Byeongjun Kim^1,#, Seung-Hun Lee^2,#, Won-Du Chang^1,*

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.2, pp. 1237-1252, 2025, DOI:10.32604/cmes.2025.073530 - 26 November 2025

Abstract Side-scan sonar (SSS) is essential for acquiring high-resolution seafloor images over large areas, facilitating the identification of subsea objects. However, military security restrictions and the scarcity of subsea targets limit the availability of SSS data, posing challenges for Automatic Target Recognition (ATR) research. This paper presents an approach that uses Cycle-Consistent Generative Adversarial Networks (CycleGAN) to augment SSS images of key subsea objects, such as shipwrecks, aircraft, and drowning victims. The process begins by constructing 3D models to generate rendered images with realistic shadows from multiple angles. To enhance image quality, a shadow extractor and More >

José Velázquez, Dolores Ojados, Adrián Semitiel, Francisco Cavas^*

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.2, pp. 1821-1837, 2025, DOI:10.32604/cmes.2025.071131 - 26 November 2025

Abstract This research establishes a methodological framework for generating geometrically accurate 3D representations of human crystalline lenses through scanning technologies and digital reconstruction. Multiple scanning systems were evaluated to identify optimal approaches for point cloud processing and subsequent development of parameterized solid models, facilitating comprehensive morpho-geometric characterization. Experimental work was performed at the 3D Scanning Laboratory of SEDIC (Industrial Design and Scientific Calculation Service) at the Technical University of Cartagena, employing five distinct scanner types based on structured light, laser, and infrared technologies. Test specimens—including preliminary calibration using a lentil and biological analysis of a human… More >

Fang Yuan, Xueyao Gao^*, Chunxiang Zhang

CMC-Computers, Materials & Continua, Vol.85, No.3, pp. 5037-5055, 2025, DOI:10.32604/cmc.2025.067760 - 23 October 2025

Abstract 3D model classification has emerged as a significant research focus in computer vision. However, traditional convolutional neural networks (CNNs) often struggle to capture global dependencies across both height and width dimensions simultaneously, leading to limited feature representation capabilities when handling complex visual tasks. To address this challenge, we propose a novel 3D model classification network named ViT-GE (Vision Transformer with Global and Efficient Attention), which integrates Global Grouped Coordinate Attention (GGCA) and Efficient Channel Attention (ECA) mechanisms. Specifically, the Vision Transformer (ViT) is employed to extract comprehensive global features from multi-view inputs using its self-attention More >

Sofija Jovanović Stojanov¹, Marija Grozdanić¹, Mila Ljujić², Sandra Dragičević², Miodrag Dragoj¹, Jelena Dinić^1,*

Oncology Research, Vol.33, No.10, pp. 2741-2785, 2025, DOI:10.32604/or.2025.067126 - 26 September 2025

Abstract Anticancer drug resistance remains a major challenge in cancer treatment hindering the efficacy of chemotherapy and targeted therapies. Conventional two-dimensional (2D) cell cultures cannot replicate the complexity of the in vivo tumor microenvironment (TME), limiting their utility for drug resistance research. Therefore, three-dimensional (3D) tumor models have proven to be a promising alternative for investigating chemoresistance mechanisms. In this review, various cancer 3D models, including spheroids, organoids, scaffold-based models, and bioprinted models, are comprehensively evaluated with a focus on their application in drug resistance studies. We discuss the materials, properties, and advantages of each model, highlighting More > Graphic Abstract

Salvatore Brischetto^*, Domenico Cesare, Tommaso Mondino

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.1, pp. 643-668, 2025, DOI:10.32604/cmes.2025.066313 - 31 July 2025

Abstract This study proposes a three-dimensional (3D) coupled magneto-electro-elastic problem for the static analysis of multilayered plates embedding piezomagnetic and piezoelectric layers by considering both sensor and actuator configurations. The 3D governing equations for the magneto-electro-elastic static behavior of plates are explicitly show that are made by the three 3D equilibrium equations, the 3D divergence equation for magnetic induction, and the 3D divergence equation for the electric displacement. The proposed solution involves the exponential matrix in the thickness direction and primary variables’ harmonic forms in the in-plane ones. A closed-form solution is performed considering simply-supported boundary… More >

Nguyen Khac Toan¹, Ho Nguyen Anh Tuan², Nguyen Truong Thinh^1,*

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.2, pp. 1273-1295, 2025, DOI:10.32604/cmes.2025.064218 - 30 May 2025

Abstract This paper presents a novel method for reconstructing a highly accurate 3D nose model of the human from 2D images and pre-marked landmarks based on algorithmic methods. The study focuses on the reconstruction of a 3D nose model tailored for applications in healthcare and cosmetic surgery. The approach leverages advanced image processing techniques, 3D Morphable Models (3DMM), and deformation techniques to overcome the limitations of deep learning models, particularly addressing the interpretability issues commonly encountered in medical applications. The proposed method estimates the 3D coordinates of landmark points using a 3D structure estimation algorithm. Sub-landmarks… More > Graphic Abstract

Ziqiang Tang¹, Chao Han¹, Hongwu Li¹, Zhou Fan¹, Ke Sun¹, Yuntian Huang¹, Yuhang Chen², Chenxing Wang^2,*

CMC-Computers, Materials & Continua, Vol.82, No.2, pp. 2813-2829, 2025, DOI:10.32604/cmc.2024.059094 - 17 February 2025

Abstract Accurate vector extraction from design drawings is required first to automatically create 3D models from pixel-level engineering design drawings. However, this task faces the challenges of complicated design shapes as well as cumbersome and cluttered annotations on drawings, which interfere with the vector extraction heavily. In this article, the transmission tower containing the most complex structure is taken as the research object, and a semantic segmentation network is constructed to first segment the shape masks from the pixel-level drawings. Preprocessing and postprocessing are also proposed to ensure the stability and accuracy of the shape mask… More >

Muhammad Aliff Haiqal Darmawan¹, Shahrul Nizan Abd Mukti², Khairul Nizam Tahar^1,*

Revue Internationale de Géomatique, Vol.34, pp. 21-35, 2025, DOI:10.32604/rig.2024.057266 - 13 January 2025

Abstract Potholes are the most prevalent type of structural defect found on roads, caused by aging infrastructure, heavy rains, heavy traffic, thin or weak substructures, and other factors. Regular assessment of road conditions is essential for maintaining and improving road networks. Current techniques for identifying potholes on urban roadways primarily rely on public reporting, such as hotlines or social networking websites, which are both time-consuming and inefficient. This study aims to detect potholes using Unmanned Aerial Vehicles (UAVs) images, enabling accurate analysis of their size, shape, and location, thereby enhancing detection efficiency compared to conventional methods.… More >

Muhammad Akbar^1,2, Huali Pan^1,*, Jiangcheng Huang³, Bilal Ahmed⁴, Guoqiang Ou¹

CMES-Computer Modeling in Engineering & Sciences, Vol.141, No.3, pp. 2625-2625, 2024, DOI:10.32604/cmes.2024.059706 - 31 October 2024

Abstract This article has no abstract. More >

Chao Chen^1,2, Yankun Chen³, Haohai Jin⁴, Li Chen^5,*, Zhisong Liu³, Haozhe Sun⁴, Junchi Hong⁴, Haonan Wang⁴, Shiyu Fang⁴, Xin Zhang²

Intelligent Automation & Soft Computing, Vol.39, No.1, pp. 113-114, 2024, DOI:10.32604/iasc.2024.051760 - 29 March 2024

Abstract This article has no abstract. More >