Jinshuo Ma, Yang Li^*, Can Guo, Wen Gao, Ruiming Zhang

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.085999 - 13 August 2026

Abstract Underwater image restoration is severely hindered by a tightly coupled degradation process: wavelength-dependent spectral distortion combined with non-uniform, multi-scale spatial scattering. Standard Convolutional Neural Networks (CNNs) and rigid physical priors frequently fail in these dynamic environments, limited by restricted receptive fields, overlooked inter-channel spectral correlations, and severe over-enhancement in photon-starved regions. To break this bottleneck, we propose the Phased Feature Rectification Network (PFR-Net), a decoupled architecture that transforms the ill-posed restoration task into a sequential global spectral calibration and deep semantic refinement paradigm. In the first phase, an efficient Multi-Layer Perceptron (MLP)-based Color Mapping (MLP-CM)… More >

Muhammad Naeem Zafar¹, Yunfei Yin^1,*, Junaid Abbas², Bayan Alabdullah³, Khaled Alnowaiser⁴, Yunyoung Nam⁵, Zepa Yang^5,*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.085136 - 13 August 2026

Abstract Accurate medical image classification increasingly relies on the joint modeling of global contextual semantics and fine-grained local structural cues, since many lesions are only reliably recognized when subtle local details are interpreted within their broader anatomical context. However, most recent hybrid CNN–Transformer and global–local frameworks still extract these features in separate streams and merge them only through late-stage static fusion, without explicit bidirectional interaction during representation learning. As a result, global context cannot effectively guide the refinement of subtle local structures, and local discriminative cues cannot recalibrate higher-level semantic reasoning before classification, which limits reciprocal… More >

David Hason Rudd^1,*, Cesar Sanin², Md Rafiqul Islam³, Xianzhi Wang¹, Huan Huo¹

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.084015 - 13 August 2026

Abstract The accurate classification of human emotions from speech remains a formidable challenge due to the dynamic, non-stationary properties of audio signals and pervasive background noise. Traditional single-domain extraction methods frequently fail to capture overlapping acoustic phenomena, resulting in high misclassification rates among acoustically similar emotions. To overcome this, we propose the Dual-Decomposition Ensemble (DDE-SER), an architecture that synergizes 1D adaptive frequency filtering with 2D spatial spectrogram separation. The framework operates through two distinct pipelines: an adaptive time-domain branch that leverages VGG-optiVMD to autonomously extract Intrinsic Mode Functions (IMFs), and a structural spectrogram branch that applies… More >

Chao Zhang, Yunfeng Dong^*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.083353 - 13 August 2026

Abstract The missile warning constellation is fundamental to national territorial security and has significant strategic and military value. This study proposes a two-stage, nested co-optimization framework with adaptive evolutionary operators, termed TNC-A, to address challenges in genetic representation, evaluation distortion, the curse of dimensionality, and search inefficiency within the co-optimization of component-level constellation morphology and mission planning. A hybrid encoding scheme combining tree-structured and real-valued vector representations was adopted to encode all optimization variables, including constellation configuration, component-level unified platform information, and mission planning parameters. Second, a multi-stage optimization strategy integrated with a double-nested structure was More >

Jordi Vallverdú^*

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.082945 - 13 August 2026

Abstract Large rule-based systems—from automated theorem provers to diagnostic engines and expert systems—face a common bottleneck: when many rules are simultaneously applicable, choosing which rule to fire can dominate search effort. We present HL-W, a formally constrained adaptive proof-search control layer over a fixed base calculus. Each inference rule R is assigned a scalar weight w(R,t)∈[0,1] at search stage t; rule applications are scheduled by combining a threshold condition w(R,t)≥θ with an explicit fairness mechanism. Because the underlying inference rules are left unchanged, every derivation produced by the framework… More >

Tallha Akram^1,*, Sadiq Ahmad^2,*, Meshal Alharbi³

CMC-Computers, Materials & Continua, Vol.89, No.1, 2026, DOI:10.32604/cmc.2026.081458 - 13 August 2026

Abstract Scalability limitations, privacy risks, and lack of adaptability remain key challenges in centralized medical digital win (MDT) architectures. While federated learning (FL) mitigates the need to share raw data, it often lacks adaptability to dynamic clinical environments and does not fully integrate formal privacy guarantees into the learning process. To address these challenges, this paper proposes a decentralized, federated, multi-agent reinforcement learning (F-MARL) framework to coordinate MDTs in the presence of partial observability. The framework is formulated as a multi-agent partially observable Markov decision process (MA-POMDP), enabling distributed policy optimization in heterogeneous and uncertain clinical… More >

Li Sun, Fanjun Zeng, Hongbo Liu, Chenglian Ma^*, Qiting Zhang, Jingzhou Zhu

Energy Engineering, Vol.123, No.9, 2026, DOI:10.32604/ee.2025.073405 - 06 August 2026

Abstract The widespread integration of large-scale wind power has resulted in decreased equivalent inertia in power systems, thereby compromising their frequency regulation (FR) capabilities. Conventional synthetic inertia control faces challenges under stochastic wind conditions, including inadequate utilization of rotor kinetic energy in high wind condition regions and the risk of triggering rotor speed stability limits in low wind condition regions. To overcome these limitations, in this paper, a parameter adaptive synthetic virtual inertial control (SVIC) framework based on wind speed partition is proposed. The control mechanisms are designed differently across partitioned wind condition intervals: in high-wind-speed More >

Gian Marco Ludovici^1,2,*, Paola Amelia Tassi², Alba Iannotti^2,3, Colomba Russo^2,3, Francesco Gargallo di Castel Lentini⁴, Timothy Alexander Mousseau⁵, Andrea Malizia^1,2

Phyton-International Journal of Experimental Botany, Vol.95, No.7, 2026, DOI:10.32604/phyton.2026.083056 - 30 July 2026

Abstract The detonation of nuclear weapons, beginning with the Trinity test in New Mexico and followed by the bombings of Hiroshima and Nagasaki, created distinct environments of ionizing radiation exposure. While the ecological consequences of reactor accidents at Chernobyl and Fukushima have been extensively investigated, the potential evolutionary implications of historical weapons testing for plant communities remain comparatively underexplored, particularly in arid ecosystems. This review synthesizes available, yet fragmented, evidence to examine the hypothesis that residual radionuclides in arid test-site environments may have acted as potential selective pressures influencing plant persistence and stress-associated traits in native… More >

Mutlu Seçer^*, Ali Alper Saylan

CMES-Computer Modeling in Engineering & Sciences, Vol.148, No.1, 2026, DOI:10.32604/cmes.2026.084228 - 27 July 2026

Abstract Climate change modifies environmental exposure conditions and affects the corrosion-driven deterioration of steel bridges, thereby challenging conventional maintenance planning approaches. Thus, more advanced maintenance management strategies are required to address the challenges associated with varying corrosion rate projections. In this study, a novel adaptive maintenance management framework is proposed for steel truss bridges to address climate change-induced corrosion under evolving deterioration conditions. Adaptivity is achieved by updating corrosion rates to consider time-varying deterioration conditions associated with climate change. This enables time-dependent representation of corrosion progression under changing environmental conditions. The framework is demonstrated on a… More >

Mahander Kumar¹, Lal Khan^2,*, Mohammad Zubair Khan^3,*, Ibrahim Aljubayri⁴

CMES-Computer Modeling in Engineering & Sciences, Vol.148, No.1, 2026, DOI:10.32604/cmes.2026.081699 - 27 July 2026

Abstract Aspect-Based Sentiment Analysis (ABSA) is a fundamental Natural Language Processing (NLP) task that aims to determine fine-grained sentiment polarity toward specific aspects mentioned in text. With the emergence of Large Language Models (LLMs) and transformer-based architectures, significant improvements have been achieved in contextual representation learning for sentiment analysis. However, existing LLM-inspired and transformer-based ABSA frameworks often suffer from inadequate aspect-context alignment, redundant feature integration, limited interpretability, and insufficient coordination between contextual and sequential modeling components. To address these challenges, this paper proposes two hybrid architectures, namely HABSA and AAC-HABSA, centered on a novel Adaptive Aspect… More > Graphic Abstract