Monalisa Jena¹, Noman Khan^2,*, Mi Young Lee^3,*, Seungmin Rho³

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.1, 2026, DOI:10.32604/cmes.2025.075119 - 29 January 2026

Abstract Mental-health risk detection seeks early signs of distress from social media posts and clinical transcripts to enable timely intervention before crises. When such risks go undetected, consequences can escalate to self-harm, long-term disability, reduced productivity, and significant societal and economic burden. Despite recent advances, detecting risk from online text remains challenging due to heterogeneous language, evolving semantics, and the sequential emergence of new datasets. Effective solutions must encode clinically meaningful cues, reason about causal relations, and adapt to new domains without forgetting prior knowledge. To address these challenges, this paper presents a Continual Neuro-Symbolic Graph… More >

Burhan Baraklı^1,*, Can Yüzkollar², Tuğrul Taşçı³, İbrahim Yıldırım²

CMES-Computer Modeling in Engineering & Sciences, Vol.146, No.1, 2026, DOI:10.32604/cmes.2025.074292 - 29 January 2026

Abstract Salient object detection (SOD) models struggle to simultaneously preserve global structure, maintain sharp object boundaries, and sustain computational efficiency in complex scenes. In this study, we propose SPSALNet, a task-driven two-stage (macro–micro) architecture that restructures the SOD process around superpixel representations. In the proposed approach, a “split-and-enhance” principle, introduced to our knowledge for the first time in the SOD literature, hierarchically classifies superpixels and then applies targeted refinement only to ambiguous or error-prone regions. At the macro stage, the image is partitioned into content-adaptive superpixel regions, and each superpixel is represented by a high-dimensional region-level… More >

Wei Chen, Yang Wu^*, Tingting Pei, Jie Lin, Guojing Yuan

Energy Engineering, Vol.123, No.2, 2026, DOI:10.32604/ee.2025.070905 - 27 January 2026

Abstract In view of the insufficient utilization of condition-monitoring information and the improper scheduling often observed in conventional maintenance strategies for photovoltaic (PV) modules, this study proposes a predictive maintenance (PdM) strategy based on Remaining Useful Life (RUL) estimation. First, a RUL prediction model is established using the Transformer architecture, which enables the effective processing of sequential degradation data. By employing the historical degradation data of PV modules, the proposed model provides accurate forecasts of the remaining useful life, thereby supplying essential inputs for maintenance decision-making. Subsequently, the RUL information obtained from the prediction process is… More >

Lifu He¹, Zhongchu Huang¹, Haidong Shao^2,*, Zhangbo Hu¹, Yuting Wang¹, Jie Mei¹, Xiaofei Zhang³

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.073227 - 12 January 2026

Abstract Deep learning-based wind turbine blade fault diagnosis has been widely applied due to its advantages in end-to-end feature extraction. However, several challenges remain. First, signal noise collected during blade operation masks fault features, severely impairing the fault diagnosis performance of deep learning models. Second, current blade fault diagnosis often relies on single-sensor data, resulting in limited monitoring dimensions and ability to comprehensively capture complex fault states. To address these issues, a multi-sensor fusion-based wind turbine blade fault diagnosis method is proposed. Specifically, a CNN-Transformer Coupled Feature Learning Architecture is constructed to enhance the ability to More >

Shuangqing Song¹, Yuan Chen², Xuguang Hu¹, Juwei Zhang^1,3,*

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072392 - 12 January 2026

Abstract In multi-domain neural machine translation tasks, the disparity in data distribution between domains poses significant challenges in distinguishing domain features and sharing parameters across domains. This paper proposes a Transformer-based multi-domain-aware mixture of experts model. To address the problem of domain feature differentiation, a mixture of experts (MoE) is introduced into attention to enhance the domain perception ability of the model, thereby improving the domain feature differentiation. To address the trade-off between domain feature distinction and cross-domain parameter sharing, we propose a domain-aware mixture of experts (DMoE). A domain-aware gating mechanism is introduced within the… More >

Haohui Su¹, Xuan Zhang^1,*, Lvjun Zheng¹, Xiaojie Shen², Hua Liao¹

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.072093 - 12 January 2026

Abstract Distributed Denial-of-Service (DDoS) attacks pose severe threats to Industrial Control Networks (ICNs), where service disruption can cause significant economic losses and operational risks. Existing signature-based methods are ineffective against novel attacks, and traditional machine learning models struggle to capture the complex temporal dependencies and dynamic traffic patterns inherent in ICN environments. To address these challenges, this study proposes a deep feature-driven hybrid framework that integrates Transformer, BiLSTM, and KNN to achieve accurate and robust DDoS detection. The Transformer component extracts global temporal dependencies from network traffic flows, while BiLSTM captures fine-grained sequential dynamics. The learned… More >

Haoxuanye Ji^*, Zhiliang Chen, Pengfei Jiang, Ziyue Wang, Ting Yu, Wei Zhang

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.071880 - 12 January 2026

Abstract Foreign body classification on coal conveyor belts is a critical component of intelligent coal mining systems. Previous approaches have primarily utilized convolutional neural networks (CNNs) to effectively integrate spatial and semantic information. However, the performance of CNN-based methods remains limited in classification accuracy, primarily due to insufficient exploration of local image characteristics. Unlike CNNs, Vision Transformer (ViT) captures discriminative features by modeling relationships between local image patches. However, such methods typically require a large number of training samples to perform effectively. In the context of foreign body classification on coal conveyor belts, the limited availability… More >

Chee Chin Lim^1,2,*, Hui Wen Tiu¹, Qi Wei Oung^1,3, Chiew Chea Lau⁴, Xiao Jian Tan^2,5

CMC-Computers, Materials & Continua, Vol.86, No.3, 2026, DOI:10.32604/cmc.2025.070468 - 12 January 2026

Abstract Breast cancer remains one of the leading causes of cancer mortality world-wide, with accurate molecular subtyping is critical for guiding treatment and improving patient outcomes. Traditional molecular subtyping via immuno-histochemistry (IHC) test is invasive, time-consuming, and may not fully represent tumor heterogeneity. This study proposes a non-invasive approach using digital mammography images and deep learning algorithm for classifying breast cancer molecular subtypes. Four pretrained models, including two Convolutional Neural Networks (MobileNet_V3_Large and VGG-16) and two Vision Transformers (ViT_B_16 and ViT_Base_Patch16_Clip_224) were fine-tuned to classify images into HER2-enriched, Luminal, Normal-like, and Triple Negative subtypes. Hyperparameter tuning,… More >

Meixi Chu¹, Xinyu Jiang^1,*, Yushu Tao²

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-23, 2026, DOI:10.32604/cmc.2025.071533 - 09 December 2025

Abstract Industrial operators need reliable communication in high-noise, safety-critical environments where speech or touch input is often impractical. Existing gesture systems either miss real-time deadlines on resource-constrained hardware or lose accuracy under occlusion, vibration, and lighting changes. We introduce Industrial EdgeSign, a dual-path framework that combines hardware-aware neural architecture search (NAS) with large multimodal model (LMM) guided semantics to deliver robust, low-latency gesture recognition on edge devices. The searched model uses a truncated ResNet50 front end, a dimensional-reduction network that preserves spatiotemporal structure for tubelet-based attention, and localized Transformer layers tuned for on-device inference. To reduce… More >

Cyreneo Dofitas¹, Yong-Woon Kim², Yung-Cheol Byun^3,*

CMC-Computers, Materials & Continua, Vol.86, No.2, pp. 1-19, 2026, DOI:10.32604/cmc.2025.069374 - 09 December 2025

Abstract Recent advances in deep learning have significantly improved flood detection and segmentation from aerial and satellite imagery. However, conventional convolutional neural networks (CNNs) often struggle in complex flood scenarios involving reflections, occlusions, or indistinct boundaries due to limited contextual modeling. To address these challenges, we propose a hybrid flood segmentation framework that integrates a Vision Transformer (ViT) encoder with a U-Net decoder, enhanced by a novel Flood-Aware Refinement Block (FARB). The FARB module improves boundary delineation and suppresses noise by combining residual smoothing with spatial-channel attention mechanisms. We evaluate our model on a UAV-acquired flood More >