Medical image datasets inherently suffer from class imbalance, label scarcity, and intra-class heterogeneity. Under semi-supervised learning, pseudo-label selection remains a central research focus. Class prototypes constructed in the latent space have been studied for pseudo-label selection, particularly because sub-class prototypes can effectively represent within-class heterogeneity in medical imaging datasets. However, since sub-class prototypes are constructed using a relatively small number of samples, they may lead to local optima during prototype updating and usage. In addition, loss weight rebalancing is commonly used to mitigate attention bias in model. Existing methods tend to focus exclusively on improving the minority class, without taking into account ambiguous samples, which are often difficult to learn and contain valuable information. Here, a prototype-driven framework PDMatch is proposed, incorporating Prototype-Driven Expert Voting (PDEV), Majority-class Pseudo-label Under-Sampling (MPUS) and Dual-Balanced Loss (DBL). First, an Expert Prototype Set is constructed, and hierarchical updating is proposed to sufficiently capture the feature distributions. PDEV then generates and filters pseudo-labels through prototype-driven voting, where multiple candidate sub-class prototypes are jointly considered. Second, MPUS offers a concise post-processing strategy that reduces imbalance in the pseudo-label distribution. Finally, Dual-Balanced Loss rebalances loss weights to jointly account for class distribution and sample difficulty. Comprehensive experiments are conducted on three datasets with distinct imbalance structures, demonstrating that our model addresses inherent data challenges and consistently outperforms state-of-the-art methods across multiple metrics. Additionally, we compare our model with clinical expert assessments to underscore its practical value in real-world applications. Source code is available at https://github.com/wang-su-lei/PDMatch .

Soft robotic devices, known for their high compliance, are increasingly being used in assistance and rehabilitation. However, the limited force output of soft actuators has hindered their broader adoption. In this study, a lobster-tail-inspired high-force-output soft pneumatic bending actuator (SPBA) is developed, featuring a soft deformable body and a rigid kirigami limiting shell. The SPBA, with a radius of 10 mm, can generate forces of approximately 22 N at an internal pressure of 0.1 MPa and 36.43 N at 0.16 MPa. An analytical model based on the Euler–Bernoulli beam theory, incorporating a hyperelastic material model, has been constructed to predict the deformation and force of the actuated SPBA. This model demonstrates good agreement with simulated and experimental results. For assistance, a soft robotic gripper with four SPBAs can lift a weight of 5.38 kg at 0.26 MPa. For rehabilitation, an SPBA-based hand exoskeleton has been developed, demonstrating significant effectiveness in mitigating hand spasticity following strokes. This study introduces a novel SPBA design with promising potential for future applications in grasping, assistance, and rehabilitation.

A new 2D dealiasing scheme has been developed to correct the aliased velocities in weather radar data. The new dealiasing scheme first chooses a reference range circle (i.e., the initial reference circle) based on a polynomial fitting of the radial velocities along azimuth. The fitted velocities in the initial reference circle are used as the reference velocities to correct velocities in the two neighboring circles. Subsequently, starting from the three reference circles, the new algorithm checks for continuities among adjacent gates and corrects the gates with a velocity difference of more than 0.8×(Nyquist velocity). Finally, an overall dealiasing is performed to correct isolated velocities and residual unprocessed velocities. The performance of the new dealiasing scheme is compared with that of the old algorithm (i.e., dealiasing starting from the selected initial reference radial) in several complex volume-scans. The results show that the new algorithm performs better, especially in isolated aliased velocities, in several large velocity-missing gaps in the azimuth, and in reducing the propagation of erroneous dealiasing. A statistical survey of 2630 volume-scans measured by the radar in Longyan, China from May to August 2016 demonstrate that the new algorithm failed to recover the aliased velocities in only 23 cases (0.87%), while the old algorithm failed to correct the aliased velocities in 38 cases (1.4%), further confirming the improved performance of the new algorithm.

Magnetically actuated miniature robots are limited in their mechanical outputting capability, because the magnetic forces decrease significantly with decreasing robot size and increasing actuating distance. Hence, the output force of these robots can hardly meet the demand for specific biomedical applications (e.g., tissue penetration). This article proposes a tetherless magnetic impact needle robot (MINRob) based on a triple-magnet system with reversible and repeatable magnetic collisions to overcome this constraint on output force. The working procedure of the proposed system is divided into several states, and a mathematical model is developed to predict and optimize the force output. These force values in magnetic impact and penetration are obtained from a customized setup, indicating a ten-fold increase compared with existing miniature robots that only utilize magnetic attractive force. Eventually, the proposed MINRob is integrated with a teleoperation system, enabling remote and precise control of the robot's position and orientation. The triple-magnet system offers promising locomotion patterns and penetration capacity via the notably increased force output, showing great potential in robot-assisted tissue penetration in minimally invasive healthcare.

In this paper, we develop a simulator that could simulate polarimetric data of airship-borne typhoon observation radar. We use the Weather Research and Forecast (WRF) model to generate a `realistic' typhoon phenomenon, combined with the T-matrix method to calculate the scattering properties. Mixtures of rain, snow, graupel and ice relative to typhoon phenomenon are considered. Polarimetric observables also depend on the angle of the incident radar beam, so we analyzed the influence of incident angles on radar observables. The simulated polarimetric observables showed a good agreement with those in previous literature.