peak currents from multiple cycles of cyclic voltammetry responses and the electroactive surface area of a multi- walled carbon nanotube (MWCNT-COOH) modified screen-printed sensor. This modified sensor enhances sensitivity compared to bare screen-printed carbon sensors, making it suitable for low-volume and portable applications. Through cross-validation, our method demonstrated strong performance, achieving a determination coefficient (R²) greater than 0.90 for all training dataset combinations and greater than 0.85 for all testing dataset combinations. Hypothesis testing further confirmed the statistical significance of the electroactive surface area (p=0.006) as predictor, indicating its meaningful contribution to concentration estimation. This approach improves portable detection performance, supporting the development of affordable and reliable personal insulin monitoring systems.
Volume: 15
Issue: 4
Page: 3683-3695
Publish at: 2025-08-01

Thematic review of light detection and ranging and photogrammetric technologies in unmanned aerial vehicles: comparison, advantages, and disadvantages

10.11591/ijece.v15i4.pp3748-3758
Diego Alexander Gómez-Moya , Yeison Alberto Garcés-Gómez
The development of unmanned aerial vehicles (UAVs) has positively influenced various remote sensing techniques, making them more accessible to different types of users. Among these, photogrammetry and light detection and ranging (LiDAR) stand out for their versatility and possibilities in terrain modeling. This study evaluates the advantages of each one in various fields of knowledge and industry, comparing their possibilities in terms of positional accuracy, completeness, and efficiency in terrain modeling. It is evident that the use of these techniques in different areas generates an opportunity to implement algorithms or processes in mapping and cartography. Regarding their use, the advantage of the LiDAR sensor is identified in inhospitable and inaccessible areas covered by vegetation and with problems in the geodetic network. On the other hand, the versatility of photogrammetry is shown in small areas with exposed soil. The advantage of point cloud fusion or the combination of techniques in the construction industry and in archaeological and architectural surveys is also noted. Finally, emphasis is placed on variables to consider, such as georeferencing techniques, the ground control point (GCP) network, algorithms and software, and flight plan reviews, in order to improve their accuracy.
Volume: 15
Issue: 4
Page: 3748-3758
Publish at: 2025-08-01

Gene set imputation method-based rule for recovering missing data using deep learning approach

10.11591/ijece.v15i4.pp4296-4317
Amer Al-Rahayfeh , Saleh Atiewi , Muder Almiani , Ala Mughaid , Abdul Razaque , Bilal Abu-Salih , Mohammed Alweshah , Alaa Alrawajfeh
Data imputation enhances dataset completeness, enabling accurate analysis and informed decision-making across various domains. In this research, we propose a novel imputation method, a spectral clustering based on a gene set using adaptive weighted k-nearest neighbor (AWKNN), and an imputation of missing data using a convolutional neural network algorithm for accurate imputed data. In this research, we have considered the Kaggle water quality dataset for the imputation of missing values in water quality monitoring. Data cleaning detects inaccurate data from the dataset by using the median modified Weiner filter (MMWFILT). The normalization technique is based on the Z-score normalization (Z-SN) approach, which improves data organization and management for accurate imputation. Data reduction minimizes unwanted data and the amount of capacity required to store data using an improved kernel correlation filter (IKCF). The characteristics and patterns of data with specific columns are analyzed using enhanced principal component analysis (EPCA) to reduce overfitting. The dataset is classified into complete data and missing data using the light- DenseNet (LIGHT DN) approach. Results show the proposed outperforms traditional techniques in recovering missing data while preserving data distribution. Evaluation based on pH concentration, chloramine concentration, sulfate concentration, water level, and accuracy.
Volume: 15
Issue: 4
Page: 4296-4317
Publish at: 2025-08-01

A hybrid model to mitigate data gaps and fluctuations in tax revenue forecasting

10.11591/ijece.v15i4.pp4099-4108
Rahman Taufik , Aristoteles Aristoteles , Igit Sabda Ilman
This study addresses the critical challenge of advancing tax revenue forecasting models to effectively handle distinctive data gaps and inherent fluctuations in tax revenue data. These challenges are evident in Lampung Province, Indonesia, where limited temporal granularity and non-linear variability hinder accurate fiscal planning. Despite advancements in statistical, machine learning, and hybrid approaches, existing models often fall short in simultaneously managing these challenges. A hybrid model integrating random forest regressors for data interpolation and Long Short-Term Memory for capturing complex temporal patterns was proposed. The model was evaluated, achieving an R² of 0.86, root mean squared error (RMSE) of 9.65 billion, and mean absolute percentage error (MAPE) of 3.49%. Although the model has limitations in generalizing to unseen data, the results demonstrate that it outperforms existing forecasting models regarding accuracy and reliability. Integrating random forest regressors and long short-term memory delivers a tailored solution to the complexities of tax revenue forecasting, contributing to fiscal forecasting and setting a foundation for further exploration into hybrid approaches.
Volume: 15
Issue: 4
Page: 4099-4108
Publish at: 2025-08-01
1 2 3
...
1895 1896
Show 41 of 1896

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