Yahya Alhaj Maz¹, Mohammed Anbar¹, Selvakumar Manickam^1,*, Mosleh M. Abualhaj², Sultan Ahmed Almalki³, Basim Ahmad Alabsi⁴

CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 5287-5307, 2025, DOI:10.32604/cmc.2025.068257 - 23 October 2025

Abstract The Internet of Things (IoT) is an innovation that combines imagined space with the actual world on a single platform. Because of the recent rapid rise of IoT devices, there has been a lack of standards, leading to a massive increase in unprotected devices connecting to networks. Consequently, cyberattacks on IoT are becoming more common, particularly keylogging attacks, which are often caused by security vulnerabilities on IoT networks. This research focuses on the role of transfer learning and ensemble classifiers in enhancing the detection of keylogging attacks within small, imbalanced IoT datasets. The authors propose… More >

Candan Tumer¹, Erdal Guvenoglu², Volkan Tunali^3,*

CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 5135-5158, 2025, DOI:10.32604/cmc.2025.067840 - 23 October 2025

Abstract Automated cartoon character recognition is crucial for applications in content indexing, filtering, and copyright protection, yet it faces a significant challenge in animated media due to high intra-class visual variability, where characters frequently alter their appearance. To address this problem, we introduce the novel Kral Sakir dataset, a public benchmark of 16,725 images specifically curated for the task of multi-label cartoon character classification under these varied conditions. This paper conducts a comprehensive benchmark study, evaluating the performance of state-of-the-art pretrained Convolutional Neural Networks (CNNs), including DenseNet, ResNet, and VGG, against a custom baseline model trained More >

Yijin Zhang, Panding Wang^*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.33, No.2, pp. 1-1, 2025, DOI:10.32604/icces.2025.011144

Abstract As a type of porous material with high porosity and a large surface-area-to-volume ratio, triply periodic minimal surface (TPMS) structures divide space into two non-interconnected parts. This increases the contact area while maintaining full connectivity and smoothness, which helps reduce flow resistance, making it naturally suited for applications in heat exchange designs. The advancement of additive manufacturing (AM) technology has contributed to the development of TPMS-based heat exchangers. However, due to the complexity of fluid heat exchanger designs, developing effective representations, models, and optimization schemes for TPMS structures in multi-fluid heat exchange problems is very… More >

Zihao Yang^1,*, Jiarui Cheng¹, Zefeng Li², Yirong Yang¹, Linghong Tang¹, Wenlan Wei¹

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.9, pp. 2149-2176, 2025, DOI:10.32604/fdmp.2025.067739 - 30 September 2025

Abstract This study presents a two-dimensional, transient model to simulate the flow and thermal behavior of CO₂ within a fracturing wellbore. The model accounts for high-velocity flow within the tubing and radial heat exchange between the wellbore and surrounding formation. It captures the temporal evolution of temperature, pressure, flow velocity, and fluid density, enabling detailed analysis of phase transitions along different tubing sections. The influence of key operational and geological parameters, including wellhead pressure, injection velocity, inlet temperature, and formation temperature gradient, on the wellbore’s thermal and pressure fields is systematically investigated. Results indicate that due to… More >

Yifan Wang¹, Shan Qing^1,2,*, Jifan Li^1,3,*, Xiaohui Zhang^1,3, Junxiao Wang⁴

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.9, pp. 2253-2272, 2025, DOI:10.32604/fdmp.2025.067429 - 30 September 2025

Abstract Heat and mass transfer within an electric arc furnace are strongly influenced by extreme temperatures and complex electromagnetic fields. Variations in temperature distribution play a crucial role in determining melt flow patterns and in the formation of stagnant regions, commonly referred to as dead zones. To better understand the internal flow dynamics and thermal behavior of the furnace, this study develops a multiphysics coupled model that integrates fluid heat transfer with Maxwell’s electromagnetic field equations. Numerical simulations are conducted to systematically examine how key operational parameters, such as electric current and arc characteristics, affect the… More >

Carlos Quiterio Gómez Muñoz¹, Fausto Pedro García Márquez^2,*, Jorge Bernabé Sanjuán³

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.3, pp. 3369-3386, 2025, DOI:10.32604/cmes.2025.069225 - 30 September 2025

Abstract Due to the continuous increase in global energy demand, photovoltaic solar energy generation and associated maintenance requirements have significantly expanded. One critical maintenance challenge in photovoltaic installations is detecting hot spots, localized overheating defects in solar cells that drastically reduce efficiency and can lead to permanent damage. Traditional methods for detecting these defects rely on manual inspections using thermal imaging, which are costly, labor-intensive, and impractical for large-scale installations. This research introduces an automated hybrid system based on two specialized convolutional neural networks deployed in a cascaded architecture. The first convolutional neural network efficiently detects More >

Ning Liu^1,*, Dong Cai¹, Shi-Kai Jian^2,3,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.33, No.1, pp. 1-1, 2025, DOI:10.32604/icces.2025.012511

Abstract One intriguing phenomenon in seismograms is seismic coda, once dismissed as noise. In 1969, seismologist Aki proposed that these coda waves reveal critical insights into small-scale inhomogeneities in the Earth's interior [1]. This scattering effect highlights geological complexity and offers valuable information for exploring targets like unconventional oil and gas reservoirs [2-5]. This paper examines elastic wave propagation and scattering in solid media. We validate the effectiveness of simulating wave field scattering by employing the discrete element method alongside energy radiative transfer theory. Then, we explore elastic wave scattering and scale inversion of non-homogeneous bodies More >

Musulmon Lolaev¹, Anand Paul^2,*, Jeonghong Kim¹

CMC-Computers, Materials & Continua, Vol.85, No.2, pp. 4155-4171, 2025, DOI:10.32604/cmc.2025.064758 - 23 September 2025

Abstract Transfer learning is the predominant method for adapting pre-trained models on another task to new domains while preserving their internal architectures and augmenting them with requisite layers in Deep Neural Network models. Training intricate pre-trained models on a sizable dataset requires significant resources to fine-tune hyperparameters carefully. Most existing initialization methods mainly focus on gradient flow-related problems, such as gradient vanishing or exploding, or other existing approaches that require extra models that do not consider our setting, which is more practical. To address these problems, we suggest employing gradient-free heuristic methods to initialize the weights… More >

Chen Zhu¹, Xiao Ma¹, Lumin Chen², Qi Ma¹, Yi Sun¹, Fuping Qian^1,*

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.8, pp. 1895-1915, 2025, DOI:10.32604/fdmp.2025.067899 - 12 September 2025

Abstract The rotary gas-gas heat exchanger (GGH) is a vital component in waste heat recovery systems, particularly for Selective Catalytic Reduction (SCR) processes employed in cement kiln operations. This study investigates the thermal performance of a rotary GGH in medium- and low-temperature denitrification systems, using a simplified porous medium model based on its actual internal structure. A porous medium representation is developed from the structural characteristics of the most efficient heat transfer element, and a local thermal non-equilibrium (LTNE) model is employed to capture the distinct thermal behaviors of the solid matrix and gas phase. To… More >

Sami Alrabie^#,*, Ahmed Barnawi^#

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.2, pp. 2481-2519, 2025, DOI:10.32604/cmes.2025.067977 - 31 August 2025

Abstract In the effort to enhance cardiovascular diagnostics, deep learning-based heart sound classification presents a promising solution. This research introduces a novel preprocessing method: iterative k-means clustering combined with silhouette score analysis, aimed at downsampling. This approach ensures optimal cluster formation and improves data quality for deep learning models. The process involves applying k-means clustering to the dataset, calculating the average silhouette score for each cluster, and selecting the cluster with the highest score. We evaluated this method using 10-fold cross-validation across various transfer learning models from different families and architectures. The evaluation was conducted on… More >