Yingli Liu^1,2, Weiyong Tang^1,2, Xiao Yang^1,2, Jiancheng Yin^3,*, Haihe Zhou^1,2

CMC-Computers, Materials & Continua, Vol.87, No.1, 2026, DOI:10.32604/cmc.2026.074681 - 10 February 2026

Abstract Quantitative analysis of aluminum-silicon (Al-Si) alloy microstructure is crucial for evaluating and controlling alloy performance. Conventional analysis methods rely on manual segmentation, which is inefficient and subjective, while fully supervised deep learning approaches require extensive and expensive pixel-level annotated data. Furthermore, existing semi-supervised methods still face challenges in handling the adhesion of adjacent primary silicon particles and effectively utilizing consistency in unlabeled data. To address these issues, this paper proposes a novel semi-supervised framework for Al-Si alloy microstructure image segmentation. First, we introduce a Rotational Uncertainty Correction Strategy (RUCS). This strategy employs multi-angle rotational perturbations… More >

Longcang Wang, Yongbing Gao^*, Xinguang Wang, Xin Liu

CMC-Computers, Materials & Continua, Vol.87, No.1, 2026, DOI:10.32604/cmc.2025.072889 - 10 February 2026

Abstract Aiming at the problem of insufficient recognition of implicit variants by existing Chinese sensitive text detection methods, this paper proposes the IPKE-MoE framework, which consists of three parts, namely, a sensitive word variant extraction framework, a sensitive word variant knowledge enhancement layer and a mixture-of-experts (MoE) classification layer. First, sensitive word variants are precisely extracted through dynamic iterative prompt templates and the context-aware capabilities of Large Language Models (LLMs). Next, the extracted variants are used to construct a knowledge enhancement layer for sensitive word variants based on RoCBert models. Specifically, after locating variants via n-gram… More >

Ming Chen^1,*, Guoqiang Ma², Ping Qi¹, Fucheng Wang¹, Lin Shen³, Xiaoya Pi¹

CMC-Computers, Materials & Continua, Vol.87, No.1, 2026, DOI:10.32604/cmc.2025.072623 - 10 February 2026

Abstract In the image fusion field, fusing infrared images (IRIs) and visible images (VIs) excelled is a key area. The differences between IRIs and VIs make it challenging to fuse both types into a high-quality image. Accordingly, efficiently combining the advantages of both images while overcoming their shortcomings is necessary. To handle this challenge, we developed an end-to-end IRI and VI fusion method based on frequency decomposition and enhancement. By applying concepts from frequency domain analysis, we used the layering mechanism to better capture the salient thermal targets from the IRIs and the rich textural information… More >

Hao Chen¹, Tong Xu¹, Yutian Huang², Dabo Xin^1,*, Changting Zhong^1,3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.1, 2026, DOI:10.32604/cmes.2026.075792 - 29 January 2026

Abstract Optimization problems are prevalent in various fields of science and engineering, with several real-world applications characterized by high dimensionality and complex search landscapes. Starfish optimization algorithm (SFOA) is a recently optimizer inspired by swarm intelligence, which is effective for numerical optimization, but it may encounter premature and local convergence for complex optimization problems. To address these challenges, this paper proposes the multi-strategy enhanced crested porcupine-starfish optimization algorithm (MCPSFOA). The core innovation of MCPSFOA lies in employing a hybrid strategy to improve SFOA, which integrates the exploratory mechanisms of SFOA with the diverse search capacity of… More >

Yiyang Fu¹, Hui Li^2,*, Wangyu Wu^3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.1, 2026, DOI:10.32604/cmes.2025.074467 - 29 January 2026

Abstract Weakly Supervised Semantic Segmentation (WSSS), which relies only on image-level labels, has attracted significant attention for its cost-effectiveness and scalability. Existing methods mainly enhance inter-class distinctions and employ data augmentation to mitigate semantic ambiguity and reduce spurious activations. However, they often neglect the complex contextual dependencies among image patches, resulting in incomplete local representations and limited segmentation accuracy. To address these issues, we propose the Context Patch Fusion with Class Token Enhancement (CPF-CTE) framework, which exploits contextual relations among patches to enrich feature representations and improve segmentation. At its core, the Contextual-Fusion Bidirectional Long Short-Term More >

Zujun Ding, Shuaichao Wu, Chenliang Ji, Xinyu Feng, Yuanyuan Shi, Baolian Liu, Wan Chen, Qiuchan Bai, Hengrui Zhou, Hui Huang, Jie Ji^*

Energy Engineering, Vol.123, No.2, 2026, DOI:10.32604/ee.2025.068106 - 27 January 2026

Abstract In the quest to enhance energy efficiency and reduce environmental impact in the transportation sector, the recovery of waste heat from diesel engines has become a critical area of focus. This study provided an exhaustive thermodynamic analysis optimizing Organic Rankine Cycle (ORC) systems for waste heat recovery from diesel engines. The study assessed the performance of five candidate working fluids—R11, R123, R113, R245fa, and R141b—under a range of operating conditions, specifically varying overheat temperatures and evaporation pressures. The results indicated that the choice of working fluid substantially influences the system’s exergetic efficiency, net output power,… More >

Md Minhazul Islam^1,2, Yunfei Yin^1,2,*, Md Tanvir Islam^1,2, Zheng Yuan^1,2, Argho Dey^1,2

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072550 - 12 January 2026

Abstract Automatic segmentation of landslides from remote sensing imagery is challenging because traditional machine learning and early CNN-based models often fail to generalize across heterogeneous landscapes, where segmentation maps contain sparse and fragmented landslide regions under diverse geographical conditions. To address these issues, we propose a lightweight dual-stream siamese deep learning framework that integrates optical and topographical data fusion with an adaptive decoder, guided multimodal fusion, and deep supervision. The framework is built upon the synergistic combination of cross-attention, gated fusion, and sub-pixel upsampling within a unified dual-stream architecture specifically optimized for landslide segmentation, enabling efficient… More >

Yuanyuan Wang^1,*, Yemeng Zhu¹, Xiuchuan Chen¹, Tongtong Yin¹, Shiwei Su²

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072404 - 12 January 2026

Abstract To solve the false detection and missed detection problems caused by various types and sizes of defects in the detection of steel surface defects, similar defects and background features, and similarities between different defects, this paper proposes a lightweight detection model named multiscale edge and squeeze-and-excitation attention detection network (MSESE), which is built upon the You Only Look Once version 11 nano (YOLOv11n). To address the difficulty of locating defect edges, we first propose an edge enhancement module (EEM), apply it to the process of multiscale feature extraction, and then propose a multiscale edge enhancement… More >

Chao Li^1,3,#, Jianing Wang^1,3,#, Caichang Ding^2,*, Zhiwei Ye^1,3

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.071242 - 12 January 2026

Abstract Underwater images frequently suffer from chromatic distortion, blurred details, and low contrast, posing significant challenges for enhancement. This paper introduces AquaTree, a novel underwater image enhancement (UIE) method that reformulates the task as a Markov Decision Process (MDP) through the integration of Monte Carlo Tree Search (MCTS) and deep reinforcement learning (DRL). The framework employs an action space of 25 enhancement operators, strategically grouped for basic attribute adjustment, color component balance, correction, and deblurring. Exploration within MCTS is guided by a dual-branch convolutional network, enabling intelligent sequential operator selection. Our core contributions include: (1) a More >

Jun Li¹, Chunyan Liang^1,*, Zhiguo Liu¹, Fengpei Ge²

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.071011 - 12 January 2026

Abstract To enhance speech emotion recognition capability, this study constructs a speech emotion recognition model integrating the adaptive acoustic mixup (AAM) and improved coordinate and shuffle attention (ICASA) methods. The AAM method optimizes data augmentation by combining a sample selection strategy and dynamic interpolation coefficients, thus enabling information fusion of speech data with different emotions at the acoustic level. The ICASA method enhances feature extraction capability through dynamic fusion of the improved coordinate attention (ICA) and shuffle attention (SA) techniques. The ICA technique reduces computational overhead by employing depth-separable convolution and an h-swish activation function and More >