Di Xiao^*, Wenting Jiang, Min Li

CMC-Computers, Materials & Continua, Vol.87, No.3, 2026, DOI:10.32604/cmc.2026.079808 - 09 April 2026

Abstract The rapid advancement of the Internet of Things (IoT) has transformed edge devices from simple data collectors into intelligent units capable of local processing and collaborative learning. However, the vast amounts of sensitive data generated by these devices face severe constraints from “data silos” and risks of privacy breaches. Federated learning (FL), as a distributed collaborative paradigm that avoids sharing raw data, holds great promise in the IoT domain. Nevertheless, it remains vulnerable to gradient leakage threats. While traditional differential privacy (DP) techniques mitigate privacy risks, they often come at the cost of significantly reduced… More >

Zakaria S. M. Abdelhalim^*, Nahla Belal, Mohamed Seifeldin

Journal of Cyber Security, Vol.8, pp. 153-169, 2026, DOI:10.32604/jcs.2026.079097 - 06 April 2026

Abstract The rapid expansion of IoT and cloud services has increased the scale and complexity of modern networks, making intrusion detection challenging. Although deep learning-based Network Intrusion Detection Systems (NIDS) often report high accuracy, such metrics can be misleading on highly imbalanced datasets, where performance is dominated by majority classes and rare attacks remain poorly detected. This issue stems from global optimization strategies that encourage models to rely on dominant feature patterns, limiting their ability to capture the class-specific features required to identify infrequent attack types. To address this limitation, this work proposes a domain knowledge-guided… More >

Mohammed Abdullah Alsuwaiket^*

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.3, 2026, DOI:10.32604/cmes.2026.078169 - 30 March 2026

Abstract The healthcare field is fraught with challenges associated with severe class imbalance, wherein such critical conditions like sepsis, cardiac arrest, and drug adverse reactions are rare but have dire clinical consequences. This paper presents a new framework, Deep Reinforcement Adaptive Gradient Optimization Network to Mining Rare Events (DRAGON-MINE), to demonstrate how deep reinforcement learning can be used synergistically with adaptive gradient optimization and address the inherent weaknesses of current methods in the prediction of rare health events. The suggested architecture uses a dual-pathway consisting of a reinforcement learning agent to dynamically reweigh samples and an… More >

Nurbek Sissenov^1,*, Gulden Ulyukova^1,*, Dina Satybaldina², Nikolaj Goranin³

CMC-Computers, Materials & Continua, Vol.87, No.2, 2026, DOI:10.32604/cmc.2026.075504 - 12 March 2026

Abstract The reliability of information systems (IS) is a key factor in the sustainable operation of modern digital services. However, existing assessment methods remain fragmented and are often limited to individual indicators or expert judgments. This paper proposes a hybrid methodology for a comprehensive assessment of IS reliability based on the integration of the international standard ISO/IEC 25010:2023, multicriteria analysis methods (ARAS, CoCoSo, and TOPSIS), and the XGBoost machine learning algorithm for missing data imputation. The structure of the ISO/IEC 25010 standard is used to formalize reliability criteria and subcriteria, while the AHP method allows for… More >

Chen Yu, Jingjing Tan, Wenwu Zhao, Ke Gu^*

CMC-Computers, Materials & Continua, Vol.87, No.2, 2026, DOI:10.32604/cmc.2026.075457 - 12 March 2026

Abstract Although federated learning (FL) improves privacy-preserving by updating parameters without collecting original user data, their shared gradients still leak sensitive user information. Existing differential privacy and encryption techniques typically focus on whether the aggregated gradient is correctly processed and verified only, rather than whether each user is honestly trained locally. To address these above issues, we propose a gradient feature-based collaborative filtering scheme in verification federated learning, where the authenticity of user training is verified using the collaborative filtering (CF) method based on gradient features. Compared with single user gradient detection (such as similarity detection More >

Qi Wang, Kelvin Amos Nicodemas^*

CMC-Computers, Materials & Continua, Vol.87, No.2, 2026, DOI:10.32604/cmc.2026.074305 - 12 March 2026

Abstract Multivariate time series forecasting plays a crucial role in decision-making for systems like energy grids and transportation networks, where temporal patterns emerge across diverse scales from short-term fluctuations to long-term trends. However, existing Transformer-based methods often process data at a single resolution or handle multiple scales independently, overlooking critical cross-scale interactions that influence prediction accuracy. To address this gap, we introduce the Hierarchical Attention Transformer (HAT), which enables direct information exchange between temporal hierarchies through a novel cross-scale attention mechanism. HAT extracts multi-scale features using hierarchical convolutional-recurrent blocks, fuses them via temperature-controlled mechanisms, and optimizes More >

Lei Sun^1,2, Jingwen Wang^2,*, Peng Hu², Xiuqing Mao^1,2, Cuiyun Hu^1,2, Zhihong Wang²

CMC-Computers, Materials & Continua, Vol.87, No.2, 2026, DOI:10.32604/cmc.2026.073657 - 12 March 2026

Abstract Transformer models face significant computational challenges in private inference (PI). Existing optimization methods often rely on isolated techniques, neglecting joint structural and operational improvements. We propose IG-3D, a unified framework that integrates structured compression and operator approximation through accurate importance assessment. Our approach first evaluates attention head importance using Integrated Gradients (IG), offering greater stability and theoretical soundness than gradient-based methods. We then apply a three-dimensional optimization: (1) structurally pruning redundant attention heads; (2) replacing Softmax with adaptive polynomial approximation to avoid exponential computations; (3) implementing layer-wise GELU substitution to accommodate different layer characteristics. A More >

Maddina Dinesh Kumar^1,#, S. U. Mamatha², Khalid Masood³, Nehad Ali Shah^4,#, Se-Jin Yook^1,*

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.1, 2026, DOI:10.32604/cmes.2025.074680 - 29 January 2026

Abstract Fluid dynamic research on rectangular and trapezoidal fins is aimed at increasing heat transfer by means of large surfaces. The trapezoidal cavity form is compared with its thermal and flow performance, and it is revealed that trapezoidal fins tend to be more efficient, particularly when material optimization is critical. Motivated by the increasing need for sustainable energy management, this work analyses the thermal performance of inclined trapezoidal and rectangular porous fins utilising a unique hybrid nanofluid. The effectiveness of nanoparticles in a working fluid is primarily determined by their thermophysical properties; hence, optimising these properties… More >

Yunpeng Wen^1,*, Bingyang Ke², Junrong Ding³

Chalcogenide Letters, Vol.23, No.1, 2026, DOI:10.32604/cl.2026.076587 - 26 January 2026

Abstract This study reports an active learning (AL)-guided strategy to optimize the sulfurization–selenization processing conditions of Sb₂(S,Se)₃ thin-film photovoltaic absorbers for enhanced power conversion efficiency (PCE). By coupling Gaussian process modeling with iterative experimental feedback, we explored 20 targeted annealing conditions across the full compositional spectrum (x = 0–1) and identified an optimal S/(S + Se) ratio of 0.40 (x = 0.60), which yielded a band gap (Eg) of ~1.34 eV, close to the theoretical Shockley–Queisser optimum. The optimized process employed a controlled two-step 420°C anneal with sequential H₂Se→H₂S exposure, which produced large plate-like grains (300–500 nm)… More >

Zhangdi Xie^1,2,*, Cantao Zhuang¹, Yong Wu¹, Linghui Niu¹, Jianming Zhao³

Structural Durability & Health Monitoring, Vol.20, No.1, 2026, DOI:10.32604/sdhm.2025.070531 - 08 January 2026

Abstract This study employed tri-component continuous monitoring data from 10 measurement points on both sides of a base isolation layer in the basement of a large-span high-rise building in Beijing, as well as from a free-field station and roof frame, during a M_w 5.5 magnitude earthquake in Pingyuan, Shandong, in 2023. The H/V spectral ratio method was used to evaluate the structural dynamic response characteristics of the building and analyze the regulatory effect of the base-isolation layer on seismic waves. The results indicate that during the earthquake, the peak frequency of the free-field and the measurement points… More >