Nour El Houda Kaiber¹, Tahar Mekhaznia¹, Akram Bennour^1,*, Mohammed Al-Sarem^2,3,*, Zakaria Lakhdara⁴, Fahad Ghaban², Mohammad Nassef^5,6

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.070337 - 12 January 2026

Abstract The generation of high-quality 3D models from single 2D images remains challenging in terms of accuracy and completeness. Deep learning has emerged as a promising solution, offering new avenues for improvements. However, building models from scratch is computationally expensive and requires large datasets. This paper presents a transfer-learning-based approach for category-specific 3D reconstruction from a single 2D image. The core idea is to fine-tune a pre-trained model on specific object categories using new, unseen data, resulting in specialized versions of the model that are better adapted to reconstruct particular objects. The proposed approach utilizes a… More >

Bin Zhang^*, Zhancheng Xu

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-12, 2026, DOI:10.32604/cmc.2025.069979 - 09 December 2025

Abstract This study aimed to enhance the performance of semantic segmentation for autonomous driving by improving the 2DPASS model. Two novel improvements were proposed and implemented in this paper: dynamically adjusting the loss function ratio and integrating an attention mechanism (CBAM). First, the loss function weights were adjusted dynamically. The grid search method is used for deciding the best ratio of 7:3. It gives greater emphasis to the cross-entropy loss, which resulted in better segmentation performance. Second, CBAM was applied at different layers of the 2D encoder. Heatmap analysis revealed that introducing it after the second… More >

D. Haouanoh^a, M. Toubane^a,*, R. Talaighil^a, F. Bensouici^b

Chalcogenide Letters, Vol.22, No.2, pp. 177-188, 2025, DOI:10.15251/CL.2025.222.177

Abstract CZTS thin layers were successfully deposited onto both glass and indium-tin oxide substrates using the chemical bath deposition method. The effects of solution pH, deposition time, and annealing temperature on the structural, morphological, and optical properties were investigated. Thermal analysis (DSC/TGA) shows that the CZTS kesterite structure crystallized at 237.2°C. Structural analysis by X- ray Diffraction, Rietveld refinement and Raman spectroscopy, revealed that the kesterite phases formation with the presence of SnO₂cassiterite and ZnO wurtzite structures in the films annealed at a higher temperature with nanocrystalline size. SEM images showed smooth and homogeneous surfaces, with the More >

Seong-Su Yoon, Dong-Hyuk Shin, Ieck-Chae Euom^*

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.2, pp. 2683-2706, 2025, DOI:10.32604/cmes.2025.071577 - 26 November 2025

Abstract With the continuous expansion of digital infrastructures, malicious behaviors in host systems have become increasingly sophisticated, often spanning multiple processes and employing obfuscation techniques to evade detection. Audit logs, such as Sysmon, offer valuable insights; however, existing approaches typically flatten event sequences or rely on generic graph models, thereby discarding the natural parent-child process hierarchy that is critical for analyzing multiprocess attacks. This paper proposes a structure-aware threat detection framework that transforms audit logs into a unified two-dimensional (2D) spatio-temporal representation, where process hierarchy is modeled as the spatial axis and event chronology as the More >

Abdulnaser M. Alshoaibi^*, Yahya Ali Fageehi

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.1, pp. 189-214, 2025, DOI:10.32604/cmes.2025.071583 - 30 October 2025

Abstract Fatigue crack growth is a critical phenomenon in engineering structures, accounting for a significant percentage of structural failures across various industries. Accurate prediction of crack initiation, propagation paths, and fatigue life is essential for ensuring structural integrity and optimizing maintenance schedules. This paper presents a comprehensive finite element approach for simulating two-dimensional fatigue crack growth under linear elastic conditions with adaptive mesh generation. The source code for the program was developed in Fortran 95 and compiled with Visual Fortran. To achieve high-fidelity simulations, the methodology integrates several key features: it employs an automatic, adaptive meshing… More >

Yiming Guo, Hongyu Ma^*

CMC-Computers, Materials & Continua, Vol.85, No.2, pp. 3485-3505, 2025, DOI:10.32604/cmc.2025.067590 - 23 September 2025

Abstract In dynamic 5G network environments, user mobility and heterogeneous network topologies pose dual challenges to the effort of improving performance of mobile edge caching. Existing studies often overlook the dynamic nature of user locations and the potential of device-to-device (D2D) cooperative caching, limiting the reduction of transmission latency. To address this issue, this paper proposes a joint optimization scheme for edge caching that integrates user mobility prediction with deep reinforcement learning. First, a Transformer-based geolocation prediction model is designed, leveraging multi-head attention mechanisms to capture correlations in historical user trajectories for accurate future location prediction.… More >

Zilu Liu^1,#, Hongjin Zhu^2,#,*

CMC-Computers, Materials & Continua, Vol.85, No.1, pp. 681-694, 2025, DOI:10.32604/cmc.2025.064191 - 29 August 2025

Abstract Real-time detection of surface defects on cables is crucial for ensuring the safe operation of power systems. However, existing methods struggle with small target sizes, complex backgrounds, low-quality image acquisition, and interference from contamination. To address these challenges, this paper proposes the Real-time Cable Defect Detection Network (RC2DNet), which achieves an optimal balance between detection accuracy and computational efficiency. Unlike conventional approaches, RC2DNet introduces a small object feature extraction module that enhances the semantic representation of small targets through feature pyramids, multi-level feature fusion, and an adaptive weighting mechanism. Additionally, a boundary feature enhancement module More >

Jingao Wu^1,2, Yong Fan^1,2,*, Zhendong Leng^1,3, Guangdong Yang^1,2

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.1, pp. 811-839, 2025, DOI:10.32604/cmes.2025.065632 - 31 July 2025

Abstract The formation process of blasting craters and blasting fragments is simulated using the continuum-discontinuum element method (CDEM), providing a reference for blasting engineering design. The calculation model of the blasting funnel is established, and the formation and fragmentation effect of the blasting crater under different explosive burial depths and different explosive package masses are numerically simulated. The propagation law of the explosion stress wave and the formation mechanism of the blasting crater are studied, and the relationship between the rock-crushing effect and blasting design parameters is quantitatively evaluated. Comparing the results of numerical simulation with… More >

Ayoub Mhaouch^1,*, Wafa Gtifa², Turke Althobaiti³, Hamzah Faraj⁴, Mohsen Machhout¹

CMC-Computers, Materials & Continua, Vol.84, No.3, pp. 5637-5663, 2025, DOI:10.32604/cmc.2025.065525 - 30 July 2025

Abstract In medical imaging, accurate brain tumor classification in medical imaging requires real-time processing and efficient computation, making hardware acceleration essential. Field Programmable Gate Arrays (FPGAs) offer parallelism and reconfigurability, making them well-suited for such tasks. In this study, we propose a hardware-accelerated Convolutional Neural Network (CNN) for brain cancer classification, implemented on the PYNQ-Z2 FPGA. Our approach optimizes the first Conv2D layer using different numerical representations: 8-bit fixed-point (INT8), 16-bit fixed-point (FP16), and 32-bit fixed-point (FP32), while the remaining layers run on an ARM Cortex-A9 processor. Experimental results demonstrate that FPGA acceleration significantly outperforms the… More >

Zainab Ouardirhi^1,2,*, Mostapha Zbakh², Sidi Ahmed Mahmoudi¹

CMES-Computer Modeling in Engineering & Sciences, Vol.143, No.3, pp. 2509-2571, 2025, DOI:10.32604/cmes.2025.064283 - 30 June 2025

Abstract Object detection in occluded environments remains a core challenge in computer vision (CV), especially in domains such as autonomous driving and robotics. While Convolutional Neural Network (CNN)-based two-dimensional (2D) and three-dimensional (3D) object detection methods have made significant progress, they often fall short under severe occlusion due to depth ambiguities in 2D imagery and the high cost and deployment limitations of 3D sensors such as Light Detection and Ranging (LiDAR). This paper presents a comparative review of recent 2D and 3D detection models, focusing on their occlusion-handling capabilities and the impact of sensor modalities such More >