Search Results (146)

Tunnel construction poses significant safety challenges due to confined spaces, limited visibility, and the dynamic movement of labourers and machinery. This study addresses a critical gap in real-time, bidirectional proximity monitoring by developing and validating a prototype early-warning system that integrates real-time location systems (RTLS) with long-range (LoRa) wireless communication and ultra-wideband (UWB) positioning. The system comprises Arduino nano microcontrollers, organic light-emitting diode (OLED) displays, and piezo buzzers to detect and signal proximity breaches between workers and equipment. Using an action research approach, three pilot case studies were conducted in a simulated tunnel environment to test the system’s effectiveness in both static and dynamic risk scenarios. The results showed that the system accurately tracked proximity and generated timely alerts when safety thresholds were crossed, although minor delays of 5–8 s and slight positional inaccuracies were noted. These findings confirm the system’s capacity to enhance situational awareness and reduce reliance on manual safety protocols. The study contributes to the tunnel safety literature by demonstrating the feasibility of low-cost, real-time monitoring solutions that simultaneously track labour and machinery. The proposed RTLS framework offers practical value for safety managers and informs future research into automated safety systems in complex construction environments. Full article

Accurate pig counting is crucial for precision livestock farming, enabling optimized feeding management and health monitoring. Detection-based counting methods face significant challenges due to mutual occlusion, varying illumination conditions, diverse pen configurations, and substantial variations in pig densities. Previous approaches often struggle with complex agricultural environments where lighting conditions, pig postures, and crowding levels create challenging detection scenarios. To address these limitations, we propose EAPC-YOLO (enhanced adaptive pig counting YOLO), a robust architecture integrating density-aware processing with advanced detection optimizations. The method consists of (1) an enhanced YOLOv8 network incorporating multiple architectural improvements for better feature extraction and object localization. These improvements include DCNv4 deformable convolutions for irregular pig postures, BiFPN bidirectional feature fusion for multi-scale information integration, EfficientViT linear attention for computational efficiency, and PIoU v2 loss for improved overlap handling. (2) A density-aware post-processing module with intelligent NMS strategies that adapt to different crowding scenarios. Experimental results on a comprehensive dataset spanning diverse agricultural scenarios (nighttime, controlled indoor, and natural daylight environments with density variations from 4 to 30 pigs) demonstrate our method achieves 94.2% mAP@0.5 for detection performance and 96.8% counting accuracy, representing 12.3% and 15.7% improvements compared to the strongest baseline, YOLOv11n. This work enables robust, accurate pig counting across challenging agricultural environments, supporting precision livestock management. Full article

Graph theory models relationships by representing entities as vertices and their interactionsas edges. To handle directionality and multiple head–tail assignments, various extensions—directed, bidirected, and multidirected graphs—have been introduced, with the multidirected graph unifying the first two. In this work, we further enrich this landscape by proposing the Multidirected hypergraph, which merges the flexibility of hypergraphs and superhypergraphs to describe higher-order and hierarchical connections. Building on this, we introduce five uncertainty-aware Multidirected frameworks—fuzzy, neutrosophic, plithogenic, rough, and soft multidirected graphs—by embedding classical uncertainty models into the Multidirected setting. We outline their formal definitions, examine key structural properties, and illustrate each with examples, thereby laying groundwork for future advances in uncertain graph analysis and decision-making. Full article

Camouflaged Object Detection (COD) aims to segment objects that are highly integrated with their background, presenting significant challenges such as low contrast, complex textures, and blurred boundaries. Existing deep learning methods often struggle to achieve robust segmentation under these conditions. To address these limitations, this paper proposes a novel COD network, SAM2-DFBCNet, built upon the SAM2 Hiera architecture. Our network incorporates three key modules: (1) the Camouflage-Aware Context Enhancement Module (CACEM), which fuses local and global features through an attention mechanism to enhance contextual awareness in low-contrast scenes; (2) the Cross-Scale Feature Interaction Bridge (CSFIB), which employs a bidirectional convolutional GRU for the dynamic fusion of multi-scale features, effectively mitigating representation inconsistencies caused by complex textures and deformations; and (3) the Dynamic Boundary Refinement Module (DBRM), which combines channel and spatial attention mechanisms to optimize boundary localization accuracy and enhance segmentation details. Extensive experiments on three public datasets—CAMO, COD10K, and NC4K—demonstrate that SAM2-DFBCNet outperforms twenty state-of-the-art methods, achieving maximum improvements of 7.4%, 5.78%, and 4.78% in key metrics such as S-measure ($S_{\alpha }$), F-measure ($F_{\beta }$), and mean E-measure ($E_{\varphi }$), respectively, while reducing the Mean Absolute Error (M) by 37.8%. These results validate the superior performance and robustness of our approach in complex camouflage scenarios. Full article

This study addresses the long-standing difficulty of predicting the remaining useful life (RUL) of rolling bearings from highly non-stationary vibration signals by proposing WaveAtten, a symmetry-aware deep learning framework. First, mirror-symmetric and bi-orthogonal Daubechies wavelet filters are applied to decompose each raw signal into multi-scale approximation/detail pairs, explicitly preserving the left–right symmetry that characterizes periodic mechanical responses while isolating asymmetric transient faults. Next, a bidirectional sparse-attention module reinforces this structural symmetry by selecting query–key pairs in a forward/backward balanced fashion, allowing the network to weight homologous spectral patterns and suppress non-symmetric noise. Finally, the symmetry-enhanced features—augmented with temperature and other auxiliary sensor data—are fed into a long short-term memory (LSTM) network that models the symmetric progression of degradation over time. Experiments on the IEEE PHM2012 bearing dataset showed that WaveAtten achieved superior mean squared error, mean absolute error, and R² scores compared with both classical signal-processing pipelines and state-of-the-art deep models, while ablation revealed a 6–8% performance drop when the symmetry-oriented components were removed. By systematically exploiting the intrinsic symmetry of vibration phenomena, WaveAtten offers a robust and efficient route to RUL prediction, paving the way for intelligent, condition-based maintenance of industrial machinery. Full article

Remote Sensing Image Change Captioning (RSICC) aims to generate natural language descriptions of changes in bi-temporal remote sensing images, providing more semantically interpretable results than conventional pixel-level change detection methods. However, existing approaches often rely on stacked Transformer modules, leading to suboptimal feature discrimination. Moreover, direct difference computation after feature extraction tends to retain task-irrelevant noise, limiting the model’s ability to capture meaningful changes. This study proposes a novel cross-spatial Transformer and symmetric difference localization network (CTSD-Net) for RSICC to address these limitations. The proposed Cross-Spatial Transformer adaptively enhances spatial-aware feature representations by guiding the model to focus on key regions across temporal images. Additionally, a hierarchical difference feature integration strategy is introduced to suppress noise by fusing multi-level differential features, while residual-connected high-level features serve as query vectors to facilitate bidirectional change representation learning. Finally, a causal Transformer decoder creates accurate descriptions by linking visual information with text. CTSD-Net achieved BLEU-4 scores of 66.32 and 73.84 on the LEVIR-CC and WHU-CDC datasets, respectively, outperforming existing methods in accurately locating change areas and describing them semantically. This study provides a promising solution for enhancing interpretability in remote sensing change analysis. Full article

Wake steering has emerged as a promising strategy to mitigate turbine wake losses, with existing research largely focusing on the aerodynamic optimization of yaw angles. However, many prior approaches rely on static look-up tables (LUTs), offering limited adaptability to real-world wind variability and leading to non-optimal results. More importantly, these energy-focused strategies overlook the mechanical implications of frequent yaw activities in pursuit of the maximum power output, which may lead to premature exhaustion of the yaw system’s design life, thereby accelerating structural degradation. This study proposes a supervisory control framework that balances energy capture with structural reliability through three key innovations: (1) upstream-based inflow sensing for real-time capture of free-stream wind, (2) fatigue-responsive optimization constrained by a dynamic actuation quota system with adaptive yaw activation, and (3) a bidirectional threshold adjustment mechanism that redistributes unused actuation allowances and compensates for transient quota overruns. A case study at an offshore wind farm shows that the framework improves energy yield by 3.94%, which is only 0.29% below conventional optimization, while reducing yaw duration and activation frequency by 48.5% and 74.6%, respectively. These findings demonstrate the framework’s potential as a fatigue-aware control paradigm that balances energy efficiency with system longevity. Full article

With the increasing significance of deep-sea resource development, Forward-Looking Sonar (FLS) has become an essential technology for real-time environmental mapping and navigation in deep-sea mining vehicles (DSMV). However, FLS images often suffer from a limited field of view, uneven imaging, and complex noise sources, making single-frame images insufficient for providing continuous and complete environmental awareness. Existing mosaicking methods typically rely on external sensors or controlled laboratory conditions, often failing to account for the high levels of uncertainty and error inherent in real deep-sea environments. Consequently, their performance during sea trials tends to be unsatisfactory. To address these challenges, this study introduces a robust FLS image mosaicking framework that functions without additional sensor input. The framework explicitly models the noise characteristics of sonar images captured in deep-sea environments and integrates bidirectional cyclic consistency filtering with a soft-weighted feature refinement strategy during the feature-matching stage. For image fusion, a radial adaptive fusion algorithm with a protective frame is proposed to improve edge transitions and preserve structural consistency in the resulting panoramic image. The experimental results demonstrate that the proposed framework achieves high robustness and accuracy under real deep-sea conditions, effectively supporting DSMV tasks such as path planning, obstacle avoidance, and simultaneous localization and mapping (SLAM), thus enabling reliable perceptual capabilities for intelligent underwater operations. Full article

Visual tracking from the unmanned aerial vehicle (UAV) perspective has been at the core of many low-altitude remote sensing applications. Most of the aerial trackers follow “tracking-by-detection” paradigms or their temporal-context-embedded variants, where the only visual appearance cue is encompassed for representation learning and estimating the spatial likelihood of the target. However, the variation of the target appearance among consecutive frames is inherently unpredictable, which degrades the robustness of the temporal context-aware representation. To address this concern, we advocate extra visual motion exhibiting predictable temporal continuity for complete temporal context-aware representation and introduce a dual-stream tracker involving explicit heterogeneous visual tracking experts. Our technical contributions involve three-folds: (1) high-order temporal context-aware representation integrates motion and appearance cues over a temporal context queue, (2) bidirectional cross-domain refinement enhances feature representation through cross-attention based mutual guidance, and (3) consistent decision-making allows for anti-drifting localization via dynamic gating and failure-aware recovery. Extensive experiments on four UAV benchmarks (UAV123, UAV123@10fps, UAV20L, and DTB70) illustrate that our method outperforms existing aerial trackers in terms of success rate and precision, particularly in occlusion and fast motion scenarios. Such superior tracking stability highlights its potential for real-world UAV applications. Full article

Deep learning has demonstrated significant success in hyperspectral image (HSI) classification by effectively leveraging spatial–spectral feature learning. However, current approaches encounter three challenges: (1) high spectral redundancy and the presence of noisy bands, which impair the extraction of discriminative features; (2) limited spatial receptive fields inherent in convolutional operations; and (3) unidirectional context modeling that inadequately captures bidirectional dependencies in non-causal HSI data. To address these challenges, this paper proposes HG-Mamba, a novel hybrid geometry-aware bidirectional Mamba network for HSI classification. The proposed HG-Mamba synergistically integrates convolutional operations, geometry-aware filtering, and bidirectional state-space models (SSMs) to achieve robust spectral–spatial representation learning. The proposed framework comprises two stages. The first stage, termed spectral compression and discrimination enhancement, employs multi-scale spectral convolutions alongside a spectral bidirectional Mamba (SeBM) module to suppress redundant bands while modeling long-range spectral dependencies. The second stage, designated spatial structure perception and context modeling, incorporates a Gaussian Distance Decay (GDD) mechanism to adaptively reweight spatial neighbors based on geometric distances, coupled with a spatial bidirectional Mamba (SaBM) module for comprehensive global context modeling. The GDD mechanism facilitates boundary-aware feature extraction by prioritizing spatially proximate pixels, while the bidirectional SSMs mitigate unidirectional bias through parallel forward–backward state transitions. Extensiveexperiments on the Indian Pines, Houston2013, and WHU-Hi-LongKou datasets demonstrate the superior performance of HG-Mamba, achieving overall accuracies of 94.91%, 98.41%, and 98.67%, respectively. Full article

To accurately monitor the operational state of Internet Data Centers (IDCs) and fulfill integrated management objectives, this paper introduces a bidirectional cross-attention LSTM–Informer with uncertainty-aware multi-task learning framework (BiCA-LI) for time series analysis. The architecture employs dual-branch temporal encoders—long short-term memory (LSTM) and Informer—to extract local transient dynamics and global long-term dependencies, respectively. A bidirectional cross-attention module is subsequently designed to synergistically fuse multi-scale temporal representations. Finally, task-specific regression and classification heads generate predictive outputs and anomaly detection results, while an uncertainty-aware dynamic loss weighting strategy adaptively balances task-specific gradients during training. Experimental results validate BiCA-LI’s superior performance across dual objectives. In regression tasks, it achieves an MAE of 0.086, MSE of 0.014, and RMSE of 0.117. For classification, the model attains 99.5% accuracy, 100% precision, and an AUC score of 0.950, demonstrating substantial improvements over standalone LSTM and Informer baselines. The dual-encoder design, coupled with cross-modal attention fusion and gradient-aware loss optimization, enables robust joint modeling of heterogeneous temporal patterns. This methodology establishes a scalable paradigm for intelligent IDC operations, enabling real-time anomaly mitigation and resource orchestration in energy-intensive infrastructures. Full article

LiDAR-based 3D object detection is fundamental in autonomous driving but remains challenging due to the irregularity, unordered nature, and non-uniform density of point clouds. Existing methods primarily rely on either graph-based or tree-based representations: Graph-based models capture fine-grained local geometry, while tree-based approaches encode hierarchical global semantics. However, these paradigms are often used independently, limiting their overall representational capacity. In this paper, we propose density-aware tree–graph cross-message passing (DA-TGCMP), a unified framework that exploits the complementary strengths of both structures to enable more expressive and robust feature learning. Specifically, we introduce a density-aware graph construction (DAGC) strategy that adaptively models geometric relationships in regions with varying point density and a hierarchical tree representation (HTR) that captures multi-scale contextual information. To bridge the gap between local precision and global contexts, we design a tree–graph cross-message-passing (TGCMP) mechanism that enables bidirectional interaction between graph and tree features. The experimental results of three large-scale benchmarks, KITTI, nuScenes, and Waymo, show that our method achieves competitive performance. Specifically, under the moderate difficulty setting, DA-TGCMP outperforms VoPiFNet by approximately 2.59%, 0.49%, and 3.05% in the car, pedestrian, and cyclist categories, respectively. Full article

This review critically analyzes recent advancements in dairy cow behavior recognition, highlighting novel methodological contributions through the integration of advanced artificial intelligence (AI) techniques such as transformer models and multi-view tracking with social network analysis (SNA). Such integration offers transformative opportunities for improving dairy cattle welfare, but current applications remain limited. We describe the transition from manual, observer-based assessments to automated, scalable methods using convolutional neural networks (CNNs), spatio-temporal models, and attention mechanisms. Although object detection models, including You Only Look Once (YOLO), EfficientDet, and sequence models, such as Bidirectional Long Short-Term Memory (BiLSTM) and Convolutional Long Short-Term Memory (convLSTM), have improved detection and classification, significant challenges remain, including occlusions, annotation bottlenecks, dataset diversity, and limited generalizability. Existing interaction inference methods rely heavily on distance-based approximations (i.e., assuming that proximity implies social interaction), lacking the semantic depth essential for comprehensive SNA. To address this, we propose innovative methodological intersections such as pose-aware SNA frameworks and multi-camera fusion techniques. Moreover, we explicitly discuss ethical challenges and data governance issues, emphasizing data transparency and animal welfare concerns within precision livestock contexts. We clarify how these methodological innovations directly impact practical farming by enhancing monitoring precision, herd management, and welfare outcomes. Ultimately, this synthesis advocates for strategic, empathetic, and ethically responsible precision dairy farming practices, significantly advancing both dairy cow welfare and operational effectiveness. Full article

To address the common issues of high small object miss rates, frequent false positives, and poor real-time performance in PCB defect detection, this paper proposes a multi-scale fusion algorithm based on the YOLOv12 framework. This algorithm integrates the Global Attention Mechanism (GAM) into the redesigned A2C2f module to enhance feature response strength of complex objects in symmetric regions through global context modeling, replacing conventional convolutions with hybrid weighted downsampling (HWD) modules that preserve copper foil textures in PCB images via hierarchical weight allocation. A bidirectional feature pyramid network (BiFPN) is constructed to reduce bounding box regression errors for micro-defects by fusing shallow localization and deep semantic features, employing a parallel perception attention (PPA) detection head combining dense anchor distribution and context-aware mechanisms to accurately identify tiny defects in high-density areas, and optimizing bounding box regression using a normalized Wasserstein distance (NWD) loss function to enhance overall detection accuracy. The experimental results on the public PCB dataset with symmetrically transformed samples demonstrate 85.3% recall rate and 90.4% mAP@50, with AP values for subtle defects like short circuit and spurious copper reaching 96.2% and 90.8%, respectively. Compared to the YOLOv12n, it shows an 8.7% enhancement in recall, a 5.8% increase in mAP@50, and gains of 16.7% and 11.5% in AP for the short circuit and spurious copper categories. Moreover, with an FPS of 72.8, it outperforms YOLOv5s, YOLOv8s, and YOLOv11n by 12.5%, 22.8%, and 5.7%, respectively, in speed. The improved algorithm meets the requirements for high-precision and real-time detection of multi-category PCB defects and provides an efficient solution for automated PCB quality inspection scenarios. Full article

Accurate extraction of dynamically evolving haul roads in open-pit mines from very-high-resolution (VHR) satellite imagery remains a critical challenge due to domain gaps between urban and mining environments, prohibitive annotation costs, and morphological irregularities. This paper introduces OMRoadNet, an unsupervised domain adaptation (UDA) framework for open-pit mine road extraction, which synergizes self-training, attention-based feature disentanglement, and morphology-aware augmentation to address these challenges. The framework employs a cyclic GAN (generative adversarial network) architecture with bidirectional translation pathways, integrating pseudo-label refinement through confidence thresholds and geometric rules (eight-neighborhood connectivity and adaptive kernel resizing) to resolve domain shifts. A novel exponential moving average unit (EMAU) enhances feature robustness by adaptively weighting historical states, while morphology-aware augmentation simulates variable road widths and spectral noise. Evaluations on cross-domain datasets demonstrate state-of-the-art performance with 92.16% precision, 80.77% F1-score, and 67.75% IoU (intersection over union), outperforming baseline models by 4.3% in precision and reducing annotation dependency by 94.6%. By reducing per-kilometer operational costs by 78% relative to LiDAR (Light Detection and Ranging) alternatives, OMRoadNet establishes a practical solution for intelligent mining infrastructure mapping, bridging the critical gap between structured urban datasets and unstructured mining environments. Full article