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 >

Alehegn Atalay Birlie^*

Journal of Renewable Materials, Vol.13, No.9, pp. 1783-1802, 2025, DOI:10.32604/jrm.2025.02025-0039 - 22 September 2025

Abstract This study explores vegan leather, an eco-friendly substitute for conventional animal-derived leather. Using materials like polyurethane, pineapple leaves, cork, and recycled plastics, vegan leather aims to transform the fashion industry and consumer products while addressing environmental concerns. Despite its advantages, challenges related to availability and durability persist. The booming market for vegan leather is expected to reach billions of dollars, reflecting a broader societal shift towards sustainable and cruelty-free alternatives. The review traces the historical development of vegan leather from its origins in Germany to modern innovations like Mylo and Piñatex. By comparing these materials More >

Shen-Haw Ju^*, Yi-Chen Huang

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.2, pp. 1631-1654, 2025, DOI:10.32604/cmes.2025.067679 - 31 August 2025

Abstract This study focuses on determining the second-order irregular wave loads in the time domain without using the Inverse Fast Fourier Transform (IFFT). Considering the substantial displacement effects that Floating Offshore Wind Turbine (FOWT) support structures undergo when subjected to wave loads, the time-domain wave method is more suitable, while the frequency-domain method requiring IFFT cannot be used for moving bodies. Nonetheless, the computational challenges posed by the considerable computer time requirements of the time-domain wave method remain a significant obstacle. Thus, the paper incorporates various numerical schemes, including parallel computing and extrapolation of wave forces… More >

Peng Sun^1,2, Dechen Yao^1,2,*, Jianwei Yang^1,2, Quanyu Long^1,2

Structural Durability & Health Monitoring, Vol.19, No.5, pp. 1221-1239, 2025, DOI:10.32604/sdhm.2025.066098 - 05 September 2025

Abstract Supervised learning-based rail fastener anomaly detection models are limited by the scarcity of anomaly samples and perform poorly under data imbalance conditions. However, unsupervised anomaly detection methods based on diffusion models reduce the dependence on the number of anomalous samples but suffer from too many iterations and excessive smoothing of reconstructed images. In this work, we have established a rail fastener anomaly detection framework called Diff-Fastener, the diffusion model is introduced into the fastener detection task, half of the normal samples are converted into anomaly samples online in the model training stage, and One-Step denoising… More >

Huagang Jin, Yu Zhou^*

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 751-768, 2025, DOI:10.32604/cmc.2025.067867 - 29 August 2025

Abstract Recently, ship detection technology has been applied extensively in the marine security monitoring field. However, achieving accurate marine ship detection still poses significant challenges due to factors such as varying scales, slightly occluded objects, uneven illumination, and sea clutter. To address these issues, we propose a novel ship detection approach, i.e., the Twin Feature Pyramid Network and Data Augmentation (TFPN-DA), which mainly consists of three modules. First, to eliminate the negative effects of slightly occluded objects and uneven illumination, we propose the Spatial Attention within the Twin Feature Pyramid Network (SA-TFPN) method, which is based More >

Ziyu Cui, Zijun Wei, Xiaohui Yuan, Pei Li^*

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.1, pp. 1045-1070, 2025, DOI:10.32604/cmes.2025.066659 - 31 July 2025

Abstract At present, noise reduction has become an urgent challenge across various fields. Whether in the context of household appliances in daily life or in the enhancement of stealth performance in military equipment, noise control technologies play a critical role. This study introduces a computational framework for simulating Helmholtz equation-governed acoustic scattering using a boundary element method (BEM) integrated with Loop subdivision surfaces. By adopting the Loop subdivision scheme—a widely used computer-aided design (CAD) technique—the framework unifies geometric representation and physical field discretization, ensuring seamless compatibility with industrial CAD workflows. The core innovation lies in the More >

Xinyu Li^1,2, Gang Wan², Xinyang Chen³, Liyue Qie³, Xinnan Fan³, Pengfei Shi³, Jin Wan^3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.1, pp. 1071-1090, 2025, DOI:10.32604/cmes.2025.064775 - 31 July 2025

Abstract The inherent limitations of 2D object detection, such as inadequate spatial reasoning and susceptibility to environmental occlusions, pose significant risks to the safety and reliability of autonomous driving systems. To address these challenges, this paper proposes an enhanced 3D object detection framework (FastSECOND) based on an optimized SECOND architecture, designed to achieve rapid and accurate perception in autonomous driving scenarios. Key innovations include: (1) Replacing the Rectified Linear Unit (ReLU) activation functions with the Gaussian Error Linear Unit (GELU) during voxel feature encoding and region proposal network stages, leveraging partial convolution to balance computational efficiency… More >

Rachana Poongodan¹, Dayanand Lal Narayan², Deepika Gadakatte Lokeshwarappa³, Hirald Dwaraka Praveena⁴, Dae-Ki Kang^5,*

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 5751-5772, 2025, DOI:10.32604/cmc.2025.066314 - 30 July 2025

Abstract In recent decades, brain tumors have emerged as a serious neurological disorder that often leads to death. Hence, Brain Tumor Segmentation (BTS) is significant to enable the visualization, classification, and delineation of tumor regions in Magnetic Resonance Imaging (MRI). However, BTS remains a challenging task because of noise, non-uniform object texture, diverse image content and clustered objects. To address these challenges, a novel model is implemented in this research. The key objective of this research is to improve segmentation accuracy and generalization in BTS by incorporating Switchable Normalization into Faster R-CNN, which effectively captures the… More >

Bandar Alotaibi^1,*, Aljawhara Almutarie², Shuaa Alotaibi³, Munif Alotaibi⁴

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 4451-4467, 2025, DOI:10.32604/cmc.2025.066050 - 30 July 2025

Abstract X (formerly known as Twitter) is one of the most prominent social media platforms, enabling users to share short messages (tweets) with the public or their followers. It serves various purposes, from real-time news dissemination and political discourse to trend spotting and consumer engagement. X has emerged as a key space for understanding shifting brand perceptions, consumer preferences, and product-related sentiment in the fashion industry. However, the platform’s informal, dynamic, and context-dependent language poses substantial challenges for sentiment analysis, mainly when attempting to detect sarcasm, slang, and nuanced emotional tones. This study introduces a hybrid… More >

Shivani Sood¹, Harjeet Singh^2,*, Surbhi Bhatia Khan^3,4,5,*, Ahlam Almusharraf⁶

CMC-Computers, Materials & Continua, Vol.84, No.2, pp. 2751-2787, 2025, DOI:10.32604/cmc.2025.060185 - 03 July 2025

Abstract Wheat fungal infections pose a danger to the grain quality and crop productivity. Thus, prompt and precise diagnosis is essential for efficient crop management. This study used the WFD2020 image dataset, which is available to everyone, to look into how deep learning models could be used to find powdery mildew, leaf rust, and yellow rust, which are three common fungal diseases in Punjab, India. We changed a few hyperparameters to test TensorFlow-based models, such as SSD and Faster R-CNN with ResNet50, ResNet101, and ResNet152 as backbones. Faster R-CNN with ResNet50 achieved a mean average precision More >