As a kind of ionic artificial muscle material, Ionic Polymer–Metal Composites (IPMCs) have the advantages of a low drive current, light weight, and significant flexibility. IPMCs are widely used in the fields of biomedicine, soft robots, etc. However, the displacement and blocking force of the traditional sheet-type Nafion-IPMC need to be improved, and it has the limitation of unidirectional actuation. In this paper, a new type of short side chain Aquivion material is used as the polymer in the IPMC. The cylindrical IPMC is prepared by extrusion technology to improve its actuation performance and realize multi-degree-of-freedom motion. In comparison to the traditional Nafion-IPMC, the ion exchange capacity, specific capacitance, and conductivity of Aquivion-IPMC are improved by 28%, 27%, and 32%, respectively, and the displacement and blocking force are improved by 57% and 25%, respectively. The cylindrical actuators can be deflected in eight directions. This indicates that Aquivion, as a polymer membrane for IPMC, holds significant application potential. By designing a cylindrical IPMC electrode distribution, the multi-degree-of-freedom deflection of IPMC can be realized.

Flexible sensors, a class of devices that can convert external mechanical or physical signals into changes in resistance, capacitance, or current, have developed rapidly since the concept was first proposed. Due to the special properties and naturally occurring excellent microstructures of biomaterials, it can provide more desirable properties to flexible devices. This paper systematically discusses the commonly used biomaterials for bio-based flexible devices in current research applications and their deployment in preparing flexible sensors with different mechanisms. According to the characteristics of other properties and application requirements of biomaterials, the mechanisms of their functional group properties, special microstructures, and bonding interactions in the context of various sensing applications are presented in detail. The practical application scenarios of biomaterial-based flexible devices are highlighted, including human-computer interactions, energy harvesting, wound healing, and related biomedical applications. Finally, this paper also reviews in detail the limitations of biobased materials in the construction of flexible devices and presents challenges and trends in the development of biobased flexible sensors, as well as to better explore the properties of biomaterials to ensure functional synergy within the composite materials.

Bipolar plate is one of the key components of Proton Exchange Membrane Fuel Cell (PEMFC) and a reasonable flow field design for bipolar plate will improve cell performance. Herein, we have reviewed conventional and bionic flow field designs in recent literature with a focus on bionic flow fields. In particular, the bionic flow fields are summarized into two types: plant-inspired and animal-inspired. The conventional methodology for flow field design takes more time to find the optimum since it is based on experience and trial-and-error methods. In recent years, machine learning has been used to optimize flow field structures of bipolar plates owing to the advantages of excellent prediction and optimization capability. Artificial Intelligence (AI)-assisted flow field design has been summarized into two categories in this review: single-objective optimization and multi-objective optimization. Furthermore, a Threats-Opportunities-Weaknesses-Strengths (TOWS) analysis has been conducted for AI-assisted flow field design. It has been envisioned that AI can afford a powerful tool to solve the complex problem of bionic flow field design and significantly enhance the performance of PEMFC with bionic flow fields.

Lizards are one of the most primitive reptiles in existence, with special limb structures that enable them to move quickly across diverse and complex terrains such as rock piles, shallow shoals, and deserts. A thorough exploration was conducted on the biomimetic mechanism and ground-touching mechanism of lizard limbs from both micro and macro perspectives. Inspired by the intricate torso and limb configurations of lizards, a novel Torso-leg-foot biomimetic robot has been conceptualized based on the design of the Big-Foot robot. This robot integrates a Torso-leg-foot system, featuring a parallel torso biomimetic structure with a 2-SPR/UPU/UPR(P) configuration. It utilizes the theory of finite screws to articulate the instantaneous movements of the parallel torso, and the inverse kinematics of this mechanism have been calculated. The reachable workspace of the 2-SPR/UPU/UPR parallel mechanism using FIS theory, which is closely related to the climbing height of the robot. A comprehensive dimension synthesis was conducted on the leg-foot system, and the adoption of the three-pair rod drive method was determined by investigating its Variable Rotating Velocity Characteristics (VRVC). Simulation tests have shown that with an integrated torso, the robot can climb vertical obstacles up to 600 mm in height. The experimental tests of climbing steps and slopes using physical prototypes have confirmed the robot’s obstacle-crossing capability. The potential applications of this Torso-leg-foot biomimetic robot is to carry heavy objects across obstacles to perform tasks such as planetary exploration and disaster relief.

Gecko-inspired robots have significant potential applications; however, deviations in the yaw direction during locomotion are inevitable for legged robots that lack external sensing. These deviations cause the robot to stray from its intended path. Therefore, a cost-effective and straightforward solution is essential for reducing this deviation. In nature, the tail is often used to maintain balance and stability. Similarly, it has been used in robots to improve manoeuvrability and stability. Our aim is to reduce this deviation using a morphological computation approach, specifically by adding a tail. To test this hypothesis, we investigated four different tails (rigid plate, rigid gecko-shaped, soft plate, and soft gecko-shaped) and assessed the deviation of the robot with these tails on different slopes. Additionally, to evaluate the influence of different tail parameters, such as material, shape, and linkage, we investigated the locomotion performance in terms of the robot’s climbing speed on slopes, its ability to turn at narrow corners, and the resistance of the tails to external disturbances. A new auto-reset joint was designed to ensure that a disturbed tail could be quickly reset. Our results demonstrate that the yaw deviation of the robot can be reduced by applying a tail. Among the four tails, the soft gecko-shaped tail was the most effective for most tasks. In summary, our findings demonstrate the functional role of the tail in reducing yaw deviation, improving climbing ability and stability and provide a reference for selecting the most suitable tail for gecko-inspired robots.

Pneumatic soft robots have undergone significant advancements in recent years. However, the majority of robot motion control still relies on electronic computers to regulate the valves and air pumps. Despite the potential reduction in controller dependency by utilizing soft pneumatic oscillators, challenges such as low flow rates, complex manufacturing processes, and lack of adjustment ability persist. Inspired by the geckos’ spine, we propose a Spinal Bistable Oscillator (SBO) that operates without discrete components or electronic control hardware, achieving stable oscillatory motion under constant air pressure. This oscillator employs a soft control valve and lagging pin, which can switch the direction of airflow conduction based on the oscillation angle of the spine. Different types of actuators can be controlled using a series connection. In this study, the effective working range of the soft control valve, influence of the spring pretension force on the torque during oscillation, and effect of different throttle tube lengths on the oscillation frequency were investigated. Furthermore, a self-crawling robot was developed. Experimental results demonstrate that the robot can crawl at speeds ranging from 3.6 to 5.7 mm/s (or 3.1 to 4.9 body length/min) and overcome its own gravity (with a weight of 165 g) to climb vertically. The SBO proposed in this study exhibits characteristics of lightweight, low cost, high oscillation torque, and tunable frequency. It holds promise for application in joint control of future pneumatic soft robots.

Achieving robust walking for different stairs is one of the most challenging tasks for quadruped robots in real world. Traditional model-based methods heavily rely on environmental factors, are burdened by intricate modelling complexities, and lack generalizability. The potential for advancements in adaptive locomotion control, often impeded by complex modelling processes, can be substantially enhanced through the application of Reinforcement Learning (RL). In this paper, a learning-based method is proposed to directionally enhance the stair-climbing skill of quadruped robots under different stair conditions. First, the general policy model based on proprioceptive perception is trained as a pre-training model. Then, the pre-training model was initialized, and different terrain information from the stairs was introduced for customized training to enhance the stair-climbing skill without affecting the existing locomotion performance. Finally, the customized control policy is deployed to the real robot to realize motion control in real environments. The experimental results demonstrate that the customized control policy can significantly improve the motion performance of quadruped robots when facing complex stair terrains and has certain generalizability in other complex terrains. The proposed algorithm can be extended to various terrestrial environments.

Animals exhibit remarkable mobility and adaptability to their environments. Leveraging these advantages, various types of robots have been developed. To achieve path tracking control for the underwater hexapod robot, a path tracking control system has been designed. Within this system, a Line-of-Sight (LOS) guidance system is utilized to generate the desired heading angle during the path tracking process. A heading tracking controller and a speed tracking controller are designed based on the super-twisting sliding mode method. Fuzzy logic is employed to establish the nonlinear relationship between the output of the upper-level controller, which includes force/torque, and the input parameters of the Central Pattern Generator (CPG) network. Finally, the effectiveness of the proposed method is verified through simulation and experimentation. The results demonstrate that the robot exhibits good tracking accuracy, as well as stability and coordination in motion. The designed path tracking system enables the underwater hexapod robot to rapidly and accurately track the desired path.

Walking is the basic locomotion pattern for bipedal robots. The walking pattern is widely generated using the linear inverted pendulum model. The linear inverted pendulum motion of each support period can be designed as a walk primitive to be connected to form a walking trajectory. A novel method of integrating double support phase into the walk primitive was proposed in this article. The method describes the generation of walking patterns using walk primitives with double support, specifically for lateral plane including walking in place, walking for lateral, and walking initiation, and for sagittal plane including fixed step length walking, variable step length walking, and walking initiation. Compared to walk primitives without double support phase, those with double support phase reduce the maximum speed required by the robot and eliminate the need to adjust foothold for achieving continuous speed. The performance of the proposed method is validated by simulations and experiments on Neubot, a position-controlled biped robot.

Flapping-Wing Air Vehicles (FWAVs) have been developed to pursue the efficient, agile, and quiet flight of flying animals. However, unlike lightweight FWAVs capable of vertical takeoff, relatively heavy FWAVs face challenges in self-takeoff, which refers to taking off without both external device and energy input. In this study, a cliff-drop method is implemented for an independent takeoff of a heavy FWAV, relying solely on gravity. In the takeoff process using the cliff-drop method, the FWAV moves on the ground to a cliff edge using a wheel-driving motor and then descends from the cliff to achieve the necessary speed for flight. To demonstrate the cliff-drop method, the KAIST Robotic Hawk (KRoHawk) with a mass of 740 g and a wingspan of 120 cm is developed. The takeoff tests demonstrate that the KRoHawk, significantly heavier than the vertical-takeoff capable FWAVs, can successfully take off using the gravity-assisted takeoff method. The scalability of cliff-drop method is analyzed through simulations. When drop constraints are absent, the wheel-driving motor mass fraction for cliff-drop method remains negligible even as the vehicle’s weight increases. When drop constraints are set to 4 m, FWAVs heavier than KRoHawk, weighing up to 4.4 kg, can perform the cliff-drop takeoffs with a wheel-driving motor mass fraction of less than 8%.

The human thumb plays a crucial role in performing coordinated hand movements for precise tool use. However, quantifying and interpreting the kinematics and couplings of the six degrees of freedom (6DOF) between the interphalangeal (IP) and metacarpophalangeal (MCP) joints during hand functional tasks remains challenging. To address this issue, advanced dynamic biplane radiography combined with a model-based 2D–3D tracking technique was employed to decode the inherent kinematics of the thumb IP and MCP joints during key pinch, tip pinch, palmar pinch and wide grasp. The results indicate that the functional tasks of the thumb are intricately modulated by the 3D rotational and translational motions of the IP and MCP joints. The IP joint exhibited the greatest flexion/extension range of motion during the tip pinch task (67.2° ± 8.4°), compared to smaller ranges in key pinch (27.6° ± 3.8°) and wide grasp (16.2° ± 7.1°) tasks. In the wide grasp task, the IP joint showed more movement in the radius/ulna direction (3.4?±?1.2 mm) compared to tip pinch (3.1?±?0.8 mm). Furthermore, the kinematic data of the IP joint challenge the traditional notion that the IP joint normally acts as a hinge mechanism. The results of this study help to elucidate the kinematics of human thumb IP and MCP joints and may provide new inspiration for the design of high-performance bionic hands or thumb prosthetics as well as for evaluating the outcomes of thumb therapeutic interventions and surgical procedures.

Moles exhibit highly effective capabilities due to their unique body structures and digging techniques, making them ideal models for biomimetic research. However, a major challenge for mole-inspired robots lies in overcoming resistance in granular media when burrowing with forelimbs. In the absence of effective forepaw design strategies, most robotic designs rely on increased power to enhance performance. To address this issue, this paper employs Resistive Force Theory to optimize mole-inspired forepaws, aiming to enhance burrowing efficiency. By analyzing the relationship between geometric parameters and burrowing forces, we propose several forepaw design variations. Through granular resistance assessments, an effective forepaw configuration is identified and further refined using parameters such as longitudinal and transverse curvature. Subsequently, the Particle Swarm Optimization algorithm is applied to determine the optimal forepaw design. In force-loading tests, the optimized forepaw demonstrated a 79.44% reduction in granular lift force and a 22.55% increase in propulsive force compared with the control group. In robotic burrowing experiments, the optimized forepaw achieved the longest burrow displacement (179.528 mm) and the lowest burrowing lift force (0.9355 mm/s), verifying its effectiveness in reducing the lift force and enhancing the propulsive force.

This paper presents a continuum manipulator inspired by the anatomical characteristics of the elephant trunk. Specifically, the manipulator mimics the conoid profile of the elephant trunk, which helps to enhance its strength. The design features two concentric parts: inner pneumatically actuated bellows and an outer tendon-driven helical spring. The tendons control the omnidirectional bending of the manipulator, while the fusion of the pneumatic bellows with the tendon-driven spring results in an antagonistic actuation mechanism that provides the manipulator with variable stiffness and extensibility. This paper presents a new design for extensible manipulator and analyzes its stiffness and motion characteristics. Experimental results are consistent with theoretical analysis, thereby demonstrating the validity of the theoretical approach and the versatile practical mechanical properties of the continuum manipulator. The impressive extensibility and variable stiffness of the manipulator were further demonstrated by performing a pin-hole assembly task.

Tendon-driven robots have distinct advantages in high-dynamic performance motion and high-degree-of-freedom manipulation. However, these robots face challenges related to control complexity, intricate tendon drive paths, and tendon slackness. In this study, the authors present a novel modular tendon-driven actuator design that integrates a series elastic element. The actuator incorporates a unique magnetic position sensing technology that enables observation of the length and tension of the tendon and features an exceptionally compact design. The modular architecture of the tendon-driven actuator addresses the complexity of tendon drive paths, while the tension observation functionality mitigates slackness issues. The design and modeling of the actuator are described in this paper, and a series of tests are conducted to validate the simulation model and to test the performance of the proposed actuator. The model can be used for training robot control neural networks based on simulation, thereby overcoming the challenges associated with controlling tendon-driven robots.

This study investigated the validity and sensitivity of a custom-made shoelace tensile testing system. The aim was to analyze the distribution pattern of shoelace tension in different positions and under different tightness levels during running. Mechanical tests were conducted using 16 weights, and various statistical analyses, including linear regression, Bland-Altman plots, coefficient of variation, and intraclass correlation coefficient, were performed to assess the system’s validity. Fifteen male amateur runners participated in the study, and three conditions (loose, comfortable, and tight) were measured during an upright stance. The system utilized VICON motion systems, a Kistler force plate, and a Photoelectric gate speed measurement system. Results showed a linear relationship between voltage and load at the three sensors (R2?≥?0.9997). Bland-Altman plots demonstrated 95% prediction intervals within ±?1.96SD from zero for all sensors. The average coefficient of variation for each sensor was less than 0.38%. Intraclass correlation coefficient values were larger than 0.999 (p<0.0001) for each sensor. The peak tension of the front shoelace was greater than that of the front and middle when the shoelace was loose and tight. The rear shoelace had the highest tension force. The study also found that shoelace tension varied throughout the gait cycle during running. Overall, this research provides a novel and validated method for measuring shoelace tensile stress, which has implications for developing automatic shoelace fastening systems.

Musculoskeletal Symptoms (MSS) often arise from prolonged maintenance of bent postures in the neck and trunk during surgical procedures. To prevent MSS, a passive exoskeleton utilizing carbon fiber beams to offer support to the neck and trunk was proposed. The application of support force is intended to reduce muscle forces and joint compression forces. A nonlinear mathematical model for the neck and trunk support beam is presented to estimate the support force. A validation test is subsequently conducted to assess the accuracy of the mathematical model. Finally, a preliminary functional evaluation test is performed to evaluate movement capabilities and support provided by the exoskeleton. The mathematical model demonstrates an accuracy for beam support force within a range of 0.8–1.2 N Root Mean Square Error (RMSE). The exoskeleton was shown to allow sufficient Range of Motion (ROM) for neck and trunk during open surgery training. While the exoskeleton showed potential in reducing musculoskeletal load and task difficulty during simulated surgery tasks, the observed reduction in perceived task difficulty was deemed non-significant. This prompts the recommendation for further optimization in personalized adjustments of beams to facilitate improvements in task difficulty and enhance comfort.

Shape Memory Polymers (SMPs) need to be given a temporary shape in advance to realize the shape memory process, but the manual shaping process is cumbersome and has low precision. Here, we propose a universal applicable method for 4D printing self-folding SMPs by pre-stretching extruded filaments during 3D printing, the temporary shape of the SMPs were designed and fixed during 3D printing. Prepared samples can automatically perform shape memory process under stimulation without manual temporary shape programming process. Furthermore, using carbon ink as a photothermal conversion agent enables the 4D printing SMPs to have thermal and light response characteristics. In addition, some bionic applications of self-folding SMPs were demonstrated, such as self-morphing grasper, DNA double helix structures, programmable sequential switching mimosa, self-folding box and human hand. The combination of SMP and 3D printing fully takes advantage of 4D printing technology, and the self-folding SMPs show great potential applications in the fields of tissue engineering scaffold, self-folding robots, self-assembly system and so on.

Flexible piezoresistive pressure sensors have attracted much attention for applications in health monitoring and human-machine interfaces due to their simple device structures and easy-to-read signals. For practical applications, the deployment of flexible pressure sensors characterized by high sensitivity and fast response time is imperative for the rapid and accurate detection and monitoring of tiny signals. Such capabilities are essential for facilitating immediate feedback and informed decision-making across a spectrum of contexts. Drawing lessons from the hypersensitive and fast-responding pressure sensing structures in the dragonfly’s neck (for stable imaging during its highly maneuverable flight), a Biomimetic Piezoresistive Pressure Sensor (BPPS) with exquisite mechanically interlocking sensing microstructures is developed. Each interlocking perceptual structure pair consists of an ox-horn-shaped and a mushroom-shaped structural unit. Through the characteristic configuration of the perceptual structure pair, the BPPS realizes a fast gradient accumulation of the contact area, thus synergistically enhancing the sensitivity and fast response capability. Remarkably, the sensitivity of the BPPS reaches 0.35 kPa^??1, which increased by 75% compared to the 0.2 kPa^??1 of the pressure sensors without biomimetic structures. Moreover, the BPPS also achieves rapid response/recovery times (<?90/15 ms). Our BPPS finds utility in tasks such as identifying objects of different weights, monitoring human respiratory status, and tracking motion, demonstrating its potential in wearable healthcare devices, assistive technology, and intelligent soft robotics. Moreover, it possesses the advantages of high sensitivity and fast response time in practical applications.

The connection efficiency of composite pre-tightened multi-tooth joint is low because of uneven load distribution and single load transmission path. In this paper, based on the principle of bio-tooth (suture) structure, combining soft material with fractal, a composite pre-tightened multi-hierarchy tooth joint is proposed, and the bearing performance and failure process of the joint through experiments and finite element method under tensile load. First, the ultimate bearing capacity, load distribution ratio, and failure process of different hierarchies of teeth joints are studied through experiments. Then, the progressive damage models of different hierarchies of tooth joints are established, and experiments verify the validity of the finite element model. Finally, the effects of soft material and increasing tooth hierarchy on the failure process and bearing capacity of composite pre-tightened tooth joints are analyzed by the finite element method. The following conclusions can be drawn: (1) The embedding of soft materials changed the failure process of the joint. Increasing the tooth hierarchy can give the joint more load transfer paths, but the failure process of the joint is complicated. (2) Embedding soft materials and increasing the tooth hierarchy simultaneously can effectively improve the bearing capacity of composite pre-tightened tooth joints, which is 87.8% higher than that of traditional three-tooth joints.

Insufficient interfacial activity and poor wettability between fibers and matrix are the two main factors limiting the improvement of mechanical properties of Carbon Fiber Reinforced Plastics (CFRP). Owl feathers are known for their unique compact structure; they are not only lightweight but also strong. In this study, an in-depth look at owl feathers was made and it found that owl feathers not only have the macro branches structure between feather shafts and branches but also have fine feather structures on the branches. The presence of these fine feather structures increases the specific surface area of the plume branches and allows neighboring plume branches to hook up with each other, forming an effective mechanical interlocking structure. These structures bring owl feathers excellent mechanical properties. Inspired by the natural structure of owl feathers, a weaving technique and a sizing process were combined to prepare bionic Carbon Fiber (CF) fabrics and then to fabricate the bionic CFRP with structural characteristics similar to owl feathers. To evaluate the effect of the fine feather structure on the mechanical properties of CFRP, a mechanical property study on CFRP with and without the fine feather imitation structure were conducted. The experimental results show that the introduction of the fine feather branch structure enhance the mechanical properties of CFRP significantly. Specifically, the tensile strength of the composites increased by 6.42% and 13.06% and the flexural strength increased by 8.02% and 16.87% in the 0° and 90° sample directions, respectively. These results provide a new design idea for the improvement of the mechanical properties of the CFRP, promoting the application of CFRP in engineering fields, such as automotive transportation, rail transit, aerospace, and construction.

Serving as the initiating explosive devices between the propellant tank and the engines, metal-based rupture diaphragms are widely used in ramjet igniters owing to the advantages provided by their simple structure, small size, and low cost. However, the reliability of rupture pressure directly affects the success of engine ignition and rocket launch, which is mainly influenced by factors like material, structure, and residual thickness of the surface notch of the diaphragm. Among those, the geometry of the notch is easy to define and control when compared to the mechanical parameters of the ruptured diaphragm. Thus, to make the diaphragm rupture (1A30 Al) within the required pressure range (0.4 MPa?±?3.5%) with highly sensitive and reliability, we draw inspiration from the arthropod’s force-sensitive slit organ which encompasses curved microgrooves to design a Ω-shaped notch for the rupture diaphragm. Finite element analysis is used to study the relationship between the burst pressure and geometric dimension of the Ω-shaped and bioinspired microgroove. Based on that, metal-based rupture diaphragms are fabricated by femtosecond laser processing technology, followed by rupture tests. Experiment results demonstrate that the practical rupture pressure of the diaphragm is highly consistent with the finite element analysis results, which verifies the effectiveness of the bionic design.

his work examines the impact of incorporating the physiological conditions of human cancellous bone, by integrating similar porosity of porous Fe with the cancellous bone under dynamic immersion test. All of the porous Fe specimens with ~?80% porosity were immersed in Simulated Body Fluid (SBF) with a flow rate of 0.3 ml/min integrated with cancellous bone for 7, 14 and 28 days. Porous Fe with the lowest surface area has the highest degradation rate despite having the lowest relative weight loss. The relationship between fluid induced shear stress and weight loss of specimens have been established.

The irregular porous structure, similar to human bone tissue, is more beneficial for bone ingrowth than the regular one. We proposed a new design method to create uniform and gradient irregular porous structures with porosities from 38 to 83% based on Voronoi tessellation. The models were fabricated using selective laser sintering, and micro-CT was used to assess their morphological features. Mechanical and fluid flow properties were evaluated through experiments and computational fluid dynamics simulations. Micro-CT scans confirmed that 3D printing can produce high-quality irregular structures. The Graded Irregular (GI) structure showed clear advantages in mechanical properties by reducing stress shielding and improving hydrodynamic performance with higher fluid flow velocity and lower permeability compared to the Uniform Irregular (UI) structure. Additionally, in vitro cell experiments indicated that the GI structure was better than the UI structure in promoting osteogenic differentiation, while in vivo animal studies showed that the GI structure was superior in terms of the ratio of Bone Volume to Total Volume (BV/TV) and Trabecular Number (Tb.N). Thus, the GI structure has greater application potential in bone tissue engineering.

Organisms on Earth evolve and coexist with natural Electromagnetic Fields (EMFs). Although many reports have suggested the potential anti-neoplastic effects of EMFs with specific parameters, the studies on the influence of natural EMFs on cancers are still rare. Herein, an EMF emitter has been developed to investigate the effects of the extremely-low frequency SR-mimicking EMF (SREMF) on cancer and normal cell proliferation. The numerical simulation has revealed that the emitter with specific parameters is able to enhance EMF intensity and uniformity on the designated plane above the emitter. More importantly, honeycomb-like emitter array can generate a stronger EMF intensity on the 20 mm plane above the array. Cell colony formation assays have demonstrated that SREMF generated by the honeycomb-like emitter array can significantly inhibit Hela cell proliferation in a cell-density-dependent manner. The morphological changes of SREMF-exposed Hela cells suggest that the anti-proliferative effect of SREMF may be caused by apoptosis induction. In contrast, no detrimental effect is observed for SREMF-treated normal cells, which probably can be explained by the evolutionary adaptation. Hence, this work can not only contribute to understanding the impact of natural EMF on creatures, but also afford a novel strategy to personalized cancer prevention and treatment.

The development of deep learning has made non-biochemical methods for molecular property prediction screening a reality, which can increase the experimental speed and reduce the experimental cost of relevant experiments. There are currently two main approaches to representing molecules: (a) representing molecules by fixing molecular descriptors, and (b) representing molecules by graph convolutional neural networks. Currently, both of these Representative methods have achieved some results in their respective experiments. Based on past efforts, we propose a Dual Self-attention Fusion Message Neural Network (DSFMNN). DSFMNN uses a combination of dual self-attention mechanism and graph convolutional neural network. Advantages of DSFMNN: (1) The dual self-attention mechanism focuses not only on the relationship between individual subunits in a molecule but also on the relationship between the atoms and chemical bonds contained in each subunit. (2) On the directed molecular graph, a message delivery approach centered on directed molecular bonds is used. We test the performance of the model on eight publicly available datasets and compare the performance with several models. Based on the current experimental results, DSFMNN has superior performance compared to previous models on the datasets applied in this paper.

Combining deep-learning image inpainting algorithms with the microfluidic technology, the paper proposes a method to achieve dynamic stealth and camouflage by using a microfluidic vision camouflage system simulating the chameleon skin. The basic principle is to perceive color changes in the external environment and collect ambient image information, and then utilize the image inpainting algorithm to adjust the control signals of the microfluidic system in real time. The detailed working principle of the microfluidic vision camouflage system is presented, and the mechanism of generating control signals for the system through deep-learning image inpainting algorithms and image-processing techniques is elucidated. The camouflage effect of the chameleon skin is analyzed and evaluated using color similarity. Results indicate that the camouflaged images are consistent with the background environment, thereby improving the target’s stealth and maneuvering characteristics. The camouflage technology developed in the paper based on the microfluidic vision camouflage system can be applied to several situations, such as military camouflage uniforms, robot skins, and weapon equipment.

This paper introduces the Surrogate-assisted Multi-objective Grey Wolf Optimizer (SMOGWO) as a novel methodology for addressing the complex problem of empty-heavy train allocation, with a focus on line utilization balance. By integrating surrogate models to approximate the objective functions, SMOGWO significantly improves the efficiency and accuracy of the optimization process. The effectiveness of this approach is evaluated using the CEC2009 multi-objective test function suite, where SMOGWO achieves a superiority rate of 76.67% compared to other leading multi-objective algorithms. Furthermore, the practical applicability of SMOGWO is demonstrated through a case study on empty and heavy train allocation, which validates its ability to balance line capacity, minimize transportation costs, and optimize the technical combination of heavy trains. The research highlights SMOGWO’s potential as a robust solution for optimization challenges in railway transportation, offering valuable contributions toward enhancing operational efficiency and promoting sustainable development in the sector.

As optimization problems continue to grow in complexity, the need for effective metaheuristic algorithms becomes increasingly evident. However, the challenge lies in identifying the right parameters and strategies for these algorithms. In this paper, we introduce the adaptive multi-strategy Rabbit Algorithm (RA). RA is inspired by the social interactions of rabbits, incorporating elements such as exploration, exploitation, and adaptation to address optimization challenges. It employs three distinct subgroups, comprising male, female, and child rabbits, to execute a multi-strategy search. Key parameters, including distance factor, balance factor, and learning factor, strike a balance between precision and computational efficiency. We offer practical recommendations for fine-tuning five essential RA parameters, making them versatile and independent. RA is capable of autonomously selecting adaptive parameter settings and mutation strategies, enabling it to successfully tackle a range of 17 CEC05 benchmark functions with dimensions scaling up to 5000. The results underscore RA’s superior performance in large-scale optimization tasks, surpassing other state-of-the-art metaheuristics in convergence speed, computational precision, and scalability. Finally, RA has demonstrated its proficiency in solving complicated optimization problems in real-world engineering by completing 10 problems in CEC2020.