Gan Zhu¹, Yongtao Yu^2,*, Xiaofan Deng¹, Yuanchen Dai³, Zhenyuan Li³

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 4317-4348, 2025, DOI:10.32604/cmes.2025.074349 - 23 December 2025

Abstract Existing deep learning Network Intrusion Detection Systems (NIDS) struggle to simultaneously capture fine-grained, multi-scale features and long-range temporal dependencies. To address this gap, this paper introduces TransNeSt, a hybrid architecture integrating a ResNeSt block (using split-attention for multi-scale feature representation) with a Transformer encoder (using self-attention for global temporal modeling). This integration of multi-scale and temporal attention was validated on four benchmarks: NSL-KDD, UNSW-NB15, CIC-IDS2017, and CICIOT2023. TransNeSt consistently outperformed its individual components and several state-of-the-art models, demonstrating significant quantitative gains. The model achieved high efficacy across all datasets, with F1-Scores of 99.04% (NSL-KDD), 91.92% More >

Dan Jiao^1,2, Yan Dong^1,2,*, Hao Xie³, Yordan Garbatov^4,*, Jiancheng Liu⁵, Hui Zhang⁵

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 3197-3216, 2025, DOI:10.32604/cmes.2025.074239 - 23 December 2025

Abstract Floating offshore wind turbine platforms typically use stiffened tubular joints at the connections between columns and braces. These joints are prone to fatigue due to complex weld geometries and the additional stress concentrations caused by the stiffeners. Existing hot-spot stress approaches may be inadequate for analysing these joints because they do not simultaneously address weld-toe and weld-root failures. To address these limitations, this study evaluates the fatigue strength of stiffened tubular joints using the effective notch strain approach and the structural strain approach. Both methods account for fatigue at the weld toe and weld root… More >

Nader Karmous¹, Wadii Jlassi¹, Mohamed Ould-Elhassen Aoueileyine¹, Imen Filali^2,*, Ridha Bouallegue¹

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 4363-4393, 2025, DOI:10.32604/cmes.2025.074178 - 23 December 2025

Abstract This paper introduces a robust Distributed Denial-of-Service attack detection framework tailored for Software-Defined Networking based Internet of Things environments, built upon a novel, synthetic multi-vector dataset generated in a Mininet-Ryu testbed using real-time flow-based labeling. The proposed model is based on the XGBoost algorithm, optimized with Principal Component Analysis for dimensionality reduction, utilizing lightweight flow-level features extracted from OpenFlow statistics to classify attacks across critical IoT protocols including TCP, UDP, HTTP, MQTT, and CoAP. The model employs lightweight flow-level features extracted from OpenFlow statistics to ensure low computational overhead and fast processing. Performance was rigorously… More >

Asgar Ali^1,*, Nayan Sardar², Poly Karmakar³, Sanatan Das⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 3563-3626, 2025, DOI:10.32604/cmes.2025.074082 - 23 December 2025

Abstract Hybrid nanofluids have gained significant attention for their superior thermal and rheological characteristics, offering immense potential in energy conversion, biomedical transport, and electromagnetic flow control systems. Understanding their dynamic behavior under coupled magnetic, rotational, and reactive effects is crucial for the development of efficient thermal management technologies. This study develops a neuro-fuzzy computational framework to examine the dynamics of a reactive Cu–TiO₂–H₂O hybrid nanofluid flowing through a squarely elevated Riga tunnel. The governing model incorporates Hall and ion-slip effects, thermal radiation, and first-order chemical reactions under ramped thermo-solutal boundary conditions and rotational electromagnetic forces. Closed-form analytical… More >

Yassir M. Abbas^1,*, Ammar Babiker², Fouad Ismail Ismail³

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 3279-3307, 2025, DOI:10.32604/cmes.2025.074069 - 23 December 2025

Abstract Accurately predicting the compressive strength of recycled aggregate concrete (RAC) incorporating supplementary cementitious materials (SCMs) remains a critical challenge due to the heterogeneous nature of recycled aggregates (RA) and the complex interactions among multiple binder constituents. This study advances the field by developing the most extensive and rigorously preprocessed database to date, which comprises 1243 RAC mixtures containing silica fume, fly ash, and ground-granulated blast-furnace slag. A hybrid, domain-informed machine-learning framework was then proposed, coupling optimized Extreme Gradient Boosting (XGBoost) with civil engineering expertise to capture the complex chemical and microstructural mechanisms that govern RAC… More >

Shuangyuan Li^1,*, Zhengwei Wang², Jiaming Liang³, Yichen Wang⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 3993-4011, 2025, DOI:10.32604/cmes.2025.073896 - 23 December 2025

Abstract Object detection plays a crucial role in the field of computer vision, and small object detection has long been a challenging issue within this domain. In order to improve the performance of object detection on small targets, this paper proposes an enhanced structure for YOLOv5, termed ATC-YOLOv5. Firstly, a novel structure, AdaptiveTrans, is introduced into YOLOv5 to facilitate efficient communication between the encoder and the detector. Consequently, the network can better address the adaptability challenge posed by objects of different sizes in object detection. Additionally, the paper incorporates the CBAM (Convolutional Block Attention Module) attention More >

Ahmed K. Ali¹, Jungpil Shin^2,*, Yujin Lim^3,*, Da-Hun Seong³

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 4245-4278, 2025, DOI:10.32604/cmes.2025.073871 - 23 December 2025

Abstract Single-signal detection in orthogonal frequency-division multiplexing (OFDM) systems presents a challenge due to the time-varying nature of wireless channels. Although conventional methods have limitations, particularly in multi-input multioutput orthogonal frequency division multiplexing (MIMO-OFDM) systems, this paper addresses this problem by exploring advanced deep learning approaches for combined channel estimation and signal detection. Specifically, we propose two hybrid architectures that integrate a convolutional neural network (CNN) with a recurrent neural network (RNN), namely, CNN-long short-term memory (CNN-LSTM) and CNN-bidirectional-LSTM (CNN-Bi-LSTM), designed to enhance signal detection performance in MIMO-OFDM systems. The proposed CNN-LSTM and CNN-Bi-LSTM architectures are… More >

Siwei Zhang, Xiaozhou Xia^*, Xin Gu, Meilin Zong, Qing Zhang^*

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 3243-3278, 2025, DOI:10.32604/cmes.2025.073841 - 23 December 2025

Abstract This study presents a coupled thermo-hydro-mechanical-fatigue (THM-F) model, developed based on variational phase-field fatigue theory, to simulate the freeze-thaw (F-T) damage process in concrete. The fracture phase-field model incorporates the F-T fatigue mechanism driven by energy dissipation during the free energy growth stage. Using microscopic inclusion theory, we derive an evolution model of pore size distribution (PSD) for concrete under F-T cycles by treating pore water as columnar inclusions. Drawing upon pore ice crystal theory, calculation models that account for concrete PSD characteristics are established to determine ice saturation, permeability coefficient, and pore pressure. To… More >

Yunjun Lee¹, Sanggyu Cheon², Woo Chul Chung^1,*

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 3381-3403, 2025, DOI:10.32604/cmes.2025.073729 - 23 December 2025

Abstract The application of carbon capture systems on ships is technically constrained by limited onboard space and the weight of the conventional absorption tower. The rotating packed bed (RPB) has emerged as a promising alternative due to its small footprint and high mass transfer performance. However, despite its advantages, the structural and vibration stability of RPBs at high rotational speed remains insufficiently studied, and no international design standards currently exist for RPBs. To address this gap, this study performed a comprehensive finite element analysis (FEA) using ANSYS to investigate the structural and dynamic characteristics of an… More >

Khulud Salem Alshudukhi^1,*, Sijjad Ali², Mamoona Humayun^3,*, Omar Alruwaili⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.145, No.3, pp. 3029-3085, 2025, DOI:10.32604/cmes.2025.073705 - 23 December 2025

Abstract Problem: The integration of Artificial Intelligence (AI) into cybersecurity, while enhancing threat detection, is hampered by the “black box” nature of complex models, eroding trust, accountability, and regulatory compliance. Explainable AI (XAI) aims to resolve this opacity but introduces a critical new vulnerability: the adversarial exploitation of model explanations themselves. Gap: Current research lacks a comprehensive synthesis of this dual role of XAI in cybersecurity—as both a tool for transparency and a potential attack vector. There is a pressing need to systematically analyze the trade-offs between interpretability and security, evaluate defense mechanisms, and outline a… More >