A distinct typing interface using surface electromyography (sEMG) can facilitate silent, hands-free typing by interpreting muscle activity in relation to specific keystrokes. Character-level recognition poses greater challenges than coarse gesture recognition because it is sensitive to subtle temporal variations and overlapping muscle dynamics. Temporal features are essential for typing recognition because keypresses may differ in duration, force, and accompanying hand movements across users. This paper proposes TransTCNet, a two-stage deep neural network architecture with a causal convolutional layer for learning local features and a transformer-based component for learning long-range temporal interactions. We evaluated our network on a publicly available 26-class typing sEMG dataset acquired from 19 individuals. The model achieved a validation accuracy of 96.53%, exceeding the baseline models. Our study revealed generalization among participants, and the AUC values were also high (>0.994) across all classes. The model was highly reliable and exhibited high prediction confidence (>0.9), enabling us to achieve a high training accuracy (97.86%) for real-time filtering decisions. TransTCNet could be suitable for wearable and edge devices due to its efficient architecture and low inference cost. The model’s ability to consistently decode fine-grained neuromuscular signals across users makes it well-suited for real-time applications such as adaptive user interfaces, virtual and augmented reality, prosthetic control, and communication systems.

Soft robotic hands are well suited for handling fragile and geometrically diverse objects, yet many existing designs still rely on fixed finger layouts, which limits grasping adaptability when object size varies substantially. To address this issue, this study proposes a four-finger pneumatic soft robotic hand with a synchronous variable-stroke base mechanism. The design combines a rigid reconfigurable base with compliant soft fingers, allowing the radial positions of the fingers to be adjusted before grasping. A system-level kinematic model is established to describe the relationship between base stroke, finger bending, and the reachable workspace of the hand. A prototype is fabricated, and comparative grasping experiments are conducted under fixed-stroke and variable-stroke configurations using objects with different grasping cross-sections. The results show that the proposed mechanism achieves stable geometric reconfiguration and improves grasping performance when the initial finger spacing is matched to the object size. In particular, the variable-stroke configuration provides better grasp stability and a wider usable grasping range than the fixed-stroke configuration. These findings indicate that geometric reconfiguration at the hand level is an effective way to enhance the adaptability of multi-finger soft robotic hands.

Objective: CAD-CAM technology enables biomimetic dentistry by producing highly accurate, minimally invasive restorations that replicate the biomechanical behavior of intact teeth. This study evaluated the fracture resistance of overlays with margins at different supragingival levels, including a flat occlusal design and compared them with conventional full crowns. All restorations were fabricated from chairside CAD/CAM resin-matrix ceramic for maxillary premolars. Methods and Materials: Sixty-four CAD/CAM resin-matrix ceramic restorations were fabricated and randomly assigned to four groups (n = 16): (1) overlay with a margin 2 mm above the gingiva (Ov2m); (2) overlay with a 4 mm supragingival margin (Ov4m); (3) overlay with a 4 mm margin and flat occlusal surface (OvF4m); and (4) full-coverage crown with a gingival-level margin (FCC). Preparations were standardized by one operator. Restorations were adhesively cemented to resin dies, thermocycled 10,000 times (5–55 °C), and loaded to failure in a universal testing machine (1 mm/min). Data were analyzed using one-way ANOVA and post hoc tests (α = 0.001). Results: Among overlays, Ov2m showed the highest fracture resistance (1605 ± 88 N), followed by Ov4m (1403 ± 63 N). OvF4m recorded the lowest value (1257 ± 73 N). FCC exhibited the greatest overall resistance (1838 ± 106 N), significantly higher than that of any overlay group. Conclusions: Overlays with margins 2 mm above the gingiva had higher fracture resistance than those with more coronal margins or flat occlusal designs. Full-coverage crowns showed the greatest strength, highlighting the impact of margin position and preparation design on restoration performance.

Water scarcity constitutes a major global challenge. Biomimetic water collection materials, which mimic the efficient water capture and transport mechanisms, offer a crucial approach to addressing the water crisis. This review summarizes the research progress on biomimetic water collection materials, focusing on biological prototypes, operational mechanisms, and core aspects of biomimetic design. Typical water-collecting biological surfaces in nature exhibit distinctive structure–function synergy: spider silk achieves directional droplet transport via periodic spindle-knot structures, utilizing Laplace pressure difference and surface energy gradient; the desert beetle’s back features hydrophilic microstructures and a hydrophobic waxy coating, forming a fog-water collection system based on heterogeneous wettability; cactus spines enhance droplet transport efficiency through the synergy of gradient grooves and barbs; and shorebird beaks enable rapid water convergence via liquid bridge effects. These biological prototypes provide vital inspiration for the design of biomimetic water collection materials. Drawing on biological mechanisms, researchers have developed diverse biomimetic water collection materials. This review offers a theoretical reference for their structural design and performance enhancement, highlighting bio-inspiration’s core value in high-efficiency water collection material development. Additionally, this paper discusses challenges and opportunities of these materials, providing insights for advancing the engineering application of next-generation high-efficiency biomimetic water collection materials.

Accurate and quantitative pain assessment remains a major challenge in clinical medicine, especially for patients unable to verbalize discomfort. Conventional methods based on self-reports or clinician observation are subjective and inconsistent. This study introduces a novel automated facial pain assessment framework built on a dual-attention convolutional neural network (CNN) that achieves clinically calibrated, high-reliability performance and interpretability. The architecture combines multi-head spatial attention to localize pain-relevant facial regions with an enhanced channel attention block employing triple-pooling (average, max, and standard deviation) to capture discriminative intensity features. Regularization through label smoothing (α = 0.1) and AdamW optimization ensures calibrated, stable convergence. Evaluated on a clinically annotated dataset using subject-wise stratified sampling, the proposed model achieved a test accuracy of 90.19% ± 0.94%, with an average 5-fold cross-validation accuracy of 83.60% ± 1.55%. The model further attained an F1-score of 0.90 and Cohen’s κ = 0.876, with macro- and micro-AUCs of 0.991 and 0.992, respectively. The evaluation covers five pain classes (No Pain, Mid Pain, Moderate Pain, Severe Pain, and Very Pain) using subject-wise splits comprising 5840 total images and 1160 test samples. Comparative benchmarking and ablation experiments confirm each module’s contribution, while Grad-CAM visualizations highlight physiologically relevant facial regions. The results demonstrate a robust, explainable, and reproducible framework suitable for integration into real-world automated pain-monitoring systems. Inspired by biological pain perception mechanisms and human facial muscle responses, the proposed framework aligns with biomimetic sensing principles by emulating how localized facial cues contribute to pain interpretation.

Background: Impaired mucus drainage from the paranasal sinuses is often associated with nasal obstruction and reduced airway function in growing patients. Orthopedic maxillary protraction and expansion techniques can enhance airway dynamics, but their underlying fluid–structure mechanisms remain insufficiently understood. Objective: To validate that the Right Angle Maxillary Protraction Appliance (RAMPA), combined with a semi-rapid maxillary expansion (sRME) intraoral device gHu-1, improves mucus drainage by enhancing nasal airflow through nasal cavity expansion. Methods: The effects of RAMPA therapy were analyzed using computational fluid dynamics (CFD) for single-phase (air) and two-phase (air–mucus) flows within the nasal cavity, employing the unsteady RANS turbulence model. Finite element method (FEM) results from prior studies were synthesized to assess changes in the center and radius of maxillary rotation induced by RAMPA-assisted sRME. A male patient (aged 8 years 7 months to 11 years 7 months) treated with extraoral RAMPA and the intraoral appliance (gHu-1) underwent pre- and post-treatment cone-beam computed tomography (CBCT) and ear, nose, and throat (ENT) evaluation. Results: FEM analysis revealed an increased radius and elevated center of maxillary rotation, producing expansion that was more parallel to the palatal plane. CFD simulations showed that nasal cavity expansion increased airflow velocity and pressure drop, enhancing the suction effect that promotes mucus clearance from the frontal sinus. Clinically, nasal passages widened, paranasal opacities resolved, and occlusal and intermolar widths improved. Conclusions: RAMPA combined with sRME improves nasal airflow and maxillary skeletal expansion, facilitating paranasal mucus clearance and offering a promising adjunctive approach for enhancing upper airway function in growing patients.

With the explosive growth of data across various fields, effective data preprocessing has become increasingly critical. Evolutionary and swarm intelligence algorithms have shown considerable potential in feature selection. However, their performance often deteriorates in large-scale problems, due to premature convergence and limited exploration ability. To address these limitations, this paper proposes an algorithm named IHBOFS, a biomimetics-inspired optimization framework that integrates multiple adaptive strategies to enhance performance and stability. The introduction of the Good Point Set and Elite Opposition-Based Learning mechanisms provides the population with a well-distributed and diverse initialization. Furthermore, adaptive exploitation–exploration balancing strategies are designed for each subpopulation, effectively mitigating premature convergence. Extensive ablation studies on the CEC2022 benchmark functions verify the effectiveness of these strategies. Considering the discrete nature of feature selection, IHBOFS is further extended with continuous-to-discrete mapping functions and applied to six real-world datasets. Comparative experiments against nine metaheuristic-based methods, including Harris Hawk Optimization (HHO) and Ant Colony Optimization (ACO), demonstrate that IHBOFS achieves an average classification accuracy of 92.57%, confirming its superiority and robustness in high-dimensional feature selection tasks.

Fish display remarkable swimming capabilities through the coordinated interaction of the body and caudal fin, yet the potential role of a passively pitching tail in enhancing hydrodynamic performance remains unresolved. In this work, we evaluate the performance of a carangiform swimmer equipped with either an actively pitching tail or a passively pitching tail. High-fidelity fluid–structure interaction simulations are employed to assess how variations in joint stiffness, damping, and inertia influence thrust generation, power demand, and overall stability at two representative Reynolds numbers, 500 and 5000. The results reveal that actively pitching tails tend to generate greater thrust, while passively pitching tails deliver improved outcomes in terms of power demand at the lower Reynolds number. Larger pitching amplitudes contribute positively only when associated with higher swimming frequency; when produced by reduced inertia or more flexible joints, they lead to unfavorable effects. At the higher Reynolds number, active tails consistently outperform passive ones, although a small subset of passive cases still achieve favorable performance. Across all cases, a recurring balance emerges, with thrust production and power expenditure varying inversely. These findings clarify the hydrodynamic consequences of passive versus active tail motion and establish design principles for bio-inspired underwater vehicles, in which smaller swimmers may benefit from passive tail pitching, whereas larger swimmers are better served by active control.

This study introduces an innovative Honey Badger Optimization (HBO) designed to address the Optimal Power Flow (OPF) challenge in electrical power systems. HBO is a unique population-based searching method inspired by the resourceful foraging behavior of honey badgers when hunting for food. In this algorithm, the dynamic search process of honey badgers, characterized by digging and honey-seeking tactics, is divided into two distinct stages, exploration and exploitation. The OPF problem is formulated with objectives including fuel cost minimization and voltage deviation reduction, alongside operational constraints such as generator limits, transformer settings, and line power flows. HBO is applied to the IEEE 30-bus test system, outperforming existing methods such as Particle Swarm Optimization (PSO) and Gray Wolf Optimization (GWO) in both fuel cost reduction and voltage profile enhancement. Results indicate significant improvements in system performance, achieving 38.5% and 22.78% better voltage deviations compared to GWO and PSO, respectively. This demonstrates HBO’s efficacy as a robust optimization tool for modern power systems. In addition to the single-objective studies, a multi-objective OPF formulation was investigated to produce the complete Pareto front between fuel cost and voltage deviation objectives. The proposed HBO successfully generated a well-distributed set of trade-off solutions, revealing a clear conflict between economic efficiency and voltage quality. The Pareto analysis demonstrated HBO’s strong capability to balance these competing objectives, identify knee-point operating conditions, and provide flexible decision-making options for system operators.

In recent years, robots have started to be used in tasks involving human interaction. For this to be possible, humans must perceive robots as suitable interaction partners. This can be achieved by giving the robots an animate appearance. One of the methods that can be utilised to endow a robot with a lively appearance is giving it the ability to perform expressions on its own, that is, combining multimodal actions to convey information. However, this can become a challenge if the robot has to use gestures and speech simultaneously, as the non-verbal actions need to support the message communicated by the verbal component. In this manuscript, we present a system that, based on a robot’s utterances, predicts the corresponding gesture and synchronises it with the speech. A deep learning-based prediction model labels the robot’s speech with the types of expressions that should accompany it. Then, a rule-based synchronisation module connects different gestures to the correct parts of the speech. For this, we have tested two different approaches: (i) using a combination of recurrent neural networks and conditional random fields; and (ii) using transformer models. The results show that the proposed system can properly select co-speech gestures under the time constraints imposed by real-world interactions.