Search Results (163)

Object detection in unstructured agricultural environments remains challenging due to large scale variations, complex backgrounds, irregular obstacle shapes, and limited computational resources. To address these challenges, this paper proposes Agri-DETR, an efficient end-to-end detection framework based on the Real-Time Detection Transformer (RT-DETR), with coordinated improvements in feature perception, multi-scale representation, spatial reconstruction, and bounding box regression. Specifically, a lightweight backbone with a high-resolution feature branch is introduced to enhance the representation of small and fine-grained targets. A large selective feature fusion module is designed to strengthen multi-scale contextual modeling and improve feature discrimination under complex backgrounds. In addition, an attention-enhanced dynamic upsampling module refines high-resolution feature reconstruction, while a scale–shape–geometry-aware Intersection over Union (SSGIoU) loss improves localization stability for irregular and elongated objects. Experimental results show that Agri-DETR achieves 66.0% Average Precision (AP) on the self-constructed Agricultural Obstacle Dataset (AO-Dataset), outperforming representative detectors while reducing the parameter count by approximately 25% compared with RT-DETR-R18 baseline. In particular, small-object AP increases by 1.4%, demonstrating improved detection capability for small obstacles. Cross-dataset evaluation on COCO2017 further shows that Agri-DETR achieves 48.3% AP, demonstrating favorable generalization capability beyond the agricultural domain. These results indicate that Agri-DETR achieves an effective balance among detection accuracy, model complexity, and practical efficiency, making it a promising solution for real-world agricultural obstacle detection. Full article

To address the insufficient accuracy of short-term load forecasting caused by the strong randomness of distributed energy output, variable electricity consumption patterns, and complex meteorological factors, this study proposes a load forecasting method that integrates K-means scene clustering and a Transformer–BiGRU–Attention (CTBA) hybrid deep learning architecture. Different from conventional Transformer–BiGRU hybrid forecasters that train a single global predictor across all operating conditions, the proposed CTBA framework first partitions daily load curves into representative scenes and then routes each sample to a scene-specific Transformer–BiGRU–Attention predictor, thereby reducing distributional heterogeneity before temporal modeling. First, the K-means algorithm is used to perform scene clustering on historical daily load curves, and the optimal number of clusters is selected according to the silhouette coefficient and downstream prediction performance. Subsequently, the CTBA model is trained separately for each clustering subset. The Transformer encoder captures the long-range global dependencies of load sequences through the self-attention mechanism, the BiGRU module extracts local bidirectional temporal fluctuation features, and the Attention mechanism further focuses on key time nodes such as morning and evening peaks while fusing multi-source data including historical load, day-ahead electricity price, and multi-dimensional meteorological factors. Experimental results based on the German ENTSO-E power dataset show that the coefficient of determination R² of the proposed model reaches 0.9893, with MAE, RMSE, and MAPE as low as 0.0141, 0.0187, and 3.92%, respectively, which are significantly improved compared to benchmark models such as SVR, LSTM, CNN, and TCN-BiGRU. Ablation experiments further demonstrate that removing the clustering, Transformer, BiGRU, or attention layer will degrade performance, thus verifying the effectiveness and superiority of the method in short-term load forecasting and providing an accurate solution for the short-term load forecasting of power systems. Full article

To address missed detections, false alarms, and deployment limitations in thermal defect detection of photovoltaic modules from unmanned aerial vehicle (UAV) infrared images, this paper proposes an improved detection method based on You Only Look Once version 8 nano (YOLOv8n). The proposed method is optimized according to the characteristics of UAV infrared photovoltaic inspection, including small thermal targets, weak and diffuse thermal responses, complex backgrounds, and lightweight deployment requirements. Specifically, a P2 shallow feature layer is introduced to enhance fine-grained feature perception for small thermal defects, while Ghost Convolution (GhostConv) is incorporated into the backbone to reduce model complexity. In addition, C2f-Large Separable Kernel Attention (C2f-LSKA) is embedded in the neck to strengthen contextual and spatial feature modeling under complex infrared backgrounds, and Wise-IoU version 3 (WIoUv3) is adopted to improve bounding box regression and localization stability for boundary-ambiguous thermal anomalies. Experiments are conducted on a self-constructed UAV infrared thermal imaging dataset. From nearly 10,000 inspection images, 3000 representative images are selected and manually annotated, covering typical challenges such as small hot spots, low-contrast defects, complex background interference, and diffuse abnormal temperature-rise regions. Compared with the baseline YOLOv8n, the proposed method improves Precision, Recall, mean average precision at an IoU threshold of 0.5 (mAP@0.5), and mean average precision averaged over IoU thresholds from 0.5 to 0.95 (mAP@0.5:0.95) by 5.1, 11.4, 9.6, and 13.2 percentage points, respectively, while reducing the number of parameters and model size by 65.8% and 61.9%, respectively. These results indicate that the proposed method improves detection accuracy and localization quality under the evaluated UAV infrared inspection setting while maintaining lightweight characteristics. Full article

Glucagon-like peptide-1 (GLP-1) receptor agonists, originally developed for type 2 diabetes and obesity, have recently attracted interest as potential modulators of addictive behavior. This narrative review summarizes current knowledge on the neurobiological basis, randomized controlled trials, and psychiatric relevance of GLP-1 analogs in substance use disorders. English-language articles available at the time of the search were reviewed between February and April 2026, with emphasis on topics most relevant to psychiatric practice. The literature suggests that GLP-1 signaling influences reward processing, cue reactivity, stress responses, relapse vulnerability, and executive control through actions in the gut–brain axis and mesocorticolimbic circuitry. Early clinical findings are most encouraging in alcohol-related outcomes, including reductions in alcohol cue reactivity, craving, alcohol self-administration, and some measures of heavy drinking, whereas evidence in nicotine dependence is mixed and appears more consistent for limiting post-cessation weight gain than for improving abstinence itself. Evidence for other substance use disorders remains preliminary. Across randomized controlled trials, interpretation is limited by small sample sizes, short follow-up, heterogeneous endpoints, and selective populations. In addition, psychiatric and behavioral safety requires careful attention, particularly regarding rapid weight loss, excessive appetite suppression, restrictive eating, dehydration, and psychological destabilization in vulnerable individuals. At present, GLP-1 receptor agonists should be regarded as promising but unproven adjunctive candidates in addiction psychiatry, warranting further rigorous trials, structured monitoring, and interdisciplinary collaboration. Full article

To address the challenges of small foreign matter size, severe occlusion, and complex backgrounds in Pu-erh ripe tea processing, this study drew inspiration from primate visual mechanisms and proposed an improved YOLOv13-based network, AE-YOLOv13-S. To mitigate loss of fine details, the weakening of discriminative features, and the frequent occurrence of missed and false detections, the Adaptive Sparse Self-Attention Network was introduced to optimize the backbone of the network, inspired by the sequential cognitive pattern of primates involving target search, local verification, selective integration, and final decision making. To address insufficient long-range semantic associations and the submergence of fine-grained differences in background noise, Emulating Self-Attention with Convolution was employed to optimize part of the Conv modules of the network, drawing on the hierarchical information processing mechanisms of primates from peripheral perception to central fine analysis. In response to the limitations of bounding boxes, such as approximate target enclosure, the large amount of geometric supervision noise, the obvious localization deviation, and delayed model convergence, a Scale-based Dynamic Loss, inspired by primate visual perception mechanisms, was introduced to optimize the network’s loss function. The results showed that, during training, compared with the baseline, AE-YOLOv13-S achieved lower training loss values: Box Loss declined by 6.76%, Cls Loss by 6.52%, and DFL Loss by 8.65%. On the validation dataset, the model demonstrated reductions of 6.58%, 16.39%, and 8.33% for these respective metrics. After the overall improvements, AE-YOLOv13-S achieved increases of 1.43, 4.85, and 2.69 percentage points in precision, recall, and mAP@50, respectively, with only a 0.3 G increase in FLOPs. The improved model can classify and detect foreign matter in Pu-erh ripe tea efficiently and accurately, providing not only a new technical pathway for foreign matter detection in tea processing but also a practically meaningful technical solution for intelligent quality control and food safety assurance in the tea processing chain. Full article

To address the issues of low accuracy in transmission line anomaly detection and recognition caused by challenges such as multi-scale targets and partial occlusion, this paper proposes an optimized transmission line anomaly detection algorithm based on improved YOLOv11n. Firstly, an improved Cross Stage Partial with kernel size 2 (C3k2_DFF) module takes the place of the original C3k2 module in the backbone network. It adaptively fuses multi-scale local features and dynamically selects salient channel-wise and spatial features according to its global information during fusion to enhance the model’s feature representation. Secondly, a Separated and Enhancement Attention Module (SEAM) attention mechanism is introduced to enhance the unoccluded area feature response to compensate for the occluded area response deficit, suppressing the background features that interfere with the model and improving the model’s occluded target perception capability. Experimental results on our self-constructed dataset indicate that the proposed improved YOLOv11n model achieves precision, recall, mAP50, and mAP50-95 of 94.2%, 90.8%, 94.3%, and 68.0%, respectively. Compared with the baseline model, it represents improvements of 2.0%, 1.3%, 1.6%, and 2.9%, while the parameters and GFLOPs increase by only 6.6% and 4.8%, demonstrating superior detection performance. Full article

Adolescent self-harm, particularly non-suicidal self-injury (NSSI), is increasingly understood as a multidetermined behavior shaped by emotional, cognitive, and interpersonal processes. This focused, non-systematic narrative review examines cognitive–affective correlates of adolescent non-suicidal self-injury, while drawing on broader self-harm and suicidality-related evidence only where relevant to the cognitive–affective formulation. Particular attention is given to executive functioning, emotional processing, and social–emotional and interpersonal cognition. The evidence is strongest for emotional processing, especially difficulties in emotion regulation, rumination, cognitive reappraisal, alexithymia, and the identification and modulation of internal states. Executive functioning also appears clinically relevant, but the current findings support a selective rather than global impairment account, with the clearest evidence involving inhibitory control, impulsivity-related regulation, and decision-making under affective pressure. Social–emotional and interpersonal cognition is treated as an emerging and indirectly supported domain; much of the available evidence concerns interpersonal and relational constructs, such as interpersonal sensitivity, relational interpretation, emotional communication, and family–emotional context, rather than direct measures of theory of mind, social inference, or emotion recognition accuracy. Overall, adolescent self-harm is best understood as emerging from the interaction of emotional dysregulation, weakened behavioral control under distress, and difficulties in social–emotional meaning-making during a developmentally sensitive period. A cognitively informed developmental framework may help refine theory, improve clinical formulation, and guide future mechanism-oriented research. Full article

Fatty acids (FAs) have drawn attention in the field of oncology due to their multifaceted role, not only as structural components of lipid-based delivery systems but also as functional moieties that can enhance the pharmacokinetic and biological behavior of anticancer drugs and, subsequently, their therapeutic performance. Due to their biocompatibility, structural diversity, high affinity for biological membranes, and albumin-binding capacity, FAs can increase drug lipophilicity, membrane permeability, systemic distribution, tissue distribution, and enable controlled enzymatic release. All these properties endorse the development of nanocarriers containing FAs, such as liposomes, lipid nanoparticles (LNPs), self-nanoemulsifying drug delivery systems (SNEDDS), and self-assembling lipidic prodrugs (LAPs). In addition, several FAs, especially polyunsaturated FAs, seem to have a direct anticancer activity by modulating lipid metabolism, oxidative stress, membrane organization, and regulating cell death pathways. This review summarizes the FA conjugation chemistry, the influence of FA on the pharmacokinetics and tumor-targeting capacity of anticancer agents, and the current developments in FA-based cancer treatment strategies, while also covering the biological functions of FA in cell death pathways and cancer metabolism. By integrating medicinal chemistry, nanocarrier design, pharmacokinetic modulation, and tumor lipid biology, this review positions FA-based strategies as a relevant and evolving platform for improving anticancer drug delivery, tumor selectivity, and therapeutic performance. Full article

Colonoscopy polyp segmentation is important for colorectal cancer screening, yet it remains challenging because polyps exhibit large morphological variation, weak lesion–background contrast, blurred boundaries, and severe foreground–background imbalance. To address these issues, this paper presents MCM-UNet++, a hybrid U-Net++-based segmentation framework that combines three targeted enhancements. First, a Multi-Axis Transformer Block (MATransformerBlock) is incorporated into convolutional feature blocks to model long-range horizontal and vertical dependencies with lower complexity than dense global self-attention. Second, a Cross-Channel Mixing (CCM) module is used in nested skip fusion paths to recalibrate the channel and spatial responses and reduce redundant feature transmissions. Third, a Multi-Objective Adaptive Loss (MOALoss) combines focal, Dice, and boundary-aware terms with learnable weights to improve supervision for small regions and ambiguous boundaries. Experiments on four public polyp segmentation datasets (Kvasir-SEG, CVC-ClinicDB, CVC-ColonDB, and ETIS-Larib) show competitive performance against the selected baseline methods, with Dice/IoU scores of 0.9563/0.9278 on Kvasir-SEG and 0.8593/0.7896 on CVC-ColonDB. These results indicate that the proposed components can improve benchmark-level polyp segmentation performance, while broader validation is still required before clinical deployment. Full article

Accurate and efficient vehicle detection from unmanned aerial vehicle (UAV) imagery is essential for intelligent transportation, urban monitoring, and public safety, yet this task remains challenging due to high target density, extreme scale variation, complex backgrounds, and stringent onboard computational constraints. Existing DETR-based detectors model global context through self-attention but incur quadratic $\mathcal{O}\left(N^2\right)$ complexity that is prohibitive for high-resolution UAV images, while CNN-based methods lack the long-range contextual awareness needed for dense small-object scenarios. We propose RSMamDet, an efficient end-to-end detection framework built upon RT-DETR that replaces quadratic self-attention with linear $\mathcal{O}\left(N\right)$ State Space Model scanning. The framework integrates a MobileMamba backbone with a Selective Feature Scanning module for efficient global context modeling, a Dimension-Aware Selective Integration module for adaptive cross-scale feature fusion, a Poly Kernel Inception Network encoder for multi-receptive-field feature enrichment, and an Adaptive Multi-Level Feature Fusion module for content-aware dynamic upsampling, complemented by an Uncertainty-Minimal Composite loss for stable query selection in cluttered aerial scenes. Experiments on DroneVehicle and VisDrone2019 demonstrate that RSMamDet achieves mAP₅₀ of 72.6% and 40.2%, surpassing state-of-the-art methods by 4.1% and 2.2%, respectively, while maintaining real-time inference at 186.2 FPS with only 19.8M parameters and 42.3 GFLOPs, representing a $6.14\times$ reduction in computational cost and a $3.86\times$ reduction in model parameters compared to the strongest baseline. Full article

In recent years, channel state information (CSI)-based sensing technology has gradually attracted widespread attention as a contactless and low-cost approach for robotic arm motion understanding. Despite continuous progress in CSI-based human sensing, existing methods of robotic motion sensing still face two key challenges when directly applied to robotic motion sensing: (1) CSI perturbations induced by robotic arm motion are weak and locally distributed, making fine-grained feature extraction difficult. (2) Discriminative information in long robotic arm motion sequences is sparsely concentrated in a few key intervals, and its adaptive temporal selection and enhancement remain challenging. To address the above challenges, this paper proposes an efficient multi-stage robotic arm motion recognition method (named MSPoolNet). The proposed method consists of three key modules: an adaptive temporal downsampling module, a temporal gating module, and a Transformer-based feature encoding module. Specifically, the adaptive temporal downsampling module processes the raw CSI signal at the input stage to achieve local pattern extraction. The temporal gating module adaptively reweights temporal features, dynamically highlighting key temporal segments while suppressing irrelevant information. The proposed Transformer-based feature encoding module replaces conventional self-attention with pooling operations, enabling global information interaction and fine-grained feature representation in a computationally efficient manner. Extensive experimental results demonstrate that the proposed method achieves state-of-the-art performance on two representative public datasets, maintaining a compact model size with an accuracy exceeding 99%. Full article

Convolutional Neural Networks (CNNs) excel at extracting local features, but due to their restricted receptive fields, they often struggle to capture large-scale global context. Transformers leverage self-attention mechanisms to facilitate global interactions, yet the computational cost of standard self-attention scales quadratically with image resolution. To overcome these limitations, we propose MFDA-UNet, which adopts a hybrid architecture of convolution and linear attention for synergistic feature processing. To fully leverage their respective strengths, we design the Mamba-inspired Frequency-Decoupled Attention (MFDA) block. Through frequency decoupling, this block utilizes convolutions to process high-frequency local information, while employing linear attention to model the long-range dependencies of low-frequency global information. To enhance the feature representation capability of linear attention, we construct the Mamba-Enhanced Linear Attention (MELA) block. Inspired by MILA, this block injects Positional Encoding to substitute the forget gate functionality of Mamba and integrates the Mamba block structure into the linear attention mechanism. This design effectively strengthens representational power, accomplishing long-range dependency modeling with highly efficient linear complexity. Furthermore, we introduce the Gated Cross-Scale Attention (GCSA) module to optimize traditional skip connections. It aggregates features via cross-scale linear attention and incorporates Mamba’s high-performance gating mechanism for adaptive feature filtering, achieving precise feature fusion and selection. We conducted extensive experiments on four multi-modal benchmarks: ISIC 2017, ISIC 2018, Synapse, and ACDC. MFDA-UNet achieved improvements in the DSC by 0.44%, 0.15%, 0.53%, and 0.84% across the respective datasets compared to the second-best models. By capturing local and global multi-scale semantics with relatively low computational overhead, MFDA-UNet provides an efficient and robust solution for medical image segmentation. Full article

With the rapid intensification of industrial and agricultural activities, water contamination by heavy metal ions has emerged as a critical global challenge, gravely imperiling ecosystem stability and public health. Among the various remediation technologies, adsorption has been widely adopted due to its high efficiency, low-cost water treatment, and simplicity of operation. However, conventional inorganic or synthetic adsorbents often exhibit poor degradability and pose a risk of secondary contamination, substantially limiting their sustainable application. Consequently, the development of environmentally benign and renewable adsorbent materials has become a central research focus in this field. Recently, cellulose-based composite hydrogels, derived from renewable resources and characterized by excellent eco-friendliness and highly tunable three-dimensional porous structures, have attracted considerable attention as promising green adsorption materials. These hydrogels demonstrate outstanding performance in the efficient sequestration of heavy metal contaminants from aqueous environments. This review systematically summarizes recent advances in cellulose-based composite hydrogels for heavy metal removal, to elucidate the structure–performance relationships linking material fabrication strategies, structural modulation, and adsorption efficiency. First, we outline the principal construction approaches, including physical crosslinking, chemical modification, and supramolecular self-assembly, and comprehensively analyze how different synthesis routes regulate pore architecture, mechanical properties, and the distribution of surface functional groups. Second, the underlying adsorption mechanisms, primarily coordination complexation, electrostatic interactions, and ion exchange, are discussed in detail. Finally, recent studies on the adsorption of cationic heavy metals (e.g., Pb(II), Cu(II), and Cd(II)) and anionic oxyanions (e.g., As(III) and Cr(VI)) are critically reviewed, with particular emphasis on the relationships between selective adsorption performance, material design principles, and specific recognition mechanisms. Overall, this review provides a theoretical foundation and practical guidance for the design and development of next-generation water treatment materials with high adsorption capacity, excellent selectivity, non-toxicity, and strong environmental compatibility, followed by future research recommendations. Full article

Significant Wave Height (SWH) is a critical parameter for ocean observation. SWH retrieval using GNSS-R data faces challenges including difficult feature selection, insufficient temporal dependency modeling, and limitations due to single-modality data. This paper proposes a novel Multimodal Transformer Network (MultTransNet) to enhance the accuracy of GNSS-R SWH retrieval. To optimize the feature set, we designed an XGBoost-based iterative feature selection module that effectively eliminates redundant features. To capture complex temporal dependencies and global context, the model employs a Transformer encoder utilizing its self-attention mechanism. Furthermore, to overcome the constraints of single-modality data, we innovatively fused 2D DDM image data with 1D auxiliary parameters, enabling multi-source information integration. Simulation results show that the Transformer architecture reduces Root Mean Square Error (RMSE) by 8.91% and increases Correlation Coefficient (CC) by 4.05% compared to a conventional Deep Neural Network (DNN) model. More significantly, the proposed multimodal algorithm further improves retrieval accuracy by 27.05% (RMSE reduction) and 7.21% (CC increase) compared to its single-modality Transformer counterpart, demonstrating superior performance, especially in complex sea-state conditions. Full article

To improve the feature representation and cross-condition generalization of bearing fault diagnosis, this paper proposes an adaptive multi-sensor fusion network with a skip fusion module and a parameter-efficient dual-convolution diagnosis block. The vibration and current signals are first augmented by overlapping segmentation and transformed into the frequency domain using FFT. Multi-scale depthwise convolutions are then employed in parallel branches to capture fault patterns at different receptive fields, and an attention-based skip fusion mechanism selectively aggregates cross-sensor features for complementary enhancement. After fusion, self-calibrated convolution and dilated convolution are alternately applied to strengthen discriminative representation without increasing model complexity. Experiments on multiple bearing datasets under both constant and variable operating conditions demonstrate that the proposed method achieves consistently higher accuracy and robustness than representative CNN-based baselines, verifying its effectiveness for practical bearing fault diagnosis. Full article