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

31,042 Article Results

A deep learning approach for electric vehicle battery charging duration estimation using IoT

10.11591/ijape.v15.i3.pp1375-1385
Tumuluri Kanthimathi , Adhimoolam Sairam , Durairaj Chandrakala , Moorthy Radhika , Bichagal Shadaksharappa , Pitchai John Britto , Minakshi Sanadhya , Balasubramanian Suganya , Chelliah Srinivasan
The rapid development of electric vehicles (EVs) has increased the desire for precise charging duration estimate to enhance charging station administration and elevate customer experience. This research presents a deep learning (DL) architecture that uses internet of things (IoT)-enabled data to categorise charging duration into short, medium, and long classifications. The assessment dataset comprises many numerical and categorical variables affecting battery performance and charging behaviour, providing a thorough foundation for prediction. The system utilises a deep neural network (DNN) architecture with nonlinear transformations and regularisation techniques, trained with adaptive optimisation to provide durable convergence. Extensive experiments indicate that the proposed model achieves an overall accuracy of 99.26%, markedly improving traditional machine learning (ML) techniques. These results highlight the potential of DL to adeptly discern complex linkages in charging dynamics, providing dependable predictions for duration classification. The framework provides an advanced basis for implementation in smart charging infrastructures, facilitating effective scheduling, minimizing waiting times, and endorsing predictive maintenance measures. It enhances the reliability and efficiency of EV charging ecosystems with data-driven, IoT-enabled DL technologies.
Volume: 15
Issue: 3
Page: 1375-1385
Publish at: 2026-09-01

Real time fuzzy energy management of hybrid storage systems in DC microgrids with dynamic voltage restorer assisted power quality enhancement

10.11591/ijpeds.v17.i3.pp2197-2209
Yacine Benatallah , Abdelkrim Benali , Mabrouk Dahane , Somia Benali
This paper presents a real-time fuzzy logic-based energy management system (EMS) for a hybrid DC microgrid supplying a constant DC load and an AC sensitive load protected by a dynamic voltage restorer (DVR). The system integrates a 25-kW photovoltaic (PV) array, a 10-kW fuel cell (FC), a 15-kW battery energy storage system, and a 396 V supercapacitor bank. The EMS calculates the net power balance (ΔP = PPV - Pload), compares it with the states-of-charge (SoC) of the battery and supercapacitor, and dynamically allocates power references to each source. Fuzzy rules prioritize renewable generation, exploit the supercapacitor for fast transient compensation, and schedule the battery and fuel cell for medium- and long-term power balancing. The DVR acts as a series active power filter, injecting real power during sags and absorbing excess energy during swells, while the EMS maintains DC bus stability under fault conditions. Simulation results demonstrate enhanced DC bus voltage regulation, reduced battery cycling, efficient hydrogen utilization, and rapid recovery from voltage disturbances. The proposed strategy improves power quality and ensures continuous operation of sensitive loads, making it suitable for smart grid and renewable-based microgrid applications.
Volume: 17
Issue: 3
Page: 2197-2209
Publish at: 2026-09-01

Multi-objective planning of distributed resources (PV and SVC) with NSGA-II for radial networks: application to the IEEE 33-bus test system

10.11591/ijape.v15.i3.pp1243-1252
Hassane Ousseyni Ibrahim , Abdoul Malik Maman Issaka , Moussa Gonda , Arouna Oloulade , François-Xavier Fifatin
The quality of electricity supply in distribution networks is critically dependent on minimizing active power losses and ensuring voltage stability. This study proposes a unified multi-objective optimization approach for the simultaneous placement and sizing of a photovoltaic (PV) source and a static var compensator (SVC) in radial networks. The non-dominated sorting genetic algorithm II (NSGA-II) is employed as the robust methodology to generate the Pareto optimal front, effectively exploring the trade-offs between two conflicting objectives: active loss minimization and voltage profile improvement. Unlike sequential or single-unit optimization strategies, this joint optimization framework is the key novelty, leveraging the specific physical interaction between PV active power injection and SVC-based dynamic reactive support to maximize overall network efficiency. Simulations are performed on the standard IEEE 33-bus test system. The results demonstrate that the optimal and coordinated integration of a 0.97 MW PV system at bus 14 and a 1.32 MVAr SVC at bus 30 yields superior electrical performance. Specifically, the system achieves a substantial active power loss reduction of 62.53% and decreases the voltage deviation index from 0.117 p.u. to a minimum of 0.0169 p.u., confirming the effectiveness of the proposed NSGA-II approach for comprehensive distributed resource planning.
Volume: 15
Issue: 3
Page: 1243-1252
Publish at: 2026-09-01

Condition assessment of medium voltage cable insulation using leakage current and phase-resolved partial discharge

10.11591/ijape.v15.i3.pp1340-1350
Kamrai Janprom , Sittadach Morkmechai , Natchanun Prainetr , Supachai Prainetr
Reliable operation of medium-voltage distribution networks critically depends on the integrity of cross-linked polyethylene (XLPE) insulated cables. This paper proposes a diagnostic methodology that integrates leakage current (LC) measurement with phase-resolved partial discharge (PRPD) analysis to assess cable insulation condition. A MATLAB R2025 simulation model is first developed to emulate partial discharge (PD) signals superimposed on leakage current, providing preliminary validation of the proposed approach. The method is then experimentally verified using a 70 mm² XLPE cable rated at 16/20 (24) kV and tested in accordance with IEC 60502. Under applied high-voltage stress, leakage current and PD activity are measured, and insulation degradation is characterized using PRPD patterns. Both simulation and experimental results confirm that the proposed method reliably detects insulation defects and provides accurate condition assessment of XLPE cables. These findings demonstrate the potential of the method as a practical tool for supporting condition-based maintenance in medium-voltage power distribution systems.
Volume: 15
Issue: 3
Page: 1340-1350
Publish at: 2026-09-01

Biophysiological responses of premature infants in neonatal nursing care: a descriptive study of infant and maternal characteristics

10.11591/ijphs.v15i3.27051
Dwi Hastuti , Anggorowati Anggorowati , Zubaidah Zubaidah , Tri Nur Kristina , Siti Yuyun Rahayu Fitri
Preterm infants are physiologically vulnerable and require continuous cardiorespiratory and thermal monitoring during neonatal nursing care. Evidence describing physiological indicators in relation to infant maturity and maternal sociodemographic characteristics remains limited. This study aimed to describe physiological indicators (heart rate, respiratory rate, oxygen saturation, and temperature) among preterm infants and examine their associations with infant and maternal characteristics. An observational descriptive study was conducted from August to December 2025 among preterm infants (
Volume: 15
Issue: 3
Page: 726-736
Publish at: 2026-09-01

Impact of power cable modelling on switching transient overvoltage analysis in medium voltage motors

10.11591/ijape.v15.i3.pp1233-1242
A. Nisar Basha , N. Mahiban Lindsay
Precise electrical cable representation is crucial for examining surge transient overvoltages in medium voltage (MV) motor systems. These brief overvoltages, initiated by swift switching actions, may induce substantial insulation strain, equipment degradation, and potential system failures. This study explores the influence of different power cable modeling techniques on transient overvoltage characteristics in MV motors during switching operations. Various modeling techniques, such as aggregated parameter, spread parameter, and frequency-dependent models, are evaluated for their effectiveness in inward capturing transient phenomena. Simulation studies using industry-standard electromagnetic temporary (EMT) assessment instruments evaluate the effect of these simulation methods on voltage spikes, shape distortions, and rise times. The discoveries indicate that exact electrical wire depiction is pivotal in molding, fleeting reactions, emphasizing the significance of choosing suitable simulation methods for efficient insulation coordination and system protection. This research provides valuable guidance for power system engineers, helping them mitigate transient overvoltage risks and improve the reliability of MV motor applications. Also, this study demonstrates electrical cable simulation that can impact the advice and verdicts obtained from moderate voltage motor.
Volume: 15
Issue: 3
Page: 1233-1242
Publish at: 2026-09-01

Microplastic exposure in anchovies: baseline evidence from small-island waters of Indonesia

10.11591/ijphs.v15i3.27108
Veronika Amelia Simbolon , Erpina Santi Meliana Nadeak , Demsa Simbolon , Ristina Rosauli Harianja
Microplastics are emerging contaminants in aquatic environments and may enter human exposure pathways through seafood consumption. However, baseline exposure data for small pelagic fish in small-island settings remain limited, particularly in Indonesia. Anchovy (Stolephorus spp.), which is commonly consumed whole, may represent a direct dietary exposure pathway. This study aimed to quantify and characterize microplastic contamination in anchovy collected from Dendun Island waters. A descriptive cross-sectional study was conducted in 2025 using 100 anchovy samples obtained from local catches. Microplastics were extracted using oxidative digestion followed by density separation, filtration, and stereomicroscopic observation. Data were analyzed descriptively. A total of 109 microplastic particles were identified, with a mean abundance of 1.09 particles per individual. Fibres dominated (67.0%), followed by films (20.2%) and fragments (12.8%). Various colours were observed, indicating heterogeneous particle characteristics. This study provides baseline evidence of microplastic contamination in anchovy from a small-island coastal setting, highlighting its potential as a dietary exposure pathway. These findings support the need for routine monitoring and strengthened plastic pollution control strategies to protect seafood safety and public health.
Volume: 15
Issue: 3
Page: 860-867
Publish at: 2026-09-01

FPGA-based hardware-defined phase generation for capacitor-less permanent split capacitor motor operation

10.11591/ijpeds.v17.i3.pp1728-1746
Lertrat Phewngam , Chaiwat Sirawattananon , Anchasa Pramuanjaroenkij
Permanent split capacitor (PSC) motors are widely used due to their simple structure and reliability; however, conventional operation depends on a fixed passive capacitor to generate phase displacement between the main and auxiliary windings, limiting controllability and adaptability. This paper proposes an FPGA-based hardware-defined phase generation architecture for capacitor-less PSC motor operation, where the capacitor phase function is replaced by digitally synthesized phase-displaced excitation signals. The proposed system was implemented on a Tang Nano 4K FPGA using multi-channel PWM generation with hardware-based dead-time protection. Experimental validation was performed on a capacitor-less PSC motor using programmable phase relationships of 60°, 90°, and 120° over excitation frequencies of 20-50 Hz. The measured main and auxiliary winding currents were analyzed to evaluate the effectiveness of the electronically synthesized phase displacement and to reconstruct the resultant rotating magnetic field. Quantitative evaluation using circularity index (CI) and ellipticity ratio (ER) showed that the 90° excitation condition produced the most balanced magnetic field trajectory among the tested configurations. The results demonstrate that FPGA-based hardware-defined phase generation provides a flexible, deterministic, and experimentally validated alternative to conventional capacitor-based PSC motor operation, while future work will focus on closed-loop optimization and efficiency-torque evaluation.
Volume: 17
Issue: 3
Page: 1728-1746
Publish at: 2026-09-01

Adaptive internal model control-proportional integral for robust control of three-phase active front-end rectifiers

10.11591/ijpeds.v17.i3.pp1794-1807
Azizah Abdul Razak , Norjulia Mohamad Nordin , Razman Ayop , Hazlina Selamat , Abobaker Kikki Abobaker , Nik Rumzi Nik Idris , Tole Sutikno
Three-phase active front-end (AFE) rectifiers are widely deployed in motor drives, electric vehicle chargers, and grid-connected renewable energy systems, where precise DC-link voltage regulation is essential for stable converter operation. In practice, DC-link capacitance degrades over time, and load profiles vary dynamically, both degrading the DC-link voltage regulation performance. Conventional proportional-integral (PI) outer voltage controllers are designed based on nominal operating conditions, with limited stability margins resulting in sluggish or oscillatory DC-link voltage responses under significant load and parameter variations. This paper proposes an adaptive internal model control-proportional integral (AIMC-PI) outer voltage loop controller for a three-phase AFE rectifier. It extends the conventional IMC-PI structure by incorporating an active damping term, an internal feedforward gain, a reference filter, and a Lyapunov-based adaptation law that updates the embedded plant model and IMC filter time constant online ensuring closed-loop stability and bounded tracking error. Simulation results show that AIMC-PI achieves a faster dynamic response than PI and performance comparable to IMC-PI and linear active disturbance rejection control (LADRC) under nominal conditions. As DC-link capacitance degrades to 0.5C, AIMC-PI maintains a well-damped DC-link voltage, whereas LADRC exhibits noticeable oscillations. Experimentally, AIMC-PI successfully eliminates the AC-supply current and DC-link voltage ripples present in fixed-λ IMC-PI.
Volume: 17
Issue: 3
Page: 1794-1807
Publish at: 2026-09-01

Occupational skin diseases: a cross-sectional survey analysis

10.11591/ijphs.v15i3.26924
Ineke Winda Ferianasari , Reza Yuridian Purwoko , Evy Aryanti , Azizah Boenjamin , Silvan Saputra , Asmail Asmail
Occupational skin diseases (OSDs) are among the most common occupational diseases worldwide, yet scientific data in Indonesia remain limited. This issue is important to study because workers across various sectors frequently encounter wet work, detergents, and chemical exposure. The present study aimed to assess individual and occupational risk factors associated with skin complaints/symptoms on the hands and forearms within the past 12 months and to test the feasibility of a simple prediction model in the Indonesian context. A cross-sectional study was conducted among 46 workers participating in health screening. Predictor variables included age, sex, type of occupation, length of employment, frequency of handwashing, shift work, and exposure status. Analysis was performed using Firth’s logistic regression with reporting of odds ratios (OR), 95% confidence intervals (CI), and significance testing. Model performance was evaluated using the Hosmer-Lemeshow test, AUC/ROC, and Nagelkerke’s pseudo-R². The prevalence of skin complaints reached 56.5%. Female workers had a 17-fold higher risk compared to males (OR = 17.20; 95% CI: 1.79-164.77; p = 0.014). The prediction model demonstrated good performance (AUC = 0.90; Hosmer-Lemeshow p = 0.307; Nagelkerke R² = 0.60). Female sex was identified as an important determinant of OSD in this population. The simple prediction model proved feasible for risk screening and could serve as a basis for prevention programs focusing on exposure control in Indonesia. Further studies with larger samples are needed to strengthen evidence across occupational categories.
Volume: 15
Issue: 3
Page: 633-639
Publish at: 2026-09-01

Smart road maintenance: real-time surface damage detection and mapping with YOLOv8

10.11591/ijict.v15i3.pp1331-1339
Preety Singh , Bommireddipalli Likhitha , Kolla Sahithi , Donthireddy Ganesh Reddy , Dammalapati Keerthana , Kolli Prasanna Adarsh
The degradation of road surfaces presents considerable obstacles for the management of urban infrastructure. This study presents a deep learning model based on YOLOv8 that can find many types of road faults, like potholes, longitudinal cracks, transverse cracks, and alligator cracks, using pictures, video streams, and live webcam feeds. The suggested system can find things with an accuracy of 91.2%, and the confidence levels range from 60% to 95%. Streamlit has been utilized to develop a web interface that makes it easier to use in real life. It makes it easy for users to choose inputs and provides outputs with notes and boundary boxes. GPS makes it possible to find problems with great accuracy, and a graphical dashboard presents damage categories and confidence levels in real time. Road maintenance is considerably more efficient with automated detection, location mapping, and easy-to-understand visualization. It is also easier to keep a check on smart municipal infrastructure. The results demonstrate that using computer vision and geospatial analytics together could make it easier to automatically check road conditions and make better decisions about how to run a city.
Volume: 15
Issue: 3
Page: 1331-1339
Publish at: 2026-09-01

Prognosis of vector borne dengue disease outbreak in urban areas using multivariate analysis

10.11591/ijict.v15i3.pp1066-1077
Pratik S. Machchar , Purvi N. Ramanuj , Rajan Patel , Jitendra Bhatia , Kuntesh Jani
Vector borne disease like dengue continues to pose a significant climate-sensitive public health challenge in tropical regions such as Brazil, Peru, and India. This study examines the feasibility of predicting dengue outbreaks using weekly multivariate time-series data from San Juan (SJ), Puerto Rico and Iquitos (IQ), Peru. Dengue incidence was analyzed alongside meteorological, environmental, and vegetation-based variables to capture key climatic influences. Several machine learning and deep learning approaches were evaluated, including LightGBM. Model performance was assessed using root mean square error (RMSE) and mean absolute error (MAE). The results show that LightGBM achieved the low est RMSE/MAE, indicating strong short-term predictive accuracy and excellent interpretability. Feature importance analysis and principal component analysis (PCA) identified precipitation, dew point temperature, and humidity as the most influential predictors of dengue incidence. The study demonstrates that advanced machine learning models can serve as reliable early warning systems for vector-borne diseases. While this research focuses on dengue, the methodology is adaptable to other vector-bone datasets and diseases, offering a flexible tool for public health authorities to predict and mitigate outbreaks in diverse urban contexts.
Volume: 15
Issue: 3
Page: 1066-1077
Publish at: 2026-09-01

A multi-expert approach to content-based image retrieval using feature fusion and late re-ranking

10.11591/ijict.v15i3.pp1376-1384
Ali Abdulazeez Mohammed Baqer Qazzaz , Yousif Samer Mudhafar
As digital data rapidly grows, content-based image retrieval (CBIR) has become important for optimizing collections of visual data. This work proposes a retrieval framework which operates in two stages and improves accuracy by using systematic fusion of features. In the first stage, first-stage wide-scope descriptors called bag-of-visual-words (BoVW), scattering wavelet transform (SWT), discrete cosine transform (DCT), and principal component analysis (PCA) retrieve initial candidate images. The second stage undertakes detailed re-ordering of candidate images by implementing the local binary pattern (LBP), histogram of oriented gradients (HOG), and singular value decomposition (SVD) descriptors to re-evaluate similarity scores. Each individual descriptor returned results for mean average precision for the top 10 retrieved images (mAP, top-10) of between 0.63 and 0.79 and the fused framework achieved 0.88, which is evidence of the viability of complementary feature integration. These findings support the hypothesis that while multiple descriptors performed well and delivered high retrieval accuracy, hierarchical fusion of multiple handcrafted descriptors does not involve the computational costs associated with deep learning methods.
Volume: 15
Issue: 3
Page: 1376-1384
Publish at: 2026-09-01

Lightweight parallel feedback network based on CRL with policy transfer and enhancement for image super-resolution

10.11591/ijict.v15i3.pp944-954
S V R Manimala , T Kavitha
Image super-resolution (SR) is essential in applications such as surveillance, medical imaging, and remote sensing, but existing deep learning (DL) models often require high computational resources and struggle to recover fine details in lightweight architectures. Although feedback and attention based methods have shown improvements, they still lack an effective combination of efficient feature refinement, edge enhancement, and low parameter complexity. To address this gap, we propose a lightweight parallel feedback network (LPFN) that combines three key components: a feedback block for repeated feature refinement, a dispersion-aware attention residual block (DARB) for highlighting important spatial and channel details, and EdgeNet for edge sharpening for sharper boundaries. These components are supported by curriculum reinforcement learning (CRL), an adaptive training strategy that gradually improves the model’s learning behavior. Instead of relying on a fixed loss function, LPFN uses a dynamically learned global feedback loss to refine reconstruction quality at each stage. Experiments on DIV2K and Flickr2K show that LPFN achieves higher PSNR and SSIMscores while keeping the model lightweight and efficient. This study emphasizes an effective lightweight feedback framework, an enhanced attention and edge-refinement mechanism, and an adaptive learning strategy that improves both accuracy and stability under different degradation conditions.
Volume: 15
Issue: 3
Page: 944-954
Publish at: 2026-09-01

Smart drones for human detection in disaster response

10.11591/ijict.v15i3.pp1179-1187
Menakadevi Nanjundan , Y. L. Ajay Kumar , V. R. Seshagiri Rao , Nagarjuna Telagam , Seetha Chaithanya , Manikadan S.
Natural disasters require swift, coordinated responses to minimise human casualties and infrastructure damage. This paper presents a novel AI-assisted drone system designed to enhance disaster relief efforts through advanced human detection and a distributed emergency Wi-Fi network. This drone system, equipped with state-of-the-art machine learning algorithms and thermal imaging, excels at locating and identifying individuals even in challenging conditions, such as smoke, debris, or low visibility. The drone fleet operates autonomously, dynamically forming an ad-hoc network that adapts to the evolving needs of the disaster zone. By integrating real-time data processing with efficient network management, our system provides a critical lifeline for communication and a powerful tool for rescuers to navigate and respond effectively. The detection and communication times are observed to be within the range of 5 to 8 seconds for this proposed system, which is widely used in disaster response.
Volume: 15
Issue: 3
Page: 1179-1187
Publish at: 2026-09-01
1 2 3
...
2069 2070
Show 11 of 2070

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