Search Results (24)

To address the issues of false positives and missed detections commonly observed in traditional underwater seafood object detection algorithms, this paper proposes an improved detection method based on YOLOv5s. Specifically, we introduce a Spatial–Channel Synergistic Attention (SCSA) module after the Fast Spatial Pyramid Pooling layer in the backbone network. This module adopts a synergistic mechanism where the channel attention guides spatial localization, and the spatial attention feeds back to optimize channel weights, dynamically enhancing the unique features of aquatic targets (such as sea cucumber folds) while suppressing seawater background interference. In addition, we replace some C3 modules in YOLOv5s with our designed three-scale convolution dual-path variable-kernel module based on Pinwheel-shaped Convolution (C3k2-PSConv). This module strengthens the model’s ability to capture multi-dimensional features of aquatic targets, especially in the feature extraction of small-sized and occluded targets, reducing the false detection rate while ensuring the model’s lightweight property. The enhanced model is evaluated on the URPC dataset, which contains real-world underwater imagery of echinus, starfish, holothurian, and scallop. The experimental results show that compared with the baseline model YOLOv5s, while maintaining real-time inference speed, the proposed method in this paper increases the mean average precision (mAP) by 2.3% and reduces the number of parameters by approximately 2.4%, significantly improving the model’s operational efficiency. Full article

Steel surface defect detection is critical for ensuring industrial product quality and safety. Although deep learning-based detectors like the YOLO series have demonstrated considerable promise, they often struggle with three key challenges under computational constraints: the anisotropic morphology (i.e., direction-variant shapes) of defects, insufficient modeling of long-range dependencies, and the confusion between signal and noise in feature representation. To address these issues, this paper proposes PSC-YOLO, an enhanced model based on YOLOv11n. Our core design philosophy leverages symmetry principles to guide feature representation and fusion. First, we introduce Pinwheel-shaped Convolution (PConv), whose set of rotationally symmetric kernels explicitly captures multi-directional features to effectively represent anisotropic defects. Second, a Pyramid Sparse Transformer (PST) module is integrated to capture global context via its efficient cross-scale sparse attention, which reduces computational complexity by dynamically focusing on the most relevant features across different scales, leveraging a symmetrical pyramid architecture for balanced multi-scale fusion, thereby overcoming the bottleneck in long-range dependency modeling. Finally, a Channel-Prior Convolutional Attention (CPCA) mechanism is embedded to perform dynamic feature recalibration, which leverages internal structural symmetry—through symmetric pooling pathways and parallel multi-scale convolutions—to suppress background noise and highlight salient defects. Comprehensive experiments on the public NEU-DET dataset show that PSC-YOLO achieves superior performance, obtaining a mAP@0.5 of 78.3% and a mAP@0.5:0.95 of 48.3%, while maintaining a real-time inference speed of 2.8 ms per image. This demonstrates the model’s strong potential for deployment on industrial production lines, enabling high-precision, real-time quality inspection. Full article

Accurate detection of fresh jujube fruits plays a vital role in precision agriculture, enabling reliable yield estimation and supporting automation tasks such as robotic harvesting. To address the challenges of detecting such small targets (≤32 × 32 pixels) in complex orchard environments, this study proposes JFST-DETR, an efficient and robust detection model based on the Real-Time DEtection TRansformer (RT-DETR). First, to address the insufficient feature representation for small jujube fruit targets, a novel module called the Global Awareness Adaptive Module (GAAM) is designed. Building on GAAM and the innovative Spatial Coding Module (SCM), a new Spatial Enhancement Pyramid Network (SEPN) is proposed. Through the spatial-depth transformation domain and global awareness adaptive processing units, SEPN captures fine-grained features of small targets, enhancing the detection accuracy for small objects. Second, a Dynamic Sampling (DySample) operator is adopted, which optimizes feature space details via dynamic offset calculation and lightweight design, improving detection accuracy while reducing computational costs. Finally, to solve the problem of complex background interference caused by foliage occlusion and illumination variations, Pinwheel-Shaped Convolution (PSConv) is introduced. By using asymmetric padding and multi-directional convolution, PSConv enhances the robustness of feature extraction, ensuring reliable recognition in complex agricultural environments. Experimental results show that JFST-DETR achieves precision, recall, F1, mAP@50, and mAP@50:95 of 93%, 86.8%, 89.8%, 94.3%, and 75.2%. Compared to the baseline model, these metrics improve by 0.8%, 3.7%, 2.4%, 2.6%, and 3.1%, respectively. Cross-dataset evaluations further confirm its strong generalizability, demonstrating potential as a practical solution for small-target detection in intelligent horticulture. Full article

Purpose: Transcatheter heart valve replacements (TVR) are typically designed in a closed shape with initial leaflet coaptation. However, recent studies suggest a semi-closed geometry without a predefined coaptation zone, relying on diastolic pressure and clinical oversizing of 10–20 % for closure. This approach may minimize pinwheeling, a phenomenon linked to early valve degeneration. Method: Seven valve geometries were assessed: one closed design (G0) and six semi-closed variations (G1–G6). The semi-closed designs differed in free edge shape (linear, concave, convex) and opening degree, defined as the relative distance from the leaflet to the valve center in the unloaded state. The opening degree was systematically increased across G1–G6, with G6 exhibiting the highest value. 30 mm valves were fabricated using porcine pericardium and self-expanding nitinol stents. Performance was assessed in a pulse duplicator system, evaluating transvalvular pressure gradient (TPG), effective orifice area (EOA), regurgitation fraction (RF) and a novel pinwheeling index (PI) which was validated by finite element simulations. Results: Finite element simulations demonstrated that semi-closed geometries achieve valve closure at a diameter reduction of >5%. In vitro tests confirmed these findings with more homogeneous coaptation and reduced pinwheeling. With increased opening degree the RF reduced significantly (RF_G0 = 18.54 ± 8.05%; RF_G6 = 8.22 ± 1.27%; p < 0.0001), while valve opening remained comparable (p = 0.4519). Conclusions: A semi-closed leaflet geometry enhances valve closure, reducing regurgitation and pinwheeling while preserving effective opening. With clinical oversizing, a higher opening degree improves coaptation and may enhance durability by mitigating structural deterioration, ultimately improving the long-term performance and lifespan of transcatheter valve replacements. Full article

Cotton is one of the world’s most important economic crops, and its yield and quality have a significant impact on the agricultural economy. However, Verticillium wilt of cotton, as a widely spread disease, severely affects the growth and yield of cotton. Due to the typically small and densely distributed characteristics of this disease, its identification poses considerable challenges. In this study, we introduce YOLO-MSPM, a lightweight and accurate detection framework, designed on the YOLOv11 architecture to efficiently identify cotton Verticillium wilt. In order to achieve a lightweight model, MobileNetV4 is introduced into the backbone network. Moreover, a single-head self-attention (SHSA) mechanism is integrated into the C2PSA block, allowing the network to emphasize critical areas of the feature maps and thus enhance its ability to represent features effectively. Furthermore, the PC3k2 module combines pinwheel-shaped convolution (PConv) with C3k2, and the mobile inverted bottleneck convolution (MBConv) module is incorporated into the detection head of YOLOv11. Such adjustments improve multi-scale information integration, enhance small-target recognition, and effectively reduce computation costs. According to the evaluation, YOLO-MSPM achieves precision (0.933), recall (0.920), mAP50 (0.970), and mAP50-95 (0.797), each exceeding the corresponding performance of YOLOv11n. In terms of model lightweighting, the YOLO-MSPM model has 1.773 M parameters, which is a 31.332% reduction compared to YOLOv11n. Its GFLOPs and model size are 5.4 and 4.0 MB, respectively, representing reductions of 14.286% and 27.273%. The study delivers a lightweight yet accurate solution to support the identification and monitoring of cotton Verticillium wilt in environments with limited resources. Full article

The inspection of the appearance quality of tea leaves is vital for market classification and value assessment within the tea industry. Nevertheless, many existing detection approaches rely on sophisticated model architectures, which hinder their practical use on devices with limited computational resources. This study proposes a lightweight object detection network, TeaAppearanceLiteNet, tailored for tea leaf appearance analysis. A novel C3k2_PartialConv module is introduced to significantly reduce computational redundancy while maintaining effective feature extraction. The CBMA_MSCA attention mechanism is incorporated to enable the multi-scale modeling of channel attention, enhancing the perception accuracy of features at various scales. By incorporating the Detect_PinwheelShapedConv head, the spatial representation power of the network is significantly improved. In addition, the MPDIoU_ShapeIoU loss is formulated to enhance the correspondence between predicted and ground-truth bounding boxes across multiple dimensions—covering spatial location, geometric shape, and scale—which contributes to a more stable regression and higher detection accuracy. Experimental results demonstrate that, compared to baseline methods, TeaAppearanceLiteNet achieves a 12.27% improvement in accuracy, reaching a mAP@0.5 of 84.06% with an inference speed of 157.81 FPS. The parameter count is only 1.83% of traditional models. The compact and high-efficiency design of TeaAppearanceLiteNet enables its deployment on mobile and edge devices, thereby supporting the digitalization and intelligent upgrading of the tea industry under the framework of smart agriculture. Full article

Fish are a vital aquatic resource worldwide, and the sustainable development of aquaculture is essential for global food security and economic growth. However, the high incidence of fish diseases in complex aquaculture environments significantly hampers sustainability, and traditional manual diagnosis methods are inefficient and often inaccurate. To address the challenges of small-lesion detection, lesion area size and morphological variation, and background complexity, we propose YOLO-TPS, a high-precision fish-disease detection model based on an improved YOLOv11n architecture. The model integrates a multi-module synergy strategy and a triple-attention mechanism to enhance detection performance. Specifically, the SPPF_TSFA module is introduced into the backbone to fuse spatial, channel, and neuron-level attention for better multi-scale feature extraction of early-stage lesions. A PC_Shuffleblock module incorporating asymmetric pinwheel-shaped convolutions is embedded in the detection head to improve spatial awareness and texture modeling under complex visual conditions. Additionally, a scale-aware dynamic intersection over union (SDIoU) loss function was designed to accommodate changes in the scale and morphology of lesions at different stages of the disease. Experimental results on a dataset comprising 4596 images across six fish-disease categories demonstrate superior performance (mAP_0.5: 97.2%, Precision: 97.9%, Recall: 95.1%) compared to the baseline. This study offers a robust, scalable solution for intelligent fish-disease diagnosis and has promising implications for sustainable aquaculture and animal health monitoring. Full article

To address the challenges in ship plate detection under complex maritime scenarios—such as small target size, extreme aspect ratios, dense arrangements, and multi-angle rotations—this paper proposes a multi-module collaborative detection algorithm, RT-DETR-HPA, based on an enhanced RT-DETR framework. The proposed model integrates three core components: an improved High-Frequency Enhanced Residual Block (HFERB) embedded in the backbone to strengthen multi-scale high-frequency feature fusion, with deformable convolution added to handle occlusion and deformation; a Pinwheel-shaped Convolution (PConv) module employing multi-directional convolution kernels to achieve rotation-adaptive local detail extraction and accurately capture plate edges and character features; and an Adaptive Sparse Self-Attention (ASSA) mechanism incorporated into the encoder to automatically focus on key regions while suppressing complex background interference, thereby enhancing feature discriminability. Comparative experiments conducted on a self-constructed dataset of 20,000 ship plate images show that, compared to the original RT-DETR, RT-DETR-HPA achieves a 3.36% improvement in mAP@50 (up to 97.12%), a 3.23% increase in recall (reaching 94.88%), and maintains real-time detection speed at 40.1 FPS. Compared with mainstream object detection models such as the YOLO series and Faster R-CNN, RT-DETR-HPA demonstrates significant advantages in high-precision localization, adaptability to complex scenarios, and real-time performance. It effectively reduces missed and false detections caused by low resolution, poor lighting, and dense occlusion, providing a robust and high-accuracy solution for intelligent ship supervision. Future work will focus on lightweight model design and dynamic resolution adaptation to enhance its applicability on mobile maritime surveillance platforms. Full article

(1) Background: This study aimed to analyse the hydrodynamic performance of two generations of self-expanding transcatheter heart valves (THV) as a valve-in-valve (ViV) in different surgical aortic valve (SAV) models under standardised conditions. The nitinol-based Evolut R valve is frequently used in ViV procedures. It is unclear whether its successor, the Evolut PRO, is superior in ViV procedures, particularly considering the previously implanted SAV model. (2) Methods: Evolut^TM R 26 mm and Evolut^TM PRO 26 mm prostheses were implanted in nine 21 mm labelled size SAV models (Hancock^® II, Mosaic^® Ultra^TM, Epic^TM Supra, Trifecta^TM GT, Perimount^®, Perimount^® Magna Ease, Avalus^TM, Intuity^TM, Freestyle^®) to analyse their hydrodynamic performance under defined circulatory conditions in a pulse duplicator. (3) Results: Both THVs presented with the lowest effective orifice area (EOA) and highest mean pressure gradient (MPG) inside Hancock^® II, whereas THVs in Intuity showed the highest EOA and lowest MPG. Evolut R and Evolut PRO showed significant hydrodynamic differences depending on the SAV. Both THVs performed similarly in porcine valves. Although the Evolut R performed better than Evolut PRO in stented bovine SAVs, the Evolut PRO was superior inside the Intuity. Further, the SAV model design markedly influenced the TAV’s geometric orifice area and pin-wheeling index. (4) Conclusions: These findings show that the Evolut R and Evolut PRO perform differently depending on the previously implanted SAV model. THV selection for treatment of a specific SAV model should consider these results. Full article

The cycloid gear wear of RV reducers leads to the degradation of the industrial robots’ transmission accuracy, but the degradation law with respect to the wear volume is still unclear. In this paper, a method for determining transmission error (TE) through a combination of numerical and simulation analysis is proposed. The wear model of cycloid gear was ascertained based on the theory of Archard. Then, the full rigid body and rigid–flexible coupling model of RV reducers were established using the multibody dynamics theory. Finally, the static transmission error (STE) and dynamic transmission error (DTE) were investigated. The results show that as working hours increase, the cycloid gear wear volume increases, and transmission accuracy deteriorates, but the rate tends to slow down. Full article

Metasurface devices have demonstrated powerful electromagnetic wave manipulation capabilities. By adjusting the shape and size parameters of the metasurface microstructure, we can control the resonance between spatial electromagnetic waves and the metasurface, which will trigger wave scattering at a specific frequency. By utilizing these characteristics, we design a metasurface device with a bandpass filtering function and a unit cell of the metasurface consisting of a double-layer pinwheel-shaped metal structure and high resistance silicon substrate (forming metal–silicon–metal configuration). A bandpass filter operating in the terahertz band has been implemented, which achieves a 36 GHz filtering bandwidth when the transmission amplitude decreases by 3 dB and remains effective in a wave incidence angle of 20°. This work uses an equivalent RC resonance circuit to explain the formation of bandpass filtering. In addition, the photosensitive properties of silicon enable the filtering function of the device to have on/off tuned characteristics under light excitation, which enhances the dynamic controllability of the filter. The designed device may have application prospects in 6G space communication. Full article

Cycloid drives are generally used in precision machinery requiring high-reduction ratios, such as robot joint (RV) reducers. The contact stress of cycloidal gears greatly affects lifetime and transmission performance. Traditional finite element method (FEM) has less computational efficiency for contact analysis of complex surface. Therefore, in this paper, isogeometric analysis (IGA) was employed to explore the multi-tooth contact problem of the cycloid pinwheel drive. Based on the nonuniform rational B spline (NURBS) curved surface generation method, the NURBS tooth profile of the cycloid gear was reconstructed. In addition, the NURBS surface of the cycloid gear–pin tooth–output pin was generated via the element splicing method. A geometrical analysis model of cycloid pinwheel drive was established to solve the contact force of the meshing pair under different input angles and compared with the finite element method in terms of convergence, resultant accuracy, and solving timeliness. The results show that isogeometric analysis has higher accuracy and efficiency than the finite element method in calculating the contact stress and contact force. The error of the IGA is only 8.8% for 10 × 10 elements in contact, while the error of the finite element method reaches about 40%. The method can improve the contact simulation accuracy of the cycloid drive and provides a reference for the design evaluation of RV reducer. Full article

Drag-dominant tidal turbine energy holds tremendous clean energy potential but faces significant hurdles as unsuitability of the actuator disc model due to the varying swept blockage area, unaccounted bypass flow downstream interaction, and rotor parasitic drag, whereas blade element momentum theory is computably effective for majorly 3-blade lift-dominated aerofoil. This study validates a novel method to find the optimal TSR of any turbine with a cost-effective and user-friendly moment balancing algorithm to support robust tidal energy development. Performance analysis CFD study of Pinwheel and Savonius tidal turbines in a Biffis canal hydrodynamic system was carried out. Thrust and idle moment are analyzed as functions of only inlet fluid velocity and rotational speed, respectively. These relationships were verified through regression analysis, and the turbines’ net moment equations were established based on these parameters. In both simulation models, rotational speed and inlet velocity were proved excellent predictor variables (R² value ≈ 1) for idle and thrust moments, respectively. The optimal TSR values for Pinwheel and Savonius turbines were 2.537 and 0.671, respectively, within an acceptable error range for experimental validation. The optimal basin efficiency (η_opt, TSR) values for Pinwheel and Savonius in the 12% blockage channel were (29.09%, 4.0) and (25.67%, 2.87), respectively. The trade-off between TSR_opt and η_opt is the key instruction concerning electricity generation and environmental impact. Full article

Current performance analysis processes for drag-dominant tidal turbines are unsuitable as disk actuator theory lacks support for varying swept blockage area, bypass flow downstream interaction, and parasitic rotor drag, whereas blade element momentum theory is computably effective for three-blade lift-dominated aerofoil. This study proposes a novel technique to calculate the optimal turbine tip speed ratio (TSR) with a cost-effective and user-friendly moment balancing algorithm. A reliable dynamic TSR matrix was developed with varying rotational speeds and fluid velocities, unlike previous works simulated at a fixed fluid velocity. Thrust and idle moments are introduced as functions of inlet fluid velocity and rotational speed, respectively. The quadratic relationships are verified through regression analysis, and net moment equations are established. Rotational speed was a reliable predictor for Pinwheel’s idle moment, while inlet velocity was a reliable predictor for thrust moment for both models. The optimal (C_p, TSR) values for Pinwheel and Savonius turbines were (0.223, 2.37) and (0.63, 0.29), respectively, within an acceptable error range for experimental validation. This study aims to improve prevailing industry practices by enhancing an engineer’s understanding of optimal blade design by adjusting the rotor speed to suit the inlet flow case compared to ‘trial and error’ with cost-intensive simulations. Full article

The rotation error is the most important quality characteristic index of a rotate vector (RV) reducer, and it is difficult to accurately optimize the design of a RV reducer, such as the Taguchi type, due to the many factors affecting the rotation error and the serious coupling effect among the factors. This paper analyzes the RV reducer rotation error and each factor based on the deep Gaussian processes (DeepGP) model and Sobol sensitivity analysis(SA) method. Firstly, using the optimal Latin hypercube sampling (OLHS) approach and the DeepGP model, a high-precision regression prediction model of the rotation error and each affecting factor was created. On the basis of the prediction model, the Sobol method was used to conduct a global SA of the factors influencing the rotation error and to compare the coupling relationship between the factors. The results show that the OLHS method and the DeepGP model are suitable for predicting the rotation error in this paper, and the accuracy of the prediction model constructed based on both of them is as high as 95%. The rotation error mainly depends on the influencing factors in the second stage cycloidal pinwheel drive part. The primary involute planetary part and planetary output carrier’s rotation error factors have little effect. The coupling effects between the matching clearance between the pin gear and needle gear hole ($\delta J$) and the circular position error of the needle gear hole ($\delta t$) is noticeably stronger. Full article