Search Results (174)

During the automated picking of table grapes, the automatic recognition and segmentation of grape pedicels, along with the positioning of picking points, are vital components for all the following operations of the harvesting robot. In the actual scene of a grape plantation, however, it is extremely difficult to accurately and efficiently identify and segment grape pedicels and then reliably locate the picking points. This is attributable to the low distinguishability between grape pedicels and the surrounding environment such as branches, as well as the impacts of other conditions like weather, lighting, and occlusion, which are coupled with the requirements for model deployment on edge devices with limited computing resources. To address these issues, this study proposes a novel picking point localization method for table grapes based on an instance segmentation network called Progressive Global-Local Structure-Sensitive Segmentation (PGSS-YOLOv11s) and a simple combination strategy of morphological operators. More specifically, the network PGSS-YOLOv11s is composed of an original backbone of the YOLOv11s-seg, a spatial feature aggregation module (SFAM), an adaptive feature fusion module (AFFM), and a detail-enhanced convolutional shared detection head (DE-SCSH). And the PGSS-YOLOv11s have been trained with a new grape segmentation dataset called Grape-⊥, which includes 4455 grape pixel-level instances with the annotation of ⊥-shaped regions. After the PGSS-YOLOv11s segments the ⊥-shaped regions of grapes, some morphological operations such as erosion, dilation, and skeletonization are combined to effectively extract grape pedicels and locate picking points. Finally, several experiments have been conducted to confirm the validity, effectiveness, and superiority of the proposed method. Compared with the other state-of-the-art models, the main metrics $F1$ score and mask mAP@0.5 of the PGSS-YOLOv11s reached 94.6% and 95.2% on the Grape-⊥ dataset, as well as 85.4% and 90.0% on the Winegrape dataset. Multi-scenario tests indicated that the success rate of positioning the picking points reached up to 89.44%. In orchards, real-time tests on the edge device demonstrated the practical performance of our method. Nevertheless, for grapes with short pedicels or occluded pedicels, the designed morphological algorithm exhibited the loss of picking point calculations. In future work, we will enrich the grape dataset by collecting images under different lighting conditions, from various shooting angles, and including more grape varieties to improve the method’s generalization performance. Full article

Background/Objectives: Recent changes in obstetric practices and population demographics have prompted a re-evaluation of labor patterns. This study aimed to characterize labor patterns in a Greek pregnant population using ultrasound and compare them with established labor curves. Methods: A prospective cohort study was conducted at the Third Department of Obstetrics and Gynecology, School of Medicine, Faculty of Health Sciences, Aristotle University of Thessaloniki, Greece, over a two-year period (December 2022 to June 2024). Transabdominal ultrasound was used to determine the fetal head position and transperineal ultrasound was used to measure angle of progression (AoP) and head–perineum distance (HPD) during labor. Maternal and labor characteristics, including body mass index (BMI), parity, labor duration, and mode of delivery, were recorded. Statistical analysis included mixed linear models to assess the relationship between AoP, HPD, and cervical dilatation. Results: In total, 500 parturients were included in this study. Women entered the active phase of labor approximately 5 h before delivery, with AoP increasing sharply and HPD decreasing rapidly at this point. Cesarean section (CS) cases showed a slower increase in AoP compared to vaginal deliveries (VDs), with CS cases having a mean AoP of 117.9° (95% CI: 111.6–124.2°) at full dilation, compared to 133.4° (95% CI: 130.6–136.2°) in VD. HPD values declined more slowly in CS cases, with a mean HPD of 45.1 mm (95% CI: 40.6–49.6 mm) at full dilation, compared to 36.4 mm (95% CI: 34.3–38.5 mm) in VD. Epidural analgesia was associated with steeper increases in AoP and decreases in HPD in the final 2.5 h before delivery, while oxytocin administration accelerated these changes in the last 3–4 h. The mean time to delivery was 3.19 h (95% CI: 2.80–3.59 h) when AoP reached 125° and 3.92 h when HPD was 40 mm (95% CI: 3.53–4.30 h). BMI in women who gave birth via CS was significantly higher compared to VD (32.03 vs. 29.94 kg/m², p-value: 0.008), and the total duration of labor was shorter in VD compared to CS and operative vaginal delivery (OVD) (8 h vs. 15 h, p-value < 0.001 and 8 h vs. 12 h, p-value < 0.001, respectively). Birthweight was also lower in VD compared to CS (3103.09 g vs. 3267.88 g, p-value: 0.05). Conclusions: This study provides the first ultrasonographic characterization of labor patterns in a Greek population, highlighting the utility of ultrasound in objectively assessing labor progression. Full article

Transverse fetal head position during labor is associated with increased rates of operative deliveries and cesarean sections. Traditional assessment methods rely on digital examination, which can be inaccurate in cases of prolonged labor. Intrapartum ultrasound offers improved diagnostic capabilities, but standardized interpretation frameworks are needed. This study aimed to evaluate the significance of appropriate assessment and management of transverse fetal head position during labor, with particular emphasis on the correlation between geometric parameters and delivery outcomes. Additionally, the investigation analyzed the potential role of Artificial Intelligence Dystocia Algorithm (AIDA) as an innovative decision support system in standardizing diagnostic approaches and optimizing clinical decision-making in cases of fetal malposition. This investigation was conducted as a focused secondary analysis of data originally collected for the development and validation of the Artificial Intelligence Dystocia Algorithm (AIDA). The study examined 66 cases of transverse fetal head position from a cohort of 135 nulliparous women with prolonged second-stage labor across three Italian hospitals. Cases were stratified by Midline Angle (MLA) measurements into classic transverse (≥75°), near-transverse (70–74°), and transitional (60–69°) positions. Four geometric parameters (Angle of Progression, Head–Symphysis Distance, Midline Angle, and Asynclitism Degree) were evaluated using the AIDA classification system. The predictive capabilities of three machine learning algorithms (Support Vector Machine, Random Forest, and Multilayer Perceptron) were assessed, and delivery outcomes were analyzed. The AIDA system successfully categorized labor dystocia into five distinct classes, with strong predictive value for delivery outcomes. A clear gradient of cesarean delivery risk was observed across the spectrum of transverse positions (100%, 93.1%, and 85.7% for near-transverse, classic transverse, and transitional positions, respectively). All cases classified as AIDA Class 4 required cesarean delivery regardless of the specific MLA value. Machine learning algorithms demonstrated high predictive accuracy, with Random Forest achieving 95.5% overall accuracy across the study cohort. The presence of concurrent asynclitism with transverse position was associated with particularly high rates of cesarean delivery. Among the seven cases that achieved vaginal delivery despite transverse positioning, none belonged to the classic transverse positions group, and five (71.4%) exhibited at least one parameter classified as favorable. The integration of artificial intelligence through AIDA as a decision support system, combined with intrapartum ultrasound, offered a promising approach for objective assessment and management of transverse fetal head position. The AIDA classification system’s integration of multiple geometric parameters, with particular emphasis on precise Midline Angle (MLA) measurement in degrees, provided superior predictive capability for delivery outcomes compared to qualitative position assessment alone. This multidimensional approach enabled more personalized and evidence-based management of malpositions during labor, potentially reducing unnecessary interventions while identifying cases where expectant management might be futile. Further prospective studies are needed to validate the predictive capability of this decision support system and its impact on clinical decision-making in real-time labor management. Full article

Pump-driven liquid cooling systems are widely utilized in unmanned aerial vehicle (UAV) electronic thermal management. As a critical power component, the miniaturization and lightweight design of the pump are essential. Increasing the operating speed of the pump allows for a reduction in impeller size while maintaining hydraulic performance, thereby significantly decreasing the overall volume and mass. However, high-speed operation introduces considerable internal flow losses, placing stricter demands on the geometric design and flow-field compatibility of the impeller. In this study, a miniature high-speed centrifugal pump (MHCP) was investigated, and a multi-objective optimization of the impeller was carried out using response surface methodology (RSM) to improve internal flow characteristics and overall hydraulic performance. Numerical simulations demonstrated strong predictive capability, and experimental results validated the model’s accuracy. At the design condition (10,000 rpm, 4.8 m³/h), the pump achieved a head of 46.1 m and an efficiency of 49.7%, corresponding to its best efficiency point (BEP). Sensitivity analysis revealed that impeller outlet diameter and blade outlet angle were the most influential parameters affecting pump performance. Following the optimization, the pump head increased by 3.7 m, and the hydraulic efficiency improved by 4.8%. In addition, the pressure distribution and streamlines within the impeller exhibited better uniformity, while the turbulent kinetic energy near the blade suction surface and at the impeller outlet was markedly decreased. This work provides theoretical support and design guidance for the efficient application of MHCPs in UAV thermal management systems. Full article

Motivation: Benign paroxysmal positional vertigo (BPPV) is characterized by torsional nystagmus induced by changes in head position, where accurate quantitative assessment of subtle torsional eye movements is essential for precise diagnosis. Conventional videonystagmography (VNG) techniques face challenges in accurately capturing the rotational components of pupil movements, and existing automated methods typically exhibit limited performance in identifying torsional nystagmus. Methodology: The objective of this study was to develop an automated system capable of accurately and quantitatively detecting torsional nystagmus. We introduce the Torsion Transformer model, designed to directly estimate torsion angles from iris images. This model employs a self-supervised learning framework comprising two main components: a Decoder module, which learns rotational transformations from image data, and a Finder module, which subsequently estimates the torsion angle. The resulting torsion angle data, represented as time-series, are then analyzed using a 1-dimensional convolutional neural network (1D-CNN) classifier to detect the presence of nystagmus. The performance of the proposed method was evaluated using video recordings from 127 patients diagnosed with BPPV. Findings: Our Torsion Transformer model demonstrated robust performance, achieving a sensitivity of 89.99%, specificity of 86.36%, an F1-score of 88.82%, and an area under the receiver operating characteristic curve (AUROC) of 87.93%. These results indicate that the proposed model effectively quantifies torsional nystagmus, with performance levels comparable to established methods for detecting horizontal and vertical nystagmus. Thus, the Torsion Transformer shows considerable promise as a clinical decision support tool in the diagnosis of BPPV. Key Findings: Technical performance improvement in torsional nystagmus detection; System to support clinical decision-making for healthcare professionals. Full article

This study presents a numerical investigation of the internal flow characteristics within the draft tube of a Kaplan turbine using computational fluid dynamics (CFD). The distribution and evolution of vortical structures, particularly the formation and development of vortex ropes under various operating conditions, are systematically analyzed. The study aims to explore the effects of blade angle and guide vane opening on the internal flow characteristics of the unit, thereby providing guidance for flow control strategies. The influence of guide vane opening and turbine head on vortex dynamics and flow stability is examined, with a focus on the pressure pulsations induced by vortex ropes through frequency-domain analysis. The results indicate that increased guide vane openings and higher heads lead to the expansion and downstream extension of the vortex rope into the elbow section, causing significant low-frequency pressure pulsations and enhancing flow instability. These findings contribute to a deeper understanding of unsteady flow behavior in Kaplan turbine draft tubes and provide a theoretical foundation for improving hydraulic stability and optimizing operational performance. Full article

Unmanned aerial vehicles (UAVs) have emerged as a promising solution for collaborative search missions in complex environments. However, in the presence of interference, communication disruptions between UAVs and ground control stations can severely degrade coordination efficiency, leading to prolonged search times and reduced mission success rates. To address these challenges, this paper proposes a novel multi-agent deep reinforcement learning (MADRL) framework for joint spectrum and search collaboration in multi-UAV systems. The core problem is formulated as a combinatorial optimization task that simultaneously optimizes channel selection and heading angles to minimize the total search time under dynamic interference conditions. Due to the NP-hard nature of this problem, we decompose it into two interconnected Markov decision processes (MDPs): a spectrum collaboration subproblem solved using a received signal strength indicator (RSSI)-aware multi-agent proximal policy optimization (MAPPO) algorithm and a search collaboration subproblem addressed through a target probability map (TPM)-guided MAPPO approach with an innovative action-masking mechanism. Extensive simulations demonstrate superior performance compared to baseline methods (IPPO, QMIX, and IQL). Extensive experimental results demonstrate significant performance advantages, including 68.7% and 146.2% higher throughput compared to QMIX and IQL, respectively, along with 16.7–48.3% reduction in search completion steps versus baseline methods, while maintaining robust operations under dynamic interference conditions. The framework exhibits strong resilience to communication disruptions while maintaining stable search performance, validating its practical applicability in real-world interference scenarios. Full article

Surface target salvage is a crucial component of marine emergencies. Although unmanned surface vehicles (USVs) have emerged as effective alternative platforms to traditional artificial salvage, salvage target tracking remains a challenging issue. Therefore, this paper proposes a salvage target tracking (STT) algorithm which enables rapid approach (RA) to the salvage target, while maintaining an appropriate salvage distance that keeps the surface target within the operational range in the terminal tracking (TT) phase. In the RA phase, the model predictive line-of-sight (PLOS) guidance algorithm is proposed to estimate and compensate for the drift angle encountered when following a curved path. In the TT phase, a guidance algorithm based on the key point is proposed to track the salvage target. To achieve the goals in the RA phase and the TT phase, a heading and speed controller based on proportional–integral–derivative control is proposed to track the desired signals computed by the PLOS and key point guidance algorithms. To verify the effectiveness of the STT algorithm, simulation analysis is conducted for the PLOS guidance algorithm and key point guidance algorithm. The simulation results show that the proposed PLOS guidance algorithm has the lowest cross-tracking error compared with the traditional LOS, integral LOS, and adaptive error constraint LOS. Moreover, the distance between the USV and the salvage target is less than the operating radius of the salvage operation. The results demonstrate that the proposed STT algorithm is capable of maintaining the appropriate salvage distance while tracking the salvage target. Full article

Autonomous ship berthing requires advanced path planning to balance multiple objectives, such as minimizing berthing time, reducing energy consumption, and ensuring safety under dynamic environmental constraints. However, traditional planning and learning methods often suffer from inefficient search or sparse rewards in such constrained and high-dimensional settings. This study introduces a double deep Q-network (DDQN)-guided dual-population constrained multi-objective evolutionary algorithm (CMOEA) framework for autonomous ship berthing. By integrating deep reinforcement learning (DRL) with CMOEA, the framework employs DDQN to dynamically guide operator selection, enhancing search efficiency and solution diversity. The designed reward function optimizes thrust, time, and heading accuracy while accounting for vessel kinematics, water currents, and obstacles. Simulations on the CSAD vessel model demonstrate that this framework outperforms baseline algorithms such as evolutionary multitasking constrained multi-objective optimization (EMCMO), DQN, Q-learning, and non-dominated sorting genetic algorithm II (NSGA-II), achieving superior efficiency and stability while maintaining the required berthing angle. The framework also exhibits strong adaptability across varying environmental conditions, making it a promising solution for autonomous ship berthing in port environments. Full article

Single-track electric agricultural chassis plays a vital role in autonomous navigation and driving operations in hilly and mountainous regions, where its path tracking performance directly affects the operational accuracy and stability. However, in complex farmland environments, traditional methods often suffer from frequent turning and large tracking errors due to variable path curvature, uneven terrain, and track slippage. To address these issues, this paper proposes a path tracking algorithm combining a segmented preview model with variable universe fuzzy control, enabling dynamic adjustment of the preview distance for better curvature adaptation. Additionally, a heading deviation prediction model based on Support Vector Regression (SVR) optimized by Particle Swarm Optimization (PSO) is introduced, and a steering angle compensation controller is designed to improve the turning accuracy. Simulation and field experiments show that, compared with fixed preview distance and fixed-universe fuzzy control methods, the proposed algorithm reduces the average number of turns per control cycle by 30.19% and 18.23% and decreases the average lateral error by 34.29% and 46.96%, respectively. These results confirm that the proposed method significantly enhances path tracking stability and accuracy in complex terrains, providing an effective solution for autonomous navigation of agricultural machinery. Full article

To rectify significant heading calculation errors in polarized light navigation for unmanned aerial vehicles (UAVs) under tilted states, this paper proposes a method for compensating horizontal attitude angles based on horizon detection. First, a defogging enhancement algorithm that integrates Retinex theory with dark channel prior is adopted to improve image quality in low-illumination and hazy environments. Second, a dynamic threshold segmentation method in the HSV color space (Hue, Saturation, and Value) is proposed for robust horizon region extraction, combined with an improved adaptive bilateral filtering Canny operator for edge detection, aimed at balancing detail preservation and noise suppression. Then, the progressive probabilistic Hough transform is used to efficiently extract parameters of the horizon line. The calculated horizontal attitude angles are utilized to convert the body frame to the navigation frame, achieving compensation for polarization orientation errors. Onboard experiments demonstrate that the horizontal attitude angle estimation error remains within 0.3°, and the heading accuracy after compensation is improved by approximately 77.4% relative to uncompensated heading accuracy, thereby validating the effectiveness of the proposed algorithm. Full article

Congested airspace conflict resolution during terminal operations is a common air traffic management issue that may produce cascading delays. Vehicles needing emergency clearance to land, at either traditional airports or vertiports, would require others on approach to move out of the way and, in some instances, cause a wave of delay to propagate through all vehicles on approach. Specifically, uncrewed aerial systems utilizing near-maximum arrival rates would be greatly impacted when requested to move off their approach path and may interfere with others. Vertiports further complicate crowded approaches because vehicles can arrive from many different angles at the same time to maximize landing area usage. Traditional air traffic management techniques were studied for vertiport applications specific to high-capacity operations. This work investigated methods of uniformly re-directing vehicles on approach to a vertiport that would be impacted by an emergency vehicle to minimize or avoid cascading delays. A route of time-optimal Bézier curves as well as Dubins paths optimized for interception heading was generated and flown on as an alternate maneuver when an unaccounted-for emergency vehicle initiated a bypass of an air traffic fleet. A comparison to flight on a holding pattern showed that the Bézier and Dubins route improved delay times and mitigated a cascading delay effect. Full article

To enhance the precision and real-time performance of trajectory tracking control in differential-steering intelligent sweeping robots and to improve the adaptability of the control algorithm to errors caused by sensor noise, tire slip, and skid, an MPC-PID (Model Predictive Control–Proportional-Integral-Derivative) dual closed-loop control strategy was proposed. This strategy integrates a Kalman filter-based state estimator and a sliding compensation module. Based on the kinematic model of the intelligent sweeping robot, a model predictive controller (MPC) was designed to regulate the vehicle’s pose, while a PID controller was used to adjust the longitudinal speed, forming a dual closed-loop control algorithm. A Kalman filter was employed for state estimation, and a sliding compensation module was introduced to mitigate wheel slip and lateral drift, thereby improving the stability of the control system. Simulation results demonstrated that, compared to traditional MPC control, the maximum lateral deviation, maximum heading angle deviation, and speed response time were reduced by 50.83%, 53.65%, and 7.10%, respectively, during sweeping operations. In normal driving conditions, these parameters were improved by 41.58%, 45.54%, and 24.17%, respectively. Experimental validation on an intelligent sweeper platform demonstrates that the proposed algorithm achieves a 16.48% reduction in maximum lateral deviation and 9.52% faster speed response time compared to traditional MPC, effectively validating its enhanced tracking effectiveness in intelligent cleaning operations. Full article

The Global Navigation Satellite System (GNSS)/Inertial Navigation System (INS) integrated navigation technology is widely utilized in vehicle positioning. However, in complex environments such as urban canyons or tunnels, GNSS signal outages due to obstructions lead to rapid error accumulation in INS-only operation, with error growth rates reaching 10–50 m per min. To enhance positioning accuracy during GNSS outages, this paper proposes an error compensation method based on CNN-BiLSTM-Attention. When GNSS signals are available, a mapping model is established between specific force, angular velocity, speed, heading angle, and GNSS position increments. During outages, this model, combined with an improved Kalman filter, predicts pseudo-GNSS positions and their covariances in real-time to compute an aided navigation solution. The improved Kalman filter integrates Sage–Husa adaptive filtering and strong tracking Kalman filtering, dynamically estimating noise covariances to enhance robustness and address the challenge of unknown pseudo-GNSS covariances. Real-vehicle experiments conducted in a city in Jiangsu Province simulated a 120 s GNSS outage, demonstrating that the proposed method delivers a stable navigation solution with a post-convergence positioning accuracy of 0.7275 m root mean square error (RMSE), representing a 93.66% improvement over pure INS. Moreover, compared to other deep learning models (e.g., LSTM), this approach exhibits faster convergence and higher precision, offering a reliable solution for vehicle positioning in GNSS-denied scenarios. Full article

To enhance the passing capacity of the Bailongtan Ship Lock on the Hongshui River, this study focused on the design scheme of its water conveyance system reconstruction and expansion project. A three-dimensional mathematical model meeting the experimental accuracy requirements was established based on the RNG k-ε turbulence model and the Volume of Fluid (VOF) free-surface tracking method. A 1:30 scale ship lock water conveyance system physical model was built and used the independently developed system for hydraulic test monitoring, acquisition, and control. Experimental research on the hydraulic characteristics and shape optimization of the water conveyance system was carried out. The experimental results show that, under the condition of a maximum head difference of 16.0 m between the upstream and downstream of the ship lock, in the design scheme, the flow in the corridor after the filling valve fails to diffuse adequately, forming a high-velocity zone and a significant pressure difference between the inner and outer sides, which poses an operational risk. By optimizing the shape of the corridor after the valve (deepening the bottom end by 2.0 m and adjusting the turning angle from 75° to 70°), the range of the high-velocity zone can be shortened from 3.0 m to 1.5 m. The pressure difference between the inner and outer sides of the corridor at the horizontal turning section is reduced by 19.2% from 5.35 m to 4.32 m of the pressure head at the moment of maximum flow rate, and the velocity in the horizontal section is less than 15 m/s. Physical model tests confirmed these improvements, with mooring forces within safety limits (longitudinal ≤ 32 kN, transverse ≤ 16 kN). The research findings indicate that integrating numerical simulation with physical model testing can effectively mitigate risks in the original design of the ship lock water conveyance system. This approach notably enhances the reliability and safety of the design scheme, as demonstrated by the significant reduction in high-velocity zones and pressure differentials. Moreover, it offers a robust scientific basis and practical technical reference for in-depth hydraulic research and targeted optimization of ship lock water conveyance systems. Full article