Shaoping Xiao^1,*, Zhaoan Wang¹, Junchao Li², Caden Noeller¹, Jiefeng Jiang³, Jun Wang⁴

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-62, 2026, DOI:10.32604/cmc.2025.072146 - 09 December 2025

Abstract The integration of human factors into artificial intelligence (AI) systems has emerged as a critical research frontier, particularly in reinforcement learning (RL), where human-AI interaction (HAII) presents both opportunities and challenges. As RL continues to demonstrate remarkable success in model-free and partially observable environments, its real-world deployment increasingly requires effective collaboration with human operators and stakeholders. This article systematically examines HAII techniques in RL through both theoretical analysis and practical case studies. We establish a conceptual framework built upon three fundamental pillars of effective human-AI collaboration: computational trust modeling, system usability, and decision understandability. Our… More >

Xiaorui Zhang^1,2,*, Chunlin Yuan³, Wei Sun⁴, Ting Wang⁵

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-19, 2026, DOI:10.32604/cmc.2025.071043 - 09 December 2025

Abstract Video emotion recognition is widely used due to its alignment with the temporal characteristics of human emotional expression, but existing models have significant shortcomings. On the one hand, Transformer multi-head self-attention modeling of global temporal dependency has problems of high computational overhead and feature similarity. On the other hand, fixed-size convolution kernels are often used, which have weak perception ability for emotional regions of different scales. Therefore, this paper proposes a video emotion recognition model that combines multi-scale region-aware convolution with temporal interactive sampling. In terms of space, multi-branch large-kernel stripe convolution is used to More >

Abeer Alnuaim^*

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-33, 2026, DOI:10.32604/cmc.2025.069110 - 10 November 2025

Abstract The rapid digitalization of urban infrastructure has made smart cities increasingly vulnerable to sophisticated cyber threats. In the evolving landscape of cybersecurity, the efficacy of Intrusion Detection Systems (IDS) is increasingly measured by technical performance, operational usability, and adaptability. This study introduces and rigorously evaluates a Human-Computer Interaction (HCI)-Integrated IDS with the utilization of Convolutional Neural Network (CNN), CNN-Long Short Term Memory (LSTM), and Random Forest (RF) against both a Baseline Machine Learning (ML) and a Traditional IDS model, through an extensive experimental framework encompassing many performance metrics, including detection latency, accuracy, alert prioritization, classification… More >

Chen-Xi Hu¹, Wu-Gui Jiang^1,*, Jin Wang¹, Tian-Yu He²

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-21, 2026, DOI:10.32604/cmc.2025.068655 - 10 November 2025

Abstract THE mechanical response and deformation mechanisms of pure nickel under nanoindentation were systematically investigated using molecular dynamics (MD) simulations, with a particular focus on the novel interplay between crystallographic orientation, grain boundary (GB) proximity, and pore characteristics (size/location). This study compares single-crystal nickel models along [100], [110], and [111] orientations with equiaxed polycrystalline models containing 0, 1, and 2.5 nm pores in surface and subsurface configurations. Our results reveal that crystallographic anisotropy manifests as a 24.4% higher elastic modulus and 22.2% greater hardness in [111]-oriented single crystals compared to [100]. Pore-GB synergistic effects are found More >

Jia Liu¹, Hao Chen¹, Hang Gu¹, Yushan Pan^2,3, Haoran Chen¹, Erlin Tian⁴, Min Huang⁴, Zuhe Li^1,*

CMC-Computers, Materials & Continua, Vol.86, No.1, pp. 1-24, 2026, DOI:10.32604/cmc.2025.068162 - 10 November 2025

Abstract Accurate and efficient detection of building changes in remote sensing imagery is crucial for urban planning, disaster emergency response, and resource management. However, existing methods face challenges such as spectral similarity between buildings and backgrounds, sensor variations, and insufficient computational efficiency. To address these challenges, this paper proposes a novel Multi-scale Efficient Wavelet-based Change Detection Network (MewCDNet), which integrates the advantages of Convolutional Neural Networks and Transformers, balances computational costs, and achieves high-performance building change detection. The network employs EfficientNet-B4 as the backbone for hierarchical feature extraction, integrates multi-level feature maps through a multi-scale fusion… More >

Yang Dou¹, Hao Qin¹, Yuzhi Zhang^1,2, Ning Wang¹, Haiqing Liu^3,4, Wanli Yang^1,2,4,*

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.12, pp. 3091-3122, 2025, DOI:10.32604/fdmp.2025.070082 - 31 December 2025

Abstract In recent years, tuned liquid dampers (TLDs) have emerged as a focal point of research due to their remarkable potential for structural vibration mitigation. Yet, progress in this field remains constrained by an incomplete understanding of the fundamental mechanisms governing sloshing-induced loads in liquid-filled containers. Aqueducts present a distinctive case, as the capacity of their contained water to function effectively as a TLD remains uncertain. To address this gap, the present study investigates the generation mechanisms of sloshing loads under non-resonant cases through a two-dimensional (2D) computational fluid dynamics (CFD) model developed in ANSYS Fluent.… More >

Somayah Albaradei^1,2,*

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 2937-2970, 2025, DOI:10.32604/cmes.2025.072584 - 23 December 2025

Abstract Cancer deaths and new cases worldwide are projected to rise by 47% by 2040, with transitioning countries experiencing an even higher increase of up to 95%. Tumor severity is profoundly influenced by the timing, accuracy, and stage of diagnosis, which directly impacts clinical decision-making. Various biological entities, including genes, proteins, mRNAs, miRNAs, and metabolites, contribute to cancer development. The emergence of multi-omics technologies has transformed cancer research by revealing molecular alterations across multiple biological layers. This integrative approach supports the notion that cancer is fundamentally driven by such alterations, enabling the discovery of molecular signatures… More > Graphic Abstract

Yang Dou¹, Hao Qin¹, Yuzhi Zhang^1,2, Ning Wang¹, Haiqing Liu^3,4, Wanli Yang^1,2,4,*

FDMP-Fluid Dynamics & Materials Processing, Vol.21, No.11, pp. 2673-2700, 2025, DOI:10.32604/fdmp.2025.069719 - 01 December 2025

Abstract In recent years, tuned liquid dampers (TLDs) have attracted significant research interest; however, overall progress has been limited due to insufficient understanding of the mechanisms governing sloshing-induced loads. In particular, it remains unclear whether the water in aqueducts—common water-diversion structures in many countries—can serve as an effective TLD. This study investigates the generation mechanisms of sloshing loads during the first-order transverse resonance of water in a U-shaped aqueduct using a two-dimensional (2D) numerical model. The results reveal that, at the equilibrium position, the free surface difference between the left and right walls, the horizontal force… More >

Jothika Palanisamy¹, Chandru Muthusamy^1,*, Higinio Ramos^2,3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.2, pp. 2017-2038, 2025, DOI:10.32604/cmes.2025.071958 - 26 November 2025

Abstract This study investigates the performance of dual curved-leg pontoon floating breakwaters in finite water depth under the assumption of linear wave theory. The analysis is carried out for four different models of curved-leg geometries, which are combinations of convex and concave shapes. The models are classified as follows. Model-1: Seaside and leeside face concave, Model-2: Seaside and leeside face convex, Model-3: Seaside face convex and leeside face concave, and Model-4: Seaside face concave and leeside face convex. The Boundary Element Method is utilized in order to find a solution to the associated boundary value problem.… More >

Zhaoqi Li, Xuan Liu, Hengkong Zhao, Zhen Zhang^*, Yan Li

The International Conference on Computational & Experimental Engineering and Sciences, Vol.33, No.4, pp. 1-1, 2025, DOI:10.32604/icces.2025.012239

Abstract The growing use of ultra-thick composite laminates in aerospace structures demands a deeper understanding of their unique damage mechanisms under tensile loading, which differ significantly from those of thin laminates. This study introduces a novel 3D progressive damage model combining solid elements, the LaRC05 3D failure criterion (enhanced with through-thickness in-situ strengthening effects), and a mixed-mode cohesive zone model (CZM) to predict interlaminar delamination. The model captures the interaction between in-plane damage and through-thickness failure modes in open-hole ultra-thick composites, and addresses stress redistribution, localized buckling, delamination migration, and in-situ strength enhancement. Mesh sensitivity analysis… More >