Mohammed Hassan Alnemari^1,2,*, Abdelrahman Osman Elfaki³, Anas Bushnag¹, Mohamed Hussien Mohamed Nerma¹

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.082976 - 23 July 2026

Abstract Sparse finite impulse response (FIR) filters reduce computational cost on resource-constrained devices, but selecting the sparsification threshold λ is typically left to grid search or hand tuning. We propose a two-stage method: a 67,331-parameter surrogate network predicts (Ap,As,S) (passband ripple in dB, stopband attenuation in dB, sparsity in %) from a filter specification and a candidate λ, and split conformal prediction (CP) calibrates ± intervals around each prediction. We then select λ by minimizing a worst-case penalty computed on the conservative ends of the intervals (the upper bound on Ap and… More >

Botambu Collins, Jin-Taek Seong^*

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.3, 2026, DOI:10.32604/cmes.2026.082245 - 30 June 2026

Abstract Classical image denoising methods remain relevant in practical scenarios where training data or noise models are unavailable, yet their performance is highly sensitive to parameter selection. Non-Local Means (NLM) is a representative example whose effectiveness depends critically on smoothing strength, patch size, and search window configuration. This paper formulates NLM parameter selection as a black-box optimization problem under unknown noise conditions and employs adaptive metaheuristic optimization strategies for this task. We propose an adaptive optimization framework that integrates rank-based perturbation, opposition-based learning, Lévy-flight exploration, and noise-aware parameter constraints to improve robustness and convergence. The proposed More >

Gaoteng Yuan^1,*, Ping Qiu², Qika Lin³, Jianchu Lin¹, Xiang Li¹, Dongping Gao⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.3, 2026, DOI:10.32604/cmes.2026.081152 - 30 June 2026

Abstract Epilepsy is a chronic neurological disorder characterized by recurrent seizures, posing significant challenges to patients’ quality of life. Accurate classification of seizure states is crucial for effective intervention. This paper presents a deep learning-based approach for epileptic seizure classification by integrating multi-feature analysis of electroencephalogram (EEG) signals. The proposed method begins with signal preprocessing, including denoising, segmentation, and label construction. Subsequently, a comprehensive set of temporal, spectral, and wavelet-based features—such as signal mean, power, heart rate, and wavelet coefficients—is extracted. Feature selection is then performed using the Maximal Information Coefficient (MIC) to identify the most… More > Graphic Abstract

Hao Jiang¹, Lucheng Sun², Liguo Shuai^1,*, Zhihan Li^3,*

FDMP-Fluid Dynamics & Materials Processing, Vol.22, No.6, 2026, DOI:10.32604/fdmp.2026.082152 - 30 June 2026

Abstract Underwater bio-inspired robots have emerged as a promising alternative to conventional propeller-driven autonomous underwater vehicles and remotely operated vehicles because of their potential for high propulsive efficiency, superior maneuverability, reduced acoustic signatures, and enhanced environmental adaptability. Unlike rigid propellers operating under approximately steady inflow conditions, bio-inspired propulsion relies on strongly unsteady hydrodynamic mechanisms, including vortex generation and shedding, added-mass effects, boundary-layer evolution, and flexible fluid–structure interaction (FSI). These processes fundamentally govern thrust production, energy conversion, and maneuvering performance, yet a systematic synthesis connecting hydrodynamic mechanisms with engineering implementation remains limited. This review addresses that gap… More >

Xiaoyong Zhao¹, Jiamin Wu^2,*, Lei Wang²

CMC-Computers, Materials & Continua, Vol.88, No.2, 2026, DOI:10.32604/cmc.2026.077179 - 15 June 2026

Abstract With the continuous improvement of the performance of large language models, how to further enhance their ability in complex tasks has become a key issue. The task of abnormal text detection poses a challenge to the model in identifying non-standard semantics due to its semantic complexity and high-risk features. However, existing fine-tuning methods rely heavily on static data selection strategies, making it difficult to adapt to the dynamic evolution of model capabilities, resulting in low training efficiency. This article proposes ADS (Adaptive Dataset Selection), an adaptive framework for selecting data in anomaly text detection. ADS… More >

Zhenhua Yang^1,2, Yifan Li^1,2, Aimin Yang^1,2,*, Jie Li^2,3, Tao Xue^1,2

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.2, 2026, DOI:10.32604/cmes.2026.081754 - 27 May 2026

Abstract Sinter quality prediction in iron ore sintering is a challenging computational modeling problem because of highly nonlinear process behavior, strong cross-variable interactions, and disturbances caused by changing operating conditions. This study develops a data-driven multi-index soft-sensing framework for sinter quality prediction by combining feature selection and hierarchical model optimization. An improved binary Greylag Goose Optimization algorithm is first employed to identify a compact subset of informative variables, reducing redundancy and multicollinearity in the original process data. A hierarchical two-stage Greylag Goose Optimization strategy is then designed to optimize the hyperparameters of a support vector regression… More >

Emerson de Medeiros de Sousa^1,#, Salvador Barros Torres^2,#, Marciana Bizerra de Morais^3,#, Clarisse Pereira Benedito², Kleane Targino Oliveira Pereira², Moadir de Sousa Leite², Maria Valdiglezia de Mesquita Arruda², Jéssica Christie Dantas de Oliveira Costa², Roseane Rodrigues de Oliveira², Giovanna Dias de Sousa², Cynthia Cavalcanti de Albuquerque³, Marco Porceddu⁴, Gianluigi Bacchetta⁴, Francisco Vanies da Silva Sá^5,*

Phyton-International Journal of Experimental Botany, Vol.95, No.5, 2026, DOI:10.32604/phyton.2026.078410 - 27 May 2026

Abstract Semiarid regions are frequently affected by low water availability, which hinders the development of horticultural species such as melon (Cucumis melo L.). In this context, techniques that enhance drought tolerance are essential for more effective crop management. This study aimed to evaluate the tolerance and antioxidant activity of different melon cultivars using seed pre-treatment with stress-attenuating agents. The experiment was conducted in two stages, both arranged in a completely randomized design with four replicates of 50 seeds. In the first stage, a 3 × 5 factorial scheme was used, combining three levels of water deficit (0.0,… More >

Federico Minelli^1,*, Diana D’Agostino¹, Vennapusa Jagadeeswara Reddy², Panagiotis Michailidis^3,4

Energy Engineering, Vol.123, No.6, 2026, DOI:10.32604/ee.2026.074048 - 27 May 2026

Abstract This study investigates the problem of prioritizing rooftop renewable energy (RE) system configurations for a multi-family residential building in Mediterranean climate. The analysis focuses on fixed-tilt photovoltaics (PV), single-axis and dual-axis tracking PV, and small vertical-axis wind turbines (VAWT), each assessed with and without lithium-ion storage. A co-simulation framework is used, coupling EnergyPlus building-HVAC system simulation with PV and wind generation modeling and rule-based battery dispatch to evaluate hourly demand–supply interactions. Three decision criteria are considered for each alternative: total system cost, annual building electric energy demand reduction, and net avoided life-cycle emissions. Stakeholder preferences… More > Graphic Abstract

Darren Chai Xin Lun, Lim Tong Ming^*

CMC-Computers, Materials & Continua, Vol.88, No.1, 2026, DOI:10.32604/cmc.2026.080068 - 08 May 2026

Abstract The deployment of specialized language models in resource-constrained edge environments (≤1B parameters, ≤2 GB memory, ≤100 ms latency) faces a critical challenge: Supervised Fine-Tuning (SFT) achieves domain expertise but suffers from irreversible catastrophic forgetting, while traditional Low-Rank Adaptation (LoRA) with conservative ranks (r ≤ 64) often underperforms due to insufficient adaptation capacity. This work introduces H-LoRA (High-Rank LoRA) for edge-deployable models and establishes a fundamental distinction between destructive forgetting and controllable knowledge retention. Through comprehensive experiments on compact models (0.12B Minimind and Qwen-0.5B) across three domains (Human Resources, Medical, Mathematics) using 29,647 samples, we… More >

Jinchuan Pei¹, Yuxiang Hu^1,2,3,4,*, Hongtao Yu¹, Zihao Wang¹, Menglong Li^1,2,3,4

CMC-Computers, Materials & Continua, Vol.88, No.1, 2026, DOI:10.32604/cmc.2026.079684 - 08 May 2026

Abstract In the cloud-edge collaborative network, advanced persistent threats (APTs) pose a serious security risk to critical network assets. Although network deception defense can mislead attackers’ cognition, its effectiveness depends on dynamically selecting appropriate rotation timings of the deception defense. However, the deployment of deception resources and state updates is not completed instantaneously, and existing methods ignore the state transition delay and the dynamic interaction between the attackers and defenders during the real attack and defense process. To address this, we propose a deception defense timing selection method based on the time-delayed FlipIt game. Firstly, a… More >