Search Results (638)

The accurate segmentation of gastric cancer cells is important in pathology for diagnosing and detecting diseases early. However, current approaches still suffer from limitations such as expensive annotation, fuzzy lesion boundaries, and weak feature expression. In order to solve these problems, we present MSAF-Net, a novel U-Net framework optimized both architecturally and in terms of the loss function. In particular, we incorporate a Multi-scale Dilated Pooling Fusion Block into the encoder stage to achieve enhanced interaction of multi-paths and thus improve features’ diversity and boundary sensitivity. We also introduce a Dual-Channel Attention Block in place of traditional convolution block in the decoder stage to restore better details and reconstruct the fuzzy boundaries. Meanwhile, a Diagonal Mahalanobis Consistency Loss is incorporated into our framework to facilitate class compactness. Experiments performed on the SEED-Gastric Carcinoma Stage 1 dataset show that the designed algorithm can reach 0.776 in Dice score and 0.821 in Accuracy, which outperforms the baseline method U-Net. It is clear that these results have shown the effectiveness and robustness of our proposed approach. The introduced algorithm allows for more precise quantification of gastric cancer cell morphology. Full article

Pine wilt disease (PWD) can spread rapidly after the disease occurs and often causes large-scale death of the pine. Therefore, the timely identification of infected trees is critical for forest conservation and effective disease management. However, early infected trees are difficult to distinguish in satellite remote sensing images. Their visual differences from healthy trees and complex background features are often subtle, and existing image-processing methods do not fully exploit heterogeneous information. To address this problem, we constructed the Naro dataset for satellite-based PWD detection and proposed SGM-RTDETR based on Real-Time Detection Transformer (RT-DETR). The proposed model consists of a Semantic–Visual Fusion Module (SVFM) and a Disease Feature Refinement Module (DFRM). In SVFM, ExG, VARI, and GLI are concatenated with RGB imagery to form a six-channel visual input, which enhances the spectral differences between diseased and non-diseased targets. In addition, textual prior knowledge is introduced into the decoder input through a Stackelberg game-based visual–text fusion strategy. This strategy helps the encoded memory features maintain clearer disease-related semantics in complex backgrounds. DFRM then performs channel recalibration, feature refinement, and residual enhancement on the fused memory features to better extract fine-grained disease cues in remote sensing scenes. Experiments on the Naro dataset show that SGM-RTDETR achieves 80.75% mAP@0.5 and 35.43% mAP@0.5:0.95, which is 2.74 percentage points higher than RT-DETR-L on mAP@0.5:0.95. Overall, the results indicate that the dual-module structure improves the precision and robustness of PWD detection in satellite remote sensing images. Full article

In response to the challenges in UAV-oriented ground small-object localization and detection, including the easy loss of tiny target features, insufficient scale adaptability, severe interference from complex backgrounds, as well as high missed and false detection rates and the inadequate localization accuracy of the conventional YOLOv11n model in such scenarios, this paper takes YOLOv11n as the basic framework and performs systematic optimization from three aspects, network structure, core modules, and feature enhancement, proposing a lightweight small-object-enhanced detection algorithm named YOLOSO for UAV applications. By introducing a P2 high-resolution feature branch with a stride of 4, a four-scale detection structure consisting of P2-P3-P4-P5 is constructed, which reduces the minimum detection stride from 8 to 4 and alleviates the loss of detailed feature information for ultra-tiny targets. A bidirectional “top-down + bottom-up” multi-scale feature fusion strategy is utilized to improve the complementation between deep semantic information and shallow detailed features, while the core modules C3k2SO and C2PSASO are optimized and redesigned, respectively; by adjusting the channel compression ratio (0.25 for shallow modules and 0.75 for deep modules in C3k2SO; 0.25 in C2PSASO), optimizing the convolution kernel configuration (combining 1 × 3 and 3 × 1 convolutions), increasing the number of attention heads (from 4 to 8), and introducing residual connections with a 1 × 1 convolutional branch, the refinement and focusing ability of small-object feature extraction are improved. Additionally, an Enhanced Dual-branch Convolutional Block Attention Module (ED-CBAM) is proposed to further suppress background interference. Experimental results on the VisDrone2019-DET dataset demonstrate that the proposed YOLOSO contains 3.56M parameters and maintains a lightweight structure, attaining P, R, and mAP50 values of 47.2%, 36.8%, and 37.3% in the test set, which are 4.5 percentage points, 4.8 percentage points, and 3.7 percentage points higher than those of the baseline YOLOv11n (42.7%, 32.0% and 33.6%), respectively. Meanwhile, the medium-to-large version YOLOSO-S (14.85M parameters, 45.3% mAP50) reduces the number of parameters by 53.6% compared with the same-scale Rtdetr-L (32.0M) while achieving significantly better performance (37.8% mAP50). Experiments on the DOTAv1 dataset further confirm the generalization of YOLOSO, achieving 62.2% precision and 27.3% mAP50, outperforming all compared YOLO models. Evaluated on the DOTA-v1 dataset, YOLOSO achieves a feasible FPS of 20.53. Although slightly slower than mainstream lightweight YOLO models, the substantial accuracy gains fully offset the minor inference speed loss, and such performance trade-off is acceptable for practical UAV deployment. Ablation experiments verify that structural optimization (2.8 percentage points mAP50 improvement, from 33.6% to 36.4%) and the proposed C2PSASO (0.7 percentage points mAP50 improvement to 34.3%) and C3k2SO (1.4 percentage points mAP50 improvement to 35.0%) modules all contribute positive performance gains with favorable complementarity. While retaining lightweight characteristics, the model effectively enhances the detection accuracy of small objects in unmanned aerial vehicle scenarios and can provide technical references for practical applications such as remote sensing monitoring and security patrolling. Full article

Early fault detection in microsatellite thermal control systems (TCS) faces fundamental challenges: high-dimensional redundant telemetry channels, overlapping multi-scale periodicities that obscure anomaly signatures, and severely limited daily data downlink (1–2 passes per day) that restricts the temporal window for diagnosis. Existing data-driven approaches either rely on supervised learning, requiring labeled fault data that are scarce in practice, or employ univariate analysis that fails to capture inter-sensor spatial correlations. To address these limitations, this paper introduces a hybrid framework integrating information-theoretic feature selection and spatiotemporal deep learning. The Generalized Maximum Information Coefficient (GMIC) quantifies nonlinear dependencies between temperature channels for key channel selection, reducing dimensionality by 82% while preserving diagnostic information. A dual-level Seasonal Trend Decomposition (STL) method disentangles orbital-periodic dynamics from diurnal cycles, effectively isolating distinct thermal characteristics at multiple timescales. Each decomposed component is modeled using Convolutional Neural Network–Long Short-Term Memory (CNN-LSTM) networks to capture spatiotemporal dependencies for accurate temperature prediction. An adaptive threshold-based weighted error fusion mechanism enables early fault detection within a single day of telemetry data. Experimental validation on real satellite telemetry data demonstrates that the proposed framework achieves high-precision fault detection across multiple fault types using a minimal set of temperature channels, significantly outperforming existing benchmarks in both prediction accuracy and detection reliability. Full article

Background: Accurate assessment of neonatal sleep is critical for monitoring brain development and identifying potential neurological disorders, yet manual scoring of multi-channel EEG recordings is labor-intensive and prone to variability. Methods: To address this, we propose a lightweight temporal–spatial feature fusion network for automatic neonatal sleep staging. The model employs a dual-branch architecture to separately capture temporal dependencies and spatial correlations in EEG signals, which are then integrated through feature concatenation and a compact classifier to obtain comprehensive feature representations while maintaining low computational complexity. Results: The framework was evaluated on a clinical neonatal dataset (CHFD) for tasks including sleep–wake classification, quiet sleep detection, and three-stage sleep staging, achieving superior performance compared with several state-of-the-art methods. Additional evaluation on the MASS-S3 adult dataset demonstrate that the model retains competitive accuracy and F1-score, indicating strong generalization across populations. Conclusions: These results suggest that jointly modeling temporal and spatial features enables robust and efficient automatic sleep staging. The proposed approach offers a practical solution for clinical applications and edge deployment, providing reliable, multi-dimensional assessment of neonatal brain activity and laying the groundwork for future studies integrating larger datasets or multimodal physiological signals. Full article

Object detection in complex industrial environments is prone to being affected by insufficient dynamic weighting of local and global features, as well as illumination variations and impurities. Moreover, existing models suffer from excessive model complexity, which directly impairs computational efficiency. To more accurately distinguish Chinese herbal materials with diverse morphologies, this paper proposes the MobileAttn module. Drawing on the idea of token representation in the Transformer architecture, this module extracts contextual information through global feature compression, fuses it with tokens to generate a spatial attention map, and realizes dynamic recalibration of convolutional features. This process enhances the feature weights of key semantic regions, suppresses redundant background information, and improves feature discriminability. To address illumination interference, brightness-aware weights are combined with dual-path (channel and spatial) attention for global control, dynamically reducing the impact of illumination; this component is named LightAttn. When Chinese herbal materials contain common industrial unknown impurities (e.g., small stones and weeds), an impurity detection auxiliary module, a post-processing step independent of the main detection network, is proposed. This module refines Non-Maximum Suppression (NMS) logic to distinguish target Chinese herbal materials from interfering impurities. Subsequently, it accurately locates and marks impurities on the conveyor belt, thereby achieving effective unknown impurity detection. Experimental results demonstrate that, compared with the original YOLOv11 on the Chinese herbal materials detection task, the optimized model achieves a 1.7% improvement in the overall mean Average Precision (mAP@0.5:0.95). On a per-class basis, gains are particularly pronounced for certain challenging high-aspect-ratio Chinese herbal materials. Prunella vulgaris and orange peel achieve respective AP improvements of 5.8% and 4.1%. Meanwhile, the model parameter count is reduced by 23.1% and the computational complexity by 20.3%. The F1-Score of the impurity detection results is 86.38%, verifying the effectiveness of the impurity detection auxiliary module. Full article

Magnetic flux leakage (MFL) testing is a vital non-destructive testing method used to identify defects in oil and gas pipelines and critical components. However, variations in defect geometry and testing conditions can lead to inaccurate data and imbalanced feature distributions, which compromise detection outcomes. To address these challenges, this paper presents a defect classification approach for MFL testing based on generating expansion and the Dual-Channel Vision Transformer (DC-ViT). First, COMSOL finite element software (version 6.1) was used to simulate magnetic flux leakage for different types of pipeline defects. Axial and radial dual-channel signals were extracted to create the initial dataset. Next, a Conditional Variational Autoencoder (CVAE) was used for Generate Expansion to effectively mitigate sample scarcity and defect category imbalance. Finally, the DC-ViT model was constructed and trained using the Generate Expansion dataset as input to achieve multidimensional feature fusion and classification prediction for defects. Experimental results demonstrate 97.97% detection accuracy. The DC-ViT model outperforms traditional convolutional neural networks and single-channel models in terms of accuracy, precision, recall, and F1-score. These results validate the method’s effectiveness and robustness in complex defect scenarios and offer a novel approach to magnetic leakage signal detection. Full article

With the occurrence of global climate change and the depletion of agricultural water resources, there is a growing need to develop rapid, non-destructive, and autonomous plant health monitoring systems. As an economically valuable crop, Ocimum basilicum L. (basil) is sensitive to changes in water availability and may exhibit stress-related morphological variations under drought and over-irrigation conditions. However, due to the visual similarity of leaf symptoms under drought stress, waterlogging stress, and optimal irrigation conditions, accurately distinguishing these conditions remains challenging in practical applications. To address this challenge, this paper presents an attention-based dual-branch deep learning framework designed to extract both subtle leaf details and channel-related features from high-resolution plant images. By combining the Convolutional Block Attention Module (CBAM) and Squeeze-and-Excitation (SE) mechanism in a parallel structure, the proposed network improves the analysis of high-resolution images with an input size of 720 × 720 pixels. Under controlled environmental conditions, with ground-truth labels obtained using soil moisture sensor measurements, the proposed model was compared with eight deep learning architectures, including DenseNet121, InceptionV3, and VGG16. The proposed model achieved a hold-out evaluation accuracy of 99.54%, outperforming the second-best model, DenseNet121, which achieved 96.43%. In addition, the proposed model reached a class-specific precision value of 100% for the Drought Stress category and achieved an area under the receiver operating characteristic curve of 1.00 under the controlled experimental setting. Taylor Diagram analysis also indicated that the model closely preserved the variability pattern of the reference data. These results suggest that the proposed application-specific framework may support non-destructive basil water-stress detection under controlled conditions. After further validation with larger datasets, different cultivars, variable environmental conditions, and real-world agricultural scenarios, the proposed approach may contribute to precision irrigation management and sustainable agricultural production. The contribution of this study should be interpreted as an application-specific implementation and evaluation of complementary attention mechanisms for controlled-environment basil water-stress classification, rather than as the introduction of a fundamentally new deep learning methodology. Full article

The Vortex Ring State (VRS) poses a catastrophic aerodynamic threat to coaxial dual-rotor unmanned aerial vehicles (UAVs). Traditional reactive detection mechanisms provide insufficient altitude for recovery, while existing data-driven diagnostics are severely bottlenecked by data leakage, extreme class imbalance, and a lack of physical interpretability. To bridge these gaps, this paper proposes a physics-informed multimodal deep learning framework that transitions from post-occurrence detection to proactive early warning. We establish a 1.5 s precursor window—creating a three-class ordinal state space—to provide the flight control system with critical intervention time for differential rotor recovery. We developed a novel ViT-LSTM architecture (MTSF-Net) to fuse continuous seven-channel onboard-recorded data (comprising three-axis acceleration, three-axis angular velocity, and barometric vertical velocity), which are subsequently transformed into Continuous Wavelet Transform (CWT) spectrograms. To ensure real-time unidirectional inference while preserving absolute physical vibration scales across heterogeneous sensors, a Calibrated Benchmark Normalization (CBN) strategy is introduced. Furthermore, a Hybrid Ordinal Loss is proposed to mitigate the extreme sample imbalance (<0.5%) of the precursor state by penalizing asymmetric aerodynamic degradation. Evaluated under a strict sortie-based isolation protocol, the proposed system achieves an exceptional test accuracy of 98.26% and an unprecedented precursor recall of 100%. Notably, it completely eliminates fatal missed detections (VRS predicted as Normal) and false-positive VRS predictions triggered by precursor states. Finally, Gradient-weighted Class Activation Mapping (Grad-CAM) is utilized to verify that the multimodal sensor processing pipeline successfully anchors onto authentic physical vibration frequencies rather than artifactual noise, laying a rigorous, interpretable foundation for intelligent aviation safety systems. Full article

Antigen detection provides rapid and convenient diagnosis of respiratory infections. This study develops an innovative dual-fluorescence aptasensing method based on polydopamine-functionalized MXene (PDA-MXene) for the simultaneous detection of spike protein and hemagglutinin protein. The method employs green- and red-emitting quantum dot (QD) probes as fluorescence reporters, and the PDA-MXene as an effective adsorption and separation substrate. Coupled with a centrifugation-assisted separation strategy, this design method reduces background interference and enhances detection reliability. The method demonstrates good analytical performance, with detection limits of 0.82 ng/mL for spike protein and 2.11 ng/mL for hemagglutinin protein in single-channel mode. The dual-channel mode enables reliable and simultaneous quantification of both target proteins with minimal spectral cross-talk. Furthermore, this method exhibits high specificity against interferents including ions, proteins, and toxins. Artificial saliva, chosen as real sample, is spiked with target proteins to investigate the practical applicability of the method, showing recovery rates for both target proteins between 100 and 114 sensing strategy is simple to operate and allows the detection of new targets by simply replacing the azide-modified aptamer lyophilized powder. It therefore holds promising application for the simultaneous detection of multiple proteins in point-of-care testing and health monitoring fields. Full article

Laser remote sensing based on wavefront sensors shows great potential for detecting minute vibrations. However, due to their high detection sensitivity, wavefront sensors are highly susceptible to interference from environmental noise and instrument-induced noise, which significantly compromises the quality of the acquired vibration signals and the accuracy of the detection. In this study, over 60,000 vibration signal data samples were collected under various amplitude and frequency conditions using a laser remote sensing seismic wave detection system. By applying a physics-aware dual-channel decoupled network (PRISM) to perform noise reduction on the vibration signals, we achieved improvements in signal quality under multiple real-world noise environments. The average signal-to-noise ratio improved by 12.16 dB, and the signal distortion ratio improved by 6.35 dB, successfully preserving faint vibration signals within the noise. Full article

To address electric bicycle detection in confined indoor environments affected by occlusion and image degradation, this study proposes DCM-YOLO, a robustness-oriented detection framework designed to improve detection accuracy under complex indoor visual conditions. First, the Dual-branch Adaptive Fusion (DAF) module combines lightweight feature generation with adaptive modulation to preserve local structures and channel diversity when target appearances are incomplete. Second, the Spatial–Channel Synergistic Attention (SCSA) mechanism sequentially refines informative regions and semantic channels, allowing the detector to suppress background interference more effectively. Third, the Multi-Scale Group-Aware Head (MSGA-Head) introduces multi-branch receptive-field modeling and grouped refinement to improve scale-sensitive classification and localization. These components form a coordinated backbone–attention–head design, reducing detection ambiguity caused by partial visibility and degraded image quality, including underexposure, overexposure, low contrast, and blur. Experimental results on a public dataset collected from representative indoor environments indicate that DCM-YOLO achieves 87.6% Precision, 83.7% Recall, 86.2% mAP50, and 65.1% mAP50-95, exceeding the baseline model by 2.5, 2.9, 2.8, and 1.7 percentage points, respectively. Additional evaluations on public benchmark datasets further verify the effectiveness and robustness of DCM-YOLO. Full article

Background/Objectives: Early and accurate discrimination of neurological conditions, dementia, stroke and healthy aging, remains a critical clinical challenge. Electroencephalography (EEG) is a non-invasive measure of brain dynamics and entropy-based features obtained from multichannel EEG have shown strong discriminative ability. However, existing deep learning approaches do not sufficiently address the combined challenges of small clinical cohorts and high-dimensional entropy feature spaces. In this study, a novel architecture is proposed for multi-class neurological EEG classification under extreme small-sample conditions. Methods: A novel dual-branch Channel-wise Transformer and Attention-Branch Network (EEG-ChTABNet) are pr to classify 19-channel EEG entropy features into three classes (dementia, stroke, healthy control; N = 45; 15 per class). The architecture suggests four new designs. First, the Channel Importance Attention (CIA) block, which adaptively learns to re-weight the importance of electrodes via squeeze-excitation. Second, the dual-branch encoder, which combines the global multi-head self-attention with the local depthwise-separable convolution. Third, the gated sigmoid fusion mechanism. Fourth, the bottleneck residual classification head, to solve overfitting. Eight entropy feature sets: Amplitude-Aware Permutation Entropy (AAPE), Attention Entropy (AttEn), Dispersion Entropy (DisEn), Distribution Entropy (DistrEn), Fluctuation-based Dispersion Entropy (FDispEn), Fuzzy Entropy (FuzEn), Linear Gaussian Estimation of the Conditional Entropy (LinEn), and Symbolic Dynamics (SyDy) were evaluated individually with stratified 5-fold cross-validation on within-fold SMOTE augmentation. Results: EEG-ChTABNet consistently outperformed the baseline Transformer on all 8 feature sets. DisEn and SyDy features yielded peak classification accuracy of 73.3% (AUC: 0.823 and 0.857, respectively) compared to the corresponding baseline of 57.8% and 55.6%. SyDy achieved the best overall AUC of 0.857 and the dementia detection sensitivity was up to 86.7% over multiple feature sets. Conclusions: EEG-ChTABNet shows the effectiveness of channel-adaptive, dual-branch Transformer Designs for EEG-based neurological classification from Small-Sample Entropy Feature Data, and Identifying SyDy and DisEn as the Most Discriminative Feature Representations for Three-Class Neurological EEG Classification. Full article

To address the joint requirements of illegal parking detection and license plate recognition under complex traffic scenarios and limited edge-device resources, this study proposes RKF-YOLO, a lightweight dual-task model based on improved YOLOv11n that integrates Rep-CSP structural optimization, knowledge-transfer-enhanced training (KTET), and Focal-CIoU loss. Compared with YOLOv11n, RKF-YOLO reduces parameters and FLOPs by 38.2% and 38.1%, respectively, while improving $\mathrm{mAP}@0.5$ and $\mathrm{mAP}@0.5:0.95$ by 0.6 and 1.1 percentage points for parking detection; for plate detection, Focal-CIoU improves $\mathrm{mAP}@0.5:0.95$ by 1.3 percentage points and contributes to a recognition accuracy of 95.7%. The unified framework uses a shared backbone and task-oriented detection heads to support vehicle-level illegal parking detection and license-plate-oriented localization. Rep-CSP enhances multi-scale feature representation, asymmetric channel reduction with feature compensation reduces redundant computation, and KTET improves convergence through optimizer and learning-rate migration. Deployment on RK3588 achieves 59.5 FPS for parking detection and 95.1% recognition accuracy, demonstrating real-time performance and practical applicability on resource-constrained edge devices. Full article

Accurate fault detection is essential for the safe and reliable operation of grid-connected photovoltaic (PV) systems under complex and dynamically varying conditions. However, existing data-driven approaches are often hindered by the scarcity of labeled fault data and by their limited ability to model complex multivariate temporal dependencies. To address these challenges, this paper first develops a realistic simulation of a grid-connected PV system to generate a large volume of labeled multivariate time-series fault data spanning diverse fault scenarios under varying operating conditions. The simulated data augment the limited real-world measurements, improving fault coverage and model generalization. On this basis, a dual-channel enhanced Mamba model is proposed for PV fault detection. The model decouples temporal modeling and variable-wise modeling into two dedicated channels, enabling complementary extraction of global temporal dependencies and intra-variable dynamics. Extensive experiments show that the proposed approach consistently outperforms several mainstream time-series classification methods in accuracy, precision, recall, and F1-score, demonstrating that it provides an effective and scalable solution for data-driven fault detection in grid-connected PV systems. Full article