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

31,456 Article Results

Mobile robot replacement in multi-robot fault-tolerant formation

10.11591/ijra.v14i4.pp311-319
Ahmed M. Elsayed , Mohamed Elshalakani , Sherif Ali Hammad , Shady Ahmed Maged
Formation control in multi-robot systems (MRS) is essential for collaborative transport, environmental surveillance, material handling, and distributed monitoring. A major challenge in MRS is maintaining predefined formations or cooperative task execution when individual robots experience operational faults, potentially isolating them from the group. In mission-critical scenarios, preserving the number of operational robots is crucial for task success. To address this, we propose a Robot Replacement approach framework for differential wheeled mobile robots. This approach isolates faulty robots and dynamically replaces them with pre-deployed spares, ensuring uninterrupted formation tasks. A graph theory-based framework models inter-robot communication and formation topology, enabling decentralized coordination. The proposed techniques were implemented in a MATLAB/Simulink simulation environment. The simulated robots are equipped with LiDAR, an inertial measurement unit (IMU), and wheel encoders for navigation. Simulation results demonstrate that the framework successfully maintains the target formation and task continuity during robot failures by dynamically integrating replacements with minimal disruption.
Volume: 14
Issue: 4
Page: 311-319
Publish at: 2025-12-01

PD characteristics of polymer insulation for inverted-fed drives under sine and square waveforms

10.11591/ijape.v14.i4.pp893-902
S. Narasimha Rao , Elanseralathan Kasinathan , Ramanujam Sarathi
In recent years, adjustable speed drives power by power electronic converters have caused insulation failure in the electrical motors with stator windings. The repeating impulse voltages produced by IGBTs created insulation reliability problems in the stator winding. Overvoltage can cause partial discharge (PD), which can rapidly result in insulation system failure. To address this issue, IEC standards and technical specifications (TS) necessitate that a PD test on the motor insulation system is done at sinusoidal and square voltages. The PD characteristics obtained are used to evaluate insulation performance, enhancing insulation design. This work focuses on the PD characterization of twisted pair samples using high frequency sine and square waveforms at room temperature. The PD characteristics were investigated at 50 Hz, 1 kHz, 2.4 kHz, and 5 kHz. The result shows that there are fewer PD events with lower PD magnitudes and shorter delay times at higher frequencies. Further, at different temperatures of 30 °C, 60 °C, and 90 °C, the partial discharge inception voltage (PDIV) of twisted pair insulation was investigated using high-frequency sine and square waveforms. The results show that the corona inception voltage (CIV) (kV) decreases as ambient temperature increases. Furthermore, the conditions for PD occurrence in the insulation system were analyzed at higher switching frequencies. The electric field distribution of twisted pairs with a 0 mm air gap was modeled from 50 Hz to 5 kHz switching frequency using COMSOL software.
Volume: 14
Issue: 4
Page: 893-902
Publish at: 2025-12-01

Optimize the position of the distributed generator and capacitor bank in the distributed grid to minimize the generation cost

10.11591/ijape.v14.i4.pp970-979
Ngoc An Luu , Dinh Chung Phan
In this paper, we focus on determining the optimal position and size of multi-distributed generators and capacitor banks to minimize the generation cost of a distributed grid. The optimal position and size of distributed generators and capacitor banks are determined using a hybrid of conventional loss sensitivity factor and an improved one. The proposed algorithm has two stages. For each distributed generator, we prioritize its position and size. After that, we find the optimal position and size of the capacitor banks corresponding to this distributed generator installation to minimize the power loss. After considering all distributed generators, the optimal number, position, and size of the distributed generators and capacitor banks are determined based on the minimum generation cost value. This idea is developed in MATLAB and verified via sample distributed grids, including the IEEE-69 bus and IEEE-85 bus. The verifying results are evaluated and analyzed. By comparing those results to those of other methods, the performance of the newly introduced method is proven.
Volume: 14
Issue: 4
Page: 970-979
Publish at: 2025-12-01

Antecedents and consequences of memorable experience in the airline industry: service robots versus human staff

10.11591/ijra.v14i4.pp409-417
Jinsoo Hwang , Ja Young (Jacey) Choe , Kyuhyeon Joo , Jinkyung Jenny Kim
The study aims to examine the type of service providers, such as service robots and human staff, as a potential moderator in the relationship between SERVQUAL and memorable experience in the airport industry. In order to verify 15 hypotheses, data were collected from 313 travelers who acquired information from service robots and 313 travelers who acquired information from human staff at the airport. The results of data analysis revealed that the five sub-dimensions of SERVQUAL, including tangibles, reliability, responsiveness, assurance, and empathy, enhance memorable experience. In addition, a memorable experience has a positive effect on customer satisfaction, which subsequently influences attitude and intention to use. In addition, the type of service providers moderated the links between i) responsiveness and memorable experience and ii) empathy and memorable experience.
Volume: 14
Issue: 4
Page: 409-417
Publish at: 2025-12-01

Edge-aware distilled segmentation with pseudo-label refinement for autonomous driving perception

10.11591/ijra.v14i4.pp376-386
Novelio Putra Indarto , Oskar Natan , Andi Dharmawan
Achieving precise semantic segmentation is essential for enabling real-time perception in autonomous systems, yet leading approaches typically require substantial annotated data and powerful hardware, restricting their use on devices with limited resources. This work introduces an efficient segmentation framework that integrates pseudo-label refinement, knowledge distillation, and entropy-based confidence filtering to train compact student networks suitable for edge deployment. High-quality pseudo-labels are first produced by a robust teacher network, then further improved using a dense conditional random field to boost spatial consistency. An entropy-based selection mechanism removes unreliable predictions, ensuring that only the most trustworthy labels guide the student model's training. The use of knowledge distillation effectively transfers detailed semantic understanding from the teacher to the student, enhancing accuracy without added computational overhead. Experimental results with multiple EfficientNet backbones reveal that this pipeline improves segmentation accuracy and output clarity, while also supporting real-time or near real-time inference on CPUs with limited processing power. Extensive ablation and qualitative studies further confirm the method's robustness and flexibility for real-world edge applications.
Volume: 14
Issue: 4
Page: 376-386
Publish at: 2025-12-01

Enhancing health status prediction and data security using transformer-based deep learning architectures

10.11591/ijra.v14i4.pp418-428
Subramaniyan Senthamarai , Raja Manickam Mala , Vellaiyan Palanisamy
This paper proposes a privacy-preserving transformer-based federated learning (PPTFL) framework designed to enhance privacy, accuracy, and computational efficiency in healthcare data analysis. Federated learning (FL) has emerged as a promising solution for distributed machine learning while preserving data privacy, especially in sensitive sectors like healthcare. However, challenges such as maintaining high accuracy and managing communication overhead remain. The proposed PPTFL framework leverages the power of transformer models to improve the performance of federated learning while integrating privacy-preserving techniques. The model demonstrates superior performance with an accuracy of 92.87%, an F1 score of 92.37%, and a privacy budget (ϵ) of 1.6, outperforming existing approaches in terms of both privacy and accuracy. The model also exhibits computational efficiency, with lower communication cost and reasonable training time. Comparative evaluations with four relevant literature models further validate the effectiveness of the proposed PPTFL framework. This work highlights the potential of PPTFL to revolutionize healthcare informatics by providing secure, accurate, and efficient solutions for federated learning applications.
Volume: 14
Issue: 4
Page: 418-428
Publish at: 2025-12-01

Performance enhancement using sensor and sensorless control techniques for a modified bridgeless Ćuk converter-based BLDC motor in EV applications

10.11591/ijape.v14.i4.pp769-782
W. Margaret Amutha , S. Premalatha , M. Karthikeyan
This work proposes a solar photovoltaic (PV)-powered, modified bridgeless Ćuk converter tailored for electric vehicle applications. It overcomes limitations such as high ripple, reduced power density, significant switching losses, and complex circuit structures in traditional designs. The system integrates a boost converter with a bridgeless Ćuk topology to ensure a reliable and efficient direct current (DC) power output. Performance evaluation includes sensor-based and sensorless speed control techniques-pulse width modulation (PWM), proportional integral derivative (PID), back electromotive force (EMF), and spider controllers-under both no-load and full-load scenarios. Key parameters such as rise time, overshoot, settling time, and steady-state error are analyzed. MATLAB/Simulink simulations indicate that the spider controller delivers superior dynamic behavior and stability. A 48 W, 1500 rpm hardware prototype confirms the simulation outcomes, demonstrating the practical viability and effectiveness of the proposed converter.
Volume: 14
Issue: 4
Page: 769-782
Publish at: 2025-12-01

Improving the adaptability of an active power filter using linearization feedback input-output sliding mode

10.11591/ijape.v14.i4.pp879-892
Leminh Thien Huynh , Van-Cuu Ho , Thanh-Vu Tran
As more and more non-linear loads are used in industrial applications, power quality problems become more serious. To address this challenge, a robust nonlinear control strategy is introduced using an active power filter (APF) to enhance the power quality of the three-phase neutral voltage. The system employs a control algorithm tailored for a three-phase split-capacitor inverter, which eliminates high-order harmonics through a voltage source inverter (VSI) equipped with an LCL filter. The grid-side components of the LCL filter are incorporated into a sliding mode control framework to minimize oscillations while maintaining performance. Additionally, the d-q-0 transformation within the synchronous reference frame is applied to effectively manage the second harmonic component. In addition, the linear feedback input-output sliding mode facilitates the control system. This system can help decrease total harmonic distortion (THD) to meet IEEE-519 standards. This method demonstrates its effectiveness through simulation results, reducing THD to less than 5% and defeating previous methods despite still using simple algorithms.
Volume: 14
Issue: 4
Page: 879-892
Publish at: 2025-12-01

Forecasting business exceptions in robotic process automation with machine learning

10.11591/ijra.v14i4.pp450-458
Igor Saez , Sara Segura , Mónica Gago
Business exceptions interrupt robotic process automation (RPA) workflows and oblige costly human intervention. This paper explores the application of machine learning (ML) time series forecasting techniques to predict business exceptions in RPA. Using RPA robot logs from a financial service company, we employ ARIMA, SARIMAX, and Prophet statistical models, comparing their performance with ML models such as XGBoost and LightGBM. Furthermore, we explore hybrid approaches that combine the strengths of statistical models with ML techniques, specifically integrating Prophet with XGBoost and LightGBM. Our findings reveal that a hybrid LightGBM model substantially outperforms traditional methods, achieving a 40% reduction in the weighted absolute percentage error (WAPE) when compared to the top-performing statistical model. These results suggest the potential of ML forecasting in optimizing RPA operations through the analysis of log-generated data.
Volume: 14
Issue: 4
Page: 450-458
Publish at: 2025-12-01

ADC-LIO: A direct LiDAR-inertial odometry method based on adaptive distortion covariance

10.11591/ijra.v14i4.pp399-408
Lixiao Yang , Youbing Feng
Focusing on the localization challenges for robots in dynamic navigation environments, this study proposes a direct LiDAR-inertial odometry (LIO) system named ADC-LIO, which achieves robust pose estimation and accurate map reconstruction using adaptive distortion covariance. ADC-LIO is engineered to address uncertain motion patterns in autonomous mobile robots, effectively integrating LiDAR scan undistortion within the Kalman filtering update process by embedding an iterative smoothing process and a backpropagation strategy. The ADC-LIO architecture enhances point cloud accuracy, improving the system's overall performance and robustness. In addition, an adaptive covariance processing method is developed to resolve motion-induced sensing uncertainties, which calculates different covariances according to the error characteristics of the point cloud. This method enhances the constraints of high-quality point clouds, reduces the limitations on low-quality point clouds, and utilizes information more effectively. Experiments on the publicly available NTU-VIRAL dataset validate the effectiveness of ADC-LIO, which improves pose estimation accuracy and reduces absolute position errors compared to other state-of-the-art methods, including FAST-LIO, Faster-LIO, FR-LIO, and Point-LIO. The proposed ADC-LIO is an appealing odometry method that delivers accurate, real-time, and reliable tracking and map-building results, posing a practical solution for robotic applications in structured indoor and GPS-denied outdoor environments.
Volume: 14
Issue: 4
Page: 399-408
Publish at: 2025-12-01

Perceptions and institutional readiness for generative AI adoption in education using a multi-method approach

10.11591/ijere.v14i6.35245
Ken Gorro , Elmo Ranolo , Lawrence Roble , Adrian Ybañez , Anthony Ilano , Joseph Pepito , Rue Nicole Santillan , Cesar Ranolo , Emardy Barbecho , Purity Mata , Anna Marie Neiz
The rapid emergence of generative artificial intelligence (GenAI) tools like ChatGPT is reshaping educational practices, presenting both transformative opportunities and institutional challenges. This study offers a novel, integrative framework for understanding the adoption of GenAI tools in higher education by combining quantitative and qualitative analyses within a hybrid methodological design. Specifically, it is the first to incorporate the analytical hierarchy process (AHP), fuzzy decision-making trial and evaluation laboratory (Fuzzy DEMATEL), and the extended technology acceptance model (ETAM) in a unified model of adoption, augmented by thematic analysis of user experiences. A stratified random sample of 1,297 participants—comprising 1,191 students and 105 faculty members from various departments—ensured proportional representation across the university. AHP was employed to prioritize key adoption criteria, Fuzzy DEMATEL uncovered the causal interdependencies among constructs, and ETAM validated the direct and indirect effects influencing behavioral intention. Thematic analysis provided contextual depth regarding institutional barriers and individual perceptions. Findings reveal that attitude toward GenAI and intention to use (IU) are the strongest drivers of adoption. Notably, university support (US) emerged as a central enabler, significantly influencing both awareness and perceived usefulness (PU). This study contributes a comprehensive and multi-method framework that educational institutions can use to ethically, effectively, and equitably integrate GenAI technologies into academic ecosystems.
Volume: 14
Issue: 6
Page: 4770-4784
Publish at: 2025-12-01

Techno-economic optimization of hybrid renewable energy systems for household energy management

10.11591/ijape.v14.i4.pp1035-1043
Faisal Irsan Pasaribu , Suwarno Suwarno , Surya Hardi , Ahmad Taufik , Albert Panjaitan , Aimil Musfi Andri , Muhammad Reza Aulia
Housing is a private palace that is safe, comfortable, and private. Techno-economic optimization of hybrid renewable energy systems and energy management for realizing green energy is a fundamental concept for ensuring security, comfort, and privacy in green housing for its residents, enabling them to carry out activities in their environment. The application of techno-economic optimization and renewable energy management to manage electrical energy so that it can be saved so that electricity costs can be reduced as one of the energy efficiency models. The problem of waste emissions and environmental pollution cannot be avoided. Therefore, a techno-economic optimization model for integrated power generation is needed, which is environmentally friendly and related to the housing problem discussed in this study. This study supports the concept that hybrid housing development is the best way to address environmental pollution, emissions, and waste in future housing and can be used as a benchmark for future housing development. In addition, the techno-economics of renewable energy used in households was also discussed.
Volume: 14
Issue: 4
Page: 1035-1043
Publish at: 2025-12-01

Three-phase power flow solution of active distribution network using trust-region method

10.11591/ijape.v14.i4.pp923-933
Rudy Gianto , M. Iqbal Arsyad , Managam Rajagukguk
Distribution systems or networks are inherently unbalanced. As a result, single-phase power flow methods are generally no longer valid for such systems. Therefore, to obtain accurate results, unbalanced systems should be analyzed using three-phase power flow methods, which are far more complicated than the single-phase methods. Moreover, at present, the penetration of distributed generation (DG) in the distribution network has significantly increased. DG integration will increase the complication of the power flow analysis as it changes the network's basic configuration from passive to active system. This computational burden will significantly be higher if the power flow calculation has to be conducted several times (for example, in feeder reconfigurations or service restorations). This paper investigates the utilization of the trust-region method in obtaining the solution to the three-phase power flow problem of an active distribution network (i.e., distribution network embedded with DG). Trust-region computation algorithm is robust and powerful since the optimization technique is employed in finding new solutions in the iteration process. Results obtained from three representative unbalanced distribution networks (i.e., 10-node, 19-node, and 25-node networks) verify the validity of the proposed method. The effects of DG installation on distribution network steady-state performances are also investigated in the present paper.
Volume: 14
Issue: 4
Page: 923-933
Publish at: 2025-12-01

Transmission line fault detection using empirical mode decomposition in presence of wind intermittency

10.11591/ijape.v14.i4.pp960-969
Venkata Krishna Bokka , E. R. Biju , Sai Veerraju Mortha , Majahar Hussain Mahammad , Shaik Mohammad Irshad
The regular fault detection approaches are failed to detect the faults in wind integrated transmission networks due to intermittency nature of the wind energy. More reliable schemes are required to accomplish the detection of faults in presence wind. This article proposed empirical mode decomposition (EMD) based fault detection scheme to detect various faults in wind integrated transmission lines during the normal and stressed conditions of the system. The instantaneous current measurements available at either sending or receiving end are processed through EMD to decompose it into a series of intrinsic mode functions (IMFs) and IMF2 is identified as a dominated IMF with numerous case wise investigations. 1/4th cycle moving window is used to calculate the absolute sum of the IMF2 coefficients to detect the faults with the support of a predefined threshold. The efficacy of the method is tested on different types of faults during the normal condition in presence of wind and later extended to stressed conditions such as power swing. The method is reliable during the typical cases and includes remote end and high resistance faults. All the experiments are carried out in Simulink to generate the measurement data and programs are executed in MATLAB.
Volume: 14
Issue: 4
Page: 960-969
Publish at: 2025-12-01

A hybrid transformer-graph neural networks framework for enhanced physical activity recognition and sedentary behavior analysis

10.11591/ijra.v14i4.pp429-438
Sudarsanam Anandanarayanan , Suvarnalingam Thirumaran
Sedentary behavior has been identified as a major risk factor for chronic diseases such as cardiovascular disorders, obesity, and diabetes. The accurate prediction of sedentary health risks is essential for early intervention and personalized healthcare strategies. This study proposes a novel machine learning-based predictive model that leverages transformer-based architectures and graph neural networks to analyze multidimensional behavioral data. Unlike traditional models, our approach incorporates temporal attention mechanisms to capture long-term dependencies in activity patterns and graph-based learning to model complex relationships between physiological and behavioral factors. The study utilizes real-world datasets, including wearable sensor data and self-reported activity logs, to train and validate the models. Experimental results demonstrate that the proposed framework outperforms conventional machine learning techniques such as random forest and XGBoost, achieving superior predictive accuracy and robustness. The findings highlight the potential of advanced machine learning algorithms in assessing sedentary health risks, enabling proactive health management and intervention strategies.
Volume: 14
Issue: 4
Page: 429-438
Publish at: 2025-12-01
1 2 3
...
2097 2098
Show 193 of 2098

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