Ionic Polymer Metal Composites (IPMCs) are considered important electroactive polymers that have recently attracted the attention of the scientific community owing to their simple structure, adaptable form, high degree of flexibility, and biocompatibility during their utilization as sensing elements. Along these lines, in this work, the recent developments in performance optimization, model construction, and applications of IPMC sensors were reported. Different methods were introduced to enhance the sensitivity, preparation efficiency, and stability of the IPMC sensors including optimising the electrode and substrate membrane preparation, as well as implementing structural and shape modifications, etc. The IPMC sensing model, which serves as the theoretical foundation for the IPMC sensor, was summarized herein to offer directions for future application research activities. The applications of these sensors in a wide range of areas were also reviewed, such as wearable electronic devices, flow sensors, humidity sensors, energy harvesting devices, etc.

This paper presents a literature review exploring the potential of piezoelectric field-effect transistors (piezo-FETs) as bionic microelectromechanical systems (MEMS). First, piezo-FETs are introduced as bionic counterparts to natural mechanoreceptors, highlighting their classic configuration and working principles. Then, this paper summarizes the existing research on piezo-FETs as sensors for pressure, inertial, and acoustic sensors. Material selections, design characteristics, and key performance metrics are reviewed to demonstrate the advantage of piezo-FETs over traditional piezoelectric sensors. After identifying the limitations in these existing studies, this paper proposes using bionic piezoelectric coupling structures in piezo-FETs to further enhance the sensing capabilities of these artificial mechanoreceptors. Experimentally validated manufacturing methods for the newly proposed piezo-FET structures are also reviewed, pointing out a novel, feasible, and impactful research direction on these bionic piezoelectric MEMS sensors.

Biomimicry is an interdisciplinary field that aims to provide sustainable solutions to technical issues. However, learners often encounter challenges in the application of biomimicry due to the multidisciplinary requisites and abstract thinking skills required. Although multiple hands-on activities and teaching strategies have been explored, significant obstacles remain. Recently, generative artificial intelligent tools have become readily accessible to the general public, among which is ChatGPT. ChatGPT is known for generating detailed responses to user inquiries and has demonstrated efficacy in enhancing learning, although its specific application to biomimicry education has yet to be explored. To bridge this knowledge gap, this study seeks to evaluate the capabilities of ChatGPT in helping its users identify biomimetic solutions. It is found that the effectiveness of ChatGPT in biomimicry education significantly depends on the user’s ability to formulate knowledgeable and effective prompts. Although, a novice user can use ChatGPT to get a fundamental overview of the technical challenge and explore potential sources of bioinspiration. The study proposes a theoretical framework to guide users in the effective use of ChatGPT for biomimicry education and application. In addition, users are cautioned against ChatGPT responses and advised to employ it as a tool to complement their own knowledge gaps. The results from this study can offer insights for teachers and self-directed learners on the effective use of prompts in ChatGPT for biomimicry education. Future investigations will seek to validate this framework by evaluating users’ experiences and feedback on its application in creating prototypes.

Biomimetic micro-robot technology based on non-contact and cable-free magnetic actuation has become one of the crucial focuses of future biomedical research and micro-industrial development. Inspired by the motion characteristics of ray fish, this article proposes a micro-robot with magnetic controlled bionic ray structure. The micro-robot is made of soft elastic materials such as poly dimethyl siloxane (PDMS), Ethylene-Propylene-Diene Monomer (EPDM), and magnetic material Neodymium Iron Boron (NdFeB) nanoparticles. The external driving magnetic field is a periodic oscillating magnetic field generated by a Helmholtz coil. In order to verify the feasibility of the ray-inspired micro-robot, the motion principle was analyzed and several experiments were carried out. Experimental results demonstrated that the ray-inspired micro-robot can excellently mimic the crucial swimming characteristics of rays under the driving force of a oscillating magnetic field with an intensity of 5 mT and a frequency of 5 Hz, the swimming speed of the biomimetic micro-robot can reach nearly 2 body lengths per second. Analysis shows that the speed and stability of the micro-robot primarily depends not only on the amplitude and frequency of the vertical oscillating magnetic field, but also on the magnitude of the horizontal uniform magnetic field. This article demonstrates that the designed biomimetic micro-robot has the potential application of remotely performing specialized tasks in confined, complex environments such as microchannel-based scenarios.

The dynamic motion capability of humanoid robots is a key indicator for evaluating their performance. Jumping, as a typical dynamic motion, is of great significance for enhancing the robot’s flexibility and terrain adaptability in unstructured environments. However, achieving high-dynamic jumping control of humanoid robots has become a challenge due to the high degree of freedom and strongly coupled dynamic characteristics. The idea for this paper originated from the human response process to jumping commands, aiming to achieve online trajectory optimization and jumping motion control of humanoid robots. Firstly, we employ nonlinear optimization in combination with the Single Rigid Body Model (SRBM) to generate a robot’s Center of Mass (CoM) trajectory that complies with physical constraints and minimizes the angular momentum of the CoM. Then, a Model Predictive Controller (MPC) is designed to track and control the CoM trajectory, obtaining the required contact forces at the robot’s feet. Finally, a Whole-Body Controller (WBC) is used to generate full-body joint motion trajectories and driving torques, based on the prioritized sequence of tasks designed for the jumping process. The control framework proposed in this paper considers the dynamic characteristics of the robot’s jumping process, with a focus on improving the real-time performance of trajectory optimization and the robustness of controller. Simulation and experimental results demonstrate that our robot successfully executed high jump motions, long jump motions and continuous jump motions under complex working conditions.

Wall climbing robots have a wide range of applications in the field of transportation, petrochemicals, aerial construction, and other monitoring prospects; however, for complex defects on the wall, it is easy for the robot to fall off from attachment. This paper puts forward the bionic wheel-tracked rolling adsorption wall-climbing robots. The paper designs flexible material as sealing material for the negative pressure chamber of wall-climbing robots through the imitation of the biological mechanism of the insect adhesion pads. The material has the advantages of wear resistance, strong wall adaptability, large load, simple structure, etc., and it has a highly reliable and stable adsorption ability on unstructured and complex walls. The mathematical model of adsorption of the wall-crawling robot is constructed in different wall environments, and the kinematic analysis is carried out. The influence of the leakage on the adsorption capacity due to the deformation of the flexible sealing material, defects of the wall surface and the air ducts formed under different roughnesses is analyzed. Through the fabrication and experiment of the prototype, the correctness of the theoretical analysis is verified. The measured load capacity of the robot is 2.47 times its own weight, and it has great obstacle-crossing ability.

Cable-driven soft robots exhibit complex deformations, making state estimation challenging. Hence, this paper develops a multi-sensor fusion approach using a gradient descent strategy to estimate the weighting coefficients. These coefficients combine measurements from proprioceptive sensors, such as resistive flex sensors, to determine the bending angle. Additionally, the fusion strategy adopted provides robust state estimates, overcoming mismatches between the flex sensors and soft robot dimensions. Furthermore, a nonlinear differentiator is introduced to filter the differentiated sensor signals to address noise and irrational values generated by the Analog-to-Digital Converter. A rational polynomial equation is also introduced to compensate for temperature drift exhibited by the resistive flex sensors, which affect the accuracy of state estimation and control. The processed multi-sensor data is then utilized in an improved PD controller for closed-loop control of the soft robot. The controller incorporates the nonlinear differentiator and drift compensation, enhancing tracking performance. Experimental results validate the effectiveness of the integrated approach, demonstrating improved tracking accuracy and robustness compared to traditional PD controllers.

The averaged equation of motion for linear acceleration in the BCF swimming mode was derived using the Elongated Body Theory (EBT) through time averaging. An analytical solution for the linear acceleration swimming velocity was obtained, revealing that the average velocity follows a hyperbolic tangent function of time, which can be considered a semi-empirical formula for linear acceleration swimming. The formula’s parameters, such as the steady swimming velocity and the acceleration time constant, can be determined by conducting experiments on linear acceleration, enabling the estimation of drag coefficient, effective added mass, thrust, and drag force. We developed a tensegrity robotic tuna and conducted a linear acceleration experiment. The results confirmed both the averaged equation of motion and its empirical formula, indicating that the formula is not limited by EBT and can be extended to large amplitude swimming and thunniform swimmers with large aspect ratio caudal fins. This provides researchers with an efficient and easy-to-implement method to estimate the swimming thrust and drag forces through linear acceleration experiments, without the need for complex and expensive flow field and force measurement equipment.

Real-time gait switching of quadruped robot with speed change is a difficult problem in the field of robot research. It is a novel solution to apply reinforcement learning method to the quadruped robot problem. In this paper, a quadruped robot simulation platform is built based on Robot Operating System (ROS). openai-gym is used as the RL framework, and Proximal Policy Optimization (PPO) algorithm is used for quadruped robot gait switching. The training task is to train different gait parameters according to different speed input, including gait type, gait cycle, gait offset, and gait interval. Then, the trained gait parameters are used as the input of the Model Predictive Control (MPC) controller, and the joint forces/torques are calculated by the MPC controller.The calculated joint forces are transmitted to the joint motor of the quadruped robot to control the joint rotation, and the gait switching of the quadruped robot under different speeds is realized. Thus, it can more realistically imitate the gait transformation of animals, walking at very low speed, trotting at medium speed and galloping at high speed. In this paper, a variety of factors affecting the gait training of quadruped robot are integrated, and many aspects of reward constraints are used, including velocity reward, time reward,energy reward and balance reward. Different weights are given to each reward, and the instant reward at each step of system training is obtained by multiplying each reward with its own weight, which ensures the reliability of training results. At the same time, multiple groups of comparative analysis simulation experiments are carried out. The results show that the priority of balance reward, velocity reward, energy reward and time reward decreases successively and the weight of each reward does not exceed 0.5.When the policy network and the value network are designed, a three-layer neural network is used, the number of neurons in each layer is 64 and the discount factor is 0.99, the training effect is better.

Compared to the traditional flapping-wing structure with single motion mode, a micro servoactuator driven Flapping-Wing Air Vehicle (FWAV) breaks free from the limitations imposed by the motion parameters of the crank-connecting rod mechanism. It allows for simultaneous control of wings’ position and velocity attitude through pulse width modulation, showcasing unrivaled controllability and promising extensive applications. However, this method of motion control also brings new challenges to the design of the wings’ motion parameters. This study seeks to investigate the relationship between the motion parameters of micro servoactuator driven FWAV and its aerodynamic characteristics, then explore a servo control method that can optimize its thrust-producing performance. To achieve this, this paper involves the establishment of Amplitude Loss Model (ALM), Flapping Wing Dynamic Model (FWDM), and Power Load Model (PLM), followed by motion capture experiments, dynamic monitoring experiments, and power monitoring experiments. Experimental results show that the proposed modeling method, which fully considers the amplitude loss effect and advanced twisting effect in flapping-wing motion, can accurately calculate thrust, power, and power load, with prediction errors of less than 10%, 5% and 13%, respectively. This high-precision model can effectively optimize motion parameters, allowing for better performance of flapping-wing motion.

Traditional robotic grippers encounter significant challenges when handling small objects in confined spaces, underscoring the need for innovative instruments with enhanced space efficiency and adaptability. Erodium cicutarium awns have evolved hygroresponsive helical deformation, efficiently driving seeds into soil crevices with limited space utilization. Drawing inspiration from this natural mechanism, we developed a biomimetic thin-walled actuator with water-responsive helical capabilities. It features a composite material structure comprising common engineering materials with low toxicity. Leveraging fused deposition modeling 3D printing technology and the composite impregnation process, the actuator’s manufacturing process is streamlined and cost-effective, suitable for real-world applications. Then, a mathematical model is built to delineate the relationship between the biomimetic actuator’s key structural parameters and deformation characteristics. The experimental results emphasize the actuator’s compact dimension (0.26 mm thickness) and its capability to form a helical tube under 5 mm diameter within 60 s, demonstrating outstanding space efficiency. Moreover, helical characteristics and stiffness of the biomimetic actuators are configurable through precise modifications to the composite material structure. Consequently, it is capable of effectively grasping an object smaller than 3 mm. The innovative mechanism and design principles hold promise for advancing robotic technology, particularly in fields requiring high space efficiency and adaptability, such as fine tubing decongestion, underwater sampling, and medical endoscopic surgery.

Delaying the sinusoidal plunging in the middle of the up- and down stroke is studied. This form of kinematics can appear if the flapping mechanism is malfunctioning, or while large birds fly in some cases. Aim of this study is to understand the effect of pausing the airfoil during plunging in the equilibrium position. The paused plunging is modelled mathematically by means of a sinusoidal waveform raised to the third power. Evaluation of this waveform is done on two stages; the wake pattern analysis and the aerodynamic and propulsive analysis. Studying this waveform reveals a robust way to generate two triads wake pattern instead of the regular reverse von Karman vortex wake pattern. The thrust generation mechanism is presented. The performance evaluation is done based on the thrust, lift, and power coefficients and the propulsive efficiency at different point in the nondimensional amplitude– reduced frequency space. Regression modeling methods are utilized to stand on the performance of the paused waveform with respect to the regular sinusoidal waveform. These findings underscore the potential of the proposed waveform as a promising alternative for enhancing the aerodynamic performance and propulsive efficiency in the design of Micro Air Vehicles (MAVs), a rapidly evolving field.

Felids, during intense activities such as jumping and sprinting, adjust their posture by twisting and stretching their body to disperse limb impact and minimize injury. This self-stabilization mechanism has garnered significant attention for inspiring biometric robot design. This study investigates the flexibility and cushioning characteristics of a cat’s spine, focusing on its biomechanical properties. A high-fidelity 3D model was used to test the range of motion (ROM) under six conditions, simulate dorsiflexion to analyze stress distribution. The torsional and compressive stiffness were tested by using five cat spinal specimens. the flexibility principles of the flexible cat’s spine were explained via morphological insights. Results indicate that the cat spine has the least rotational stiffness in axial rotation, followed by extension and lateral bending, with a compressive stiffness of 53.62?±?4.68 N/mm. Stress during dorsiflexion is evenly distributed across vertebrae. The vertebrae heights account for 90.34% of total spinal length with a mean height-to-width ratio of 1.04. Cats’ spines, with more articulations and elongated vertebrae, allow for significant twisting and bending, aiding in rapid body posture adjustments and impact mitigation. These biomechanical traits could inspire the design of robots for confined rescue operations.

In this study, we present the design and development evaluation of BalanSENS toward the realization of the Integrated Balance Rehabilitation (I-BaR) framework. BalanSENS is designed to encourage active participation by integrating multi-sensory information with the co-improvement of sensory and motor functions. Moreover, it can offer individual rehabilitation design with the integration of three phases. The first phase provides foot-ankle muscle activation and movement sensation development. In the second phase, sensory weighting skills and upper extremities independence can be improved by using multi-sensory input. In the last/stepping phase, walking parameters are aimed to be improved with modulated distance. The parallel manipulator is designed through simulations to determine actuation properties and analyze the load-bearing capacity and feasibility of the materials. Drawing from simulation outcomes, an operational 3 DoF platform is constructed to demonstrate their design suitability for the I-BaR framework. Furthermore, design evaluations demonstrated promising results in quantifying force and real-time data monitoring during the passive ankle preparation phase.

Along with the flourishing of brain-computer interface technology, the brain-to-brain information transmission between different organisms has received high attention in recent years. However, specific information transmission mode and implementation technology need to be further studied. In this paper, we constructed a brain-to-brain information transmission system between pigeons based on the neural information decoding and electrical stimulation encoding technologies. Our system consists of three parts: (1) the “perception pigeon” learns to distinguish different visual stimuli with two discrepant frequencies, (2) the computer decodes the stimuli based on the neural signals recorded from the “perception pigeon” through a frequency identification algorithm (neural information decoding) and encodes them into different kinds of electrical pulses, (3) the “action pigeon” receives the Intracortical Microstimulation (ICMS) and executes corresponding key-pecking actions through discriminative learning (electrical stimulation encoding). The experimental results show that our brain-to-brain system achieves information transmission from perception to action between two pigeons with the average accuracy of about 72%. Our study verifies the feasibility of information transmission between inter-brain based on neural information decoding and ICMS encoding, providing important technical methods and experimental program references for the development of brain-to-brain communication technology.

The anthropometric differences between European/American and Chinese population are remarkable and have significant influences on pedestrian kinematics and injury response in vehicle crashes. Therefore, the current study aims to develop and validate a Finite Element (FE) human body model representing the anthropometry of Chinese 50th percentile adult male for pedestrian safety analysis and development of Chinese ATDs (Anthropomorphic Test Devices). Firstly, a human body pedestrian model, named as C-HBM (Chinese Human Body Model), was developed based on the medical image data of a volunteer selected according to both anthropometry and anatomy characteristics of 50th percentile Chinese adult male. Then, the biofidelity of the C-HBM pedestrian model was validated against cadaver impact test data reported in the literature at the segment and full-body level. Finally, the validated C-HBM pedestrian model was employed to predict Chinese pedestrian injuries in real world vehicle crashes. The results indicate that the C-HBM pedestrian model has a good capability in predicting human body mechanical response in cadaver tests and Chinese leg and thorax injuries in vehicle crashes. Kinematic analysis shows that the C-HBM pedestrian model has less sliding on the hood surface, shorter movement in the horizontal direction, and higher pelvis displacement in the vertical direction than cadavers and the pedestrian model in the anthropometry of westerner due to anthropometric differences in the lower limbs. The currently developed C-HBM pedestrian model provides a basic tool for vehicle safety design and evaluation in China market, and for development of Chinese ATDs.

Micro- and nano-structures are intentionally incorporated into various biological surfaces, such as fish scales, snakeskin, and burr-covered plant leaves, to enhance their interactions with other surfaces. The mechanical anisotropy affects friction, interlocking, propulsion, and mobility on substrates. This study investigates a novel method for developing a robust, stratified, soft, lubricating coating on a surface. 3-Methacryloyloxypropyl-trimethoxysilane (MPS) is a cohesive adhesion promoter that functions by infiltrating Polydimethylsiloxane (PDMS) silicone elastomers to maintain low friction levels and high mechanical load-bearing capacity. MPS makes it easier for organic and inorganic materials to adhere to the surface of the initiator layer P(AAm-co-AA-co-PDMS/Fe). We investigate how the tough hydrogel layer of the module impacts the lubricating ability of the multilayer coating when the tough hydrogel layer of the module adheres to the bio-based polyurethane substrate. After 1,000 sliding cycles with a 1 N load, the improved PDMS’s Coefficient of Friction (COF) remains steady and low (COF?<?0.81). We recommend using the suggested structure and a standard set of optimal variables to enhance the functional efficiency of such systems. In conclusion, we have demonstrated the optimal simulation of these parameters for stimulus-responsive, adjustable surface systems.

Photovoltaic (PV) power generation is highly regarded for its capability to transform solar energy into electrical power. However, in real-world applications, PV modules are prone to issues such as increased self-heating and surface dust accumulation, which contribute to a reduction in photoelectric conversion efficiency. Furthermore, elevated temperatures can adversely affect the components’ operational longevity. To augment the efficiency and extend the lifespan of PV modules, it is crucial to implement cooling strategies and periodic surface dust removal. In this research, we introduce a composite PV module design that amalgamates a hygroscopic hydrogel with self-cleaning attributes. The design incorporates a superhydrophobic polydimethylsiloxane (PDMS) film as its exposed surface layer and employs a PAM-CaCl2-SiC hygroscopic hydrogel for rear cooling. This arrangement is intended to facilitate efficient surface self-cleaning and passive cooling of the composite PV module. Experimental studies were conducted to evaluate the performance of this innovative composite PV module design, and the results showed that the composite PV panel had an increase of about 1.39% in power generation compared to an ordinary PV panel in the spring of Shenzhen, China.

The shortage of transplantable skin is the leading cause of death in patients with extensive skin defect. Addressing this challenge urgently requires the development of skin substitutes capable of wound repair and facilitating skin regeneration. In this study, a biomimetic bilayer skin tissue model consisting of collagen, gelatin/sodium alginate, fibroblasts, human umbilical vein endothelial cells, keratinocytes, melanocytes, and verteporfin was devised. Then, the skin model was fabricated using precise extrusion/inkjet bioprinters, and it reconstruction capabilities were evaluated through skin defect repair experiments. The printed skin tissue reduced the inflammatory response of the wound by 38% and inhibited the expression of TGF-β and YAP, and promoted the transformation of macrophages from M1 phenotype to M2 phenotype, thus promoting the reasonable reconstruction of fibronectin and collagen on the wound, finally promoting the wound healing, and reducing the wound contraction and scar formation. In addition, the proliferation and differentiation of human umbilical vein endothelial cells, keratinocytes, and melanocytes in printed skin increased the number of regenerated blood vessels by 123%, while promoting the reconstruction of multilayer epidermal structure and skin color. The outcomes of this investigation present a promising skin model and therapeutic strategy for skin injury, offering a potential avenue for the reconstruction of skin structure and function.

Aiming to address the issues of poor optimization-seeking ability and easily falling into local optimization of the Snow Ablation Optimizer (SAO), a Physically Hybrid strategy-based Improved Snow Ablation Optimizer (PHISAO) is proposed. In this paper, a snow blowing strategy was introduced during the initialization phase of the population to improve population diversity. Secondly, the dual-population iterative strategy of SAO has been replaced by a multi-population iterative strategy, which is supplemented with a position update formula for the water evaporation phase. Additionally, Cauchy mutation perturbation has been introduced in the snow melting phase. This set of improvements better balances the exploration and exploitation phases of the algorithm, enhancing its ability to pursue excellence. Finally, a fluid activation strategy is added to activate the potential of the algorithm when its update iterations enter stagnation, helping the algorithm to escape from the local optimum. Comparison experiments between PHISAO and six metaheuristics were conducted on the CEC (Congress on Evolutionary Computation)-2017 and CEC-2022 benchmark suites. The experimental results demonstrate that the PHISAO algorithm exhibits excellent performance and robustness. In addition, the PHISAO is applied into the unmanned aerial vehicle trajectory planning problem together with particle swarm optimization, beluga whale optimization, sand cat swarm optimization, and SAO. The simulation results show that the proposed PHISAO can plan the optimal trajectory in all two different maps. The proposed PHISAO objective function values were reduced by an average of 29.49% (map 1), and 18.34% (map 2) compared to SAO.

Nature-inspired optimization algorithms refer to techniques that simulate the behavior and ecosystem of living organisms or natural phenomena. One such technique is the “Photosynthesis Spectrum Algorithm,” which was developed by mimicking the process by which photons behave as a population in plants. This optimization technique has three stages that mimic the structure of leaves and the fluorescence phenomenon. Each stage updates the fitness of the solution by using a mathematical equation to direct the photon to the reaction center. Three stages of testing have been conducted to test the efficacy of this approach. In the first stage, functions from the CEC 2019 and CEC 2021 competitions are used to evaluate the performance and convergence of the proposed method. The statistical results from non-parametric Friedman and Kendall’s W tests show that the proposed method is superior to other methods in terms of obtaining the best average of solutions and achieving stability in finding solutions. In other sections, the experiment is designed for data clustering. The proposed method is compared with recent data clustering and classification metaheuristic algorithms, indicating that this method can achieve significant performance for clustering in less than 10 s of CPU time and with an accuracy of over 90%.

This paper proposes an improved version of the Partial Reinforcement Optimizer (PRO), termed LNPRO. The LNPRO has undergone a learner phase, which allows for further communication of information among the PRO population, changing the state of the PRO in terms of self-strengthening. Furthermore, the Nelder-Mead simplex is used to optimize the best agent in the population, accelerating the convergence speed and improving the accuracy of the PRO population. By comparing LNPRO with nine advanced algorithms in the IEEE CEC 2022 benchmark function, the convergence accuracy of the LNPRO has been verified. The accuracy and stability of simulated data and real data in the parameter extraction of PV systems are crucial. Compared to the PRO, the precision and stability of LNPRO have indeed been enhanced in four types of photovoltaic components, and it is also superior to other excellent algorithms. To further verify the parameter extraction problem of LNPRO in complex environments, LNPRO has been applied to three types of manufacturer data, demonstrating excellent results under varying irradiation and temperatures. In summary, LNPRO holds immense potential in solving the parameter extraction problems in PV systems.

To solve the shortcomings of Particle Swarm Optimization (PSO) algorithm, local optimization and slow convergence, an Opposition-based Learning Adaptive Chaotic PSO (LCPSO) algorithm was presented. The chaotic elite opposition-based learning process was applied to initialize the entire population, which enhanced the quality of the initial individuals and the population diversity, made the initial individuals distribute in the better quality areas, and accelerated the search efficiency of the algorithm. The inertia weights were adaptively customized during evolution in the light of the degree of premature convergence to balance the local and global search abilities of the algorithm, and the reverse search strategy was introduced to increase the chances of the algorithm escaping the local optimum. The LCPSO algorithm is contrasted to other intelligent algorithms on 10 benchmark test functions with different characteristics, and the simulation experiments display that the proposed algorithm is superior to other intelligence algorithms in the global search ability, search accuracy and convergence speed. In addition, the robustness and effectiveness of the proposed algorithm are also verified by the simulation results of engineering design problems.

The Unit Commitment Problem (UCP) corresponds to the planning of power generation schedules. The objective of the fuel-based unit commitment problem is to determine the optimal schedule of power generators needed to meet the power demand, which also minimizes the total operating cost while adhering to different constraints such as power generation limits, unit startup, and shutdown times. In this paper, four different binary variants of the Bald Eagle Search (BES) algorithm, were introduced, which used two variants using S-shape, U-shape, and V-shape transfer functions. In addition, the best-performing variant (using an S-shape transfer function) was selected and improved further by incorporating two binary operators: swap-window and window-mutation. This variation is labeled Improved Binary Bald Eagle Search (IBBESS2). All five variants of the proposed algorithm were successfully adopted to solve the fuel-based unit commitment problem using seven test cases of 4-, 10-, 20-, 40-, 60-, 80-, and 100-unit. For comparative evaluation, 34 comparative methods from existing literature were compared, in which IBBESS2 achieved competitive scores against other optimization techniques. In other words, the proposed IBBESS2 performs better than all other competitors by achieving the best average scores in 20-, 40-, 60-, 80-, and 100-unit problems. Furthermore, IBBESS2 demonstrated quicker convergence to an optimal solution than other algorithms, especially in large-scale unit commitment problems. The Friedman statistical test further validates the results, where the proposed IBBESS2 is ranked the best. In conclusion, the proposed IBBESS2 can be considered a powerful method for solving large-scale UCP and other related problems.

Feature Selection (FS) is an optimization problem that aims to downscale and improve the quality of a dataset by retaining relevant features while excluding redundant ones. It enhances the classification accuracy of a dataset and holds a crucial position in the field of data mining. Utilizing metaheuristic algorithms for selecting feature subsets contributes to optimizing the FS problem. The White Shark Optimizer (WSO), as a metaheuristic algorithm, primarily simulates the behavior of great white sharks’ sense of hearing and smelling during swimming and hunting. However, it fails to consider their other randomly occurring behaviors, for example, Tail Slapping and Clustered Together behaviors. The Tail Slapping behavior can increase population diversity and improve the global search performance of the algorithm. The Clustered Together behavior includes access to food and mating, which can change the direction of local search and enhance local utilization. It incorporates Tail Slapping and Clustered Together behavior into the original algorithm to propose an Improved White Shark Optimizer (IWSO). The two behaviors and the presented IWSO are tested separately using the CEC2017 benchmark functions, and the test results of IWSO are compared with other metaheuristic algorithms, which proves that IWSO combining the two behaviors has a stronger search capability. Feature selection can be mathematically described as a weighted combination of feature subset size and classification error rate as an optimization model, which is iteratively optimized using discretized IWSO which combines with K-Nearest Neighbor (KNN) on 16 benchmark datasets and the results are compared with 7 metaheuristics. Experimental results show that the IWSO is more capable in selecting feature subsets and improving classification accuracy.

The persistently high incidence of breast cancer emphasizes the need for precise detection in its diagnosis. Computer-aided medical systems are designed to provide accurate information and reduce human errors, in which accurate and effective segmentation of medical images plays a pivotal role in improving clinical outcomes. Multilevel Threshold Image Segmentation (MTIS) is widely favored due to its stability and straightforward implementation. Especially when dealing with sophisticated anatomical structures, high-level thresholding is a crucial technique in identifying fine details. To enhance the accuracy of complex breast cancer image segmentation, this paper proposes an improved version of RIME optimizer EECRIME, denoted as the double Enhanced solution quality Crisscross RIME algorithm. The original RIME initially conducts an efficient optimization to target promising solutions. The double-enhanced solution quality (EESQ) mechanism is proposed for thorough exploitation without falling into local optimum. In contrast, the crisscross operations perform a further local exploration of the generated feasible solutions. The performance of EECRIME is verified with basic and advanced algorithms on IEEE CEC2017 benchmark functions. Furthermore, an EECRIME-based MTIS method in combination with Kapur’s entropy is applied to segment breast Infiltrating Ductal Carcinoma (IDC) histology images. The results demonstrate that the developed model significantly surpasses its competitors, establishing it as a practical approach for complex medical image processing.

Convolutional Neural Networks (CNNs) have shown remarkable capabilities in extracting local features from images, yet they often overlook the underlying relationships between pixels. To address this limitation, previous approaches have attempted to combine CNNs with Graph Convolutional Networks (GCNs) to capture global features. However, these approaches typically neglect the topological structure information of the graph during the global feature extraction stage. This paper proposes a novel end-to-end hybrid architecture called the Multi-Graph Pooling Network (MGPN), which is designed explicitly for chest X-ray image classification. Our approach sequentially combines CNNs and GCNs, enabling the learning of both local and global features from individual images. Recognizing that different nodes contribute differently to the final graph representation, we introduce an NI-GTP module to enhance the extraction of ultimate global features. Additionally, we introduce a G-LFF module to fuse the local and global features effectively.