Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Filter Icon

Filters article

Years

FAQ Arrow
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

28,188 Article Results

Enhancing software fault prediction using wrapper-based metaheuristic feature selection methods

10.11591/ijece.v15i5.pp4803-4812
Ha Thi Minh Phuong , Dang Thi Kim Ngan , Dao Khanh Duy , Nguyen Thanh Binh
The application of software fault prediction (SFP) to predict faulty components at the early stage has been investigated in various studies. Reducing feature redundancy is key to enhancing the predictive accuracy of SFP models. Feature selection methods are utilized to select and retain the features that contribute the most information while eliminating irrelevant or redundant features from software fault datasets. However, feature selection (FS) in the field of SFP remains a broad and continuously evolving field, encompassing a diverse range of techniques and methodologies. In this work, we study and perform empirical evaluation of ten wrapper FS methods, namely artificial butterfly optimization (ABO), atom search optimization (ASO), equilibrium optimizer (EO), Henry gas solubility optimization (HGSO), poor and rich optimization (PRO), generalized normal distribution optimization (GNDO), slime mold algorithm, Harris hawk’s optimization, pathfinder algorithm (PFA) and manta ray foraging optimization for resolving the data redundancy issue in SFP datasets. Experimental results on nine fault datasets from the PROMISE and AEEEM repositories show that the EO achieves the best performance, with PRO and HGSO ranking next. The comparative analysis revealed that ten wrapper-based FS methods demonstrated a substantial improvement in handling data redundancy issues for SFP.
Volume: 15
Issue: 5
Page: 4803-4812
Publish at: 2025-10-01

Applications of satellite information for rainwater estimation and usage: a comprehensive review

10.11591/ijece.v15i5.pp4671-4681
Laura Valeria Avendaño-García , Yeison Alberto Garcés-Gómez
Global climate change introduces significant uncertainty in water resource availability, making precipitation studies essential for societal sustainability. Satellite precipitation products (SPPs) have emerged as a vital alternative and complement to traditional meteorological station data for hydrological and climate research. This review examines scientific literature on SPP applications for daily, monthly, and annual rainfall estimations globally. Eleven widely used SPPs were identified, with the tropical rainfall measuring mission (TRMM) and climate hazards group infrared precipitation with station data (CHIRPS) standing out due to their frequent usage, high resolution, and extensive data records. A growing trend in research utilizes SPPs for hydrological studies and validates their estimates by contrasting satellite information with ground station measurements using continuous and categorical statistics. TRMM and CHIRPS, in particular, show precipitation accuracies closer to station data, influenced by local topography and climatology. Furthermore, SPP data, combined with geographic information systems (GIS), proves useful for identifying potential rainwater harvesting sites, offering an alternative information source to address water availability crises in drought-prone areas.
Volume: 15
Issue: 5
Page: 4671-4681
Publish at: 2025-10-01

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

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

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

Tomographic image reconstruction enhancement through median filtering and K-means clustering

10.11591/ijece.v15i5.pp4395-4408
Nguyen Quang Huy , Nguyen Truong Thang
Ultrasound tomography is a powerful and widely utilized imaging technique in the field of medical diagnostics. Its non-invasive nature and high sensitivity in detecting small objects make it an invaluable tool for healthcare professionals. However, a significant challenge associated with ultrasound tomography is that the reconstructed images often contain noise. This noise can severely compromise the accuracy and interpretability of the diagnostic information derived from these images. In this paper, we propose and rigorously evaluate the application of a median filter to address and mitigate noise artifacts in the reconstructed images obtained through the distorted born iterative method (DBIM). The primary aim is to enhance the quality of these images and thereby improve diagnostic reliability. The effectiveness of our proposed noise reduction approach is quantitatively assessed using the normalized error evaluation metric, which provides a precise measure of improvement in image quality. Furthermore, to enhance the interpretability and utility of the reconstructed images, we incorporate a basic machine learning technique known as K-means clustering. This method is employed to automatically segment the reconstructed images into distinct regions that represent objects, background, and noise. Hence, it facilitates a clearer delineation of different components within the images. Our results demonstrate that K-means clustering, when applied to images processed with the proposed median filter method, effectively delineates these regions with a significant reduction of noise. This combination not only enhances image clarity but also ensures that critical diagnostic details are preserved and more easily interpreted by medical professionals. The substantial reduction in noise achieved through our approach underscores its potential for improving the accuracy and reliability of ultrasound tomography in medical diagnostics.
Volume: 15
Issue: 5
Page: 4395-4408
Publish at: 2025-10-01

Remote sensing applied to cocoa crop identification, a thematic review

10.11591/ijece.v15i5.pp4848-4855
Luisa Fernanda Cuellar-Escobar , Vladimir Henao-Céspedes
This article presents a thematic review of 25 publications related to the use of remote sensing techniques for the identification of cocoa crops from 2000 to 2023. Although the use of remote sensing techniques is widely used for mapping different covers because it is very useful in discriminating them, the generation of maps of cocoa crops presents challenges due to their spectral behavior similar to that of forests. This is because cocoa cultivation, being an agroforestry system that is developed in association with timber trees, causes the classification algorithms used to fail to differentiate between forest cover and cocoa crops. For this reason, this study seeks to investigate the different remote sensing techniques used in the mapping of cocoa crops, as well as an analysis of the structure of the publications highlighting the connections between countries and the factors that motivated the authors to research this crop.
Volume: 15
Issue: 5
Page: 4848-4855
Publish at: 2025-10-01

Energy yields and performance analysis of vertical and tilted oriented bifacial photovoltaic modules in tropical region

10.11591/ijece.v15i5.pp4508-4519
Rudi Darussalam , Agus Risdiyanto , Ant Ardath Kristi , Agus Junaedi , Noviadi Arief Rachman , Dalmasius Ganjar Subagio , Muhammad Kasim , Udin Komarudin , Ahmad Fudholi
This study experimentally investigates the performance of bifacial photovoltaic (bPV) modules under vertical and tilted orientations in a tropical region. Related studies are reviewed, then performance metrics including solar radiation, module temperature, bifaciality gain, and energy yield were monitored and analyzed over a specified period. The aim is to determine the optimal orientation for maximizing output power generation, temperature module, and understanding the bifaciality factor through real-world conditions. The experimental setup consisted of three different bifacial photovoltaic module configurations: two vertically mounted with facing east-west (E/W) and north-south (N/S) respectively, while the third was tilted 15 facing north. The study findings revealed that the tilted orientation produced the highest energy yield of 1951 Wh, followed by the vertical east-west (E/W) and vertical north-south (N/S) orientations with 1504 Wh and 609 Wh, respectively. While tilted bPV module benefit from higher irradiance, they also experience elevated temperatures (39% above ambient) compared to vertically bPV modules (8-21%). This can negatively affect efficiency, especially during peak solar hours. The results also show that differences in bPV installation orientation affect the bifaciality factor and gain. These findings offer valuable guidance for optimizing bPV system design and deployment in tropical regions with low latitude, supporting sustainable energy solutions.
Volume: 15
Issue: 5
Page: 4508-4519
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

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

Discount factor-based data-driven reinforcement learning cascade control structure for unmanned aerial vehicle systems

10.11591/ijece.v15i5.pp4542-4554
Ngoc Trung Dang , Quynh Nga Duong
This article investigates the discount factor-based data-driven reinforcement learning control (DDRLC) algorithm for completely uncertain unmanned aerial vehicle (UAV) quadrotors. The proposed cascade control structure of UAV is categorized with two control loops of attitude and position sub-systems, which are established the proposed discount factor-based DDRLC algorithm. Through the analysis of the Bellman function's time derivative from two perspectives, a revised Hamilton-Jacobi-Bellman (HJB) equation including a discount factor is developed. Then, in the view of off-policy consideration, an equation is formulated to simultaneously solve the approximate Bellman function and approximate optimal control law in the proposed DDRLC algorithm with guaranteed convergence. According to the modified state variables vector, the development of the discount factor-based DDRLC algorithm in each control loop is indirectly implemented by transforming the time-varying tracking error model into the time invariant system. Finally, a simulation study on the proposed discount factor-based DDRLC algorithm is provided to validate its effectiveness. To validate the tracking performance of the quadrotor, four performance indices are considered, including IAE_p=3.0527, IAE_Ω=0.1175, ITAE_p=1.8408, and ITAE_Ω=0.0144, where the subscript p denotes position tracking error and Ω denotes attitude tracking error.
Volume: 15
Issue: 5
Page: 4542-4554
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

Multi-robot coverage algorithm in complex terrain based on improved bio-inspired neural network

10.11591/ijra.v14i3.pp348-360
Fangfang Zhang , Mengdie Duan , Jianbin Xin , Jinzhu Peng
Biological neural network (BNN) algorithms have become popular in coverage search in recent years. However, its edge activity values are weak, and it is simple to fall into a local optimum at a late stage of coverage. When applied to complex environments, the 3D BNN network structure has high computational and storage complexity. In order to solve the above problems, we propose an algorithm for multi-robot cooperative coverage of complex terrain based on an improved BNN. The algorithm models the complex terrain using a 2.5-dimensional (2.5D) elevation map. Combining the dual-layer BNN network with the 2.5D elevation map, we propose an elevation value priority mechanism. This mechanism lets the robot make elevation-based decisions and prioritizes higher terrain areas. The dual neural network's first layer plans the robot's path in normal mode. The second network layer helps the robot escape the local optimum. Finally, the algorithm's full coverage effect in complex terrains and the speed of covering high terrain are verified by simulations. The experiments show that our algorithm preferentially covers high points of the region and eventually covers 100% of complex terrain. Compared with other algorithms, our algorithm covers more efficiently and takes fewer steps than others. The speed of covering high terrain areas has increased by 34.51%.
Volume: 14
Issue: 3
Page: 348-360
Publish at: 2025-09-01

Hybrid deep learning and active contour for segmenting hazy images

10.11591/ijra.v14i3.pp429-437
Firhan Azri Ahmad Khairul Anuar , Jenevy Jone , Raja Farhatul Aiesya Raja Azhar , Abdul Kadir Jumaat
Image segmentation seeks to distinguish the foreground from the background for further analysis. A recent study presented a new active contour model (ACM) for image segmentation, termed Gaussian regularization selective segmentation (GRSS). This interactive ACM is effective for segmenting certain objects in images. However, a weakness of the GRSS model becomes apparent when utilized on hazy images, as it is not intended for such conditions and produces inadequate outcomes. This paper introduces a new ACM for segmenting hazy images that hybridizes a pretrained deep learning model, namely DehazeNet, with the GRSS model. Specifically, the haze-free images are estimated using DehazeNet, which fuses the information with the GRSS model. The new formulation, designated as GRSS with DehazeNet (GDN), is addressed via the calculus of variations and executed in MATLAB software. The segmentation accuracy was evaluated by calculating Error, Jaccard, and Dice metrics, while efficiency was determined by measuring processing time. Despite the increased processing time, numerical experiments demonstrated that the GDN model achieved higher accuracy, as indicated by the lower error and higher Jaccard and Dice than the GRSS model. The GDN model can potentially be formulated in the vector-valued image domain in the future.
Volume: 14
Issue: 3
Page: 429-437
Publish at: 2025-09-01

LoRa-enabled remote-controlled surveillance robot for monitoring and navigation in disaster response missions

10.11591/ijra.v14i3.pp311-321
Anita Gehlot , Rajesh Singh , Rahul Mahala , Mahim Raj Gupta , Vivek Kumar Singh
Rescue missions must be conducted within a strict timeframe, and the safety of all rescuers and civilians is prioritized. The proposed system aims to design a remote-operated aerial surveillance robot for disaster-affected areas for search and rescue missions. Real-time video transmission and RS-232 long-range communication enable operators to navigate rough environments and monitor data collected in real-time. This powerful tool ensures the protection of human life while collecting accurate and meaningful data. Cloud storage for data and surveillance strengthens the system, preventing part failure and fostering collaboration among users. This is a significant step towards using Internet of Things systems alongside remote-controlled robots in disaster response. The robot's key contribution to disaster management is identifying the environment, addressing issues of no visibility, complicated terrains, and speed. Its modification and expansion capabilities make it useful in armed surveillance, industrial monitoring, and environmental studies, making it an important innovation for many other fields.
Volume: 14
Issue: 3
Page: 311-321
Publish at: 2025-09-01
Show 8 of 1880

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