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

30,376 Article Results

Multi-objective energy management optimization in electric vehicles using fuzzy logic and particle swarm optimization

10.11591/ijpeds.v17.i2.pp1025-1035
V. Lakshmi Devi , Damodhar Reddy , Srikanth Velpula , K. Kumar , Basi Reddy Avula
This paper proposes a hybrid energy management system (EMS) for electric vehicles by integrating fuzzy logic control (FLC) with particle swarm optimization (PSO) to improve power-split decision-making under dynamic driving conditions. The FLC is designed using state of charge (SoC) and vehicle speed as input variables and power split as the output. A set of fuzzy rules defines the EMS behavior, while PSO is employed to fine-tune decisions by maximizing an efficiency objective function defined as the closeness of the power split to an ideal reference. The simulation is implemented in Python using Colab-compatible packages such as scikit-fuzzy, DEAP, and matplotlib, ensuring accessibility and reproducibility. A test grid covering 10 SoC levels (10-100%) and 10 speed levels (10-120 km/h) is used to evaluate the system. Visualization tools, including heatmaps, 3D surface plots, and contour plots, are employed to represent the EMS behavior. The PSO-enhanced system achieved a maximum efficiency of 98.2% at an optimized SoC of 61.7% and a speed of 53.6 km/h, outperforming standalone fuzzy logic control. Tabulated results and statistical summaries validate the effectiveness of the proposed system.
Volume: 17
Issue: 2
Page: 1025-1035
Publish at: 2026-06-01

Permanent magnet generator for small and medium-scale hydropower: a systematic review

10.11591/ijpeds.v17.i2.pp1462-1474
Ngatono Ngatono , Raja Nor Firdaus Kashfi Raja Othman , M. Nazri Othman , Mohd Zulkifli Ab Rahman
Renewable energy, particularly hydropower, is a key focus in reducing reliance on fossil fuels and mitigating environmental impacts. Permanent magnet generator (PMG) has emerged as a highly efficient option for converting hydro-energy into electricity, offering advantages such as high efficiency, compact design, and minimal maintenance. This review explores the latest developments in PMG technology, particularly for small and medium-scale hydropower applications. A systematic review method was used to analyse 617 papers and narrow them down to 20 relevant studies. Key findings highlight advancements in PMG design, including modular stators, counter-rotating turbines, and cordless designs that enhance efficiency and adaptability in low-speed environments. However, significant challenges remain, including the high cost of magnetic materials like Neodymium Iron Boron (NdFeB), thermal stability issues, and more robust control systems to manage variable water flow conditions. The review concludes that while PMG holds great potential for hydropower applications, Further research is needed to optimize material usage, improve design, and reduce costs. Future work should focus on developing new magnetic materials and innovative rotor designs to ensure PMG can provide a scalable and sustainable solution for global energy needs.
Volume: 17
Issue: 2
Page: 1462-1474
Publish at: 2026-06-01

Proximal policy optimization-based type II PPC for EV fast charging

10.11591/ijpeds.v17.i2.pp835-848
Franco Aldrin Joseph Menezes , Gopala Reddy Krishnappa
In recent years, efficient and fast charging is critical for accelerating the adoption of electric vehicle (EV). However, traditional fully rated converters process the total power flow to the battery, but leading to excessive thermal stress, high energy losses, and quick battery degradation. Similarly, existing partial power converter (PPC) designs like type I and type II PPC, improve efficiency by processing only a fraction of the total power; however, they still face challenges such as additional isolation requirements, limited step-down performance, and lack of advanced control for fluctuating state of charge (SoC) conditions. To overcome these challenges, this research proposes a proximal policy optimization (PPO)-enhanced type II PPC for fast EV charging. Initially, the power is routed through a low-frequency (LF) isolation transformer and filtered to mitigate high-frequency noise. A portion of the power is partially processed through a SiC MOSFET-based phase-shifted full-bridge converter, while the remaining power bypasses directly to the battery. The PPO controller efficiently adjusts the phase shift angle in real time, optimizing switching cycles to reduce switching and thermal losses. The proposed PPO-type II PPC achieved better results in terms of peak efficiency (99.36%) and partial power handling (12.21%) when compared to existing type II PPC designs.
Volume: 17
Issue: 2
Page: 835-848
Publish at: 2026-06-01

Stability analysis of photovoltaic grid-connected power systems employing virtual synchronous generator control

10.11591/ijpeds.v17.i2.pp1451-1461
Abdallah El Ghaly , Abdullah Hamdan , Mohamad Tarnini
The rapid integration of photovoltaic (PV) systems into power networks poses significant challenges to grid stability, including reduced inertia, voltage fluctuations, and limited fault ride-through (FRT) capabilities. This study presents a comparative analysis of two inverter control strategies: the synchronous reference frame (SRF) controller and the virtual synchronous generator (VSG) controller. A high-fidelity MATLAB/Simulink model was developed, incorporating the effects of irradiance and temperature, maximum power point tracking (MPPT), and battery energy storage system (BESS) interaction. Standardized fault scenarios were applied at PV penetration levels ranging from 30% to 150% in accordance with IEEE-1547, IEEE-519, and IEC 61727 requirements. The results show that SRF control achieves superior harmonic suppression, with a total harmonic distortion (THD) consistently below 0.5%, confirming its suitability for strong grids prioritizing power quality. However, its stability deteriorated at higher penetration levels, with the voltage overshoot reaching approximately 16% and recovery times exceeding 3 s. In contrast, the VSG control demonstrates enhanced transient stability and effective FRT performance, with the overshoot limited to ≤5% and recovery achieved within 0.8 s across all operating conditions. The main contribution of this study lies in the direct benchmarking of the SRF and VSG control strategies under identical operating conditions using a unified evaluation framework, including an extended analysis beyond 100% PV penetration. The findings highlight a fundamental trade-off between harmonic performance and transient stability and provide practical guidance for selecting appropriate inverter control strategies for renewable-dominated power systems.
Volume: 17
Issue: 2
Page: 1451-1461
Publish at: 2026-06-01

Improved control strategy for harmonic current mitigation in DFIG-based wind turbines supplying linear and nonlinear loads

10.11591/ijpeds.v17.i2.pp933-945
Hind Elaimani , Noureddine Elmouhi
Improving power quality is a major challenge in grid-connected wind energy systems, especially under mixed linear and nonlinear load conditions. This paper proposes an enhanced control strategy for harmonic current mitigation in a doubly fed induction generator (DFIG)-based wind turbine. The proposed approach integrates flux-oriented vector control with an active harmonic compensation algorithm implemented through the rotor-side converter (RSC). Unlike conventional methods that target only specific harmonic orders, the proposed strategy mitigates all current harmonics at the point of common coupling (PCC). Simulation studies conducted under various load conditions demonstrate that the method significantly reduces the total harmonic distortion (THD) and ensures near-sinusoidal stator currents. The results confirm the effectiveness and robustness of the proposed control approach in improving the power quality of DFIG-based wind energy conversion systems.
Volume: 17
Issue: 2
Page: 933-945
Publish at: 2026-06-01

Robust power optimization strategy for wind-driven induction machines using type-2 and type-1 fuzzy logic controllers

10.11591/ijpeds.v17.i2.pp1313-1325
Driss Belkhiri , Boujemaa Nassiri , Mohamed Ajaamoum
This paper proposes a reliable power optimization strategy that maximizes the harvested power of induction machines driven by wind, taking into account variable wind turbulence and uncertain machine parameters. This work explores the challenging task of designing type-2 fuzzy logic (T2FL) and conventional type-1 fuzzy logic (T1FL) controllers for wind energy conversion systems that exhibit multiple non-linearities. T2FL controllers are proficient in tackling uncertainties and offer quicker and more precise decision-making capabilities. The proposed approach is beneficial as it is independent of accurate wind turbine parameters, wind speed data, or additional sensors. Rather, it utilizes the mechanical rotor speed and the wind turbine power as input, which corresponds to maximum power point tracking (MPPT) through the management of the rotor speed via the machine-side converter. Real data validates the scheme against classical controllers, and via a set of simulations and statistical analyses, performance metrics like steady-state error, overshoot, tracking speed, and efficiency are widely assessed. The results show that the proposed scheme, which is independent of a dedicated wind speed sensor, demonstrates superior tracking performance, lower tracking errors, such as lower RMSE/MAE, and higher energy yield, although the wind speed and the system parameters change rapidly. Overall, this design provides more robust performance to random wind speed variations, increases operational efficiency and wind turbines' service life, and is low in adding mass and cost.
Volume: 17
Issue: 2
Page: 1313-1325
Publish at: 2026-06-01

Pre-driving fatigue screening from short-term heart rate variability with subject-independent validation

10.11591/ijai.v15.i3.pp2885-2895
Tia Haryanti , Eri Prasetyo Wibowo , Wahyu Kusuma Raharja , Rossi Septy Wahyuni , Imliyati Sari
This study evaluates fatigue screening from 30-second electrocardiogram (ECG) recordings using short-term heart rate variability (HRV) features in a pre-driving context. The dataset comprises 99 participants (one session each) with fatigue labels derived from the Karolinska sleepiness scale (KSS), where the primary label (K1) defines non-fit as KSS ≥ 7. A subject-independent logistic-regression model was trained under a leave-one-subject-out (LOSO) scheme. Probabilities were calibrated using Platt scaling and evaluated through threshold-free metrics (receiver operating characteristic (ROC)-area under the curve (AUC), precision-recall (PR)-AUC) as well as calibration performance using the Brier score. The model achieved ROC-AUC =0.687 (95% confidence interval: 0.591–0.776), PR-AUC =0.621, and a Brier score of 0.200. At the operating threshold t = 0.255, the model achieved sensitivity of 1.000 with no false negatives, while specificity remained 0.091 (95% confidence interval: 0.030–0.140). Reliability analysis indicated reasonable calibration in the operational probability range. These findings support short-term HRV derived from ECG as a screening tool that prioritizes avoiding missed non-fit cases, paired with a triage scheme (fit/review/non-fit) to manage uncertainty near the decision threshold. Future work should incorporate ECG morphology and signal quality cues and aim to improve specificity without sacrificing sensitivity.
Volume: 15
Issue: 3
Page: 2885-2895
Publish at: 2026-06-01

Handwriting-based personality classification on Indian samples using long-short term memory

10.11591/ijai.v15.i3.pp2511-2520
Pradeep Kumar Mishra , Gouri Sankar Mishra , Ali Imam Abidi , Tarun Maini , Amit Kumar
Traditional handwriting analysis methods have historically faced criticism for their lack of scientific basis, but more contemporary models based on layered artificial neural network (ANN) architecture have evidently been more successful. In the proposed model, a deep neural network (DNN) layered, long-short term memory (LSTM) model with contextual analysis has been proposed for handwriting-based personality classification. The model has been trained over a manually curated verbose dataset of ~6,000 Indian handwriting sample images, varying across genders, age groups, and regions. The classification is based on the five major personality traits. The proposed framework achieved an accuracy of 97.75%, which is over 10% better than the next best performing model on a comparably numerically bigger dataset; demonstrating the enhanced potential of context based neural networks on handwriting-based personality prediction when coupled with an appropriately varied and unbiased dataset.
Volume: 15
Issue: 3
Page: 2511-2520
Publish at: 2026-06-01

DriveShield: attention-based hybrid neural network for intrusion detection in automotive controller area networks

10.11591/ijai.v15.i3.pp2618-2632
Vismaya Kootayi Kunnacheri , Arul Leena Rose Peter Joseph
Vehicle network security is important as increasing amounts of connected technology are being added to vehicles nowadays, putting them at risk of cyberattacks. This paper presents DriveShield, a novel real-time intrusion detection system (IDS) that is the first to combine gated recurrent units (GRU), convolutional neural networks (CNN), and long short-term memory (LSTM) with an attention mechanism. The systematic pre-processing pipeline, which includes feature engineering, the synthetic minority oversampling technique (SMOTE) for class balancing, and normalization. The model was validated on the open training intrusion detection system (OTIDS) dataset and the Hacking and Countermeasure Research Lab (HCRL) car hacking dataset. In the HCRL dataset, the model had an accuracy of 96.30% with F1-scores as high as 96% for all kinds of attacks. On the OTIDS dataset, it performed very well in terms of generalization, with a highest accuracy of 99.78% and a weighted F1-score of 99.78%. The addition of an attention mechanism enabled the model to concentrate on the most significant features, providing better adaptability to changing threats. These findings demonstrate the efficacy, scalability, and reliability of the system for in-vehicle network security. The future research will focus on performance on lower-frequency attacks through the study of unsupervised learning methods and real-world deployment trials.
Volume: 15
Issue: 3
Page: 2618-2632
Publish at: 2026-06-01

Enhancing torque performance in electric four-wheel drive systems using fuzzy GPC

10.11591/ijape.v15.i2.pp845-857
Djamila Allali , Youssef Mouloudi , Abdeldjebar Hazzab , Najia Allali
This paper presents a robust supervisory control strategy for speed regulation in a four-wheel-drive electric vehicle (EV) equipped with in-wheel induction motors. A hybrid control architecture is developed by combining fuzzy logic control (FLC) and generalized predictive control (GPC), with an intelligent switching mechanism that dynamically allocates control authority based on real-time operating conditions. FLC is employed to manage transient phases such as acceleration and deceleration, while GPC ensures optimal performance during steady-state operation. The proposed control system is modeled and validated in the MATLAB/Simulink environment. Simulation results demonstrate that the hybrid controller achieves a 27% improvement in transient response, a 15% reduction in steady-state speed fluctuations, and a 19% decrease in energy consumption under urban driving conditions. Furthermore, the controller maintains reliable performance under parameter variations of up to 25% and road gradients of up to 15%. Compared to standalone FLC and GPC controllers, the hybrid approach improves transient speed recovery by 35% and reduces steady-state error by 22%. Overall, this hybrid FLC-GPC strategy effectively addresses key challenges in EV control, such as system nonlinearity, parameter uncertainty, and external disturbances, while ensuring high dynamic responsiveness, steady-state precision, and energy efficiency. These results highlight the potential of the proposed method for future intelligent and autonomous electric mobility systems.
Volume: 15
Issue: 2
Page: 845-857
Publish at: 2026-06-01

Optimized resonant capacitor and switching frequency for high-efficiency wireless power transfer in E-bikes using CST Studio Suite

10.11591/ijape.v15.i2.pp514-524
Wan Muhamad Hakimi Wan Bunyamin , Rahimi Baharom
Wireless power transfer (WPT) is increasingly adopted for E-bike charging; however, its performance is often constrained by inaccurate resonant tuning, inefficient capacitor selection, and improper switching-frequency operation, which lead to significant power loss and reduced transfer efficiency. This study addresses these limitations by formulating an optimized design methodology for selecting resonant capacitors and inverter switching frequency to achieve high-efficiency energy transfer. A 40-mm air gap between the transmitter and receiver coils is modeled using CST Studio Suite, where a 3D electromagnetic circuit co-simulation framework is applied to evaluate mutual inductance, resonant behavior, magnetic-field distribution, and S-parameter characteristics. Parametric sweeps combined with a convergence-based optimization algorithm identify the optimal resonant operating point, yielding a peak resonant frequency of 38.1 kHz, a maximum simulated transfer efficiency of 99%, and a deep reflection coefficient of -21.77 dB. The optimized configuration also demonstrates stable voltage and field distribution at resonance, confirming effective impedance matching. The main contributions of this work include: i) establishing a unified EM–circuit optimization workflow for determining resonant capacitance and switching frequency, ii) providing quantitative resonance parameters and performance indicators suitable for compact E-bike WPT systems, and iii) integrating mathematical modelling to validate CST-based predictions and ensure theoretical consistency. The proposed approach significantly enhances design accuracy and efficiency, offering a scalable and high-performance solution for next-generation low-power electric vehicle (EV) and E-bike wireless charging applications.
Volume: 15
Issue: 2
Page: 514-524
Publish at: 2026-06-01

Integrating Sustainable Development Goals into educational information systems: toward a theoretical model for sustainable school management

10.11591/ijece.v16i3.pp1350-1359
Veri Arinal , Miswanto Miswanto , Kiki Setiawan , Agus Tanti Rahayu
This research addresses the critical challenge of implementing Sustainable Development Goal (SDG) 4, "Quality education," in Indonesian secondary schools. While national policies exist, schools lack a systematic digital tool to plan, monitor, and evaluate sustainability-based activities against concrete SDG indicators. To bridge this gap, this study employs a six-cycle design science research (DSR) methodology to develop a theoretical model for a sustainable education information system. The model is designed to integrate SDG principles into school management, enabling systematic data handling, adaptive curriculum functions, and real-time monitoring. A web-based prototype was developed using a React.js frontend and Node.js backend and evaluated through a mixed-methods approach. Data from interviews with 15 administrators and surveys of 97 teachers (yielding a usability satisfaction score of 4.34/5) validated the model’s effectiveness in making educational administration more efficient, transparent, and quality-oriented. The resulting artifact serves as a foundational technical and managerial reference for schools, education offices, and policymakers to leverage information technology in fostering a sustainable, participatory learning culture aligned with the SDGs.
Volume: 16
Issue: 3
Page: 1350-1359
Publish at: 2026-06-01

Variance-k-means++: A deterministic centroid initialization method based on variance for enhanced clustering stability

10.11591/ijece.v16i3.pp1434-1448
Widodo Widodo , Jiel Vayyad Ramadhan , Muhammad Ficky Duskarnaen , Via Tuhamah Fauziastuti , Chelsea Zaomi Pondayu , Mada Rekadarma Septianda
K-means++ is developed to improve the performance of k-means when choosing a starting centroid. However, both algorithms in clustering still select an initial centroid randomly. Randomly selecting initial centroids has the potential to produce unstable clusters. This paper proposes a deterministic centroid initialization method called variance-k-means++, which utilizes statistical properties—mean and variance—to generate pseudo-centroids and derive initial centroids. The method aims to improve clustering stability and reduce the number of iterations. For the initial study, we used low-dimensional data to conduct the experiment series. Then, we employed two baseline methods for benchmarking, k-means and k-means++. The results show that variance-k-means++ outperformed the baseline method on average. Evaluating in Davies-Bouldin Index (DBI) and convergence analysis, we obtained DBI values at 0.756 and 0,771 for vertical and horizontal variance k-means++ with Iris dataset. At the same time, baseline methods have 0.802 and 0.830 for k-means++ and k-means, respectively. In convergence analysis, the results are 5.158 for vertical and 5.474 for horizontal, while baseline methods are 9.000 and 8.842. The primary contribution of this study lies in its achievement of minimizing the number of iterations while enhancing cluster stability.
Volume: 16
Issue: 3
Page: 1434-1448
Publish at: 2026-06-01

Analyzing learners' perceptions of engagement and learning interaction in gamified massive open online courses for TVET using SEM-PLS

10.11591/ijece.v16i3.pp1319-1328
Azizul Mohd Yusoff , Sazilah Salam , Siti Nurul Mahfuzah Mohamad , Rujianto Eko Saputro
The introduction of gamified massive open online courses (G-MOOCs) represents a novel advancement in technical and vocational education and training (TVET). The use of gamification in education has been shown to increase engagement and motivation, which are crucial for effective learning. However, there is limited research on the specific impacts of G-MOOCs on learner outcomes in TVET. A key feature of G-MOOCs is the integration of gamification elements to enhance learner engagement and interest. This research employs structural equation modelling with partial least squares (SEM-PLS) to examine learners' perceptions of their participation and learning experiences in G-MOOCs for TVET. Specifically, the study aims to identify how gamification approaches such as fun, engagement, and learner interaction influence knowledge acquisition, skills development, satisfaction, and overall learning outcomes. The analysis reveals that G-MOOCs have a strong positive correlation (0.505) with learning engagement. Additionally, learning engagement significantly moderates learning outcomes (p=0.002). Interaction also has a significant impact (p=0.381) on learning outcomes. Overall, the findings indicate a significant positive relationship between learners' activities and their performance in G-MOOCs.
Volume: 16
Issue: 3
Page: 1319-1328
Publish at: 2026-06-01

Enhancing road damage detection performance using the YOLOv9 model

10.11591/ijict.v15i2.pp616-624
Muhammad Farkhan Adhitama , Sutikno Sutikno , Rismiyati Rismiyati
Roads are essential infrastructure that support community mobility, and their condition significantly impacts road user safety. However, manual road damage detection remains inefficient, time-consuming, costly, and prone to human error. To address this issue, this study proposed the YOLOv9 model for automated road damage detection and explored parameter combinations to optimize its performance. The proposed solution leverages the YOLOv9 model, which offers enhanced detection speed and accuracy compared to previous YOLO versions, due to its improved backbone and dynamic label assignment techniques. The method uses pre-trained weights and performs parameter tuning to adapt the model for identifying common road defects, including potholes, longitudinal, lateral, and alligator cracks. A publicly available dataset of road condition images was used for training and evaluation. Experimental results demonstrated that the optimized YOLOv9 model achieved a mean average precision (mAP) of 62.8%, indicating a promising ability to detect multiple types of road damage accurately. This study highlights the potential of YOLOv9 as an effective tool for road monitoring systems, contributing to proactive maintenance strategies and more efficient infrastructure management.
Volume: 15
Issue: 2
Page: 616-624
Publish at: 2026-06-01
1 2 3
...
2025 2026
Show 22 of 2026

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