Search Results (1,881)

Current state-of-the-art (SoTA) instance segmentation models often struggle to accurately segment small and densely distributed vessels. In this study, we introduce MAKSEA, a new satellite imagery dataset collected from the Makkoran Coast that contains small and overlapping vessels. We also propose an efficient and robust segmentation architecture, namely MVSegNet, to segment small and overlapping ships. MVSegNet leverages three modules on the baseline UNet++ architecture: a Multi-Scale Context Aggregation block based on Atrous Spatial Pyramid Pooling (ASPP) to detect vessels with different scales, Attention-Guided Skip Connections to focus more on ship relevant features, and a Multi-Head Self-Attention Block before the final prediction layer to model long-range spatial dependencies and refine densely packed regions. We evaluated our final model with SoTA instance segmentation architectures on two benchmark datasets including LEVIR_SHIP and DIOR_SHIP as well as our challenging MAKSEA datasets using several evaluation metrics. MVSegNet achieves the best performance in terms of F1-Score on LEVIR_SHIP (0.9028) and DIOR_SHIP (0.9607) datasets. On MAKSEA, it achieves an IoU of 0.826, improving the baseline by about 7.0%. The extensive quantitative and qualitative ablation experiments confirm that the proposed approach is effective for real-world maritime traffic monitoring applications, particularly in scenarios with dense vessel distributions. Full article

Anti-UAV detection is paramount for safeguarding airspace security. However, existing methodologies often exhibit low detection accuracy due to their inability to adaptively address target scale variations and complex backgrounds. To enhance detection precision, this paper introduces a UAV detection method founded on non-local feature learning. Initially, we design a Cross-scale Non-local Feature Interaction (CNFI) module. This module explicitly models long-range dependencies between features at disparate scales, thereby effectively integrating multi-scale information and adapting to target scale variations. Subsequently, a Non-local Feature Enhancement (NFE) module is proposed, which fuses global contextual information, acquired via non-local attention, with low-level structural cues such as gradients, to bolster the boundary and detail features of UAV targets amidst complex backgrounds. The proposed method was experimentally validated on the DUT-Anti-UAV and Det-Fly dataset. In comparison with the state-of-the-art model, our approach demonstrates improvements of 0.93%, 1.09%, and 2.12% in Precision (P), Recall (R), and mAP50 on DUT-Anti-UAV dataset, respectively. Experimental results affirm that our proposed enhancements yield superior performance in the anti-UAV detection task. Full article

Lane detection, as one of the key real-time tasks in vehicle tracking, often faces numerous challenges due to the complex shapes and inherent symmetry of lane lines. Aiming at the requirements of high accuracy and real-time performance of the lane detection, this paper proposes an adaptive structural optimization and enhanced receptive field network for lane detection (ASO-ERFNet). Specifically, we propose a Multi-receptive Field Fusion Layer (MFFL) that optimizes the structure of the pooling operation to fully utilize its hierarchical characteristics, leverage the symmetry of lane layouts, and precisely preserve the spatial geometric properties of lane lines. Then, we design a Dynamic Cross Attention Mechanism (DCAM) that can adaptively adjust convolutional kernel weights, thereby further enhancing detection precision. In addition, compared with the existing single-feature extraction networks, we propose a Dual-Perception Network (DPNet) that fuses features from different scale levels through a U-shaped structure. The experimental findings show that compared with state-of-the-art methods, our model obtains superior performance, achieving the best results in six scenes, such as normal and crowded scenes. Specifically, our method achieved 76.61% and 79.90% performance in crowded and shadow scenes, respectively, while reducing the false positive rate by 22.90% in cross scenes. Moreover, with an average processing time of only 5.5 ms per frame, our method achieves an F1 score of 96.65% on the TuSimple dataset and 76.23% on the CULane dataset. These results indicate that our model effectively balances detection accuracy and speed by leveraging lane symmetry, providing an efficient and reliable solution for lane detection in vehicle tracking. Full article

Deep learning-based respiratory sound classification (RSC) has emerged as a promising non-invasive approach to assist clinical diagnosis. However, existing methods often face challenges, such as sub-optimal feature representation and limited model expressiveness. To address these issues, we propose an Attention-based Dual-stream Feature Fusion Network (ADFF-Net). Built upon the pre-trained Audio Spectrogram Transformer, ADFF-Net takes Mel-filter bank and Mel-spectrogram features as dual-stream inputs, while an attention-based fusion module with a skip connection is introduced to preserve both the raw energy and the relevant tonal variations within the multi-scale time–frequency representation. Extensive experiments on the ICBHI2017 database with the official train–test split show that, despite critical failure in sensitivity of 42.91%, ADFF-Net achieves state-of-the-art performance in terms of aggregated metrics in the four-class RSC task, with an overall accuracy of 64.95%, specificity of 81.39%, and harmonic score of 62.14%. The results confirm the effectiveness of the proposed attention-based dual-stream acoustic feature fusion module for the RSC task, while also highlighting substantial room for improving the detection of abnormal respiratory events. Furthermore, we outline several promising research directions, including addressing class imbalance, enriching signal diversity, advancing network design, and enhancing model interpretability. Full article

Diabetic macular edema (DME) is a leading cause of vision loss, and predicting patients’ response to anti-vascular endothelial growth factor (anti-VEGF) therapy remains a clinical challenge. In this study, we developed an interpretable deep learning model for treatment prediction and biomarker analysis. We retrospectively analyzed 402 eyes from 371 patients with DME. The proposed DME-Receptance Weighted Key Value (RWKV) integrates optical coherence tomography (OCT) and ultra-widefield (UWF) imaging using Causal Attention Learning (CAL), curriculum learning, and global completion (GC) loss to enhance microlesion detection and structural consistency. The model achieved a Dice coefficient of 71.91 ± 8.50% for OCT biomarker segmentation and an AUC of 84.36% for predicting anti-VEGF response, outperforming state-of-the-art methods. By mimicking clinical reasoning with multimodal integration, DME-RWKV demonstrated strong interpretability and robustness, providing a promising AI framework for precise and explainable prediction of anti-VEGF treatment outcomes in DME. Full article

Foggy weather critically undermines the autonomous perception capabilities of unmanned aerial vehicles (UAVs) by degrading image contrast, obscuring object structures, and impairing small target recognition, which often leads to significant performance deterioration in conventional detection models. To address these challenges in automated UAV operations, this study introduces Hazy Aware-YOLO (HA-YOLO), an enhanced detection framework based on YOLO11, specifically engineered for reliable object detection under low-visibility conditions. The proposed model incorporates wavelet convolution to suppress haze-induced noise and enhance multi-scale feature fusion. Furthermore, a novel Context-Enhanced Hybrid Self-Attention (CEHSA) module is developed, which sequentially combines channel attention aggregation (CAA) with multi-head self-attention (MHSA) to capture local contextual cues while mitigating global noise interference. Extensive evaluations demonstrate that HA-YOLO and its variants achieve superior detection precision and robustness compared to the baseline YOLO11, while maintaining model efficacy. In particular, when benchmarked against state-of-the-art detectors, HA-YOLO exhibits a better balance between detection accuracy and complexity, offering a practical and efficient solution for real-world autonomous UAV perception tasks in adverse weather. Full article

Prognostics and Health Management (PHM) is a vital approach which aims to predict the failure of engineering systems at an early stage and optimize maintenance strategies. It operates through continuous system monitoring, anomaly detection, fault detection, and Remaining Useful Life (RUL) estimation. Accurate RUL prediction for aircraft engines is critical for enhancing operational safety and minimizing maintenance costs. Traditional methods are largely dependent on handcrafted features and domain-specific knowledge. They often fail to capture the nonlinear and high-dimensional degradation dynamics of real-world systems. In this study, we propose an enhanced deep learning architecture combining Long Short-Term Memory (LSTM) and Bidirectional LSTM networks with a new Matrix-Statistics-Aware Attention (LSTM-MSAA) method. Unlike conventional attention methods, our proposed method incorporates auxiliary scalar features, such as the Frobenius norm, spectral norm, and soft rank, into the attention score computation. This hybrid model provides a more informative representation of engine state transitions. The model is evaluated on both legacy and newly released C-MAPSS datasets from NASA’s Prognostics Data Repository. Experimental results reveal a reduction in RMSE compared to baseline models, validating the effectiveness of our attention fusion strategy in capturing intricate degradation behaviors and improving predictive performance. Full article

This paper discusses the evolution of convolutional (CNN) and recurrent (RNN) artificial neural networks in applications for Building Information Modeling (BIM). The paper outlines the milestones reached in the last two decades. The article organizes the current state of knowledge and technology in terms of three aspects: (1) computer visualization coupled with BIM models (detection, segmentation, and quality verification in images, videos, and point clouds), (2) sequence and time series modeling (prediction of costs, energy, work progress, risk), and (3) integration of deep learning results with the semantics and topology of Industry Foundation Class (IFC) models. The paper identifies the most used architectures, typical data pipelines (synthetic data from BIM models, transfer learning, mapping results to IFC elements) and practical limitations: lack of standardized benchmarks, high annotation costs, a domain gap between synthetic and real data, and discontinuous interoperability. We indicate directions for development: combining CNN/RNN with graph models and transformers for wider use of synthetic data and semi-/supervised learning, as well as explainability methods that increase trust in AECOO (Architecture, Engineering, Construction, Owners & Operators) processes. A practical case study presents a new application, Bimetria, which uses a hybrid CNN/OCR (Optical Character Recognition) solution to generate 3D models with estimates based on two-dimensional drawings. A deep review shows that although the importance of attention-based and graph-based architectures is growing, CNNs and RNNs remain an important part of the BIM process, especially in engineering tasks, where, in our experience and in the Bimetria case study, mature convolutional architectures offer a good balance between accuracy, stability and low latency. The paper also raises some fundamental questions to which we are still seeking answers. Thus, the article not only presents the innovative new Bimetria tool but also aims to stimulate discussion about the dynamic development of AI (Artificial Intelligence) in BIM. Full article

Despite the growing interest in physiological stress monitoring, an objective measure of stress is currently lacking, especially in clinical and rehabilitation contexts. With the emerging integration of artificial intelligence (AI) in data analytics, heart rate variability (HRV) has gained attention as an effective biomarker; however, the literature remains fragmented across disciplines, stress types, and methodological approaches. This scoping review aims to investigate how AI techniques are applied to HRV analysis for stress detection and prediction in adult populations. Although this review does not focus on a specific subtype of stress, its primary objective is to explore the current methodological state of the art as reported in the literature, without restrictions on stress typology. Following PRISMA-ScR guidelines, a systematic search was conducted across PubMed, Scopus, and Google Scholar for studies published between 2005 and 2025, using MeSH terms including “HRV”, “Rehabilitation”, “SCI” (for Spinal Cord Injury), “Stress”, “Sympathetic”, “Parasympathetic”, “Non-linear”, “Gamification”, “AI” and “Machine Learning”. Inclusion criteria targeted adult human populations and studies employing HRV features as input for AI and machine learning techniques for psychophysical stress assessment. Of the 566 records identified, 15 studies met the eligibility criteria. The reviewed studies exhibit substantial heterogeneity in terms of settings, populations, sensors, and algorithms with most employing supervised methods (e.g., random forest, support vector machine), alongside several applications of deep learning and explainable AI. Only one study focused specifically on physiological stress, none focused on SCI populations, and rehabilitation-related research was scarce, thereby underscoring important gaps in the current literature. Overall, HR variability analysis, especially when combined with artificial intelligence techniques, represents a promising approach for stress assessment; however, the field is methodologically fragmented and clinically underdeveloped in critical areas, underscoring the need for a multidisciplinary methodological framework. Full article

Gastrointestinal (GI) cancers represent a heterogeneous group of malignant neoplasms arising from the digestive tract, including gastric, colorectal, hepatic, pancreatic, and biliary cancers. These tumors represent a major public health challenge due to their aggressive nature and poor prognosis. Although significant progress has been made in diagnostic imaging, endoscopy, and multimodal therapies, early detection remains difficult. Conventional serum biomarkers often lack sufficient sensitivity and specificity for reliable diagnosis, prompting a growing interest in identifying novel, minimally invasive biomarkers. In this context, liquid biopsy is emerging as a revolutionary tool in oncology. Among its components, extracellular vesicles (EVs) have gained increasing attention because they carry a wide range of molecular cargoes that reflect the biological state of their tumor of origin. In particular, EV-associated microRNAs (miRNAs) hold great promise as biomarkers for early cancer detection, real-time monitoring of disease progression, and assessment of therapeutic response. This review discusses the diagnostic and prognostic potential of EVs as novel biomarkers in GI cancers, emphasizing EV-contained miRNAs as a key resource for the development of personalized and precision medicine strategies. Full article

Detecting small objects in unmanned aerial vehicle (UAV) imagery remains a challenging task due to the limited target scale, cluttered backgrounds, severe occlusion, and motion blur commonly observed in dynamic aerial environments. This study presents STAIR-DETR, a real-time synergistic detection framework derived from RT-DETR, featuring comprehensive enhancements in feature extraction, resolution transformation, and detection head design. A Statistical Feature Attention (SFA) module is incorporated into the neck to replace the original AIFI, enabling token-level statistical modeling that strengthens fine-grained feature representation while effectively suppressing background interference. The backbone is reinforced with a Diverse Semantic Enhancement Block (DSEB), which employs multi-branch pathways and dynamic convolution to enrich semantic expressiveness without sacrificing spatial precision. To mitigate information loss during scale transformation, an Adaptive Scale Transformation Operator (ASTO) is proposed by integrating Context-Guided Downsampling (CGD) and Dynamic Sampling (DySample), achieving context-aware compression and content-adaptive reconstruction across resolutions. In addition, a high-resolution P2 detection head is introduced to leverage shallow-layer features for accurate classification and localization of extremely small targets. Extensive experiments conducted on the VisDrone2019 dataset demonstrate that STAIR-DETR attains 41.7% mAP@50 and 23.4% mAP@50:95, outperforming contemporary state-of-the-art (SOTA) detectors while maintaining real-time inference efficiency. These results confirm the effectiveness and robustness of STAIR-DETR for precise small object detection in complex UAV-based imaging scenarios. Full article

Detecting low-altitude, slow-speed, small (LSS) UAVs is especially challenging in low-visibility scenes (low light, haze, motion blur), where inherent uncertainties in sensor data and object appearance dominate. We propose GAME-YOLO, a novel detector that integrates a Bayesian-inspired probabilistic reasoning framework with Global Attention and Multi-Scale Enhancement to improve small-object perception and sub-pixel-level localization. Built on YOLOv11, our framework comprises: (i) a visibility restoration front-end that probabilistically infers and enhances latent image clarity; (ii) a global-attention-augmented backbone that performs context-aware feature selection; (iii) an adaptive multi-scale fusion neck that dynamically weights feature contributions; (iv) a sub-pixel-aware small-object detection head (SOH) that leverages high-resolution feature grids to model sub-pixel offsets; and (v) a novel Shape-Aware IoU loss combined with focal loss. Extensive experiments on the LSS2025-DET dataset demonstrate that GAME-YOLO achieves state-of-the-art performance, with an AP@50 of 52.0% and AP@[0.50:0.95] of 32.0%, significantly outperforming strong baselines such as LEAF-YOLO (48.3% AP@50) and YOLOv11 (36.2% AP@50). The model maintains high efficiency, operating at 48 FPS with only 7.6 M parameters and 19.6 GFLOPs. Ablation studies confirm the complementary gains from our probabilistic design choices, including a +10.5 pp improvement in AP@50 over the baseline. Cross-dataset evaluation on VisDrone-DET2021 further validates its generalization capability, achieving 39.2% AP@50. These results indicate that GAME-YOLO offers a practical and reliable solution for vision-based UAV surveillance by effectively marrying the efficiency of deterministic detectors with the robustness principles of Bayesian inference. Full article

Attention-Deficit/Hyperactivity Disorder (ADHD) is a highly prevalent neurodevelopmental condition that is typically identified through behavioral assessments and subjective clinical reports. However, electroencephalography (EEG) offers a cost-effective and non-invasive alternative for capturing neural activity patterns closely associated with this disorder. Despite this potential, EEG-based ADHD classification remains challenged by overfitting, dependence on extensive preprocessing, and limited interpretability. Here, we propose a novel neural architecture that integrates transformer-based temporal attention with Gaussian mixture functional connectivity modeling and a cross-entropy loss regularized through $\alpha$-Rényi mutual information, termed T-GARNet. The multi-scale Gaussian kernel functional connectivity leverages parallel Gaussian kernels to identify complex spatial dependencies, which are further stabilized and regularized by the $\alpha$-Rényi term. This design enables direct modeling of long-range temporal dependencies from raw EEG while enhancing spatial interpretability and reducing feature redundancy. We evaluate T-GARNet on a publicly available ADHD EEG dataset using both leave-one-subject-out (LOSO) and stratified group k-fold cross-validation (SGKF-CV), where groups correspond to control and ADHD, and compare its performance against classical and modern state-of-the-art methods. Results show that T-GARNet achieves competitive or superior performance (82.10% accuracy), particularly under the more challenging SGKF-CV setting, while producing interpretable spatial attention patterns consistent with ADHD-related neurophysiological findings. These results underscore T-GARNet’s potential as a robust and explainable framework for objective EEG-based ADHD detection. Full article

Anomaly detection is a critical task in video surveillance, with significant applications in the management and prevention of criminal activities. Traditional convolutional neural networks often struggle with motion modeling and multi-scale feature fusion due to their localized field of view. To address these limitations, this work proposes a Dual-Branch Interactive Feature Fusion Network (DBIFF-Net). DBIFF-Net integrates a CNN branch and a swin transformer branch to extract multi-scale features. To optimize these features for efficient fusion, an interactive fusion module is introduced to efficiently fuse these multi-scale features through skip connections. Then, the temporal shift module is employed to exploit dependencies between video frames, thereby improving the identification of anomalous events. Finally, the channel attention is utilized for decoder to better assist in restoring complex object features in the video. System performance is evaluated on three standard benchmark datasets. DBIFF-Net achieves the area under the receiver operating characteristic (AUC) of 97.7%, 84.5%, and 73.8% on the UCSD ped2, CUHK Avenue, and ShanghaiTech Campus dataset, respectively. Extensive experiments demonstrate that DBIFF-Net outperforms most state-of-the-art methods, validating the effectiveness of our method. Full article

Photovoltaic systems (PV) are increasingly recognized as fundamental to the worldwide adoption of renewable energy technologies. Nonetheless, the efficiency and longevity of solar panels can be compromised by various anomalies, ranging from physical defects to environmental impacts. Early and accurate detection of these anomalies is crucial for maintaining optimal performance and preventing significant energy losses. This study presents SolarAttnNet, a novel convolutional neural network (CNN) architecture with integrated channel and spatial attention mechanisms for solar panel anomaly detection. The proposed model addresses the critical need for automated detection systems, which are crucial for maintaining energy production efficiency and optimizing maintenance. This approach leverages attention mechanisms that emphasize the most relevant features within thermal and visual imagery, improving detection accuracy across multiple anomaly types. SolarAttnNet is evaluated on three distinct solar panel datasets, demonstrating its effectiveness through comprehensive ablation studies that isolate the contribution of each architectural component. Experimental results show that SolarAttnNet achieves superior performance compared to state-of-the-art methods, with accuracy improvements of 3.9% on the PV Systems-AD dataset (94.2% vs. 90.3%), 3.6% on the InfraredSolarModules dataset (92.1% vs. 88.5%), and 3.5% on the RoboflowAnomalies dataset (89.7% vs. 86.2%) compared to baseline ResNet-50. For challenging subtle anomalies like cell cracks and PID, the proposed model demonstrates even more significant improvements with F1-score gains of 4.8% and 5.4%, respectively. Ablation studies reveal that the channel attention mechanism contributes a 2.6% accuracy improvement while spatial attention adds 2.3% across datasets. This work contributes to advancing automated inspection technologies for renewable energy infrastructure, supporting more efficient maintenance protocols and ultimately enhancing solar energy production. Full article