Search Results (2,766)

Radiation pneumonitis (RP), one of the most common and severe complications in locally advanced non-small cell lung cancer (LA-NSCLC) patients following thoracic radiotherapy, presents significant challenges in prediction due to the complexity of clinical risk factors, incomplete multimodal data, and unavailable slice-level annotations in pre-radiotherapy CT images. To address these challenges, we propose a multimodal fusion framework based on Dual-Layer Attention-Based Adaptive Bag Embedding Multiple-Instance Learning (DAAE-MIL) for accurate RP prediction. This study retrospectively collected data from 995 LA-NSCLC patients who received thoracic radiotherapy between November 2018 and April 2025. After screening, Subject datasets (n = 670) were allocated for training (n = 535), and the remaining samples (n = 135) were reserved for an independent test set. The proposed framework first extracts pre-radiotherapy CT image features using a fine-tuned C3D network, followed by the DAAE-MIL module to screen critical instances and generate bag-level representations, thereby enhancing the accuracy of deep feature extraction. Subsequently, clinical data, radiomics features, and CT-derived deep features are integrated to construct a multimodal prediction model. The proposed model demonstrates promising RP prediction performance across multiple evaluation metrics, outperforming both state-of-the-art and unimodal RP prediction approaches. On the test set, it achieves an accuracy (ACC) of 0.93 and an area under the curve (AUC) of 0.97. This study validates that the proposed method effectively addresses the limitations of single-modal prediction and the unknown key features in pre-radiotherapy CT images while providing significant clinical value for RP risk assessment. Full article

Additive manufacturing (AM), particularly Fused Deposition Modeling (FDM), has revolutionized polymer-based fabrication through design freedom and material efficiency. This work presents a comprehensive statical optimization of FDM parameters affecting the flexural properties of acrylonitrile/butadiene/styrene (ABS) specimens. The effects of layer thickness (0.15–0.25 mm), infill density (30–70%), printing speed (35–95 mm/s), and build orientation (Flat, On-edge, Vertical) were investigated following ASTM D790 standards. A Taguchi L9 orthogonal array coupled with ANOVA analysis was employed to quantity parameter significance. According to the ANOVA analysis, infill density was identified as the most influential parameter, accounting for 61.3% of the variation in flexural strength (σ_f) and 60.1% in flexural modulus (E_b). The optimal configuration (0.25 mm layer thickness, 70% infill, 65 mm/s speed, horizontal orientation) yielded a flexural strength of 84.9 MPa and modulus of 2.54 GPa. Microstructural observations confirmed that higher infill and moderate speed improved interlayer fusion and reduced void formation. The developed Taguchi–ANOVA framework offers quantitative insights for tailoring process–structure–property relationships in polymer-based additive manufacturing. Full article

Historic buildings often exhibit high energy use intensity (EUI), while conservation constraints limit envelope retrofits, making it difficult to identify robust and actionable operational predictors. Using four in-use historic buildings in Shenyang, China, this study presents a pilot methodological demonstration with a controlled-comparability workflow consisting of two linked layers: (i) a Driver layer of intervenable operational variables and (ii) a Pathway layer of calibrated EnergyPlus heat-balance terms for physics-informed interpretation. Three importance approaches (Spearman, wrapper RFE with XGBoost, and Random Forest) are compared; rankings are fused via reciprocal rank fusion, and stability is tested using cross-period rolling validation across Top-K feature sets. After similarity screening, EUI variation is better explained by operational predictors and the corresponding simulated loss channels than by macro-scale structural heterogeneity. Infiltration-related indicators and envelope/infiltration loss components remain consistently prominent, while Spearman importance is less stable in the Pathway layer under seasonal switching and nonlinear coupling. A Top-10 subset provides a favorable accuracy–stability trade-off. The proposed Driver–Pathway mapping supports conservation-compatible prioritization hypotheses within a simulation-consistent interpretive framework; findings are associational and context dependent and should be validated through field measurements and experimental or quasi-experimental studies before prescriptive claims are made. Full article

Additive manufacturing by Selective Laser Melting (SLM) or, precisely, Laser Powder Bed Fusion (L-PBF), offers new opportunities for producing electrically functional metal components with tailored geometric designs and material properties. In this study, the electrical contact resistance and related properties of 3D-printed samples made from Al5086 aluminum alloy are tested. The benefits of Al5086 include flexibility without cracking, welding ability and exceptional resistance to corrosion in saltwater and industrial environments. This makes it an excellent candidate for power electric applications due to its good electrical conductivity and corrosion resistance. In this study, an analysis is performed to assess the impact of internal volumetric properties and surface parameters on general contact resistance performance. This analysis combines advanced testing procedures and parameter identification of the electric contact resistance model. This study investigates how these parameters affect contact resistance, which is a critical factor in the reliability of electrical devices. Electrical contact resistance was measured using a dedicated test setup that applied consistent pressure and maintained directional alignment. The results show that the printing direction of the samples slightly affects resistance values due to the continuity of current paths along the build direction, likely due to homogenous inter-layer boundaries and mechanical stress distribution. These findings suggest that both print orientation and internal structure must be considered when designing 3D-printed contact elements for electrical applications. Overall, this study demonstrates the feasibility of using L-PBF-fabricated aluminum components in electric applications where both electrical and structural performances are essential. Full article

The Internet of Things (IoT) plays an increasingly central role in healthcare by enabling continuous patient monitoring, remote diagnosis, and data-driven clinical decision-making through interconnected medical devices and sensing infrastructures. Despite these advances, IoT healthcare systems remain constrained by persistent challenges related to data privacy, computational efficiency, scalability, and regulatory compliance. Federated learning (FL) reduces reliance on centralised data aggregation but remains vulnerable to inference-based privacy risks, while edge-oriented approaches are limited by device heterogeneity and restricted computational and energy resources; the deployment of large language models (LLMs) further exacerbates concerns surrounding privacy exposure, communication overhead, and practical feasibility. This study introduces Trustworthy Intelligence (TI) as a guiding framework for privacy-preserving distributed intelligence in IoT healthcare, explicitly integrating predictive performance, privacy protection, and deployment-oriented system design. Within this framework, split learning (SL) is examined as a core architectural mechanism and extended to support split-aware LLM integration across heterogeneous devices, supported by a structured taxonomy spanning architectural configurations, system adaptation strategies, and evaluation considerations. The study establishes a systematic mapping between SL design choices and representative healthcare scenarios, including wearable monitoring, multi-modal data fusion, clinical text analytics, and cross-institutional collaboration, and analyses key technical challenges such as activation-level privacy leakage, early-round vulnerability, reconstruction risks, and communication–computation trade-offs. An energy- and resource-aware adaptive cut layer selection strategy is outlined to support efficient deployment across devices with varying capabilities. A proof-of-concept experimental evaluation compares the proposed SL–LLM framework with centralised learning (CL), federated learning (FL), and conventional SL in terms of training latency, communication overhead, model accuracy, and privacy exposure under realistic IoT constraints, providing system-level evidence for the applicability of the TI framework in distributed healthcare environments and outlining directions for clinically viable and regulation-aligned IoT healthcare intelligence. Full article

Distracted driving is one of the primary causes of road traffic accidents. Behavior recognition technology based on machine vision has emerged as a research hotspot due to its non-contact and high-efficiency nature. To address the challenges of complex lighting conditions in the driver’s cabin, low detection accuracy for small-scale keypoints, and the difficulty in effectively characterizing behavioral features, this paper proposes a distracted driving behavior recognition method based on an improved YOLOv8n-Pose model and multi-feature fusion. First, the original YOLOv8n-Pose model is optimized. A P2 detection layer is added to enhance the feature extraction capabilities for small-scale human keypoints, and the SE attention module is incorporated to improve the model’s robustness under complex lighting conditions. In addition, the loss function is replaced with focal loss to tackle the class imbalance problem, thus forming the YOLOv8n-PSF-Pose keypoint detection network. Subsequently, based on the coordinates of 12 human keypoints extracted by this network, a multi-dimensional feature vector is constructed, which takes joint angles as the core and integrates the relative distances between keypoints and the number of valid keypoints. Finally, a BP neural network is adopted to classify the constructed feature vectors, enabling the accurate recognition of six typical distracted driving behaviors (normal driving, drinking or eating, making phone calls, using mobile phones, operating vehicle infotainment systems, and turning around to fetch items). The experimental results show that the improved YOLOv8n-PSF-Pose model achieves an mAP50 of 93.8% in keypoint detection, which is 6.7 percentage points higher than the original model; the BP classification model based on multi-feature fusion achieves an F1-score of 97.7% in the behavior recognition task, which is significantly better than traditional classifiers such as SVM and random forest, and the image processing speed on the NVIDIA RTX 3090TI reaches a high throughput of 45 FPS. This proves that the proposed method achieves an excellent balance between accuracy and speed. This study provides an effective solution for the real-time and accurate recognition of distracted driving behaviors. Full article

To tackle the challenges of high computational expense, limited detection accuracy, and imbalanced detection performance across multi-scale targets in rice disease identification within complex natural environments, we propose the Rice Disease Deformable Detection Transformer (RDD-DETR). This model serves as a full-scale detection framework based on the Deformable Detection Transformer (Deformable DETR). The model introduces a Rectified Linear Unit (ReLU)-enhanced lightweight linear attention module, which uses differentiated position coding and ReLU kernel mapping to reduce computational complexity. A cross-layer dynamic fusion and inter-layer supervision module is designed to break the serial dependence in decoders and strengthen interlayer supervision, enabling the decoder to generate more accurate and robust target representations. Furthermore, we design an optimization mechanism for sub-scale positioning loss to substantially boost detection accuracy across all target scales. Experiments on our custom RiceLeafDisease-RSOD dataset demonstrate that RDD-DETR achieves an average precision (AP) at Intersection over Union (IoU) threshold 0.5:0.95 of 0.7363 across all categories, surpassing the baseline model by 6.09%. Notably, detection accuracy improves by 6.10% for small targets, 6.61% for medium targets, and 5.42% for large targets. Evaluated on the validation set (671 images with 2482 labeled bounding boxes), the model achieves an AP at IoU threshold 0.5 of 0.9684 while reducing computational cost by 37.41% (from 136.02 to 85.1 Giga Floating Point Operations, GFLOPs) compared to the original Deformable DETR. These results validate RDD-DETR as an effective solution for accurate and efficient real-time rice disease monitoring in complex field environments. Full article

To address the challenges of modal differences in multimodal farmland images and insufficient segmentation accuracy for small targets, this paper proposes a multi-source image fusion branch (DAMFusion) based on modal competitive selection. The branch dynamically selects infrared and visible light features through the Competitive Query Module (CQM) using Top-K screening, combined with IOU-aware loss optimization to avoid cross-modal interference. The multimodal fusion module (MMFormer) employs cross-modal attention and symmetric mechanisms, enhancing single-modal features through a self-enhancement module and unifying multimodal distributions via linear projection. The Boundary Region Attention Multi-level Fusion Module (BRM) extracts boundary information through feature differencing, strengthens it with spatial attention, and fuses it with shallow features to achieve cross-layer detail recovery. Through the collaborative design of dynamic modal feature selection, cross-modal distribution unification, and boundary region enhancement, DAMFusion effectively solves the problems of multimodal differences and small target segmentation in multispectral images, providing precise feature representation for fine farmland segmentation. Experiments on the OUC-UAV-MSEG dataset show that DAMFusion achieves 93.25% OA, 91.71% F1, and 89.70% mIoU, demonstrating clear advantages over representative comparison methods. In addition, ablation results verify the effectiveness of the proposed modules, where CQM improves OA from 91.00% to 93.25%, confirming the importance of discriminative modality selection before fusion. Full article

Convolution is still the main method for hyperspectral image classification, since it takes into account both spatial and spectral characteristics. However, the convolution relies on local perceptual computation, ignoring the effective discriminant of context association for classification. In this paper, we propose a Double-Attention Context Interactive Network (DACINet) for hyperspectral image classification. Specifically, a Context Interaction Fusion Module (CIFM) is designed to enhance long-range contextual dependencies. By stacking multiple 3D convolutional layers, the module progressively enlarges its receptive field, while cross-layer residual connections facilitate the integration of features from different contextual scales, thereby strengthening the model’s ability to capture complex relationships within the hyperspectral data. Then, a Channel–Spatial Double-Attention (CSDA) mechanism based on 3D is proposed for enhancing the two-dimensional spatial features and one-dimensional spectral features, respectively, and fusing the enhanced features. Furthermore, we also construct a hybrid convolutional layer, which combines 2D and 3D convolution to further enhance spectral bands on the basis of three-dimensional understanding. Extensive experiments on the widely used IP, UP, SA and HU datasets show that the proposed DACINet achieves superior classification accuracy, reaching Overall Accuracies of 96.78%, 97.77%, 99.53% and 86.67% respectively, outperforming other state-of-the-art models. Full article

Gesture recognition with electrical impedance tomography (EIT) is an enormous potential tool for human–machine interaction because of its low cost, low complexity and high temporal resolution. Although high-precision EIT-based gesture recognition has been achieved in ideal scenarios, ensuring its consistent performance under interference remains challenging. This article presents a novel method to alleviate the effect of confounding factors on EIT gesture recognition. An EIT armband was designed to mitigate the effect of contact impedance variation based on equivalent circuit analysis, and a spatial–temporal fusion network, named the Fold Atrous Spatial Pyramid Pooling-Gated Recurrent Unit (FASPP-GRU), was developed for robust gesture classification. The results showed that the proposed two-layer electrode maintained a stable contact impedance when its contact force with the skin was changed. Although confounding factors caused significant changes in baseline forearm impedance, FASPP-GRU achieved 80% accuracy under the effect of limb position changes and dynamic changes in muscle state over time, which outperforms conventional classifiers. With an 87 μs inference time, the proposed system shows enormous potential in real-time applications. Full article

Unmanned aerial vehicle (UAV) small object detection faces critical challenges including irreversible geometric detail loss during multi-level downsampling, cross-scale feature distortion from interpolation blur and aliasing, and limited long-range dependency modeling due to constrained receptive fields. To address these limitations, we propose HMF-DEIM (High-Fidelity Multi-Domain Fusion Transformer for UAV Small Object Detection), an end-to-end architecture tailored for UAV small object detection. First, we design a lightweight hierarchical differentiation backbone that removes redundant deepest-layer features (P5) to prevent tiny object information loss, employing Multi-Domain Feature Blending (MDFB) in shallow layers for geometric detail preservation and a Hierarchical Attention-guided Feature Modulation Block (HAFMB) in deep layers for global semantic modeling. Second, we develop a full-chain high-fidelity feature transformation framework comprising Channel-Adaptive Shift Upsampling (CASU) for interpolation-free resolution recovery, Multi-scale Context Alignment Fusion (MCAF) for bridging deep–shallow semantic gaps via bidirectional gating, and Diversified Residual Frequency-aware Downsampling (DRFD) for aliasing suppression through a three-branch parallel architecture. Finally, we devise the FocusFeature module that aligns multi-scale features to a unified scale and employs parallel multi-scale large-kernel depthwise convolutions to capture cross-scale long-range dependencies, generating dual-scale (P3/P4) features balancing details and semantics. Experiments demonstrate that HMF-DEIM outperforms DEIM on VisDrone2019 test by 0.405 mAP⁵⁰ (+2.1%) and 0.235 mAP^50–95 (+1.6%), with a remarkable 21.3% relative improvement in AP_s for tiny objects, while maintaining real-time inference (465 FPS with TensorRT FP16) on an NVIDIA A100 GPU with only 11.87M parameters and 34.1 GFLOPs. Further validation on AI-TOD v2 and DOTA v1.5 datasets confirms robust generalization across diverse aerial scenarios, making it a practical solution for resource-constrained UAV applications. Full article

The current study proposes an improved DenseNet-based Sequential Multimodal Biometric Authentication System, involving face and ear modality for better human identification. The architecture is composed of three convolutional layers and two dense layers, which are optimized for obtaining the discriminative spatial representations in 200 × 200 pixel facial and ear images. Evaluation is performed based on strict 5-fold subject disjoint cross-validation data to ensure the unbiased assessment. The model proposed attained a steady classification accuracy of 97.1 ± 0.79%, and balanced values for Precision, Recall and F1-score under controlled validation conditions, while the Performance analysis including False Acceptance (FAR), False Rejection (FRR) and Equal Error Rate (EER) showed that the EER found is around 1.05% at the optimum operating value. Comparative experiments between parallel feature concatenation and sequential verification techniques show that the sequential framework yields decreased FAR, when compared to the parallel framework, without having a detrimental effect on overall accuracy, while the Statistical validation by analysis of variance shows that the incremental architectural improvements have a significant impact on performance improvements. Findings of this analysis show a “score distribution” that both “single-trait and traditional multifactor systems” exceed the presentation of a novel method for Nex-G authentication solutions. This study advances biometric security by demonstrating how multimodal fusion may address the increasing global demand for robust and privacy-aware authentication methods, thereby setting a standard for intelligent multimodal recognition systems. Full article

In disease control and precision management in aquaculture, rapid and accurate identification of common fish diseases is pivotal to mitigating economic losses and ensuring aquaculture profitability. However, fish diseases are characterized by subtle symptoms, polymorphic lesions, and high susceptibility to environmental perturbations such as water turbidity and illumination fluctuations. Existing detection models generally suffer from inadequate lightweight design, poor fine-grained lesion feature extraction, and deficient adaptability to class imbalance, failing to meet the stringent requirements of precise diagnosis in real-world aquaculture scenarios. To address these challenges, this study proposes FDR-Net: a fine-grained lesion detection model for tilapia via multi-scale feature enhancement and spatial attention fusion. Using image data of Nile tilapia (Oreochromis niloticus) covering 6 common diseases and healthy individuals (from the NTD-1 dataset), the model incorporates symmetry-aware design logic, leveraging the morphological and textural symmetry of healthy tilapia tissues to capture lesion-induced symmetry-breaking features, thereby improving fine-grained lesion detection accuracy. Through depth-width scaling coefficients, FDR-Net achieves lightweight optimization while integrating three core modules and a task-specific loss function for full-chain optimization: specifically, a Micro-lesion Feature Enhancement Module (MLFEM) is embedded in key feature layers of the backbone network to accurately extract edge and texture features of incipient fine-grained lesions via multi-scale frequency decomposition and residual fusion; subsequently, a Lightweight Multi-scale Position Attention Module (MS_PSA) and a Single-modal Intra-feature Contrastive Fusion Module (SMICFM) are collaboratively deployed—the former focusing on spatial localization of lesion features, and the latter enhancing lesion-background discriminability through channel-spatial feature recalibration and contrastive fusion; finally, a Class-Aware Weighted Hybrid Loss (CAWHL) function is combined with customized small-target anchor boxes to alleviate class imbalance and further improve localization and classification accuracy of fine-grained lesions. Empirical evaluations on the NTD-1 dataset demonstrate that compared with mainstream state-of-the-art baseline models, FDR-Net achieves a peak recognition accuracy of 90.1% with substantially enhanced mAP_50-95 performance. Retaining lightweight characteristics, it exhibits superior performance in identifying incipient fine-grained lesions and strong adaptability to simulated complex aquaculture scenarios. Collectively, this study provides an efficient technical backbone for the rapid and precise detection of tilapia fine-grained lesions, offering a potential solution for precise disease management in tilapia farming. Full article

Transformer models have achieved powerful performance in various computer vision tasks. However, their black-box nature severely limits model interpretability and the reliability of real-world applications. Most existing interpretation methods generate explanation maps by perturbing masks from the last layer of the Transformer encoder, but they often overlook uncertain information in masks and detail loss during upsampling and downsampling, resulting in coarse localization, blurred boundaries, and significant background noise in explanations. To address these issues, this paper proposes a self-distillation object segmentation method based on sequential three-way mask and attention fusion (SAF-SD), targeting salient and camouflaged binary object segmentation tasks (sub-tasks of binary pixel-level segmentation). The method consists of two core modules: the sequential three-way mask (S3WM) module and the attention fusion (AF) module. The S3WM module performs strict threshold filtering on masks generated from the final-layer feature maps of the Transformer, aiming to accurately segment foreground objects from backgrounds via binary pixel-level prediction. The AF module aggregates attention matrices across all Transformer encoder layers to construct a cross-layer relation matrix, capturing global semantic dependencies among image patches (e.g., interactions between foreground, background, and edge regions). It then computes the importance score for each patch, refining details and suppressing noise in the initial explanation results. Extensive experimental results demonstrate that SAF-SD significantly outperforms existing baseline methods across key evaluation metrics. Full article

Laser Powder Bed Fusion (LPBF) enables the fabrication of complex titanium alloy components with high geometric freedom; however, surface integrity and tribological performance remain critical limitations for sliding-contact applications in biomedical and aerospace systems. In this study, the influence of in-layer laser remelting on the microstructure, surface topography, and dry sliding tribological behavior of LPBF-fabricated Ti-6Al-4V ELI (Grade 23) is systematically investigated. Disc-shaped specimens were produced using single-scan (SS) and double-scan (DS, in-layer remelting) strategies and tested in ball-on-disc configuration against AISI 52100 steel at a constant normal load of 10 N and three sliding speeds of 0.10, 0.15, and 0.20 m·s⁻¹. Microstructural and phase-related characteristics were analyzed by X-ray diffraction combined with Rietveld refinement and Warren–Averbach analysis, revealing that the DS strategy increases retained β-phase fraction (up to 5.2%) and promotes crystallite coarsening relative to the SS condition, without significantly altering bulk hardness. Surface morphology examined by SEM/EDS and AFM revealed a more homogeneous near-surface topography in the DS condition. Tribological results indicate that sliding speed governs steady-state friction and wear, with specific wear rates increasing progressively from 5.13 to 5.44 × 10⁻⁴ mm³·N⁻¹·m⁻¹ for SS and from 6.47 to 7.52 × 10⁻⁴ mm³·N⁻¹·m⁻¹ for DS across the investigated speed range. The DS specimens exhibited higher wear rates than the SS condition across all tested speeds, while steady-state COF values remained comparable between strategies, indicating that remelting-induced microstructural modifications affect material removal mechanisms without proportionally destabilizing the frictional regime. These findings suggest that in-layer laser remelting represents a process-integrated parameter with measurable consequences for surface integrity and tribological performance, though the generalizability of these results warrants validation across broader experimental conditions. Full article