Search Results (52)

Steady-State Visual Evoked Potentials (SSVEPs) have emerged as an efficient means of interaction in brain–computer interfaces (BCIs), achieving bioinspired efficient language output for individuals with aphasia. Addressing the underutilization of frequency information of SSVEPs and redundant computation by existing transformer-based deep learning methods, this paper analyzes signals from both the time and frequency domains, proposing a stacked encoder–decoder (SED) network architecture based on an xLSTM model and spatial attention mechanism, termed SED-xLSTM, which firstly applies xLSTM to the SSVEP speller field. This model takes the low-channel spectrogram as input and employs the filter bank technique to make full use of harmonic information. By leveraging a gating mechanism, SED-xLSTM effectively extracts and fuses high-dimensional spatial-channel semantic features from SSVEP signals. Experimental results on three public datasets demonstrate the superior performance of SED-xLSTM in terms of classification accuracy and information transfer rate, particularly outperforming existing methods under cross-validation across various temporal scales. Full article

Hyperspectral imagery (HSI) has demonstrated significant potential in remote sensing applications because of its abundant spectral and spatial information. However, current mainstream hyperspectral image classification models are generally characterized by high computational complexity, structural intricacy, and a strong reliance on training samples, which poses challenges in meeting application demands under resource-constrained conditions. To this end, a lightweight hyperspectral image classification model inspired by bionic design, named BioLiteNet, is proposed, aimed at enhancing the model’s overall performance in terms of both accuracy and computational efficiency. The model is composed of two key modules: BeeSenseSelector (Channel Attention Screening) and AffScaleConv (Scale-Adaptive Convolutional Fusion). The former mimics the selective attention mechanism observed in honeybee vision for dynamically selecting critical spectral channels, while the latter enables efficient fusion of spatial and spectral features through multi-scale depthwise separable convolution. On multiple hyperspectral benchmark datasets, BioLiteNet is shown to demonstrate outstanding classification performance while maintaining exceptionally low computational costs. Experimental results show that BioLiteNet can maintain high classification accuracy across different datasets, even when using only a small amount of labeled samples. Specifically, it achieves overall accuracies (OA) of 90.02% ± 0.97%, 88.20% ± 5.26%, and 78.64% ± 7.13% on the Indian Pines, Pavia University, and WHU-Hi-LongKou datasets using just 5% of samples, 10% of samples, and 25 samples per class, respectively. Moreover, BioLiteNet consistently requires fewer computational resources than other comparative models. The results indicate that the lightweight hyperspectral image classification model proposed in this study significantly reduces the requirements for computational resources and storage while ensuring classification accuracy, making it well-suited for remote sensing applications under resource constraints. The experimental results further support these findings by demonstrating its robustness and practicality, thereby offering a novel solution for hyperspectral image classification tasks. Full article

Photoelectrochemical (PEC) sensors have garnered increasing attention due to their high sensitivity, low background signal, and rapid response. The incorporation of hydrogels into PEC platforms has significantly expanded their analytical capabilities by introducing features such as biocompatibility, tunable porosity, antifouling behavior, and mechanical flexibility. This review systematically categorizes hydrogel materials into four main types—nucleic acid-based, synthetic polymer, natural polymer, and carbon-based—and summarizes their functional roles in PEC sensors, including structural support, responsive amplification, antifouling interface construction, flexible electrolyte integration, and visual signal output. Representative applications are highlighted, ranging from the detection of ions, small biomolecules, and biomacromolecules to environmental pollutants, photodetectors, and flexible bioelectronic devices. Finally, key challenges—such as improving fabrication scalability, enhancing operational stability, integrating emerging photoactive materials, and advancing bio-inspired system design—are discussed to guide the future development of hydrogel-enhanced PEC sensing technologies. Full article

To enable intelligent inspection of underground cable systems, this study presents a gecko-inspired quadruped robot that integrates multi-degree-of-freedom motion with a deep learning-based visual detection system. Inspired by the gecko’s flexible spine and leg structure, the robot exhibits strong adaptability to confined and uneven tunnel environments. The motion system is modeled using the standard Denavit–Hartenberg (D–H) method, with both forward and inverse kinematics derived analytically. A zero-impact foot trajectory is employed to achieve stable gait planning. For defect detection, the robot incorporates a binocular vision module and an enhanced YOLOv8 framework. The key improvements include a lightweight feature fusion structure (SlimNeck), a multidimensional coordinate attention (MCA) mechanism, and a refined MPDIoU loss function, which collectively improve the detection accuracy of subtle defects such as insulation aging, micro-cracks, and surface contamination. A variety of data augmentation techniques—such as brightness adjustment, Gaussian noise, and occlusion simulation—are applied to enhance robustness under complex lighting and environmental conditions. The experimental results validate the effectiveness of the proposed system in both kinematic control and vision-based defect recognition. This work demonstrates the potential of integrating bio-inspired mechanical design with intelligent visual perception to support practical, efficient cable inspection in confined underground environments. Full article

Biomimetic lattice structures, inspired by natural architectures such as bone, coral, mollusk shells, and Euplectella aspergillum, have gained increasing attention for their exceptional strength-to-weight ratios, energy absorption, and deformation control. These properties make them ideal for advanced engineering applications in aerospace, biomedical devices, and structural impact protection. This study presents a comprehensive bibliometric analysis of global research on biomimetic lattice structures published between 2020 and 2025, aiming to identify thematic trends, collaboration patterns, and underexplored areas. A curated dataset of 3685 publications was extracted from databases like PubMed, Dimensions, Scopus, IEEE, Google Scholar, and Science Direct and merged together. After the removal of duplication and cleaning, about 2226 full research articles selected for the bibliometric analysis excluding review works, conference papers, book chapters, and notes using Cite space, VOS viewer version 1.6.20, and Bibliometrix R packages (4.5. 64-bit) for mapping co-authorship networks, institutional affiliations, keyword co-occurrence, and citation relationships. A significant increase in the number of publications was found over the past year, reflecting growing interest in this area. The results identify China as the most prolific contributor, with substantial institutional support and active collaboration networks, especially with European research groups. Key research focuses include additive manufacturing, finite element modeling, machine learning-based design optimization, and the performance evaluation of bioinspired geometries. Notably, the integration of artificial intelligence into structural modeling is accelerating a shift toward data-driven design frameworks. However, gaps remain in geometric modeling standardization, fatigue behavior analysis, and the real-world validation of lattice structures under complex loading conditions. This study provides a strategic overview of current research directions and offers guidance for future interdisciplinary exploration. The insights are intended to support researchers and practitioners in advancing next-generation biomimetic materials with superior mechanical performance and application-specific adaptability. Full article

Wall-climbing robots have garnered significant attention for their ability to operate in hazardous environments. Among these, bioinspired gecko robots exhibit exceptional adaptability and climbing performance due to their flexible morphology and intelligent motion strategies. This review systematically analyzes studies published between 2000–2025, sourced from IEEE Xplore, Web of Science, and Scopus databases, to explore the biological principles of gecko adhesion and locomotion. A structured literature review methodology is employed, through which representative climbing robots are systematically categorized based on spine flexibility (rigid vs. flexible) and attachment mechanisms (adhesive, suction, claw-based). We analyze various motion control strategies, from hierarchical architectures to advanced neural algorithms, with a focus on central pattern generator (CPG)-based systems. By synthesizing current research and technological advancements, this paper provides a roadmap for developing more efficient, adaptive, and intelligent wall-climbing robots, addressing key challenges and future directions in the field. Full article

Antibody lead discovery, crucial for immunotherapy development, requires identifying candidates with potent binding affinities to target antigens. Recent advances in protein language models have opened promising avenues to tackle this challenge by predicting antibody–antigen interactions (AAIs). Despite their appeals, precisely detecting binding sites (i.e., paratopes and epitopes) within the complex landscape of long-sequence biomolecules remains challenging. Herein, we propose MambaAAI, a bio-inspired model built upon the Mamba architecture, designed to predict AAIs and identify binding sites through selective attention mechanisms. Technically, we employ ESM-2, a pre-trained protein language model to extract evolutionarily enriched representations from input antigen and antibody sequences, which are modeled as residue-level interaction matrixes. Subsequently, a dual-view Mamba encoder is devised to capture important binding patterns, by dynamically learning embeddings of interaction matrixes from both antibody and antigen perspectives. Finally, the learned embeddings are decoded using a multilayer perceptron to output interaction probabilities. MambaAAI provides a unique advantage, relative to prior techniques, in dynamically selecting bio-enhancing residue sites that contribute to AAI prediction. We evaluate MambaAAI on two large-scale antibody–antigen neutralization datasets, and in silico results demonstrate that our method marginally outperforms the state-of-the-art baselines in terms of prediction accuracy, while maintaining robust generalization to unseen antibodies and antigens. In further analysis of the selective attention mechanism, we found that MambaAAI successfully uncovers critical epitope and paratope regions in the SARS-CoV-2 antibody examples. It is believed that MambaAAI holds great potential to discover lead candidates targeting specific antigens at a lower burden. Full article

The rapidly evolving field of functional yarns has garnered substantial research attention due to their exceptional potential in enabling next-generation electronic textiles for wearable health monitoring, human–machine interfaces, and soft robotics. Despite notable advancements, the development of yarn-based strain sensors that simultaneously achieve high flexibility, stretchability, superior comfort, extended operational stability, and exceptional electrical performance remains a critical challenge, hindered by material limitations and structural design constraints. Here, we present a bioinspired, hierarchically structured core-sheath yarn sensor (CSSYS) engineered through an efficient dip-coating process, which synergistically integrates the two-dimensional conductive MXene nanosheets and one-dimensional silver nanowires (AgNWs). Furthermore, the sensor is encapsulated using a yarn-based protective layer, which not only preserves its inherent flexibility and wearability but also effectively mitigates oxidative degradation of the sensitive materials, thereby significantly enhancing long-term durability. Drawing inspiration from the natural architecture of plant stems—where the inner core provides structural integrity while a flexible outer sheath ensures adaptive protection—the CSSYS exhibits outstanding mechanical and electrical performance, including an ultralow strain detection limit (0.05%), an ultrahigh gauge factor (up to 744.45), rapid response kinetics (80 ms), a broad sensing range (0–230% strain), and exceptional cyclic stability (>20,000 cycles). These remarkable characteristics enable the CSSYS to precisely capture a broad spectrum of physiological signals, ranging from subtle arterial pulsations and respiratory rhythms to large-scale joint movements, demonstrating its immense potential for next-generation wearable health monitoring systems. Full article

Insect flight mechanisms are highly efficient and involve complex hinge structures that facilitate amplified wing movement through thoracic deformation. However, in the field of flapping-wing robots, the replication of thoracic skeletal structures has received little attention. In this study, we propose and compare two different hinge models inspired by insect flight: an elastic hinge model (EHM) and an axle hinge model (AHM). Both models were fabricated using 3D printing technology using PLA material. The EHM incorporates flexible structures in both the hinge and lateral scutum regions, allowing for deformation-driven wing motion. In contrast, the AHM employs metal pins in the hinge region to reproduce joint-like articulation, while still permitting elastic deformation in the lateral scutum. To evaluate their performance, we employed an SMA actuator to generate flapping motion, and measured the wing displacement, flapping frequency, and exoskeletal deformation. The experimental results demonstrate that the EHM achieves wing flapping through overall structural flexibility, whereas the AHM provides more defined hinge motion while maintaining exoskeletal elasticity. These findings contribute to our understanding of the role of hinge mechanics in bioinspired flapping-wing robots. Future research will focus on optimizing these mechanisms for higher frequency operation, weight reduction, and better energy efficiency. Full article

Optimization techniques aim to identify optimal solutions for a given problem. In single-objective optimization, the best solution corresponds to the one that maximizes or minimizes the objective function. However, when dealing with multi-objective optimization, particularly when the objectives are conflicting, identifying the best solution becomes significantly more complex. In such cases, exact or analytical methods are often impractical, leading to the widespread use of heuristic and metaheuristic approaches to identify optimal or near-optimal solutions. Recent advancements have led to the development of various nature-inspired metaheuristics designed to address these challenges. Among these, the Whale Optimization Algorithm (WOA) has garnered significant attention. An adapted version of the WOA has been proposed to handle multi-objective optimization problems. This work extends the WOA to tackle multi-objective optimization by incorporating a decomposition-based approach with a cooperative mechanism to approximate Pareto-optimal solutions. The multi-objective problem is decomposed into a series of scalarized subproblems, each with a well-defined neighborhood relationship. Comparative experiments with seven state-of-the-art bio-inspired optimization methods demonstrate that the proposed decomposition-based multi-objective WOA consistently outperforms its counterparts in both real-world applications and widely used benchmark test problems. Full article

Artificial intelligence, with its remarkable adaptability, has gradually integrated into daily life. The emergence of the self-attention mechanism has propelled the Transformer architecture into diverse fields, including a role as an efficient and precise diagnostic and predictive tool in medicine. To enhance accuracy, we propose the Double-Attention (DA) method, which improves the neural network’s biomimetic performance of human attention. By incorporating matrices generated from shifted images into the self-attention mechanism, the network gains the ability to preemptively acquire information from surrounding regions. Experimental results demonstrate the superior performance of our approaches across various benchmark datasets, validating their effectiveness. Furthermore, the method was applied to patient kidney datasets collected from hospitals for diabetes diagnosis, where they achieved high accuracy with significantly reduced computational demands. This advancement showcases the potential of our methods in the field of biomimetics, aligning well with the goals of developing innovative bioinspired diagnostic tools. Full article

In this research, inspired by the principles of biological visual attention mechanisms and swarm intelligence found in nature, we present an Enhanced Self-Correlation Attention and Multi-Branch Joint Module Network (EMNet), a novel model for few-shot image classification. Few-shot image classification aims to address the problem of image classification when data are limited. Traditional models require a large amount of labeled data for training, while few-shot learning trains models using only a small number of samples (just a few samples per class) to recognize new categories. EMNet shows its potential for bio-inspired algorithms in optimizing feature extraction and enhancing generalization capabilities. It features two key modules: Enhanced Self-Correlated Attention (ESCA) and Multi-Branch Joint Module (MBJ Module). EMNet tackles two main challenges in few-shot learning: how to make an effective important feature extraction and enhancement in images, and improving generalization to new categories. The ESCA module boosts the precision in extracting crucial local features, enhancing classification accuracy. The MBJ module focuses on shared features across images, emphasizing similarities within classes and subtle differences between them. This enhances model adaptability and generalization to new categories. Experimental results show that our model performs better than existing models in one-shot and five-shot tasks on mini-ImageNet, CUB-200, and CIFAR-FS datasets, which proves the proposed model to be an efficient end-to-end solution for few-shot image classification. In the five-way one-shot and five-way five-shot experiments on the CUB-200-2011 dataset, EMNet achieved classification accuracies that were 1.27 and 0.54 percentage points higher than those of RENet, respectively. In the five-way one-shot and five-way five-shot experiments on the miniImageNet dataset, EMNet’s classification accuracies were 0.02 and 0.48 percentage points higher than those of RENet, respectively. In the five-way one-shot and five-way five-shot experiments on the CIFAR-FS dataset, EMNet’s classification accuracies were 0.19 and 0.18 percentage points higher than those of RENet. Full article

In recent years, additive manufacturing has reached the required reliability to effectively compete with standard production techniques of mechanical components. In particular, the geometrical freedom enabled by innovative manufacturing techniques has revolutionized the design trends for compact heat exchangers. Bioinspired structures, such as the gyroid lattice, have relevant mechanical and heat exchange properties for their light weight and increased heat exchange area, which also promotes the turbulent regime of the coolant. This work focuses its attention on the effect of the relevant design parameters of the gyroid lattice on heat exchange performances. A numerical comparative analysis is carried out from the thermal and fluid dynamic points of view to give design guidelines. The results of numerical analyses, performed on cylindrical samples, are compared to the experimental results on the pressure drop. Lattices samples were successfully printed with material extrusion, which is a low-cost and easy-to-use metal AM technology. For each lattice sample, counter pressure, heat exchange, and turbulence intensity ratio are calculated from the numerical point of view and discussed. At the end, the gyroid lattice is proven to be very effective at enhancing the heat exchange in cylindrical pipes. Guidelines are given about the choice of the best lattice, depending on the considered applications. Full article

The impressive adhesive capacity of marine mussels has inspired various fascinating designs in biomedical fields. Mussel-inspired injectable adhesive hydrogels, as a type of promising mussel-inspired material, have attracted much attention due to their minimally invasive property and desirable functions provided by mussel-inspired components. In recent decades, various mussel-inspired injectable adhesive hydrogels have been designed and widely applied in numerous biomedical fields. The rational incorporation of mussel-inspired catechol groups endows the injectable hydrogels with the potential to exhibit many properties, including tissue adhesiveness and self-healing, antimicrobial, and antioxidant capabilities, broadening the applications of injectable hydrogels in biomedical fields. In this review, we first give a brief introduction to the adhesion mechanism of mussels and the characteristics of injectable hydrogels. Further, the typical design strategies of mussel-inspired injectable adhesive hydrogels are summarized. The methodologies for integrating catechol groups into polymers and the crosslinking methods of mussel-inspired hydrogels are discussed in this section. In addition, we systematically overview recent mussel-inspired injectable adhesive hydrogels for biomedical applications, with a focus on how the unique properties of these hydrogels benefit their applications in these fields. The challenges and perspectives of mussel-inspired injectable hydrogels are discussed in the last section. This review may provide new inspiration for the design of novel bioinspired injectable hydrogels and facilitate their application in various biomedical fields. Full article

The back support exoskeletons have garnered significant attention to alleviate musculoskeletal injuries, prevalent in industrial settings. In this paper, we propose AeBS, a quasi-passive back-support exoskeleton developed to provide variable assistive torque across the entire range of hip joint motion, for tasks with frequent load changes. AeBS can adjust the assistive torque levels while minimizing energy for the torque variation without constraining the range of motion of the hip joint. To match the requisite assistance levels for back support, a compact variable gravity compensation module with reinforced elastic elements is applied to AeBS. Additionally, we devised a bio-inspired hip joint mechanism that mimics the configuration of the human hip axis to ensure the free body motion of the wearer, significantly affecting assistive torque transmission and wearing comfort. Benchtop testing showed that AeBS has a variable assistive torque range of 5.81 Nm (ranging from 1.23 to 7.04 Nm) across a targeted hip flexion range of 135°. Furthermore, a questionnaire survey revealed that the bio-inspired hip joint mechanism effectively facilitates the transmission of the intended assistive torque while enhancing wearer comfort. Full article