Search Results (345)

This paper addresses the trajectory tracking control problem of underactuated ships in ocean engineering, which faces the dual challenges of tracking error time–performance regulation and robustness design due to the system’s underactuated characteristics, model uncertainties, and external disturbances. Aiming to address the issues of traditional finite-time control (convergence time dependent on initial states) and fixed-time control (control chattering and parameter conservativeness), this paper proposes a predefined-time adaptive control framework that integrates an event-triggered mechanism and neural networks. By constructing a Lyapunov function with time-varying weights and designing non-periodic dynamically updated dual triggering conditions, the convergence process of tracking errors is strictly constrained within a user-prespecified time window without relying on initial states or introducing non-smooth terms. An adaptive approximator based on radial basis function neural networks (RBF-NNs) is employed to compensate for unknown nonlinear dynamics and external disturbances in real-time. Combined with the event-triggered mechanism, it dynamically adjusts the update instances of control inputs, ensuring prespecified tracking accuracy while significantly reducing computational resource consumption. Theoretical analysis shows that all signals in the closed-loop system are uniformly ultimately bounded, tracking errors converge to a neighborhood of the origin within the predefined-time, and the update frequency of control inputs exhibits a linear relationship with the predefined-time, avoiding Zeno behavior. Simulation results verify the effectiveness of the proposed method in complex marine environments. Compared with traditional control strategies, it achieves more accurate trajectory tracking, faster response, and a substantial reduction in control input update frequency, providing an efficient solution for the engineering implementation of embedded control systems in unmanned ships. Full article

The red plant phenotype of R1 cotton is a genetic marker produced by light-induced anthocyanin accumulation. GhPAP1D controls this trait. There are two 228 bp tandem repeats upstream of GhPAP1D in R1 cotton. In this study, GUS staining assays in transgenic Arabidopsis thaliana (L.) Heynh. demonstrated that tandem repeats in the GhPAP1D promoter-enhanced transcriptional activity. GhPAP1D is a homolog of A. thaliana AtPAP1. AtPAP1’s expression is regulated by photomorphogenesis-related transcription factors such as AtHY5 and AtBBXs. We identified the homologs of A. thaliana AtHY5, AtBBX21, and AtBBX24 in R1 cotton, designated as GhHY5, GhBBX21, and GhBBX24, respectively. Y1H assays confirmed that GhHY5, GhBBX21, and GhBBX24 each bound to the GhPAP1D promoter. Dual-luciferase reporter assays revealed that GhHY5 weakly activated the promoter activity of GhPAP1D. Heterologous expression assays in A. thaliana indicated that GhBBX21 promoted anthocyanin accumulation, whereas GhBBX24 had the opposite effect. Dual-luciferase assays showed GhBBX21 activated GhPAP1D transcription, while GhBBX24 repressed it. Further study indicated that GhHY5 did not enhance GhBBX21-mediated transcriptional activation of GhPAP1D but alleviates GhBBX24-induced repression. Together, our results demonstrate that GhBBX21 and GhBBX24 antagonistically regulate anthocyanin accumulation in R1 cotton under GhHY5 mediation, providing insights into light-responsive anthocyanin biosynthesis in cotton. Full article

Focusing on the problem of insufficient detection accuracy caused by blurred target boundaries, variable scales, and severe noise interference in side-scan sonar images, this paper proposes a high-precision detection network named ESL-YOLO, which integrates edge perception and adaptive quality assessment. Firstly, an Edge Fusion Module (EFM) is designed, which integrates the Sobel operator into depthwise separable convolution. Through a dual-branch structure, it realizes effective fusion of edge features and spatial features, significantly enhancing the ability to recognize targets with blurred boundaries. Secondly, a Self-Calibrated Dual Attention (SCDA) Module is constructed. By means of feature cross-calibration and multi-scale channel attention fusion mechanisms, it achieves adaptive fusion of shallow details and deep-rooted semantic content, improving the detection accuracy for small-sized targets and targets with elaborate shapes. Finally, a Location Quality Estimator (LQE) is introduced, which quantifies localization quality using the statistical characteristics of bounding box distribution, effectively reducing false detections and missed detections. Experiments on the SIMD dataset show that the mAP@0.5 of ESL-YOLO reaches 84.65%. The precision and recall rate reach 87.67% and 75.63%, respectively. Generalization experiments on additional sonar datasets further validate the effectiveness of the proposed method across different data distributions and target types, providing an effective technical solution for side-scan sonar image target detection. Full article

The characterization of Large Reasoning Models (LRMs) as exhibiting an “illusion of thinking” has recently emerged in the literature, sparking widespread public discourse. Some have suggested these manifestations represent bugs requiring fixes. I challenge this interpretation by reframing LRM behavior through dual-process theory from cognitive psychology. I draw on more than half a century of research on human cognitive effort and disengagement. The observed patterns include performance collapse at high complexity and counterintuitive reduction in reasoning effort. These appear to align with human cognitive phenomena, particularly System 2 engagement and disengagement under cognitive load. Rather than representing technical limitations, these behaviors likely manifest computational processes analogous to human cognitive constraints. In other words, they represent not a bug but a feature of bounded rational systems. I propose empirically testable hypotheses comparing LRM token patterns with human pupillometry data. I suggest that computational “rest” periods may restore reasoning performance, paralleling human cognitive recovery mechanisms. This reframing indicates that LRM limitations may reflect bounded rationality rather than fundamental reasoning failures. Accordingly, this article is presented as a hypothesis paper: it collates six decades of cognitive effort research and invites the scientific community to subject the dual-process predictions to empirical tests through coordinated human–AI experiments. Full article

Bird-dropping fouling and hotspot anomalies remain the most prevalent and detrimental defects in utility-scale photovoltaic (PV) plants; their co-occurrence on a single module markedly curbs energy yield and accelerates irreversible cell degradation. However, markedly disparate visual–thermal signatures of the two phenomena impede high-fidelity concurrent detection in existing robotic inspection systems, while stringent onboard compute budgets also preclude the adoption of bulky detectors. To resolve this accuracy–efficiency trade-off for dual-defect detection, we present YOLOv8-SG, a lightweight yet powerful framework engineered for mobile PV inspectors. First, a rigorously curated multi-modal dataset—RGB for stains and long-wave infrared for hotspots—is assembled to enforce robust cross-domain representation learning. Second, the HSV color space is leveraged to disentangle chromatic and luminance cues, thereby stabilizing appearance variations across sensors. Third, a single-head self-attention (SHSA) block is embedded in the backbone to harvest long-range dependencies at negligible parameter cost, while a global context (GC) module is grafted onto the detection head to amplify fine-grained semantic cues. Finally, an auxiliary bounding box refinement term is appended to the loss to hasten convergence and tighten localization. Extensive field experiments demonstrate that YOLOv8-SG attains 86.8% mAP@0.5, surpassing the vanilla YOLOv8 by 2.7 pp while trimming 12.6% of parameters (18.8 MB). Grad-CAM saliency maps corroborate that the model’s attention consistently coincides with defect regions, underscoring its interpretability. The proposed method, therefore, furnishes PV operators with a practical low-latency solution for concurrent bird-dropping and hotspot surveillance. Full article

This paper studies the adaptive practical tracking control (PTC) problem for a class of uncertain nonlinear systems (UNSs) with nontriangular structured uncertain terms and unknown parameters, where the boundary of nontriangular structured uncertain terms depends on all state variables. Based on the improved adaptive backstepping technique, the state feedback tracking controller and update laws are first constructed. Then, by seeking the linear relationship between the state vector and the error vector, and by utilizing the comparison principle, it is verified that the developed adaptive PTC scheme can ensure that all signals of the closed-loop system are bounded and the tracking error converges to a bounded region. Finally, two examples, including a numerical example and the dual-motor drive servo system, are provided to show the effectiveness of this control method. Full article

The all-weather imaging capability of synthetic aperture radar (SAR) confers unique advantages for maritime surveillance. However, ship detection under complex sea conditions still faces challenges, such as high-frequency noise interference and the limited computational power of edge computing platforms. To address these challenges, we propose a lightweight SAR small ship detection network, LWSARDet, which mitigates feature redundancy and reduces computational complexity in existing models. Specifically, based on the YOLOv5 framework, a dual strategy for the lightweight network is adopted as follows: On the one hand, to address the limited nonlinear representation ability of the original network, a global channel attention mechanism is embedded and a feature extraction module, GCCR-GhostNet, is constructed, which can effectively enhance the network’s feature extraction capability and high-frequency noise suppression, while reducing computational cost. On the other hand, to reduce feature dilution and computational redundancy in traditional detection heads when focusing on small targets, we replace conventional convolutions with simple linear transformations and design a lightweight detection head, LSD-Head. Furthermore, we propose a Position–Morphology Matching IoU loss function, P-MIoU, which integrates center distance constraints and morphological penalty mechanisms to more precisely capture the spatial and structural differences between predicted and ground truth bounding boxes. Extensive experiments conduct on the High-Resolution SAR Image Dataset (HRSID) and the SAR Ship Detection Dataset (SSDD) demonstrate that LWSARDet achieves superior overall performance compared to existing state-of-the-art (SOTA) methods. Full article

Accurate and efficient object detection is essential for aerial airport surveillance, playing a critical role in aviation safety and the advancement of autonomous operations. Although recent deep learning approaches have achieved notable progress, significant challenges persist, including severe object occlusion, extreme scale variation, dense panoramic clutter, and the detection of very small targets. In this study, we introduce a novel and unified detection framework designed to address these issues comprehensively. Our method integrates a Normalized Gaussian Wasserstein Distance loss for precise probabilistic bounding box regression, Dilation-wise Residual modules for improved multi-scale feature extraction, a Hierarchical Screening Feature Pyramid Network for effective hierarchical feature fusion, and DualConv modules for lightweight yet robust feature representation. Extensive experiments conducted on two public airport surveillance datasets, ASS1 and ASS2, demonstrate that our approach yields substantial improvements in detection accuracy. Specifically, the proposed method achieves an improvement of up to 14.6 percentage points in mean Average Precision (mAP@0.5) compared to state-of-the-art YOLO variants, with particularly notable gains in challenging small-object categories such as personnel detection. These results highlight the effectiveness and practical value of the proposed framework in advancing aviation safety and operational autonomy in airport environments. Full article

To address the obstacle-avoidance path-planning requirements of dual-arm robots operating in complex environments, such as chemical laboratories and biomedical workstations, this paper proposes ODSN-RRT (optimization-direction-step-node RRT), an efficient planner based on rapidly-exploring random trees (RRT). ODSN-RRT integrates three key optimization strategies. First, a two-stage sampling-direction strategy employs goal-directed growth until collision, followed by hybrid random-goal expansion. Second, a dynamic safety step-size strategy adapts each extension based on obstacle size and approach angle, enhancing collision detection reliability and search efficiency. Third, an expansion-node optimization strategy generates multiple candidates, selects the best by Euclidean distance to the goal, and employs backtracking to escape local minima, improving path quality while retaining probabilistic completeness. For collision checking in the dual-arm workspace (self and environment), a cylindrical-spherical bounding-volume model simplifies queries to line-line and line-sphere distance calculations, significantly lowering computational overhead. Redundant waypoints are pruned using adaptive segmental interpolation for smoother trajectories. Finally, a master-slave planning scheme decomposes the 14-DOF problem into two 7-DOF sub-problems. Simulations and experiments demonstrate that ODSN-RRT rapidly generates collision-free, high-quality trajectories, confirming its effectiveness and practical applicability. Full article

Detecting small objects in remote sensing images is challenging due to their size, which results in limited distinctive features. This limitation necessitates the effective use of contextual information for accurate identification. Many existing methods often struggle because they do not dynamically adjust the contextual scope based on the specific characteristics of each target. To address this issue and improve the detection performance of small objects (typically defined as objects with a bounding box area of less than 1024 pixels), we propose a novel backbone network called the Dynamic Context Branch Attention Network (DCBANet). We present the Dynamic Context Scale-Aware (DCSA) Block, which utilizes a multi-branch architecture to generate features with diverse receptive fields. Within each branch, a Context Adaptive Selection Module (CASM) dynamically weights information, allowing the model to focus on the most relevant context. To further enhance performance, we introduce an Efficient Branch Attention (EBA) module that adaptively reweights the parallel branches, prioritizing the most discriminative ones. Finally, to ensure computational efficiency, we design a Dual-Gated Feedforward Network (DGFFN), a lightweight yet powerful replacement for standard FFNs. Extensive experiments conducted on four public remote sensing datasets demonstrate that the DCBANet achieves impressive mAP@0.5 scores of 80.79% on DOTA, 89.17% on NWPU VHR-10, 80.27% on SIMD, and a remarkable 42.4% mAP@0.5:0.95 on the specialized small object benchmark AI-TOD. These results surpass RetinaNet, YOLOF, FCOS, Faster R-CNN, Dynamic R-CNN, SKNet, and Cascade R-CNN, highlighting its effectiveness in detecting small objects in remote sensing images. However, there remains potential for further improvement in multi-scale and weak target detection. Future work will integrate local and global context to enhance multi-scale object detection performance. Full article

Target detection in UAV aerial images has found increasingly widespread applications in emergency rescue, maritime monitoring, and environmental surveillance. However, traditional detection models suffer significant performance degradation due to challenges including substantial scale variations, high proportions of small targets, and dense occlusions in UAV-captured images. To address these issues, this paper proposes DMF-YOLO, a high-precision detection network based on YOLOv10 improvements. First, we design Dynamic Dilated Snake Convolution (DDSConv) to adaptively adjust the receptive field and dilation rate of convolution kernels, enhancing local feature extraction for small targets with weak textures. Second, we construct a Multi-scale Feature Aggregation Module (MFAM) that integrates dual-branch spatial attention mechanisms to achieve efficient cross-layer feature fusion, mitigating information conflicts between shallow details and deep semantics. Finally, we propose an Expanded Window-based Bounding Box Regression Loss Function (EW-BBRLF), which optimizes localization accuracy through dynamic auxiliary bounding boxes, effectively reducing missed detections of small targets. Experiments on the VisDrone2019 and HIT-UAV datasets demonstrate that DMF-YOLOv10 achieves 50.1% and 81.4% mAP50, respectively, significantly outperforming the baseline YOLOv10s by 27.1% and 2.6%, with parameter increases limited to 24.4% and 11.9%. The method exhibits superior robustness in dense scenarios, complex backgrounds, and long-range target detection. This approach provides an efficient solution for UAV real-time perception tasks and offers novel insights for multi-scale object detection algorithm design. Full article

Water within coal reservoirs exerts dual effects on methane adsorption–desorption by competing for adsorption sites and reducing permeability. The bound water effect, caused by coal wettability, significantly constrains coalbed methane (CBM) production, rendering investigations into coal wettability crucial for efficient CBM development. Compared with other geological formations, coals are characterized by a highly developed microporous structure, making the CO₂ sequestration mechanism in coal seams closely linked to the microscale interactions among gas, water, and coal matrixes. However, the intrinsic mechanisms remain poorly understood. In this study, molecular dynamics simulations are employed to investigate the wettability behaviors of CO₂, CH₄, and water on different coal matrix surfaces under varying temperature and pressure conditions, for coal macromolecules representative of four coal ranks. The study reveals the evolution of water wettability in response to CO₂ and CH₄ injection, identifies wettability differences among coal ranks, and analyzes the microscopic mechanisms governing wettability. The results show the following: (1) The contact angle increases with gas pressure, and the variation in wettability is more pronounced in CO₂ environments than in CH₄. As pressure increases, the number of hydrogen bonds decreases, while the peak gas density of CH₄ and CO₂ increases, leading to larger contact angles. (2) Simulations under different temperatures for the four coal ranks indicate that temperature has minimal influence on low-rank Hegu coal, whereas for higher-rank coals, gas adsorption on the coal surface increases, resulting in reduced wettability. Interfacial tension analysis further suggests that higher temperatures reduce water surface tension, cause dispersion of water molecules, and consequently improve wettability. Understanding the wettability variations among different coal ranks under variable pressure–temperature conditions provides a fundamental model and theoretical basis for investigating deep coal seam gas–water interactions and CO₂ geological sequestration mechanisms. These findings have significant implications for the advancement of CO₂-ECBM technology. Full article

Accurate land parcel segmentation in remote sensing imagery is critical for applications such as land use analysis, agricultural monitoring, and urban planning. However, existing methods often underperform in complex scenes due to small-object segmentation challenges, blurred boundaries, and background interference, often influenced by sensor resolution and atmospheric variation. To address these limitations, we propose a dual-stage framework that combines an enhanced YOLOv5s detector with the Segment Anything Model (SAM) to improve segmentation accuracy and robustness. The improved YOLOv5s module integrates Efficient Channel Attention (ECA) and BiFPN to boost feature extraction and small-object recognition, while Soft-NMS is used to reduce missed detections. The SAM module receives bounding-box prompts from YOLOv5s and incorporates morphological refinement and mask stability scoring for improved boundary continuity and mask quality. A composite Focal-Dice loss is applied to mitigate class imbalance. In addition to the publicly available CCF BDCI dataset, we constructed a new WuJiang dataset to evaluate cross-domain performance. Experimental results demonstrate that our method achieves an IoU of 89.8% and a precision of 90.2%, outperforming baseline models and showing strong generalizability across diverse remote sensing conditions. Full article

This paper proposes a novel sparse twin parametric insensitive support vector regression (STPISVR) model, designed to enhance sparsity and improve generalization performance. Similar to twin parametric insensitive support vector regression (TPISVR), STPISVR constructs a pair of nonparallel parametric insensitive bound functions to indirectly determine the regression function. The optimization problems are reformulated as two sparse linear programming problems (LPPs), rather than traditional quadratic programming problems (QPPs). The two LPPs are originally derived from initial L1-norm regularization terms imposed on their respective dual variables, which are simplified to constants via the Karush–Kuhn–Tucker (KKT) conditions and consequently disappear. This simplification reduces model complexity, while the constraints constructed through the KKT conditions— particularly their geometric properties—effectively ensure sparsity. Moreover, a two-stage hybrid tuning strategy—combining grid search for coarse parameter space exploration and Bayesian optimization for fine-grained convergence—is proposed to precisely select the optimal parameters, reducing tuning time and improving accuracy compared to a singlemethod strategy. Experimental results on synthetic and benchmark datasets demonstrate that STPISVR significantly reduces the number of support vectors (SVs), thereby improving prediction speed and achieving a favorable trade-off among prediction accuracy, sparsity, and computational efficiency. Overall, STPISVR enhances generalization ability, promotes sparsity, and improves prediction efficiency, making it a competitive tool for regression tasks, especially in handling complex data structures. Full article

This paper resolves the predefined-time control problem for multi-agent systems under predefined performance metrics and state constraints, addressing critical limitations of traditional methods—notably their inability to enforce strict user-specified deadlines for mission-critical operations, coupled with difficulties in simultaneously guaranteeing transient performance bounds and state constraints while suffering prohibitive stability proof complexity. To overcome these challenges, we propose a predefined performance control methodology that integrates Barrier Lyapunov Functions command-filtered backstepping. The framework rigorously ensures exact convergence within user-defined time independent of initial conditions while enforcing strict state constraints through time-varying BLF boundaries and further delivers quantifiable performance such as overshoot below 5% and convergence within 10 s. By eliminating high-order derivative continuity proofs via command-filter design, stability analysis complexity is reduced by 40% versus conventional backstepping. Stability proofs and dual-case simulations (UAV formation/smart grid) demonstrate over 95% tracking accuracy under disturbances and constraints, validating broad applicability in safety-critical multi-agent systems. Full article