Shuangqing Song¹, Yuan Chen², Xuguang Hu¹, Juwei Zhang^1,3,*

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072392 - 12 January 2026

Abstract In multi-domain neural machine translation tasks, the disparity in data distribution between domains poses significant challenges in distinguishing domain features and sharing parameters across domains. This paper proposes a Transformer-based multi-domain-aware mixture of experts model. To address the problem of domain feature differentiation, a mixture of experts (MoE) is introduced into attention to enhance the domain perception ability of the model, thereby improving the domain feature differentiation. To address the trade-off between domain feature distinction and cross-domain parameter sharing, we propose a domain-aware mixture of experts (DMoE). A domain-aware gating mechanism is introduced within the… More >

Jiajun Sun, Shunshun Ji, Chao Zhang^*

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-23, 2026, DOI:10.32604/cmc.2025.068668 - 09 December 2025

Abstract Asparagus stem blight is a devastating crop disease, and the early detection of its pathogenic spores is essential for effective disease control and prevention. However, spore detection is still hindered by complex backgrounds, small target sizes, and high annotation costs, which limit its practical application and widespread adoption. To address these issues, a semi-supervised spore detection framework is proposed for use under complex background conditions. Firstly, a difficulty perception scoring function is designed to quantify the detection difficulty of each image region. For regions with higher difficulty scores, a masking strategy is applied, while the… More >

Weixi Zhu^1,2,3, Yongdong Meng^1,3,*, Jindong Xie², Zhenglong Cai^1,3, Yu Lyu², Xiaowei Xu^1,3

Structural Durability & Health Monitoring, Vol.19, No.6, pp. 1733-1744, 2025, DOI:10.32604/sdhm.2025.070098 - 17 November 2025

Abstract To mitigate the severe abrasion damage caused by high-velocity water flow in hydraulic engineering applications in Xizang, China, this study systematically optimized key mix design parameters, including aggregate gradation, sand ratio, fly ash content, and superplasticizer dosage. Based on the optimized mix, the combined effects of an abrasion-resistance enhancement admixture (AEA) and silica fume (SF) on the abrasion resistance of self-compacting concrete (SCC) were examined. The results demonstrated that the appropriate incorporation of AEA and SF significantly improved the abrasion resistance of SCC without compromising its workability. The proposed mix design not only achieves superior… More >

Kui Lin^*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.33, No.4, pp. 1-1, 2025, DOI:10.32604/icces.2025.011838

Abstract The phase separation of confined polymeric mixtures plays a critical role in the design of advanced materials and nanoscale devices. Over the past decades, extensive studies have highlighted the interplay of wetting dynamics, hydrodynamics, and interfacial forces in governing phase separation under confinement. In this work [1], we employ molecular dynamics simulations to investigate the dynamics of a binary mixture confined by van der Waals (vdW) walls, revealing a novel phenomenon termed Perpendicular Separation of Two Phases (PSTP). In the initial stage, water molecules residing in the central region rapidly diffuse and condense symmetrically along… More >

Khalil Ibrahim Lairedj¹, Zouaoui Chama¹, Amina Bagdaoui¹, Samia Larguech², Younes Menni^3,4,*, Nidhal Becheikh⁵, Lioua Kolsi^6,*, Badr M. Alshammari⁷

CMES-Computer Modeling in Engineering & Sciences, Vol.144, No.2, pp. 2419-2443, 2025, DOI:10.32604/cmes.2025.069396 - 31 August 2025

Abstract Brain tumor segmentation from Magnetic Resonance Imaging (MRI) supports neurologists and radiologists in analyzing tumors and developing personalized treatment plans, making it a crucial yet challenging task. Supervised models such as 3D U-Net perform well in this domain, but their accuracy significantly improves with appropriate preprocessing. This paper demonstrates the effectiveness of preprocessing in brain tumor segmentation by applying a pre-segmentation step based on the Generalized Gaussian Mixture Model (GGMM) to T1 contrast-enhanced MRI scans from the BraTS 2020 dataset. The Expectation-Maximization (EM) algorithm is employed to estimate parameters for four tissue classes, generating a More >

Yuliang He¹, Weihong Lou¹, Da Hang², Youhua Su^3,*

Structural Durability & Health Monitoring, Vol.19, No.4, pp. 887-902, 2025, DOI:10.32604/sdhm.2025.062070 - 30 June 2025

Abstract The computational accuracy and efficiency of modeling the stress spectrum derived from bridge monitoring data significantly influence the fatigue life assessment of steel bridges. Therefore, determining the optimal stress spectrum model is crucial for further fatigue reliability analysis. This study investigates the performance of the REBMIX algorithm in modeling both univariate (stress range) and multivariate (stress range and mean stress) distributions of the rain-flow matrix for a steel arch bridge, using Akaike’s Information Criterion (AIC) as a performance metric. Four types of finite mixture distributions—Normal, Lognormal, Weibull, and Gamma—are employed to model the stress range. More >

Alexey Melkikh^1,2, Sergey Rutin², Dmitrii V. Antonov³, Pavel Skripov^2,*

Frontiers in Heat and Mass Transfer, Vol.23, No.3, pp. 721-737, 2025, DOI:10.32604/fhmt.2025.066528 - 30 June 2025

Abstract The article considers a relaxation of the water/polypropylene glycol-425 solution with a lower critical solution temperature (LCST) following its pulsed superheating concerning liquid-liquid and liquid-vapor equilibrium lines, as well as the liquid-liquid spinodal. Superheating was performed using the pulsed heat generation method in a micro-sized wire probe. The main heating mode was the constant (over the pulse length) power mode. Characteristic heating rates ranged from 0.05 × 10⁵ to 2 × 10⁵ K/s, while the degree of superheating concerning the spinodal was up to 200 K. The temperature of spontaneous boiling-up and the amplitude of the… More > Graphic Abstract

Anna Chiara Uggenti¹, Giorgio Rech², Raffaella Gerboni^2,*, Gianmario Ledda², Amedeo Aliberti¹, Claudia Vivalda³, Emanuela Bruno², Andrea Carpignano²

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.4, pp. 757-782, 2025, DOI:10.32604/fdmp.2025.062347 - 06 May 2025

Abstract The paper presents an innovative approach to studying the reuse of a decommissioned natural gas production platform for the seasonal storage and extraction of a hydrogen-methane (H₂-CH₄) mixture from a depleted reservoir. The reuse plan involves removing outdated equipment from the platform’s decks while retaining essential components such as wellheads and separators. Exploiting a depleted reservoir for the injection of an H₂-CH₄ mixture requires a thorough understanding of its specific characteristics. This paper focuses on the engineering approach adopted in the basic design phase for such a conversion, providing recommendations and HSE guidelines. Given the hazardous… More >

Ke Chen^1,2, Cheng Peng^1,2, Xinyang He^1,2, Jiakang Sun^1,2, Xu Liu^1,2, Xiaolin Qin^1,2,*, Yong Zhong^1,2,*

CMC-Computers, Materials & Continua, Vol.82, No.3, pp. 4003-4019, 2025, DOI:10.32604/cmc.2025.057443 - 06 March 2025

Abstract In natural language processing (NLP), managing multiple downstream tasks through fine-tuning pre-trained models often requires maintaining separate task-specific models, leading to practical inefficiencies. To address this challenge, we introduce AdaptForever, a novel approach that enables continuous mastery of NLP tasks through the integration of elastic and mutual learning strategies with a stochastic expert mechanism. Our method freezes the pre-trained model weights while incorporating adapters enhanced with mutual learning capabilities, facilitating effective knowledge transfer from previous tasks to new ones. By combining Elastic Weight Consolidation (EWC) for knowledge preservation with specialized regularization terms, AdaptForever successfully maintains More >

Baishun Yang¹, Biao Li^1,*

The International Conference on Computational & Experimental Engineering and Sciences, Vol.32, No.3, pp. 1-1, 2024, DOI:10.32604/icces.2024.011944

Abstract Hot corrosion behavior of GH4169 nickel-based superalloy coated with 95wt.%Na₂SO₄+5wt.%NaCl salt mixture at 650 ℃,800 ℃, and 950 ℃ were investigated by some material characterization methods. The Experimental results showed that hot corrosion kinetics followed a parabolic, linear and exponential laws at 650 ℃, 800 ℃, and 950 ℃ respectively. Notably, as the temperature ascended from 650 ℃ to over 800 ℃, the corrosion mechanisms underwent a transition from pit corrosion to uniform erosion, corresponding to low-temperature hot corrosion (LTHC) and high-temperature hot corrosion (HTHC). At 650 ℃, a large number of semi-ellipsoidal corrosion pits manifested More >