The soft robotics field is on the rise. The highly adaptive robots provide the opportunity to bridge the gap between machines and people. However, their elastomeric nature poses significant challenges to the perception, control, and signal processing. Hydrogels and machine learning provide promising solutions to the problems above. This review aims to summarize this recent trend by first assessing the current hydrogel-based sensing and actuation methods applied to soft robots. We outlined the mechanisms of perception in response to various external stimuli. Next, recent achievements of machine learning for soft robots’ sensing data processing and optimization are evaluated. Here we list the strategies for implementing machine learning models from the perspective of applications. Last, we discuss the challenges and future opportunities in perception data processing and soft robots’ high level tasks.

By imitating the behavioral characteristics of some typical animals, researchers develop bionic stepping motors to extend the working range of piezoelectric materials and utilize their high accuracy advantage as well. A comprehensive review of the bionic stepping motors driven by piezoelectric materials is presented in this work. The main parts of stepping piezoelectric motors, including the feeding module, clamping module, and other critical components, are introduced elaborately. We classify the bionic stepping piezoelectric motors into inchworm motors, seal motors, and inertia motors depending on their main structure modules, and present the mutual transformation relationships among the three types. In terms of the relative position relationships among the main structure modules, each of the inchworm motors, seal motors, and inertia motors can further be divided into walker type, pusher type, and hybrid type. The configurations and working principles of all bionic stepping piezoelectric motors are reported, followed by a discussion of the advantages and disadvantages of the performance for each type. This work provides theoretical support and thoughtful insights for the understanding, analysis, design, and application of the bionic stepping piezoelectric motors.

The structural evolutions of the organisms during the development of billions of years endow them with remarkable thermal-regulation properties, which have significance to their survival against the outer versatile environment. Inspired by the nature, there have been extensive researches to develop thermoregulating materials by mimicking and utilizing the advantages from the natural organisms. In this review, the latest advances in thermal regulation of bioinspired microstructures are summarized, classifying the researches from dimension. The representative materials are described with emphasis on the relationship between the structural features and the corresponding thermal-regulation functions. For one-dimensional materials, wild silkworm cocoon fibers have been involved, and the reasons for unique optical phenomena have been discussed. Pyramid cone structure, grating and multilayer film structure are chosen as typical examples of two-dimensional bionics. The excellent thermal performance of the three-dimensional network frame structures is the focus. Finally, a summary and outlook are given.

Oil–water mixing has brought many problems to a society, and it is of great significance to develop a simple, convenient, efficient, and durable separation material to solve the problem of oil–water mixing. In this paper, modified cottons were successfully prepared using polydopamine as the in situ mineralization site of TiO2 nanoparticles combined with synergistic crosslinking with KH550. A large number of hydrophilic groups endowed the cotton with superhydrophilic ability, which greatly shortened its water spreading time. The prepared modified cotton could be successfully separated from oil and water, and still had a separation efficiency of 99.999% after 50 cycles. In addition, after 24 h immersion in 1 M HCl, NaOH, and NaCl solutions and 50 abrasion experiments, the modified cotton showed excellent oil–water separation ability, and the separation efficiency was above 99.990%. Successfully provided a simple preparation method to prepare high-efficiency and clean cottons for oil–water separation.

Bionic superhydrophobic coating has extremely broad application prospects and practical value. It is based on two important conditions, one is the construction of micro–nano structure, the other is the material with low surface energy. How to stabilize the micro–nano structure has become the focus of researches. In this work, a layer of Zn film is deposited on the stainless steel mesh with sturdy micron structure by RF magnetron sputtering. The solid micron structure of the stainless steel mesh itself, combined with the method of thermal oxidation, the surface of the stainless steel mesh is thus formed into a nanorod like ZnO nano structure, and then modified with perfluorodecyltriethoxysilane (PFDS) for low surface energy. The maximum contact angle of the superhydrophobic sample is 154.8°, and the minimum sliding angle is 2°, and it also has excellent corrosion resistance, thermal stability, self-cleaning, anti-aging and anti-icing properties, which provides a design idea for the preparation of superhydrophobic coatings.

This paper proposes the bioinspired soft frog robot. All printing technology was used for the fabrication of the robot. Polyjet printing was used to print the front and back limbs, while ultrathin filament was used to print the body of the robot, which makes it a complete soft swimming robot. Dual thrust generation approach has been proposed by embedding the main muscle and antagonistic muscle in all the limbs, which enables it to attain high speed (18 mm/s), significant control to swim in dual mode (synchronous and asynchronous modes). To achieve the swimming motion of frog, four SMA (BMF 300) muscle wires were used. The frog robot is named as (FROBOT). The hind limbs are 60 mm long and 10 mm thick on average, while the front limbs are 35 mm long and 7 mm thick. Model-based design and rigorous analysis of the dynamics of real frogs have allowed FROBOT to be developed to swim at a level that is remarkably consistent with real frogs. Electrical and mechanical characteristics have been performed. In addition, the test data were further processed using TRACKER to analyze angle, displacement and velocity. FROBOT (weighs 65 g) can swim at different controllable frequencies (0.5–2 Hz), can rotate in any direction on command from custom built LabVIEW software allowing it to swim with speed up to 18 mm/s on deep water surface (100 cm) with excellent weight balance.

Bionic amphibious robots have important prospects in scientific, commercial, and military fields. Compared with traditional amphibious robots which use propellers/jets for aquatic medium and wheels/tracks for terrestrial medium, bionic propulsion method has great advantages in terms of manoeuvrability, efficiency, and reliability, because there is no need to switch between different propulsion systems. To explore the integrated driving technology of amphibious robot, a novel bio-inspired soft robotic fin for amphibious use is proposed in this paper. The bionic fin can swim underwater and walk on land by the same undulating motion. To balance the conflicting demands of flexibility underwater and rigidity on land, the undulating fin adopts a special combination of a membrane fin and a bending spring. A periodic longitudinal wave in horizontal direction has been found generating passively in dynamic analysis. To find the composite wave-driven mechanics, theoretical analysis is conducted based on the walking model and swimming model. A virtual prototype is built in ADAMS software to verify the walking mechanics. The simulation result reveals that the passive longitudinal wave is also periodical and the composite wave contributes to land walking. Finally, an amphibious robot prototype actuated by a pair of undulating fins has been developed. The experiments show that the robot can achieve multiple locomotion, including walking forward/backward, turning in place, swimming underwater, and crossing medium, thus giving evidence to the feasibility of the newly designed undulating fin for amphibious robot.

It is common for robotic fish to generate thrust using reactive force generated by the tail’s physical motion, which interacts with the surrounding fluid. The coupling effect of the body strongly correlates with this thrust. However, hydrodynamics cannot be wholly modeled in analytical form. Therefore, data-assisted modeling is necessary for robotic fish. This work presents the first method of its kind using Genetic Algorithm (GA)-based optimization methods for data-assistive modeling for robotic fish applications. To begin, experimental data are collected in real time with the robotic fish that has been designed and fabricated using 3D printing. Then, the model’s influential parameters are estimated using an optimization problem. Further, a model-based deep reinforcement learning (DRL) controller is proposed to track the desired speed through extensive simulation work. In addition to a deep deterministic policy gradient (DDPG), a twin delayed DDPG (TD3) is employed in the training of the RL agent. Unfortunately, due to its local optimization problem, the RL-DDPG controller failed to perform well during training. In contrast, the RL-TD3 controller effectively learns the control policies and overcomes the local optima problem. As a final step, controller performance is evaluated under different disturbance conditions. In contrast to DDPG and GA-tuned proportional-integral controllers, the proposed model with RL-TD3 controller significantly improves the performance.

Bioinspired Soft Bending Actuators (SBA) are increasingly being used in rehabilitation, assistant robots, and grippers. Despite many investigations on free motion modeling, understanding how these actuators interact with the environment requires more detailed research. It is caused by high compliance and nonlinearity of bioinspired soft material, which leads to serious challenges in contact conditions. In this paper, a continuous deformation analysis is presented to describe the free motion nonlinear behavior of the actuator. Based on the achieved result, this study proposes static modeling of SBA affected by a concentrated external force. For this purpose, the finite rigid element method is utilized, which is based on discretizing the actuator into smaller parts and assuming these parts as rigid serial links connected by nonlinear torsional springs. To verify the proposed model, two kinds of forces are considered to be acting on the actuator, i.e. following force and constant direction force. In addition, the effect of gravity on the actuator configuration is also investigated. The validity of the model has been demonstrated through experiments in free motion, contact conditions and the presence of gravity. It generally shows that the prediction error of robot configuration is lower than 7.5%.

Morphing botanical tissues and animal muscles are all fiber-mediated composites, in which fibers play a passive and active role, respectively. Herein, inspired by the mechanism of fibers functioning in morphing botanical tissues and animal muscles, we propose two sorts of fiber-dominated composite actuators. First, inspired by the deformation of awned seeds in response to humidity change, we fabricate passive fiber-dominated actuators using non-active aligned carbon fibers via 4D printing method. The effects of process parameters, structural parameters, and fiber angles on the deformation of the printed actuators are examined. The experimental results show that the orientation degree is enhanced, resulting in a better swelling effect as the printing speed increases. Then, motivated by the actuation mechanism of skeletal muscle, we prepare active fiber-dominated actuators using active polyurethane fibers via 4D printing and pre-stretching method. The effect of fiber angle and loading on the actuation mode is experimentally analyzed. The experimental results show that the rotation angle of the actuator gradually decreases with the angle from 45° to 60°. When the fiber angle is 0° and 90°, the driver basically stops rotating while shrinking along the loading direction. Based on the above actuation mechanisms, identical contraction behaviors are realized both in passive and active fiber-dominated soft actuators. This work provides a validation method for biologically actuation mechanisms via 4D printing technique and smart materials and adds further insights to the design of bioinspired soft actuators.

Rehabilitation using exoskeleton robots can effectively remediate dysfunction and restore post-stroke survivors’ physical ability. However, low kinematic compatibility and poor self-participation of post-stroke patients in rehabilitation restrict the outcomes of exoskeleton-based therapy. The study presents an Unpowered Shoulder Complex Exoskeleton (USCE), consisting of Shoulder Girdle Mechanism (SGM), Ball-and-Socket Joint Mechanism (BSM), Gravity Compensating Mechanism (GCM) and Adjustable Alignment Design (AAD), to achieve self-rehabilitation of shoulder via energy transfer from the healthy upper limb to the affected counterpart of post-stroke hemiplegic patients. The SGM and AAD are designed to improve the kinematic compatibility by compensating for displacements of the glenohumeral joint with the adaptable size of USCE for different wearers. The BSM and GCM can transfer the body movement and energy from the healthy half of the body to the affected side without external energy input and enhance the self-participation with sick posture correction. The experimental results show that the USCE can provide high kinematic compatibility with 90.9% movement similarity between human and exoskeleton. Meanwhile, the motion ability of a post-stroke patient’s affected limb can be increased through energy transfer. It is expected that USCE can improve outcomes of home-based self-rehabilitation.

A variety of prosthetic ankles have been successfully developed to reproduce the locomotor ability for lower limb amputees in daily lives. However, they have not been shown to sufficiently improve the natural gait mechanics commonly observed in comparison to the able-bodied, perhaps due to over-simplified designs of functional musculoskeletal structures in prostheses. In this study, a flexible bionic ankle prosthesis with joints covered by soft material inclusions is developed on the basis of the human musculoskeletal system. First, the healthy side ankle–foot bones of a below-knee amputee were reconstructed by CT imaging. Three types of polyurethane rubber material configurations were then designed to mimic the soft tissues around the human ankle, providing stability and flexibility. Finite element simulations were conducted to determine the proper design of the rubber materials, evaluate the ankle stiffness under different external conditions, and calculate the rotation axes of the ankle during walking. The results showed that the bionic ankle had variable stiffness properties and could adapt to various road surfaces. It also had rotation axes similar to that of the human ankle, thus restoring the function of the talocrural and subtalar joints. The inclination and deviation angles of the talocrural axis, 86.2° and 75.1°, respectively, as well as the angles of the subtalar axis, 40.1° and 29.9°, were consistent with the literature. Finally, dynamic characteristics were investigated by gait measurements on the same subject, and the flexible bionic ankle prosthesis demonstrated natural gait mechanics during walking in terms of ankle angles and moments.

To ensure the safety, comfort, and effectiveness of lower limb rehabilitation exoskeleton robots in the rehabilitation training process, compliance is a prerequisite for human–machine interaction safety. First, under the premise of considering the mechanical structure of the lower limb rehabilitation exoskeleton robot (LLRER), when conducting the dynamic transmission of the exoskeleton knee joint, the soft axis is added to ensure that the rotation motion and torque are flexibly transmitted to any position to achieve flexible force transmission. Second, to realize the active compliance control of LLRER, the sliding mode impedance closed-loop controller is developed based on the kinematics and dynamics model of LLRER, and the stability of the designed control system is verified by Lyapunov method. Then the experiment is designed to track the collected bicycle rehabilitation motion data stably, and the algorithm and dynamic model are verified to satisfy the experimental requirements. Finally, aiming at the transmission efficiency and response performance of the soft shaft in the torque transmission process of the knee joint, the soft shaft transmission performance test is carried out to test the soft shaft transmission performance and realize the compliance of the LLRER, so as to ensure that the rehabilitation training can be carried out in a safe and comfortable interactive environment. Through the design of rehabilitation exercise training, it is verified that the LLRER of flexible transmission under sliding mode impedance control has good adaptability in the actual environment, and can achieve accurate and flexible control. During the experiment, the effectiveness of monitoring rehabilitation training is brought through the respiratory belt.

The pelvis plays a significant role in creating smooth and efficient motion during gait. In this study, an orthosis is designed to support pelvis motion of patients with the inability to walk. This assistive device is un-powered and consists of only passive elements. By focusing on the motion of the lower extremities during treadmill walking, a 3D dynamic model of the human body is simulated through a coupled optimization process. Based on two approaches of direct and inverse dynamics, the optimization problems are defined to derive optimum structural parameters of the pelvic orthosis. The optimization results of the direct dynamics problem indicate good matches between the optimized time plots of pelvis rotations with corresponding desired ones. Moreover, by solving the inverse dynamics problem, the minimum value of torque vector of the hip joint of the stance leg during a gait cycle is obtained. Furthermore, by utilizing a prototype of the orthosis, preliminary experiments are conducted on a normal user to validate the model and to investigate the feasibility of using the device for rehabilitation. For this purpose, the rotational movements of the pelvis and energy consumption of the subject in two cases with and without the device are compared during gait on a treadmill. Decreased energy consumption and the compliant motion of the pelvis while using the device verify simulation results and confirm the favorable performance of the assistive device for pelvic support during walking rehabilitation.

Biodegradable hydrogels are promising biomaterials for use in controlled-release systems for skin tissue regeneration. Controlled delivery systems constitute an important aspect of tissue engineering because they can modulate various physiological responses, including early immune response, tissue remodeling, and cell proliferation and maturation in the wound-healing process. Hydrogels composed of various biomaterials have been developed to overcome the limitations of conventional drug- or protein-delivery systems, such as limited targeting ability, low stability, and the induction of drug resistance. Hydrogels based on keratin, a natural polymer extracted from human hair, can provide adequate cell support and control homeostasis. Consequently, they can be applied for skin tissue engineering. In this study, we prepared degradable, tunable, and biocompatible hydrogels for controllable protein delivery. We synthesized keratin-fibrinogen (KER-FBG) by the chemical coupling reaction and prepared hydrogels through polymerization with thrombin. The structures and morphologies of the KER-FBG hydrogels were confirmed. Furthermore, the mechanical properties, swelling ratio, degradation, release behavior, and biocompatibility were investigated. The KER-FBG hydrogels presented promising biological performance, indicating that the material is suitable as a controlled protein delivery carrier.

Biological scaffolds have been the focus of bone tissue engineering research in recent years. In this paper, emodin (EM), macromolecular compound polycaprolactone (PCL), and hydroxyapatite (HA) were used as raw materials to prepare EM/PCL/HA fibers containing different EM ratios by electrospinning, and the properties and osteogenic efficacy of EM/PCL/HA were studied. Scanning electron microscopy, transmission electron microscopy, and atomic force microscopy were used to characterize the structures of HA and the electrospun fibers. Results showed that HA has high crystallinity and loose porous structure, and the electrospun fibers have a smooth and flat surface. In vitro release results showed that EM was slowly released from EM/PCL/HA within 216 h. Cell proliferation assay in mouse embryonic osteoblast precursor cells (MC3T3-E1) exhibited that 5% EM/PCL/HA had the best effect on promoting cell proliferation. Alkaline phosphatase (ALP) and mineralized nodules staining results also showed that 5% EM/PCL/HA had the best effect on promoting osteogenic differentiation. qRT-PCR results showed that the mRNA expression level of osteoblast differentiation markers, namely, bone morphogenetic protein (BMP)-2, BMP-9, and osteocalcin were significantly upregulated by 5% EM/PCL/HA treatment. These results indicate that EM/PCL/HA is a potential osteogenic material, which can provide a reference for the development of bone injury repair materials.

Poly (vinyl alcohol) hydrogel has been perceived as a promising replacement for articular cartilage due to its superior water-absorption ability and excellent biocompatibility, but its mechanical properties are still insufficient. In this study, the poly (vinyl alcohol)/sodium tetraborate triple-network (PVA/SB TN) hydrogel was developed by repeated freeze–thaw method. Scanning electron microscopy images demonstrated that the structure of as-prepared hydrogels was three-dimensional porous network structure similar to that of natural articular cartilage. Compared to the pure PVA hydrogel, the mechanical performance of the PVA/SB TN hydrogels were improved by 116% and 461% in tensile and compressive strengths, respectively. This was mainly because that the complexation reaction between the PVA and SB strengthened the stability of the hydrogel network. Notably, the biotribological performance of PVA hydrogel has also been improved significantly. Even at high load, the friction coefficient of the PVA/SB TN hydrogel was both very low in calf serum or deionized water. This PVA/SB TN hydrogel with good mechanical property and low friction has high application potential in cartilage repair.

Bioinspired active camber morphing is an innovative solution for the aerodynamic performance enhancement of flight vehicles such as Micro Aerial Vehicles (MAVs) and Unmanned Aerial Vehicles (UAVs). In the present article, a bio-inspired Fish Bone Active Camber (FishBAC) corrugated rib design concept with and without a spine for an Unmanned Aerial Vehicle (UAV) is proposed. The wing model is composed of multiple corrugated ribs and a splitted spar for connecting each rib. The rib geometry is subjected to static structural analysis using ANSYS Finite Element Analysis (FEA) module under the unit load conditions. The deformation modes are first extracted from the solution of the wind tunnel test and the elastically deformed NACA 4412 profile will be used to perform Fluid-Structure Interaction (FSI) studies as a partly coupled analysis. FishBAC corrugated rib with spine design is a stable structure as inspired from nature species that can withstand elastic and inertial loads. Computational fluid dynamics (CFD) simulation is performed to compute the coefficient of lift (Cl), coefficient of drag (Cd) at different Angle of Attack (AoA) for a modified NACA 4412 airfoil and the pressure loads acting on the deformed shape is extracted. The Cl obtained for the modified airfoil at lower AoA is about 60–80% higher and the maximum Cl (Clmax) is 62% higher than the baseline airfoil. The Cd of modified airfoil is reduced about 20% at the AoA α?=?3° as compared with the baseline model. The proposed corrugated rib structure has been successfully 3D printed with Polylactic Acid plus (PLA+) material and the wind tunnel testing is done to validate the Cl, Cd values obtained through CFD simulations and the results are presented.

Owls are widely known for their silent flight, which is attributed to their unique wing morphologies comprising leading-edge (LE) serrations, trailing-edge (TE) fringes, and a velvety surface. The aeroacoustic characteristics of owl-inspired TE fringes have been widely investigated through two-dimensional (2D) modeling, but remain yet poorly studied in association with their three-dimensional (3D) effects. Here, we present a numerical study of the 3D aeroacoustic characteristics of owl-inspired TE fringes in which we combined large-eddy simulations (LES) with the Ffowcs Williams?Hawkings analogy. We constructed a clean wing model and three wing models with TE fringes that were distributed differently spanwise. The aerodynamic forces and 3D acoustic characteristics reveal that, like the 2D results of our previous studies, the 3D TE fringes enable remarkable sound reduction spatially while having aerodynamic performance comparable to the clean model. Visualizations of the near-field 3D flow structures, vortex dynamics, and flow fluctuations show that TE fringes can robustly alter the 3D flow by breaking 3D TE vortices into small eddies and mitigating 3D flow fluctuations. Particularly, it is verified that TE fringes alter spanwise flows, thus dominating the 3D aeroacoustic characteristics in terms of passive flow control and flow stabilizations, whereas the fringes are inefficient in suppressing the acoustic sources induced by wingtip vortices. Moreover, the TE fringes distributed at midspan have better acoustic performance than those in the vicinity of the wingtip, indicating the importance of a spanwise distribution in enhancing aeroacoustic performance.

The movement mode of snakes is crawling, and the living environment of snakes with numerous branches and stones will cause plenty of wear for the snake scales. There are plenty of surface structures and morphology on snake scales to avoid severe wear. Among them, the research towards the keeled structure on snake scales is missing. Therefore, in this research, the wear resistance improvement of the keeled structure on the snake scales and the overlapped distribution of snake scales are investigated. The keeled and smooth snake scales were 3D printed and they were distributed on the substrate in the overlapped or paralleled ways. Besides these four samples with keeled/smooth scales and overlapped/paralleled distributed, there is also a reference sample with the same thickness. Based on the tribology test, the number of grooves of samples with the keeled structures is higher than that of samples with smooth surfaces, which indicates that the keeled structure dramatically enhances the wear resistance of snake scales, especially during the wear in the vertical direction. The experiment on surface morphology greatly compromised the result of the tribology test. In addition, the bottom portion of the keeled snake scales can be protected by the keeled structure. Besides, the overlapped distribution can protect the central region of snake scales and provide double-layer protection of the snake body. Overall, the keeled structure and the overlapped distribution play a significant part in the improvement of wear resistance of the snake skin. These findings can enhance the knowledge of the reptiles-mimic surface structure and facilitate the application of military uniforms under high-wear conditions.

The temperature distribution along the surface of evaporating droplets can afect signifcantly the fow feld inside the liquid and consequently the deposition pattern on the substrate. Although a “phase diagram” for the temperature distribution along the droplet surface was revealed by the numerical simulations, its experimental verifcation has still not been reported. In this paper, the surface temperature of evaporating droplets has been observed by using an infrared (IR) camera. The experimental observations show that three diferent patterns of temperature distribution along the droplet surface occur in succession with the change of the contact angle during the evaporation process, which is in good agreement with the theoretical predictions by the “phase diagram” of the surface temperature distribution. Furthermore, the efects of evaporative cooling on the “phase diagram” of sessile droplets have been explored. The numerical results indicate that the evaporative cooling efect can alter the size of the phase regions in the “phase diagram”. These results may provide a better understanding of the evaporation process of drying sessile droplets.

This paper proposes an artificial neural network to determine orientation using polarized skylight. This neural network has specific dilated convolution, which can extract light intensity information of different polarization directions. Then, the degree of polarization (DOP) and angle of polarization (AOP) are directly extracted in the network. In addition, the exponential function encoding of orientation is designed as the network output, which can better reflect the insect’s encoding of polarization information and improve the accuracy of orientation determination. Finally, training and testing were conducted on a public polarized skylight navigation dataset, and the experimental results proved the stability and effectiveness of the network.

Harris Hawks Optimizer (HHO) is a recent well-established optimizer based on the hunting characteristics of Harris hawks, which shows excellent efficiency in solving a variety of optimization issues. However, it undergoes weak global search capability because of the levy distribution in its optimization process. In this paper, a variant of HHO is proposed using Crisscross Optimization Algorithm (CSO) to compensate for the shortcomings of original HHO. The novel developed optimizer called Crisscross Harris Hawks Optimizer (CCHHO), which can effectively achieve high-quality solutions with accelerated convergence on a variety of optimization tasks. In the proposed algorithm, the vertical crossover strategy of CSO is used for adjusting the exploitative ability adaptively to alleviate the local optimum; the horizontal crossover strategy of CSO is considered as an operator for boosting explorative trend; and the competitive operator is adopted to accelerate the convergence rate. The effectiveness of the proposed optimizer is evaluated using 4 kinds of benchmark functions, 3 constrained engineering optimization issues and feature selection problems on 13 datasets from the UCI repository. Comparing with nine conventional intelligence algorithms and 9 state-of-the-art algorithms, the statistical results reveal that the proposed CCHHO is significantly more effective than HHO, CSO, CCNMHHO and other competitors, and its advantage is not influenced by the increase of problems’ dimensions. Additionally, experimental results also illustrate that the proposed CCHHO outperforms some existing optimizers in working out engineering design optimization; for feature selection problems, it is superior to other feature selection methods including CCNMHHO in terms of fitness, error rate and length of selected features.

The purpose of community detection in complex networks is to identify the structural location of nodes. Complex network methods are usually graphical, with graph nodes representing objects and edges representing connections between things. Communities are node clusters with many internal links but minimal intergroup connections. Although community detection has attracted much attention in social media research, most face functional weaknesses because the structure of society is unclear or the characteristics of nodes in society are not the same. Also, many existing algorithms have complex and costly calculations. This paper proposes different Harris Hawk Optimization (HHO) algorithm methods (such as Improved HHO Opposition-Based Learning(OBL) (IHHOOBL), Improved HHO Lévy Flight (IHHOLF), and Improved HHO Chaotic Map (IHHOCM)) were designed to balance exploitation and exploration in this algorithm for community detection in the social network. The proposed methods are evaluated on 12 different datasets based on NMI and modularity criteria. The findings reveal that the IHHOOBL method has better detection accuracy than IHHOLF and IHHOCM. Also, to offer the efficiency of the , state-of-the-art algorithms have been used as comparisons. The improvement percentage of IHHOOBL compared to the state-of-the-art algorithm is about 7.18%.

Coronavirus Disease 2019 (COVID-19) is the most severe epidemic that is prevalent all over the world. How quickly and accurately identifying COVID-19 is of great signifcance to controlling the spread speed of the epidemic. Moreover, it is essential to accurately and rapidly identify COVID-19 lesions by analyzing Chest X-ray images. As we all know, image segmentation is a critical stage in image processing and analysis. To achieve better image segmentation results, this paper proposes to improve the multi-verse optimizer algorithm using the Rosenbrock method and difusion mechanism named RDMVO. Then utilizes RDMVO to calculate the maximum Kapur’s entropy for multilevel threshold image segmentation. This image segmentation scheme is called RDMVO-MIS. We ran two sets of experiments to test the performance of RDMVO and RDMVO-MIS. First, RDMVO was compared with other excellent peers on IEEE CEC2017 to test the performance of RDMVO on benchmark functions. Second, the image segmentation experiment was carried out using RDMVO-MIS, and some meta-heuristic algorithms were selected as comparisons. The test image dataset includes Berkeley images and COVID-19 Chest X-ray images. The experimental results verify that RDMVO is highly competitive in benchmark functions and image segmentation experiments compared with other meta-heuristic algorithms.

This paper proposes a modified version of the Dwarf Mongoose Optimization Algorithm (IDMO) for constrained engineering design problems. This optimization technique modifies the base algorithm (DMO) in three simple but effective ways. First, the alpha selection in IDMO differs from the DMO, where evaluating the probability value of each fitness is just a computational overhead and contributes nothing to the quality of the alpha or other group members. The fittest dwarf mongoose is selected as the alpha, and a new operator ω is introduced, which controls the alpha movement, thereby enhancing the exploration ability and exploitability of the IDMO. Second, the scout group movements are modified by randomization to introduce diversity in the search process and explore unvisited areas. Finally, the babysitter's exchange criterium is modified such that once the criterium is met, the babysitters that are exchanged interact with the dwarf mongoose exchanging them to gain information about food sources and sleeping mounds, which could result in better-fitted mongooses instead of initializing them afresh as done in DMO, then the counter is reset to zero. The proposed IDMO was used to solve the classical and CEC 2020 benchmark functions and 12 continuous/discrete engineering optimization problems. The performance of the IDMO, using different performance metrics and statistical analysis, is compared with the DMO and eight other existing algorithms. In most cases, the results show that solutions achieved by the IDMO are better than those obtained by the existing algorithms

The Salp Swarm Algorithm (SSA) is a recently proposed swarm intelligence algorithm inspired by salps, a marine creature similar to jellyfish. Despite its simple structure and solid exploratory ability, SSA suffers from low convergence accuracy and slow convergence speed when dealing with some complex problems. Therefore, this paper proposes an improved algorithm based on SSA and adds three improvements. First, the Real-time Update Mechanism (RUM) underwrites the role of ensuring that excellent individual information will not be lost and information exchange will not lag in the iterative process. Second, the Communication Strategy (CMS), on the other hand, uses the multiplicative relationship of multiple individuals to regulate the exploration and exploitation process dynamically. Third, the Selective Replacement Strategy (SRS) is designed to adaptively adjust the variance ratio of individuals to enhance the accuracy and depth of convergence. The new proposal presented in this study is named RCSSSA. The global optimization capability of the algorithm was tested against various high-performance and novel algorithms at IEEE CEC 2014, and its constrained optimization capability was tested at IEEE CEC 2011. The experimental results demonstrate that the proposed algorithm can converge faster while obtaining better optimization results than traditional swarm intelligence and other improved algorithms. The statistical data in the table support its optimization capabilities, and multiple graphs deepen the understanding and analysis of the proposed algorithm.

This work proposes an improved multi-objective slime mould algorithm, called IBMSMA, for solving the multi-objective truss optimization problem. In IBMSMA, the chaotic grouping mechanism and dynamic regrouping strategy are employed to improve population diversity; the shift density estimation is used to assess the superiority of search agents and to provide selection pressure for population evolution; and the Pareto external archive is utilized to maintain the convergence and distribution of the non-dominated solution set. To evaluate the performance of IBMSMA, it is applied to eight multi-objective truss optimization problems. The results obtained by IBMSMA are compared with other 14 well-known optimization algorithms on hypervolume, inverted generational distance and spacing-to-extent indicators. The Wilcoxon statistical test and Friedman ranking are used for statistical analysis. The results of this study reveal that IBMSMA can fnd the Pareto front with better convergence and diversity in less time than state-of-the-art algorithms, demonstrating its capability in tackling large-scale engineering design problems.

Hybrid metaheuristic algorithms play a prominent role in improving algorithms' searchability by combining each algorithm's advantages and minimizing any substantial shortcomings. The Quantum-based Avian Navigation Optimizer Algorithm (QANA) is a recent metaheuristic algorithm inspired by the navigation behavior of migratory birds. Different experimental results show that QANA is a competitive and applicable algorithm in different optimization fields. However, it suffers from shortcomings such as low solution quality and premature convergence when tackling some complex problems. Therefore, instead of proposing a new algorithm to solve these weaknesses, we use the advantages of the bonobo optimizer to improve global search capability and mitigate premature convergence of the original QANA. The effectiveness of the proposed Hybrid Quantum-based Avian Navigation Optimizer Algorithm (HQANA) is assessed on 29 test functions of the CEC 2018 benchmark test suite with different dimensions, 30, 50, and 100. The results are then statistically investigated by the Friedman test and compared with the results of eight well-known optimization algorithms, including PSO, KH, GWO, WOA, CSA, HOA, BO, and QANA. Ultimately, five constrained engineering optimization problems from the latest test suite, CEC 2020 are used to assess the applicability of HQANA to solve complex real-world engineering optimization problems. The experimental and statistical findings prove that the proposed HQANA algorithm is superior to the comparative algorithms.

In this study, water hyacinth powder-reinforced polymer composites with eggshell filler material are investigated for their mechanical, absorption, morphological, thermal, and characterization properties. Hyacinth powder particles have not been extensively studied in polymer composites. This study investigates the use of eggshell powder for composites made from hyacinth powder. The use of hyacinth powder improves the mechanical properties of composites. With the help of the powder particles, composite samples are produced by compression moulding using an epoxy polymer matrix. 5% eggshell filler varied from 18.25 to 33.64 MPa for tensile strength, 40.28–49.66 MPa for flexural strength, and 2.45–4.75 J for impact strength. X-ray diffraction and Fourier transforms can be used to determine chemical groups, function groups, and crystallinity indexes. Powder particles can be observed by scanning electron microscopes in terms of their bonding behavior, eggshell powder combinations, and primary- and secondary-phase material absorption. According to the research presented in this paper, commercial particleboard applications can benefit substantially from hyacinth powder particles reinforced with eggshell fillers.