Jiahui Liu, Longzhen Dong^*, Zeling Hou

CMC-Computers, Materials & Continua, Vol.89, No.2, 2026, DOI:10.32604/cmc.2026.085242 - 15 September 2026

Abstract Detecting surface defects on steel is challenging because many defect regions are visually weak, have blurred boundaries, and contain minimal pixel information. In detectors from the You Only Look Once (YOLO) family, these subtle cues may be weakened at the early feature extraction stage and further attenuated during repeated downsampling. To improve the preservation and utilization of such defect-related details, this paper proposes EFAS-YOLO, a lightweight YOLOv11-based detection framework for steel surface defect inspection. First, an Edge-Frequency Aware Stem (EFAS) is introduced before the backbone to explicitly extract Sobel-based gradient responses and fuse them with… More >

Ti-Lun Miao¹, Hsien-Tsung Chang^1,2,3,*

CMES-Computer Modeling in Engineering & Sciences, Vol.148, No.2, 2026, DOI:10.32604/cmes.2026.086762 - 28 August 2026

Abstract Personalized fashion recommendation requires models that can capture visual compatibility, textual semantics, structured attributes, and user-specific preferences. However, existing multimodal approaches often rely on static word embeddings and shallow text encoders, limiting their ability to represent nuanced fashion descriptions. This study proposes a multimodal recommendation framework enhanced by large language models (LLMs) that integrates visual features, contextual textual representations, and structured attribute features for personalized outfit matching. A Japanese pretrained BERT encoder is used to replace the conventional Word2Vec and convolutional neural network (CNN)-based text pipeline, while GPT-4o is employed to extract fine-grained fashion attributes… More >

Chia-Hui Liu^*, Chen-Chuan Cheng

CMES-Computer Modeling in Engineering & Sciences, Vol.148, No.2, 2026, DOI:10.32604/cmes.2026.083813 - 28 August 2026

Abstract Industrial air quality forecasting remains challenging due to nonlinear pollutant formation, localized emissions, meteorological variability, and nonstationary spatiotemporal dependencies among monitoring stations. This study proposes FFTGNet, a frequency-aware spatiotemporal graph neural network for multi-pollutant forecasting in industrial air quality systems. It integrates an FFT-guided dominant-period estimation and period-folding module with a temporal-to-spatial graph backbone composed of TemporalGLU and Chebyshev graph convolution. The frequency-guided module reorganizes input sequences into intra-period and inter-period representations, TemporalGLU adaptively filters nonlinear temporal fluctuations and short-term spikes, and ChebGCN propagates information across inter-station spatial dependencies. Experiments were conducted using five years… More >

Shounak Mandal¹, Subhadip Pati^1,#, Nirmallyadeb Ray^1,#, Bipasha Guha Roy^2,#, Priyanka Saha³, Deepsubhra Guha Roy^2,*

Digital Engineering and Digital Twin, Vol.4, pp. 27-47, 2026, DOI:10.32604/dedt.2026.081859 - 14 August 2026

Abstract HealthyBrain is a scalable, interoperable, and intelligent Remote Patient Monitoring (RPM) platform built on Internet of Things (IoT) technologies and a modular microservices architecture. The system integrates wearable IoT devices, MQTT (Message Queuing Telemetry Transport)-based lightweight messaging, and high-throughput real-time data streaming via Apache Kafka. Edge-side preprocessing enables low-latency analytics, while machine learning-based anomaly detection models facilitate early identification of critical health events. To ensure clinical interoperability, the platform adheres to the HL7 FHIR (Fast Healthcare Interoperability Resources) standard for electronic health record exchange. The system’s novel contribution lies in the unified integration of edge… More >

Adnan Hnaif^1,*, Hanadi Al-Shawabkah², Ayman Alqafaan², Mohammad Alia¹

CMC-Computers, Materials & Continua, Vol.88, No.3, 2026, DOI:10.32604/cmc.2026.082998 - 23 July 2026

Abstract Many fast pattern-matching mechanisms are used in NIDS (Network Intrusion Detection Systems) to filter higher volumes of network traffic prior to invoking expensive rule verification stages. This filtering phase in signature-based engines, such as Snort, needs to preserve exact matching semantics while being able to process at high throughput on commodity hardware. Here, we introduce a hybrid CPU–GPU architecture-aware framework for exact multi-pattern matching based on the Weighted Exact Matching Algorithm (WEMA). WEMA performs the most relevant matching based on deterministic ordered indexing of category units, which eliminates chaotic control flow (which occurs with automata… More >

Mazin Ahmed Abdelraouf^1,2, Xiaoqi He¹, Hind Abdelmonim Elsanosi^1,3, Tiantian Zhu¹, Jinghui Shi¹, Ullah Habib¹, Li Song^1,*

Phyton-International Journal of Experimental Botany, Vol.95, No.6, 2026, DOI:10.32604/phyton.2026.079749 - 29 June 2026

Abstract The fasciclin-like arabinogalactan protein (FLA) family is involved in important plant wall formation and mechanical strength of the stems, and has never been systematically characterized in soybean (Glycine max), a huge crop in which stem lodging has been the cause of significant losses in yield. Here, we found that the soybean genome has 64 GmFLA genes, or a considerable increase over Arabidopsis, rice, and poplar, and these genes were grouped into three phylogenetic clusters (A, B, and C) that have varied domain structures. Evolutionary studies showed that duplication of segments was the most common cause of family… More >

Menahil Rahman¹, Waqas Ishtiaq², Amerah Alabrah^3,*, Arif Mehmood⁴, Rana Faraz Ahmed⁴, Iqra Khalid⁵, Farhan Amin^6,*

CMES-Computer Modeling in Engineering & Sciences, Vol.147, No.2, 2026, DOI:10.32604/cmes.2026.078549 - 27 May 2026

Abstract Access to safe drinking water is a fundamental determinant of global health. The presence of contaminated water affects the citizens’ health. Per- and polyfluoroalkyl substances (PFAS) are often referred to as forever chemicals. They pose a persistent and growing threat to drinking water. In the literature, machine learning methods are used to identify the forever chemicals in water. However, traditional methods are not efficient and scalable. Thus, to solve this issue. This study develops a large-scale machine-learning framework for PFAS risk screening in US public water systems. The proposed framework incorporates data ingestion, preprocessing, and More >

Lihua Zhong¹, Feng Pan¹, Yuyao Yang¹, Lei Feng¹, Jinghe Jiang², Guo Lin², Xiaoshun Zhang^3,*

Energy Engineering, Vol.123, No.6, 2026, DOI:10.32604/ee.2025.073240 - 27 May 2026

Abstract This paper addresses the challenge of efficiently calculating dynamic carbon emission factors (CEFs) in large-scale power systems. Traditional methods that rely on direct matrix inversion are computationally intensive and become impractical for networks with thousands of nodes. To overcome this limitation, a fast and scalable computational framework is proposed based on the incomplete LU (ILU) preconditioned biconjugate gradient stabilized (BiCGSTAB) iterative solver. The proposed approach formulates the nodal CEF model as a sparse linear system and employs Krylov subspace acceleration with ILU preconditioning to enhance convergence and numerical stability. The method is applied to synthetic… More > Graphic Abstract

Xin Lu¹, Jian-Hong Wang^1,*, Kuo-Chun Hsu^2,*

CMC-Computers, Materials & Continua, Vol.88, No.1, 2026, DOI:10.32604/cmc.2026.078547 - 08 May 2026

Abstract Aiming at the problems of data sparsity, uneven behavior weight allocation, and insufficient timeliness modeling existing in traditional recommendation systems in the scenario of personalized fashion recommendation, this paper proposes a personalized recommendation method that integrates multi-behavior weights and multi-modal features. A dynamic weighted collaborative filtering algorithm is designed, which comprehensively considers the multi-dimensional behaviors of users, and introduces a time attenuation factor to construct a time-sensitive user-item scoring matrix, so as to more accurately depict the dynamic changes of user interests. A multi-modal deep fusion framework is built: ResNet-50 is used to extract commodity… More >

Jialun Liu^1,2,3,*, Yuchang Lu⁴, Jianjun Lin³, Shebing Li³, Ruixia Gao⁵, Zhao Li⁶

Frontiers in Heat and Mass Transfer, Vol.24, No.2, 2026, DOI:10.32604/fhmt.2026.076292 - 30 April 2026

Abstract A steady thermo-hydraulic model of the helical tube steam generator was first constructed to study the coupled heat transfer process between the primary and secondary sides based on a discrete modeling method, and obtain the heat flux density distribution along the steam generator. Then, taking the obtained coupled heat flux density distribution as the thermal boundary condition input, considering the dynamic variation of physical properties on the secondary side, a dynamic model based on the time-domain method suitable for two-phase flow instability among parallel multiple channels of the steam generator was constructed. Finally, taking the… More >