Danilo Greco^*

CMC-Computers, Materials & Continua, Vol.88, No.2, 2026, DOI:10.32604/cmc.2026.082708 - 15 June 2026

Abstract The Enhanced Graph Neural Network Autoencoder (Enhanced GNN-AE), recently proposed for unsupervised cybersecurity monitoring in battery energy storage systems (BESSs), builds a multiscale k-nearest neighbour graph over measurement samples and learns compact latent representations via manifold-regularised training. Its spatial encoder, however, employs the original Graph Attention Network (GAT), which has been formally shown to compute a rank-1 attention function equivalent to graph convolutional networks on many graph structures. This work investigates whether replacing the GAT encoder with the strictly more expressive GATv2 formulation—which applies the attention vector after a joint, asymmetric linear transformation of source… More >

Pangwei Wang^1,*, Jie Wang¹, Zipeng Wang¹, Hangrui Dong², Li Wang¹

CMC-Computers, Materials & Continua, Vol.88, No.2, 2026, DOI:10.32604/cmc.2026.080815 - 15 June 2026

Abstract Traffic holographic perception refers to the real-time, high-fidelity, and multi-dimensional sensing of traffic states through the fusion of heterogeneous sensors, including cameras, radars, and connected vehicle data. The multi-source perception data obtained thereby can provide a complete digital representation of the road network for the Intelligent Transportation System (ITS). However, sensors are vulnerable to environmental interference, which can result in data loss at specific points or along arterial highways for certain periods, potentially undermining system safety and decision-making reliability. To address these challenges, a deep learning method based on Graph Convolutional Networks (GCN) and Gated… More >

Mohammed Shukur Alfaras^1,2,*, Oguz Karan³, Sefer Kurnaz¹, Ayca Kurnaz Turkben⁴

CMC-Computers, Materials & Continua, Vol.88, No.2, 2026, DOI:10.32604/cmc.2026.079577 - 15 June 2026

Abstract Despite deep learning’s high precision in emotion identification, centralized training is associated with privacy and scalability concerns. The privacy-preserving federated learning model, Federated Hybrid-Optimized Emotion Recognition (Fed-HOER), introduced in this paper is an auto-tuning hyperparameters optimizer based on a hybrid Dung Beetle Optimizer-Fick’s Law Algorithm (DBO-FLA) optimizer. The global and local searches are optimized at two levels, and validation loss is minimized by 22%–24% without sharing raw data. The experiments on Extended Cohn–Kanade (CK+), Japanese Female Facial Expressions (JAFFE), and Karolinska Directed Emotional Faces (KDEF) exhibit a high generalization rate with a mean accuracy of More >

Li Chen¹, Fan Zhang^2,*, Guangwei Xie³, Yanzhao Gao¹, Xiaofeng Qi¹, Mingqian Sun²

CMC-Computers, Materials & Continua, Vol.88, No.2, 2026, DOI:10.32604/cmc.2026.078314 - 15 June 2026

Abstract Remote sensing object detection aims to identify and localize specific targets in satellite or aerial imagery. Spiking Neural Networks (SNNs), benefiting from their implicit feedback-based and event-driven brain-inspired dynamics, offer a promising solution to alleviate the high energy consumption of conventional ANN-based detection models. However, existing SNN-based approaches for remote sensing object detection—particularly for small, arbitrarily rotated objects—are still in their infancy and suffer from a substantial performance gap compared with ANN counterparts. In this work, we draw inspiration from the hierarchical sparse perception mechanisms of biological vision and integrate dynamic receptive field modulation into… More >

Miao Ye¹, Ziheng Wang¹, Qiuxiang Jiang¹, Xingsi Xue², Wenxi Liu³, Yu Ning¹, Cheng Zhu^1,4,*

CMC-Computers, Materials & Continua, Vol.88, No.2, 2026, DOI:10.32604/cmc.2026.078282 - 15 June 2026

Abstract In recent years, anomaly detection in Wireless Sensor Networks (WSNs) has been widely studied using Graph Neural Networks and Transformer-based methods. However, in multi-node and multi-modal data scenarios, these approaches still face challenges such as insufficient extraction of spatiotemporal correlation features, limited modeling capabilities when relying solely on either time-domain or frequency-domain information, and high computational overhead. To address these issues, this work aims to develop an anomaly detection model that balances detection performance with computational efficiency, enabling effective identification of complex anomaly patterns. Specifically, we propose a time–frequency feature extraction method with topological information… More >

Edward Danso Ansong¹, David Adlai Nettey^1,*, Sarika S², Simon Bonsu Osei¹

Journal on Big Data, Vol.8, pp. 1-10, 2026, DOI:10.32604/jbd.2026.065126 - 12 June 2026

Abstract Credit card fraud has emerged as a pervasive threat, impacting financial institutions and individuals as online banking and payment methods become increasingly integral to daily life. Despite efforts to mitigate this problem through measures like passwords and two-factor authentication, financial institutions continue to suffer substantial losses, often amounting to millions of dollars. Traditional machine learning solutions, developed and trained as supervised learning models, have failed to address this issue effectively. In anomaly detection, such as credit card fraud detection, the available training datasets are vast but inherently imbalanced, posing a formidable obstacle for supervised learning… More >

Irfan Saif Ud Din¹, Imran Siddique^2,3,4,5, Zohaib Zahid¹, Muhammad Nadeem⁶, Ibrahim Alraddadi^2,*, Taha Radwan^7,*

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.2, 2026, DOI:10.32604/cmes.2026.081726 - 27 May 2026

Abstract This study examines the variable thermal conductivity and electroosmotic performance of Sutterby hybrid nanofluid (SBHNF) thin film flow over a stretched inclined sheet using an artificial neural network (ANN)-based on NARX (Multilayer Nonlinear Autoregressive Networks with Exogenous Inputs) multiple-layer backpropagation simulation with the Levenberg-Marquardt algorithm (LMA). AA7075 and AA7072 nanoparticles suspended in sodium alginate (SA) base fluid make up the hybrid nanofluid (HNF), which was selected due to its improved heat transfer properties and superior thermal conductivity. The model’s practical applicability is enhanced by melting heat, nonlinear thermal radiation, boundary slip, and Newtonian heating effects,… More >

Ronak Patel¹, Miral Patel², Deep Kothadiya³, Noor A. Khan⁴, Shaha Al-Otaibi^5,*, Roaa Khalil Mohamed Ali Abed⁶, Tanzila Saba⁷

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.2, 2026, DOI:10.32604/cmes.2026.080819 - 27 May 2026

Abstract Magnetic resonance imaging (MRI) is widely utilized for brain tumor segmentation, yet significant challenges persist due to intensity variations, irregular boundaries, and substantial morphological heterogeneity. Current state-of-the-art deep learning methods often struggle to capture long-range spatial dependencies, delineate fine boundary details, and efficiently process 3D volumetric data. This study introduces a novel hybrid framework that integrates state-space models with frequency-domain learning to address these limitations. The proposed model offers four primary contributions: (1) incorporation of a morphological attention block in the encoder to enhance boundary localization via dilation-erosion gradient modeling; (2) a dual-domain bottleneck module… More >

Thao Nguyen-Trang^1,2,*, Hiep Ha-Hoang³

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.2, 2026, DOI:10.32604/cmes.2026.080808 - 27 May 2026

Abstract Solving differential equations (DEs), including ordinary differential equations (ODEs) and partial differential equations (PDEs), is fundamental to scientific computing and engineering. The development of deep learning has led to Physics-Informed Neural Networks (PINNs), in which physical laws are embedded directly into the loss function. However, PINNs inherit the intrinsic instability of deep neural networks (DNNs) and lack an effective mechanism for Uncertainty Quantification (UQ). This paper proposes a stochastic ensemble framework to address these limitations. The proposed method is a double-stochastic ensemble framework that combines bagging (via bootstrap resampling and randomized collocation points) with Monte… More >

Alanoud Al Mazroa¹, Fahad Masood², Bakri Hussain Awaji³, Mohammad Alhefdi⁴, Abeer Aljohani⁵, Jawad Ahmad^6,*

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.2, 2026, DOI:10.32604/cmes.2026.080134 - 27 May 2026

Abstract The rapid integration of Internet of Things (IoT) devices and distributed energy resources into smart grids has improved monitoring, control, and energy efficiency. However, it also exposes the grid to cyberattacks and privacy risks, as increased connectivity and data exchange can significantly disrupt energy management and system stability. Studies focused on centralized cybersecurity mechanisms that lacked scalability and did not emphasize the inherent graph structure of power networks. This study proposes a privacy-preserving and cyber-resilient energy-optimization framework, FedGNN, for IoT-enabled smart grids that jointly integrates federated learning, graph neural network-based trust inference, and trust-aware energy dispatch.… More >