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

Real time object detection for advanced driver assistance systems using deep learning techniques

10.11591/ijece.v15i5.pp4942-4953
Sudarshan Sivakumar , Shikha Tripathi
Object detection plays a critical role in advanced driver assistance systems (ADAS), where timely and accurate detection of objects on road is essential for vehicular safety. In this study, we propose and evaluate deep learning-based object detection techniques—specifically, convolutional neural networks (CNN) and dense neural networks for real-time object detection. The proposed model is trained on a publicly available image dataset demonstrating its potential to enhance the reliability of ADAS systems without the use of an image preprocessing block. Here the system automatically stops without any human intervention. Our results highlight the strengths and limitations of using CIFAR-10, CIFAR-100 and YOLO datasets for transfer learning, pre-training and algorithm classification. Improvements in model optimization and hardware integration have been achieved using hardware in loop (HIL) set up. The models are evaluated on CIFAR-10, CIFAR-100 and YOLO datasets, with a focus on the impact of image pre-processing on detection accuracy and speed. Experimental results show that the proposed algorithm outperforms the previous methods, by achieving a better accuracy, contributing to safer and robust system without an additional image preprocessing block.
Volume: 15
Issue: 5
Page: 4942-4953
Publish at: 2025-10-01

Experimental validation of a dual-band printed antenna array operating at 2.45/5.8 GHz with a high efficiency for wireless power transmission applications

10.11591/ijece.v15i5.pp4662-4670
Walid En-Naghma , Mohamed Latrach , Hanan Halaq , Abdelghani El Ougli
This paper presents a simple dual-band antenna element with a rectangular patch designed for the industrial, scientific, and medical bands at 2.45/5.8 GHz. The antenna achieves satisfactory simulated performance at both resonant frequencies, including a reflection coefficient below -10 dB, a voltage standing wave ratio (VSWR) not exceeding 1.2, radiation efficiencies of approximately 90% at 2.45 GHz and 95.55% at 5.8 GHz, and bandwidths of 125.80 MHz around 2.45 GHz and 308.60 MHz around 5.8 GHz. Building on this single-element design, an antenna array configuration comprising two elements etched on a Taconic TLY-5 substrate is developed. The two rectangular patches are connected via a T-junction to a 50 Ω excitation port. The proposed array's effectiveness is validated through simulations using three electromagnetic solvers and experimental measurements. The fabricated antenna array demonstrates improved performance, including a measured return loss of -16.78 dB at 2.45 GHz and -20.61 dB at 5.8 GHz, a VSWR not exceeding 1.5 (1.34 and 1.22 at 2.45 and 5.8 GHz, respectively), input impedance close to 50 Ω, high gain exceeding 8 dBi, bandwidths of 179.50 MHz at 2.45 GHz and 462.90 MHz at 5.8 GHz, and high radiation efficiencies of 96.54% at 2.45 GHz and 98.65% at 5.8 GHz. With only two patches, the proposed antenna array offers a compact, efficient, and practical solution for wireless power transmission applications, particularly for small wireless devices like rectenna systems, due to its simplicity, compact design, and excellent radiation efficiency.
Volume: 15
Issue: 5
Page: 4662-4670
Publish at: 2025-10-01

Comparative analysis of convolutional neural network architecture for post forest fire area classification based on vegetation image

10.11591/ijece.v15i5.pp4723-4731
Ahmad Bintang Arif , Imas Sukaesih Sitanggang , Hari Agung Adrianto , Lailan Syaufina
This study presents a comparative analysis of 7 Convolutional Neural Network (CNN) architectures—MobileNetV2, VGG16, VGG19, LeNet5, AlexNet, ResNet50, and InceptionV3—for classifying post-forest fire areas using field-based vegetation imagery. A total of 56 models were evaluated through combinations of batch size, input size, and optimizer. The results show that MobileNetV2, VGG16, and VGG19 outperformed other models, with validation accuracies exceeding 88%. MobileNetV2 emerged as the most balanced model, achieving 96% accuracy with the lowest model size and training time, making it ideal for resource-constrained applications. This study highlights the potential of CNN-based classification using mobile field imagery, offering an efficient alternative to costly and condition-dependent satellite or drone data. The findings support real-time, localized identification of burned areas after forest fires, providing actionable insights for prioritizing recovery areas and guiding ecological restoration and land rehabilitation strategies.
Volume: 15
Issue: 5
Page: 4723-4731
Publish at: 2025-10-01

Low complexity human fall detection using body location and posture geometry

10.11591/ijece.v15i5.pp4620-4629
Pipat Sakarin , Suchada Sitjongsataporn
This paper presents the human fall detection using body location (HFBL) and posture geometry. The main contribution of the proposed HFBL system is to reduce the computational complexity of fall detection system while maintaining accuracy, as most fall detection techniques rely on computationally complex algorithms from machine learning or deep learning. This approach examines the human posture by applying the image segmentation and ratio by posture geometry. Then, the distance transform is used to calculate the high brightness points on the human body. These points are the maximum values compared with the edge values. Afterward, one of these points is selected as a center point. A line is formed by this center point aligned horizontally to separate the upper area and lower area, then an intersection line is drawn through this center point vertically that can separate the four quadrants of body location. With the help of posture geometry, the angles are employed for prediction “Fall” or “NotFall” actions at each frame of video sequence. Referring to the dynamic balance, the ratio between the distance vectors from the center point to the right and left legs is calculated to confirm fall and non-fall activities, utilizing the Pythagorean trigonometric identity. For experiments, 2,542 images from the UR fall detection dataset, with dimensions of 640×480×3 were prepared through image segmentation to find the human body shape for analysis using the proposed HFBL system. Results demonstrate that the low computational HFBL approach can provide 91.23% accuracy, the precision value is 99.14%, the recall value is 84.48%, and the F1-score value is 91.22%.
Volume: 15
Issue: 5
Page: 4620-4629
Publish at: 2025-10-01

Enhancing source currents and ensuring load voltage stability in railway electrification system via unified power quality conditions implementation

10.11591/ijece.v15i5.pp4430-4444
Kittaya Somsai , Jeerapong Srivichai , Veera Thanyaphirak
In recent years, interest in electric railway system as a transportation solution for large urban areas has grown significantly. This increased attention stems from several key advantages, including environmental friendliness, high performance, reduced maintenance costs, and lower energy expenses. Railway electrification system rely on supplying power to trains through single-phase transformers. However, these transformers can cause issues such as current imbalances and harmonics at the system connection point, which may impact critical loads. Additionally, fluctuations in source voltage can influence the system's performance. This study examines the causes of unbalanced loading in railway electrification system and introduces an innovative unified power quality conditioner (UPQC) specifically designed for integration into low-voltage railway electrification system. The proposed UPQC aims to restore current balance, minimize harmonics, and enhance overall power quality. Furthermore, it addresses the mitigation of voltage sags in the power distribution network. The simulation results generated through MATLAB programming demonstrate the UPQC's effectiveness in enhancing system performance. The findings reveal that the UPQC reduces source current imbalance to less than 1.6% and total harmonic distortion (THD) to below 4.89% across all test scenarios. Additionally, the UPQC successfully maintains a load bus voltage of 25 kV during single-phase-to-ground and unbalanced three-phase-to-ground fault conditions.
Volume: 15
Issue: 5
Page: 4430-4444
Publish at: 2025-10-01

A solar-powered autonomous power system for aquaculture: optimizing dual-battery management for remote operation

10.11591/ijece.v15i5.pp4376-4386
Thomas Yuven Handaka Laksi , Levin Halim , Ali Sadiyoko
In Indonesia, growing fish consumption demands necessitate expanded, yet sustainable, fish production without sacrificing quality. The process of feeding and the quality of the surrounding water are important factors influencing fish quality. To address this, Parahyangan Catholic University's Fishery 4.0 project pioneers a unique technology that integrates water quality monitoring with a fish feeding feature. The design and implementation of an independent, reliable power module, which is fundamental to the functionality of this system, is at the focus of this research. This study shows that a designed power module adapted to the specific needs of Fishery 4.0 is feasible. The system powers all modules with a 12 V battery and is recharged with a solar panel. The battery can be charged to 95% capacity, yielding 8550 mAh from a 9000 mAh capacity. A UC-3906 charger IC controls the charging process, deliberately managing the parameters required for optimal battery charging. Particularly, when exposed to ideal solar radiation, the charger recharges a 9 Ah battery from 30% to full capacity in about 10 hours and 10 minutes. This study proposes a novel to battery management, which is critical for the operation of aquaculture equipment at isolated locations.
Volume: 15
Issue: 5
Page: 4376-4386
Publish at: 2025-10-01

New approximations for the numerical radius of an n×n operator matrix

10.11591/ijece.v15i5.pp4732-4739
Amer Hasan Darweesh , Adel Almalki , Kamel Al-Khaled
Many mathematicians have been interested in establishing more stringent bounds on the numerical radius of operators on a Hilbert space. Studying the numerical radii of operator matrices has provided valuable insights using operator matrices. In this paper, we present new, sharper bounds for the numerical radius 1/4 ‖|A|^2+|A^* |^2 ‖≤w^2 (A)≤1/2 ‖|A|^2+|A^* |^2 ‖, that found by Kittaneh. Specifically, we develop a new bound for the numerical radius w(T) of block operators. Moreover, we show that these bounds not only improve upon but also generalize some of the current lower and upper bounds. The concept of finding and understanding these bounds in matrices and linear operators is revisited throughout this research. Furthermore, the study emphasizes the importance of these bounds in mathematics and their potential applications in various mathematical fields.
Volume: 15
Issue: 5
Page: 4732-4739
Publish at: 2025-10-01

Dynamic head pose estimation in varied conditions using Dlib and MediaPipe

10.11591/ijece.v15i5.pp4581-4592
Rusnani Yahya , Rozita Jailani , Nur Khalidah Zakaria , Fazah Akhtar Hanapiah
This paper presents the formulation and validation of a dynamic head pose estimation (HPE) algorithm, addressing challenges related to diverse conditions, complex poses, and partial obstructions. The study aims to create a robust algorithm that maintains high accuracy in real-time applications across varying conditions. The algorithm was implemented and assessed using Dlib and MediaPipe models. The study involved 30 participants in face and head without obstacles, face with obstacles and head with obstacles conditions. The results demonstrated impressive performance in both controlled and spontaneous head movement categories. The algorithm achieved an average accuracy of 93% for head pose estimation and 88% in detecting visual attention under spontaneous head movement categories. A correlation coefficient of 0.866 indicates a strong positive linear association between performance and attention accuracy, indicating that performance improvements are intricately linked to proportional increases in attention accuracy. However, this does not necessarily imply causation. The findings provide valuable insights into the effectiveness of the proposed algorithms in assessing visual attention and demonstrate their potential applications in healthcare monitoring, educational intervention, and driver monitoring systems. The significance of these results lies in the ability to advance human-computer interaction, enhance healthcare diagnostics, and offer innovative solutions across various domains.
Volume: 15
Issue: 5
Page: 4581-4592
Publish at: 2025-10-01

Prospective applications of assistive robotics for the benefit of population groups

10.11591/ijece.v15i5.pp4531-4541
Anny Astrid Espitia-Cubillos , Robinson Jimenez-Moreno , Javier Eduardo Martínez-Baquero
The development of robotics has reached various fields of application such as the assistance field, where robots support people with different abilities in different activities to provide independence, comfort and interaction, even improving their self-esteem and quality of life. The objective is to identify the main benefits of the application of assistive robotics achieved to project its future fields of action. For this purpose, the Scopus database is used to find documents related to assistive robotics, which are filtered by publication date and according to the elimination criteria determined by the authors, and then bibliometric networks are constructed using VOSviewer. Finally, the main findings are analyzed and presented according to their area of application. Five areas of application of assistive robotics are identified that benefit children, the elderly, provide hospital assistance, help people with disabilities or support therapy and rehabilitation work, developments that allow the formulation of areas for future study. It is concluded that there are many advances in assistive robotics that demonstrate robotic development and provide assistance to a particular population, but more work is still needed to increase the number of beneficiaries, reduce costs and expand research in the areas mentioned and to be developed.
Volume: 15
Issue: 5
Page: 4531-4541
Publish at: 2025-10-01

The underlying physics concept of a soccer game as a catalyst for enhancing creative thinking skills

10.11591/ijere.v14i5.32682
Ida Sriyanti , Mardiah Afifa , Meilinda Meilinda , Anisya Sefina Puteri , Nyimas Aisyah , Wahyu Indra Bayu , Zulkardi Zulkardi , Ratu Ilma Indra Putri , Hapizah Hapizah
Teachers need to improve students’ creative thinking skills by incorporating relevant everyday contexts. Soccer, as a familiar part of daily life, has not been widely used in education, and its impact on creative thinking requires further study. This research aimed to develop a contextual physics e-module centered on soccer to enhance creative thinking in physics learning. The study followed Rowntree's development model, including planning, development, and evaluation, with Tessmer’s formative evaluation through expert reviews, one-on-one assessments, small-group evaluations, and field tests. The creative thinking indicators used in the research are fluency, flexibility, originality, and elaboration. Data were collected from 346 high school students in Palembang via walkthroughs, questionnaires, and written tests, then analyzed using SPSS version 16. The results showed that the soccer-based physics e-module is valid (Sig. 0.00), practical (one-to-one: 82.75%; small group: 91.00%), and in the moderate category for improving creative thinking (N-gain: 0.59). These findings highlight the need to explore other everyday contexts and assess the long-term impact of the e-module across different educational settings.
Volume: 14
Issue: 5
Page: 3712-3726
Publish at: 2025-10-01

TawjihiNavigator: a novel hybrid information retrieval system for educational guidance in Morocco

10.11591/ijere.v14i5.32803
Hassan Silkhi , Brahim Bakkas , Khalid Housni
In this paper, we propose a novel hybrid method for improving Arabic educational information retrieval (IR) in Moroccan high schools. Traditional search methods often struggle with Arabic’s rich morphology and educational terminology, hindering students’ access to accurate guidance information. The proposed method TawjihiNavigator that combines vector-based semantic search with lexical matching, enhanced by advanced Arabic natural language processing (NLP) techniques. Using a comprehensive dataset collected from official Ministry of education sources. To validate the IR-Abhato system, we integrate CAMeL Tools and Farasa stemmer for Arabic preprocessing, testing multiple embedding models including Word2Vec, FastText, and AraT5. The obtained results demonstrate that our hybrid method’s superiority over standalone vector and full-text search approaches, achieving a mean reciprocal rank (MRR) of 0.7987 and mean average precision (MAP) of 0.5628. The AraT5 model achieved the highest precision@5 score of 0.4500, specially in educational query processing. These findings indicate that our model enhances Arabic educational IR accuracy, that can be improve student decision-making processes.
Volume: 14
Issue: 5
Page: 3665-3674
Publish at: 2025-10-01

Practical specification of the speech universe of the maximum power point tracking controller based on the asymmetrical fuzzy logic: a dynamic behavior study of the photovoltaic system

10.11591/ijece.v15i5.pp4355-4365
Ahmed Amine Barakate , Sami Choubane , Abdelkader Hadjoudja
In this paper, we present a procedure for extracting data from a stand-alone photovoltaic (PV) panel to program a maximum power point tracking (MPPT) controller based on the fuzzy logic (FL) method, aiming to optimize the performance of the photovoltaic system. Photovoltaic data acquisition enables the determination of the input and output speech universe for the MPPT controller using fuzzy logic. This method adapts to nonlinear systems without requiring a complex mathematical model. Additionally, it improves the performance of the photovoltaic system in both dynamic and steady-state conditions. To further enhance the method’s efficiency, an asymmetric membership function concept is proposed based on the dynamic behavior study of the photovoltaic system. Compared to the symmetric method, the asymmetric fuzzy logic controller achieves higher maximum power output and better tracking precision. This technology is essential for maximizing photovoltaic panel efficiency, a key requirement as solar energy gains prominence as a clean and renewable energy source.
Volume: 15
Issue: 5
Page: 4355-4365
Publish at: 2025-10-01

Learning strategies in distance nursing education during the COVID-19 lockdown: a cross-sectional analysis

10.11591/ijere.v14i5.33377
Khadija Ait Moussa , Sabah Selmaoui , Nadia Ouzennou
The COVID-19 pandemic led to a rapid transition to distance learning (DL), significantly affecting nursing students due to the disruption of essential practical training. This cross-sectional descriptive study examines the learning strategies (LS) adopted by 200 students at the Higher Institute of Nursing and Health Techniques of Marrakech (ISPITS-M) and identifies the factors influencing their adoption. Data were collected using a structured, expert-validated questionnaire (Cronbach’s alpha=0.72). Statistical analyses, conducted using SPSS (version 25.0), included descriptive, bivariate, and multivariate analyses. The findings indicate a predominance of metacognitive strategies, such as planning and time management (63.8%), and cognitive strategies, including memorization (58.9%), which were often adopted intuitively. The blended learning mode (synchronous and asynchronous) (OR=0.621; p=0.013) and student satisfaction with pedagogical modalities (OR=1.446; p=0.019) emerged as key determinants of learning strategy adoption. These findings underscore the need to develop structured blended learning environments that foster interaction, student engagement, and digital competency training. Implementing targeted pedagogical interventions could enhance academic performance and adaptability, addressing the specific needs of health sciences education while promoting long-term student success.
Volume: 14
Issue: 5
Page: 4066-4075
Publish at: 2025-10-01

Field-programmable gate array-based voltage-feedback-driven battery charging with DC-DC buck converter

10.11591/ijece.v15i5.pp4993-5002
Afarulrazi Abu Bakar , Suhaimi Saiman , Tharnisha Sithananthan , Muhammad Nafis Ismail , Saidina Hamzah Che Harun
This paper presents the design and development of a reference-driven field-programmable gate array (FPGA)-based controllable battery charging system featuring a buck converter. The controller tracks and adjusts the system's duty cycle based on output voltage feedback. The primary goal was to introduce a digital pulse-width modulation generator program using a Hardware Description Language within a feedback loop. To enhance the buck converter's accuracy, the system's switching frequency was set to 20 kHz with an 8-bit counter, achieving a resolution of 0.390625% per clock cycle. An 8-bit parallel analog-to-digital converter provided feedback by measuring the output voltage and comparing it with the reference setpoint. The simulation model was developed using MATLAB/Simulink, while the Quartus II software was employed for controller programming. The resultant data was meticulously analyzed to assess the circuit's performance across various voltage and control parameters. To validate the proposed controller's effectiveness, a 400 W system prototype comprising a step-down transformer, rectifier, and buck converter was constructed and tested for voltage ranging from 24 to 72 V. Through FPGA-based digital control, this system demonstrated a voltage regulation accuracy of ±0.39 per clock cycle and the capability to continuously track and regulate the duty cycle with each clock trigger, ensuring precise control over the charging process.
Volume: 15
Issue: 5
Page: 4993-5002
Publish at: 2025-10-01

Development and testing of a dedicated cooling system for photovoltaic panels

10.11591/ijece.v15i5.pp4387-4394
Omar Elkhoundafi , Rachid Elgouri
Solar energy is a viable alternative to fossil fuels, but its efficiency is limited by photovoltaic panel overheating, which causes a decrease in efficiency. This paper suggests a passive cooling method that incorporates aluminum heat sinks beneath the solar cells. This simple, low-cost device maximizes heat dissipation using natural convection. It requires no external energy. The goal is to provide a solution to the challenge of selecting an effective, sustainable, and flexible cooling system while considering technological, economic, and environmental constraints. Experimental results demonstrate that modules fitted with heatsinks experience an average 8.13 °C drop in temperature, as well as a 0.51 V rise in open-circuit voltage when compared to the reference panel. This increase demonstrates how well-designed passive solutions can dramatically improve the energy performance of solar panels. The study emphasizes the relevance of thermal design in photovoltaic system optimization and provides specific opportunities for the development of more efficient solar technologies, particularly in high-temperature situations.
Volume: 15
Issue: 5
Page: 4387-4394
Publish at: 2025-10-01
1 2 3
...
2097 2098
Show 210 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