Search Results (794)

Reliable perception of small floating objects is critical for the management of aquatic environments and supports key applications, including the autonomous navigation of Unmanned Surface Vehicles (USVs), waterborne debris monitoring, and Search and Rescue (SAR) operations. However, accurate detection in dynamic water-surface environments remains a significant challenge, as targets are frequently obscured by high-frequency wave clutter, and feature distributions are destabilized by covariate shifts caused by illumination. To address these limitations, this study proposes YOLO11-MCN, a real-time detection framework that integrates two architectural components specifically designed for water-surface monitoring. The Multi-Scale Contextual Attention (MSCA) module distinguishes target signatures from background noise by aggregating contextual information across heterogeneous receptive fields, thereby suppressing false positives generated by waves. The Channel Normalization Attention Mechanism (CNAM) addresses illumination instability through feature statistic calibration based on Group Normalization, effectively mitigating covariate shifts induced by extreme lighting variations. Furthermore, these components are complemented by a high-resolution P2 detection head, which recovers the geometric details of small-scale targets typically lost during downsampling. Extensive experiments conducted on a dataset of 5812 images demonstrate that YOLO11-MCN achieves an mAP@0.5 of 92.7%, outperforming the YOLO11n baseline by 5.9 percentage points. Robustness evaluations confirm that MSCA and CNAM significantly reduce missed detections under severe wave clutter and backlighting conditions. With a recall of 90.5%, an inference speed of 94 FPS on desktop hardware, and a compact footprint of 3.89M parameters and 14.8 GFLOPs, the proposed framework offers a robust and efficient solution for intelligent water-surface surveillance systems within the single-class detection paradigm evaluated in this study, with strong potential for edge-device deployment following platform-specific optimization. Full article

Depression is a critical global public health challenge, and the demand for accurate automated detection methods has generated considerable research interest in Transformer-based models. Despite their substantial promise, a comprehensive investigation into their architectural efficacy, intrinsic mechanisms, and barriers to practical implementation remains lacking. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, this systematic review was conducted across six databases (IEEE Xplore, Elsevier, Springer, MDPI, PubMed, and arXiv). The final search was performed in October 2025, covering English-language empirical studies published between 2020 and 2025 that employed Transformer-based architectures for depression detection. Risk of bias and methodological quality were independently appraised by two authors using a six-dimension structured rubric, with disagreements resolved by a third author. Findings were narratively synthesized given substantial cross-study heterogeneity. This systematic review analyzed 46 studies and provided the first comprehensive, mechanism-level, architecturally stratified comparison of encoder-only, decoder-only, hybrid, and multimodal fusion paradigms, examining self-attention dynamics and transfer learning strategies. Since 2019, these frameworks have evolved from text-centric approaches to advanced multimodal systems. Encoder-only models show consistently strong results in high-throughput text-based screening, decoder-only models demonstrate stronger few-shot learning capabilities, hybrid architectures show the highest observed median performance in clinical interview settings across the reviewed studies, and multimodal fusion systems offer complementary advantages when heterogeneous signal integration is critical. These trends are task-contextualized and should not be interpreted as unconditional rankings, given heterogeneity in evaluation metrics and tasks across studies. Nonetheless, four principal challenges hinder clinical translation: overreliance on self-reported data, cross-linguistic bias, absence of uncertainty quantification, and substantial computational overhead. Future efforts should shift from incremental benchmark improvements toward clinical utility through standardized psychiatric validation, uncertainty-aware architectures, fairness-enforced training across diverse populations, and the integration of Transformer-based models with wearable and mobile health data to improve detection stability and reduce translational risk. This systematic review was registered on the Open Science Framework (OSF; DOI: 10.17605/OSF.IO/SYF9N). This research was funded by the Faculty of Information Science and Technology and by Universiti Kebangsaan Malaysia under Grant TAP-K014364. Full article

Social media sentiment analysis demands systems that are simultaneously accurate, scalable, and interpretable. Lexicon-based methods offer transparency but ignore context, while pre-trained language models (PLMs) capture contextual semantics yet encode sentiment only implicitly. Existing integration strategies inject lexicon signals at the input, attention, or feature layer—all outside the recurrent gating mechanism that controls how affective evidence accumulates over a sequence. We propose the SAGU-Net, a framework built around the Sentiment-Aware Gated Unit (SAGU), a gated recurrent unit (GRU) variant with a dedicated sentiment gate conditioned on external lexicon signals. A complementary Context-Adaptive Sentiment Scoring (CASS) module transforms static polarity scalars into context-dependent vectors via learned projections over PLM representations, bridging the gap between discrete lexicon scores and continuous embeddings. The sentiment gate activations provide token-level explainability without post hoc attribution. On a 12,700-sample Chinese social media corpus of intellectual property co-branding reviews (Fleiss’ $\kappa =0.82$) and two public benchmarks, the SAGU-Net achieves 93.62% accuracy and 93.21% Macro-F1, outperforming nine baselines and matching or exceeding LoRA-fine-tuned large language models (GPT-5, Claude Sonnet 4.6, DeepSeek V3.2, Qwen3.5) while requiring three to four orders of magnitude fewer parameters. Ablation confirms the sentiment gate as the single most impactful component. Full article

Accurate crop row detection is identified as a critical prerequisite for autonomous agricultural navigation, yet it remains challenging in complex field environments. To achieve a balance between segmentation accuracy, robustness, and real-time performance, an improved crop row segmentation and navigation method based on the DeepLabV3+ framework was developed. MobileNetV2 was adopted as the backbone to minimize computational costs, while feature representation was enhanced through integrated attention mechanisms and multi-scale fusion. Specifically, split-attention convolution was integrated into the backbone, a DenseASPP + SP module was employed for multi-scale contextual capture, and a Convolutional Block Attention Module (CBAM) was added to refine feature responses. Experimental results demonstrated that the proposed method outperformed mainstream models, achieving a mean Intersection over Union (mIoU) of 93.42% and an f1-score of 96.8%. The model maintained a lightweight architecture with 8.35 M parameters and a real-time speed of 32 FPS. Furthermore, crop row anchor points were extracted and processed via DBSCAN clustering and RANSAC fitting to generate high-precision navigation lines. Validation showed that the middle crop row yielded the highest fitting accuracy with minimal angular and lateral errors. This study provides an efficient visual perception solution for intelligent field operations. Full article

Hyperspectral image classification (HSIC) is a crucial task for remote sensing applications, requiring accurate pixel-level labeling while effectively capturing both spectral and spatial information. Traditional convolutional neural network architectures often struggle to balance local texture detail and global contextual consistency, and existing neural architecture search (NAS) methods rarely incorporate attention mechanisms, limiting their performance. To address these challenges, this study proposes a multi-scale Transformer-based NAS framework (TR-NAS) for fine-grained hyperspectral image classification. The framework combines local cube sampling, shallow and deep multi-scale convolutions, and a searchable Transformer module that adaptively selects global, local window, and multi-scale attention operators. Lightweight enhanced convolution operators, including dual-gated (DG-Conv) and mixed depthwise (MixConv) convolutions, are incorporated to improve spectral discrimination and scale robustness. Extensive experiments on the PU and Hanchuan datasets demonstrate that TR-NAS achieves superior classification accuracy, stability, and boundary consistency compared to traditional methods and existing NAS architectures, showing improved robustness to spectral similarity and spatial heterogeneity in complex remote sensing scenes. Full article

The grading of green jujube is a key factor in improving production efficiency and market competitiveness. However, traditional grading methods are inefficient, imprecise, and struggle to detect minor damages. This study proposes an improved BCW-YOLO deep learning model specifically designed for automated grading of green jujube. The model integrates a Bidirectional Feature Pyramid Network (BiFPN) and a Contextual Transformer Attention (COT) mechanism to enhance feature fusion accuracy and capture fine-grained details. In addition, the WIoU v3 loss function is introduced to optimize object localization performance. By constructing a multi-angle green jujube dataset and applying data augmentation techniques, the model’s generalization capability was significantly improved. The results of the experiement indicate that the improved BCW-YOLO achieves precision, recall, mAP, and F1 score of 90.87%, 92.12%, 95.66%, and 91.49%, respectively, representing increases of 1.93%, 2.77%, 1.58%, and 2.34% compared to the original YOLO model. Through comprehensive validation using confusion matrices, PR curves, heatmap analyses, and ablation studies, the model’s performance was thoroughly verified. Compared with other YOLO series models, BCW-YOLO performs exceptionally well in detecting minor damages, demonstrating its potential in practical agricultural grading. The findings provide a new technical approach for precise grading and automated sorting of green jujube, showing promising application prospects. Full article

The way robots represent the environment, make decisions, and express themselves can positively influence human–robot interaction if they clearly communicate their intentions and needs. To improve human–robot communication, biologically inspired models that mimic human communication skills, including task and scenario-specific contextual information, can facilitate mutual understanding and successful task execution. This paper presents a Context-Awareness and Biologically Inspired Behaviour system to generate a more natural human–robot interaction. The architecture combines sensory information processed by a Joint Attention System that prioritises stimuli based on internal processes with task-related motivations to generate context- and goal-adapted verbal and non-verbal interaction. We evaluate the system through a video-based user study that compares two robots with similar appearances but different behaviours, one using the proposed approach and the other not using the internal state and joint attention mechanisms, to make verbal and non-verbal responses. The results show that participants rated the robot endowed with the proposed system as significantly more sociable, agentic, and animated than the robot without it. Additionally, the robot not showing the responses developed in this work was perceived as more disturbing than the robot integrating the proposed system. Full article

Accurate individual tree crown (ITC) segmentation from unmanned aerial vehicle (UAV) imagery is important for fine-scale forest inventory, plantation management, and ecological monitoring. However, delineating ITCs in dense plantation environments remains difficult because crowns are strongly adjacent, canopy structures are highly homogeneous, and crown boundaries are often blurred, making it hard for existing methods to preserve both regional integrity and boundary continuity. This study proposes the Perceptual Segment-Anything Model with Multi-head Cross-Parallel Attention (Per-SAM-MCPA), a lightweight and effective framework for fine-grained ITC segmentation in dense plantation scenes. Based on a compact ResNet-50 backbone, the framework integrates perceptual target-aware representation, multi-scale detail enhancement, global contextual modeling, and semantic-boundary collaborative refinement to improve crown discrimination and structural consistency. A perceptual relation module is used to strengthen pixel-level semantic dependency modeling, and a Multi-head Cross-Parallel Attention (MCPA) mechanism is designed to capture long-range contextual interactions through orthogonally decomposed spatial attention, improving global geometric consistency with limited computational overhead. A Composite Constraint Loss (CCL) that combines a weighted cross-entropy loss, a structural similarity loss, and a boundary term based on Hausdorff distance is introduced to jointly optimize region-level segmentation quality and boundary fidelity. Experiments on the Catalpa bungei UAV dataset show that the proposed method achieves an intersection over union (IoU) of 87.3% and an F1-score of 91.0%, outperforming representative baseline methods such as SAM and Mask R-CNN while maintaining an inference speed of 35.7 FPS on a single GPU. These results indicate that Per-SAM-MCPA offers an accurate, efficient, and practical solution for ITC segmentation in dense plantation environments. Full article

In vision-based low-altitude unmanned aerial vehicle (UAV) remote sensing, detecting small targets accurately and maintaining stable tracking under fast-motion conditions remain significant challenges. Specifically, small-object detection suffers from low feature representation, while camera motion often induces tracking drift and identity switches. To address these issues, this paper proposes a novel small target detection and tracking algorithm named TCYOLO-SofByteTrack, which integrates an improved YOLOv11 with ByteTrack. The algorithm comprises two core innovative modules: First, the TCYOLO detector is designed by integrating the C3k2-TA feature enhancement module with triplet attention mechanism to achieve cross-dimensional interaction modeling, significantly improving small target feature representation capability and network contextual awareness. A Cross-Scale Feature Fusion Module for UAVs (CCFM-UAV) is constructed to provide precise detection support for small targets at different scales. Second, building upon the ByteTrack framework, the SofByteTrack tracker is designed, which introduces a sparse optical flow-based motion compensation strategy. This strategy estimates and compensates for image displacement caused by UAV motion in real time, ensuring the stability of target bounding boxes under fast-motion conditions, thereby effectively mitigating tracking drift and identity switches. Experimental results demonstrate that the TCYOLO detector achieves a 7.4% improvement in mAP for small target detection compared to the baseline YOLOv11 model. The complete TCYOLO-SofByteTrack tracking algorithm achieves a HOTA score of 45.3%, MOTA of 42.7%, and IDF1 of 57.8%, representing improvements of 4.5%, 5.9%, and 8.0%, respectively, over the baseline methods. Furthermore, the number of successfully tracked targets increased by 37.3%, while identity switches decreased by 23.4%. These results demonstrate the notable advantages of the proposed method in small target detection accuracy, tracking precision, and identity consistency. Its generalization capability is further validated on a custom highway inspection dataset. Moreover, deployment tests on an NVIDIA Jetson Orin NX platform show that, compared to YOLOv11n, the proposed algorithm achieves higher detection accuracy while still meeting real-time processing requirements, highlighting its practical applicability in resource-constrained scenarios. Full article

Yak (Bos grunniens) is a vital livestock resource on the Qinghai–Tibet Plateau, and its body measurement parameters play a crucial role in growth and development assessment, health monitoring, and breeding improvement. To overcome the limitations of traditional manual measurements—such as low efficiency, unstable accuracy, and the tendency to induce animal stress—this study proposes an intelligent yak body measurement prediction method that integrates keypoint detection with regression modeling, termed UST-YOLO11Pose-TRM. Within the YOLO11-Pose framework, three attention mechanisms—UIB, SENetV2, and TripleAttention—are incorporated to construct a lightweight yet high-precision keypoint detection model, UST-YOLO11Pose, thereby enhancing channel feature representation, global contextual modeling, and spatial dependency perception. Meanwhile, a Transformer-based regression model is designed, leveraging multi-head self-attention to characterize global geometric relationships among keypoints and to achieve accurate prediction of key body measurement parameters, including body length, body height, oblique body length, chest girth, and cannon circumference. Experimental results demonstrate that UST-YOLO11Pose achieves an mAP of 0.958, a Precision of 0.967, and a Recall of 0.955 in keypoint detection tasks, significantly outperforming both same-series and cross-series comparative models with a parameter size of only 10.06 MB. In the body measurement regression task, the Transformer-based regression model attains an RMSE of 0.185, an MAE of 0.122, an MAPE of 2.3%, and a coefficient of determination (R²) of 0.962 on the test set, indicating excellent predictive accuracy and robust fitting stability. In summary, UST-YOLO11Pose-TRM enables accurate, efficient, non-contact yak body measurement, showing strong potential for smart pasture development and precision livestock management. Full article

Ethno Sense is defined as a culturally mediated cognitive–perceptual capacity through which individuals discern, select, and interpret mathematically salient structures in socially situated practices. The increasing recognition of mathematics as a culturally situated practice has prompted growing interest in integrating cultural contexts into mathematics education. Approaches such as ethnomathematics and Realistic Mathematics Education emphasize the importance of culture and meaningful contexts; however, a critical gap remains in explaining how individuals perceive and recognize mathematical structures within culturally embedded experiences. This entry addresses this gap by introducing Ethno Sense as a novel conceptual construct. Conceptualized as a pre-formal layer of mathematical cognition, it explains how culturally conditioned perception, interpretive schemas, and value systems shape the recognition of mathematical meaning prior to formalization. It proposes a mechanism comprising contextual indexing, schema activation and selection, and value-informed interpretation. These processes operate dynamically to guide engagement with culturally meaningful phenomena and the identification of mathematical relevance. The entry further positions Ethno Sense as an epistemological foundation for Ethno-Realistic Mathematics Education, supporting authentic context selection and progressive mathematization. By foregrounding culturally mediated perception, it shifts attention from problem solving to recognizing situations as mathematically meaningful. This study contributes a unifying theoretical construct linking cultural experience and mathematical cognition, and outlines implications for practice and future research on culturally situated learning. Ultimately it offers a lens for understanding reciprocal relationships between culture and mathematics across educational contexts. Full article

To address the challenges of insufficient small target recognition, difficulty in edge information extraction, and high computational overhead in insulator defect detection, this paper proposes a lightweight detection method based on the YOLO-MLSL model for transmission line insulator defect detection. First, a C2f-LRFCA module is introduced, effectively enhancing feature interaction through a long-range convolutional attention mechanism, thereby improving the perception of fine-grained defects. Second, an MEUM multi-scale feature enhancement module is designed to achieve more efficient contextual information fusion during upsampling, improving the detection performance for multi-scale targets. Third, the ShapeIoU loss function is employed to improve the bounding box regression accuracy in complex backgrounds, and LAMP pruning technology significantly reduces the model’s computational and storage overhead. Experimental results show that the improved algorithm achieves an mAP@0.5 of 85.4%, a 4.1% improvement compared to the original YOLOv8n, while maintaining a low parameter count and computational complexity, demonstrating both high accuracy and efficiency. This research provides a valuable reference for the design and application of lightweight target detection models in the intelligent inspection of power equipment. Full article

To address the limitations of YOLOv8n in multi-scale feature representation and high false negative rates for small traffic signs under edge-computing constraints, this paper proposes an improved lightweight detection algorithm integrating the VoVGSCSP module and a Multi-scale Contextual Attention (MCA) mechanism. Specifically, the original C2f module is replaced with VoVGSCSP to enhance gradient flow and aggregate multi-scale receptive fields, while MCA captures discriminative shape, boundary, and color features via multi-branch pooling with dynamic weight fusion. The PAN-FPN is further optimized using Learnable Weight Concatenation (LWConcat) for adaptive multi-level feature fusion. On the CTSDB dataset, the proposed model reduces parameter count to 2.90 M (4.0% reduction) and FLOPs to 7.4 G (8.6% reduction), while improving mAP0.5 from 96.2% to 99.4% and mAP0.5:0.95 from 94.8% to 98.6%. On the TT100K dataset, mAP0.5 increases from 60.2% to 61.9% and mAP0.5:0.95 from 44.9% to 46.5%. The smaller improvement on TT100K suggests greater dataset diversity and annotation complexity, indicating a direction for future work. Overall, the proposed algorithm achieves a favorable trade-off among accuracy, model size, and computational cost, validating its practicality for resource-constrained edge deployment. Full article

Spatial transcriptomics (ST) has emerged as an essential technology for interpreting the molecular profiles underlying pathological tissue morphology. Most existing ST analyses are limited to 2D sections, which ignore the complex structural and molecular heterogeneity of biological tissues in 3D space and may cause diagnostic oversights. Since acquiring complete 3D ST volumes is resource-intensive, recent 3D imputation paradigms provide a cost-effective alternative by integrating 3D whole-slide images (WSIs) with sparse 2D ST references (e.g., a single slide). Despite this methodological advancement, effectively modeling complex cross-layer spatial dependencies remains challenging. Current mainstream solutions predominantly adopt standard Transformers for cross-scale feature aggregation, which may bring computational overhead and higher overfitting risk while having limited explicit mechanisms for hierarchical anatomical guidance. To address these limitations, we propose a Hierarchical MambaOut-based Spatial Imputation Graph Network (HM-ASIGN) for anatomy-aware 3D spatial transcriptomics imputation. Our architecture leverages MambaOut’s dynamic gated 1D convolutions as a parameter-efficient alternative to dense global self-attention. This design captures the depth-wise evolution of pathological features while reducing over-parameterization. Inspired by the macro-to-micro diagnostic reasoning of clinical pathologists, HM-ASIGN introduces a multi-scale recursive guidance mechanism. It constructs a top-down information flow by extracting global anatomical priors at macroscopic scales and injecting them as contextual anchors into regional and spot-level features in a cascaded manner. This helps ensure that fine-grained molecular predictions are properly constrained by global morphological structures. Evaluation experiments on multiple public breast cancer datasets demonstrate that HM-ASIGN achieves competitive reference-level performance against existing baselines, reaching a Pearson Correlation Coefficient (PCC) of 0.772. Specifically, when evaluated against the foundational ASIGN framework, it improves predictive accuracy while reducing the total parameter count by approximately 33.3% and improving inference throughput. Our results suggest that HM-ASIGN provides a computationally efficient approach for 3D spatial molecular mapping. Full article

Nutritional supplement use has emerged as an important health-related consumption behavior in digitalized environments, with implications for both public health and individual well-being. While prior research has largely focused on general populations, limited attention has been paid to how occupational pressures and digital information contexts jointly shape supplement-related decision-making among highly educated professionals. Addressing this gap, this study examines the behavioral determinants of nutritional supplement use among academics within an intention–behavior framework. Using survey data collected from academic professionals, the proposed model was tested through confirmatory factor analysis and structural equation modeling. The findings reveal that health motivation and academic work stress significantly predict supplement use intention, which, in turn, strongly influences actual consumption behavior. In contrast, digital health literacy and digital marketing exposure do not exert significant direct effects on usage intention. These results provide theoretical insight into the boundary conditions of informational determinants in consumer behavior models, suggesting that intrinsic motivation and contextual stressors may play a more dominant role than digital influences among highly educated consumers. From a practical perspective, the findings highlight the importance of addressing stress-related health coping mechanisms and motivation-driven behaviors in promoting informed supplement use. Full article