Biomimetics最新文献

{"title":"Application of Metaheuristics for Optimizing Predictive Models in iHealth: A Case Study on Hypotension Prediction in Dialysis Patients.","authors":"Felipe Cisternas-Caneo, María Santamera-Lastras, José Barrera-Garcia, Broderick Crawford, Ricardo Soto, Cristóbal Brante-Aguilera, Alberto Garcés-Jiménez, Diego Rodriguez-Puyol, José Manuel Gómez-Pulido","doi":"10.3390/biomimetics10050314","DOIUrl":"10.3390/biomimetics10050314","url":null,"abstract":"<p><p>Intradialytic hypotension (IDH) is a critical complication in patients with chronic kidney disease undergoing dialysis, affecting both patient safety and treatment efficacy. This study examines the application of advanced machine learning techniques, combined with metaheuristic optimization methods, to improve predictive models for intradialytic hypotension (IDH) in hemodialysis patients. Given the critical nature of IDH, which can lead to significant complications during dialysis, the development of effective predictive tools is vital for improving patient safety and outcomes. Dialysis session data from 758 patients collected between January 2016 and October 2019 were analyzed. Particle Swarm Optimization, Grey Wolf Optimizer, Pendulum Search Algorithm, and Whale Optimization Algorithm were employed to reduce the feature space, removing approximately 45% of clinical and analytical variables while maintaining high recall for the minority class of patients experiencing hypotension. Among the evaluated models, the XGBoost classifier showed superior performance, achieving a macro F-score of 0.745 with a recall of 0.756 and a precision of 0.718. These results highlight the effectiveness of the combined approach for early identification of patients at risk for IDH, minimizing false negatives, and improving clinical decision-making in nephrology.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12108628/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Energy-Efficient Fall-Detection System Using LoRa and Hybrid Algorithms.","authors":"Manny Villa, Eduardo Casilari","doi":"10.3390/biomimetics10050313","DOIUrl":"10.3390/biomimetics10050313","url":null,"abstract":"<p><p>Wearable fall-detection systems have received significant research attention during the last years. Fall detection in wearable devices presents key challenges, particularly in balancing high precision with low power consumption-both of which are essential for the continuous monitoring of older adults and individuals with reduced mobility. This study introduces a hybrid system that integrates a threshold-based model for preliminary detection with a deep learning-based approach that combines a CNN (Convolutional Neural Network) for spatial feature extraction with a LSTM (Long Short-Term Memory) model for temporal pattern recognition, aimed at improving classification accuracy. LoRa technology enables long-range, energy-efficient communication, ensuring real-time monitoring across diverse environments. The wearable device operates in ultra-low-power mode, capturing acceleration data at 20 Hz and transmitting a 4-s window when a predefined threshold in the acceleration magnitude is exceeded. The CNN-LSTM classifier refines event identification, significantly reducing false positives. This design extends operational autonomy to 178 h of continuous monitoring. The experimental and systematic evaluation of the prototype achieved a 96.67% detection rate (sensitivity) for simulated falls and a 100% specificity in classifying conventional Activities of Daily Living as non-falls. These results establish the system as a robust and scalable solution, effectively addressing limitations in power efficiency, connectivity, and detection accuracy while enhancing user safety and quality of life.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109012/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Obstacle Feature Information-Based Motion Decision-Making Method for Obstacle-Crossing Motions in Lower Limb Exoskeleton Robots.","authors":"Yuepeng Zhang, Guangzhong Cao, Jun Wu, Bo Gao, Linzhong Xia, Chen Lu, Hui Wang","doi":"10.3390/biomimetics10050311","DOIUrl":"10.3390/biomimetics10050311","url":null,"abstract":"<p><p>To overcome the problem of insufficient adaptability to the motion environment of lower limb exoskeleton robots, this paper introduces computer vision technology into the motion control of lower limb exoskeleton robots and studies an obstacle-crossing-motion method based on detecting obstacle feature information. Considering the feature information of different obstacles and the distance between obstacles and robots, a trajectory planning method based on direct point matching was used to generate offline adjusted gait trajectory libraries and obstacle-crossing gait trajectory libraries. A lower limb exoskeleton robot obstacle-crossing motion decision-making algorithm based on obstacle feature information is proposed by combining gait constraints and motion constraints, enabling it to select appropriate motion trajectories in the trajectory library. The proposed obstacle-crossing-motion method was validated at three distances between the obstacle and the robot and with the feature information of four obstacles. The experimental results show that the proposed method can select appropriate trajectories from the trajectory library based on the detected obstacle feature information and can safely complete obstacle-crossing motions.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109428/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149017","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Bionic Goal-Oriented Path Planning Method Based on an Experience Map.","authors":"Qiang Zou, Yiwei Chen","doi":"10.3390/biomimetics10050305","DOIUrl":"10.3390/biomimetics10050305","url":null,"abstract":"<p><p>Brain-inspired bionic navigation is a groundbreaking technological approach that emulates the biological navigation systems found in mammalian brains. This innovative method leverages experiences within cognitive space to plan global paths to targets, showcasing remarkable autonomy and adaptability to various environments. This work introduces a novel bionic, goal-oriented path planning approach for mobile robots. First, an experience map is constructed using NeuroSLAM, a bio-inspired simultaneous localization and mapping method. Based on this experience map, a successor representation model is then developed through reinforcement learning, and a goal-oriented predictive map is formulated to address long-term reward estimation challenges. By integrating goal-oriented rewards, the proposed algorithm efficiently plans optimal global paths in complex environments for mobile robots. Our experimental validation demonstrates the method's effectiveness in experience sequence prediction and goal-oriented global path planning. The comparative results highlight its superior performance over traditional Dijkstra's algorithm, particularly in terms of adaptability to environmental changes and computational efficiency in optimal global path generation.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12108672/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149078","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Can Anthropomorphic Interfaces Improve the Ergonomics and Safety Performance of Human-Machine Collaboration in Multitasking Scenarios?-An Example of Human-Machine Co-Driving in High-Speed Trains.","authors":"Yunan Jiang, Jinyi Zhi","doi":"10.3390/biomimetics10050307","DOIUrl":"10.3390/biomimetics10050307","url":null,"abstract":"<p><p>High-speed trains are some of the most important transportation vehicles requiring human-computer collaboration. This study investigated the effects of different types of icons on recognition performance and cognitive load during frequent observation and sudden takeover tasks in high-speed trains. The results of this study can be used to improve the efficiency of human-computer collaboration tasks and driving safety. In this study, 48 participants were selected for a simulated driving experiment on a high-speed train. The recognition reaction time, operation completion time, number of recognition errors, number of operation errors, SUS scale, and NASA-TLX questionnaire for the icons were all analyzed using analysis of variance (ANOVA) and the nonparametric Mann-Whitney U test. The results show that anthropomorphic icons can reduce the drivers' visual fatigue and mental load in frequent observation tasks due to the anthropomorphic facial features attracting driver attention through simple lines and improving visual search efficiency. However, for the sudden takeover human-computer collaboration task, the facial features of the anthropomorphic icons were not recognized in a short period of time. Additionally, due to the positive emotions produced by the facial features, the drivers did not perceive the suddenness and danger of the sudden takeover human-computer collaboration task, resulting in the traditional icons being more capable of arousing the drivers' alertness and helping them take over the task quickly. At the same time, neither type of icon triggered misrecognition or operation for sufficiently skilled drivers. These research results can provide guidance for the design of icons in human-computer collaborative interfaces for different types of driving tasks in high-speed trains, which can help improve the recognition speed, reaction speed, and safety of drivers.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109194/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148892","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DEM Study and Field Experiments on Coupling Bionic Subsoilers.","authors":"Zihe Xu, Hongyan Qi, Lidong Wang, Shuo Wang, Xuanting Liu, Yunhai Ma","doi":"10.3390/biomimetics10050306","DOIUrl":"10.3390/biomimetics10050306","url":null,"abstract":"<p><p>Subsoiling is an effective tillage method for breaking up the plough pan and reducing soil bulk density. However, subsoilers often encounter challenges such as high draft resistance and excessive energy consumption during operation. In this study, the claw toes of the badger and the scales of the pangolin were selected as bionic prototypes, based on which coupling bionic subsoilers were designed. The discrete element method (DEM) was used to simulate and analyze the interactions between soil and both the standard subsoiler and coupling bionic subsoilers. Field experiments were conducted to validate the simulation results. The simulation results showed that the coupling bionic subsoilers reduced the draft force by 7.70-16.02% compared to the standard subsoiler at different working speeds. Additionally, the soil disturbance coefficient of the coupling bionic subsoilers decreased by 5.91-13.57%, and the soil bulkiness was reduced by 2.84-18.41%. The field experiment results showed that coupling bionic subsoilers reduced the average draft force by 11.06% and decreased the soil disturbance area. The field experiments validated the accuracy of DEM simulation results. This study provides valuable insights for designing more efficient subsoilers.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12108598/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148918","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Path Optimization Strategy for Unmanned Aerial Vehicles Based on Improved Black Winged Kite Optimization Algorithm.","authors":"Shuxin Wang, Bingruo Xu, Yejun Zheng, Yinggao Yue, Mengji Xiong","doi":"10.3390/biomimetics10050310","DOIUrl":"10.3390/biomimetics10050310","url":null,"abstract":"<p><p>The Black-winged Kite Optimization Algorithm (BKA) is likely to experience a sluggish convergence rate when confronted with the optimization of complex multimodal functions. The fundamental algorithm has a tendency to get stuck in local optima, thus rendering it arduous to identify the global optimal solution. When dealing with large-scale data or high-dimensional optimization challenges, the BKA algorithm entails significant computational expenses, which might lead to excessive memory usage or prolonged running durations. In order to enhance the BKA and tackle these problems, a revised Black-winged Kite Optimization Algorithm (TGBKA) that incorporates the Tent chaos mapping and Gaussian mutation strategies is put forward. The algorithm is simulated and analyzed alongside other swarm intelligence algorithms by utilizing the CEC2017 test function set. The optimization outcomes of the test functions and the function convergence curves indicate that the TGBKA demonstrates superior optimization precision, a quicker convergence speed, as well as robust anti-interference and environmental adaptability. It is also contrasted with numerous similar algorithms via simulation experiments in various scene models for Unmanned Aerial Vehicle (UAV) path planning. In comparison to other algorithms, the TGBKA produces a shorter flight route, a higher convergence speed, and stronger adaptability to complex environments. It is capable of efficiently addressing UAV path planning issues and improving the UAV's path planning abilities.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109460/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"µ-Raman Spectroscopic Temperature Dependence Study of Biomimetic Lipid 1,2-Diphytanoyl-sn-glycero-3-phosphocholine.","authors":"Carmen Rizzuto, Antonello Nucera, Irene Barba Castagnaro, Riccardo C Barberi, Marco Castriota","doi":"10.3390/biomimetics10050308","DOIUrl":"10.3390/biomimetics10050308","url":null,"abstract":"<p><p>Raman spectroscopy is one of the best techniques for obtaining information concerning the physical-chemical interactions between a lipid and a solvent. Phospholipids in water are the main elements of cell membranes and, by means of their chemical and physical structures, their cells can interact with other biological molecules (i.e., proteins and vitamins) and express their own biological functions. Phospholipids, due to their amphiphilic structure, form biomimetic membranes which are useful for studying cellular interactions and drug delivery. Synthetic systems such as DPhPC-based liposomes replicate the key properties of biological membranes. Among the different models, phospholipid mimetic membrane models of <i>lamellar vesicles</i> have been greatly supported. In this work, a biomimetic system, a deuterium solution (50 mM) of the synthetic phospholipid 1,2-diphytanoyl-sn-glycero-3-phosphocholine (DPhDC), is studied using μ-Raman spectroscopy in a wide temperature range from -181.15 °C up to 22.15 °C, including the following temperatures: -181.15 °C, -146.15 °C, -111.15 °C, -76.15 °C, -61.15 °C, -46.15 °C, -31.15 °C, -16.15 °C, -1.15 °C, 14.15 °C, and 22.15 °C. Based on the Raman evidence, phase transitions as a function of temperature are shown and grouped into five classes, where the corresponding Raman modes describe the stretching of the (C-N) bond in the choline head group (gauche) and the asymmetric stretching of the (O-P-O) bond. The acquisition temperature of each Raman spectrum characterizes the rocking mode of the methylene of the acyl chain. These findings enhance our understanding of the role of artificial biomimetic lipids in complex phospholipid membranes and provide valuable insights for optimizing their use in biosensing applications. Although the phase stability of DPhPC is known, the collected Raman data suggest subtle molecular rearrangements, possibly due to hydration and second-order transitions, which are relevant for membrane modeling and biosensing applications.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12108912/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144149045","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a Dragonfly-Inspired High Aerodynamic Force Flapping-Wing Mechanism Using Asymmetric Wing Flapping Motion.","authors":"Jinze Liang, Mengzong Zheng, Tianyu Pan, Guanting Su, Yuanjun Deng, Mengda Cao, Qiushi Li","doi":"10.3390/biomimetics10050309","DOIUrl":"10.3390/biomimetics10050309","url":null,"abstract":"<p><p>Bionic micro air vehicles are currently being popularized for military as well as civilian use and dragonflies display a wealth of skill in their remarkable flight capabilities. This study designs an asymmetric motion flapping-wing mechanism inspired by the dragonfly, using a single actuator to achieve the coupling of stroke and pitch motion. This study simulates the motion of the dragonfly's wings using the designed mechanism and experimentally validates the motion laws and aerodynamic characteristics of the mechanism. The analysis focuses on the asymmetry in the wing's stroke and pitch motion and their aerodynamic implications. The flapping-wing mechanism accurately replicates the wing motion of a real dragonfly in flight, and the maximum lift-to-weight ratio can reach up to 230.2%, demonstrating significant aerodynamic benefits. This mechanism provides valuable guidance for the structural design and kinematic control of future flapping-wing vehicles.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12108758/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148924","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Comprehensive Adaptive Enterprise Optimization Algorithm and Its Engineering Applications.","authors":"Shuxin Wang, Yejun Zheng, Li Cao, Mengji Xiong","doi":"10.3390/biomimetics10050302","DOIUrl":"10.3390/biomimetics10050302","url":null,"abstract":"<p><p>In this study, a brand-new algorithm called the Comprehensive Adaptive Enterprise Development Optimizer (CAED) is proposed to overcome the drawbacks of the Enterprise Development (ED) algorithm in complex optimization tasks. In particular, it aims to tackle the problems of slow convergence and low precision. To enhance the algorithm's ability to break free from local optima, a lens imaging reverse learning approach is incorporated. This approach creates reverse solutions by utilizing the concepts of optical imaging. As a result, it expands the search range and boosts the probability of finding superior solutions beyond local optima. Moreover, an environmental sensitivity-driven adaptive inertial weight approach is developed. This approach dynamically modifies the equilibrium between global exploration, which enables the algorithm to search for new promising areas in the solution space, and local development, which is centered on refining the solutions close to the currently best-found areas. To evaluate the efficacy of the CAED, 23 benchmark functions from CEC2005 are chosen for testing. The performance of the CAED is contrasted with that of nine other algorithms, such as the Particle Swarm Optimization (PSO), Gray Wolf Optimization (GWO), and the Antlion Optimizer (AOA). Experimental findings show that for unimodal functions, the standard deviation of the CAED is almost 0, which reflects its high accuracy and stability. In the case of multimodal functions, the optimal value obtained by the CAED is notably better than those of other algorithms, further emphasizing its outstanding performance. The CAED algorithm is also applied to engineering optimization challenges, like the design of cantilever beams and three-bar trusses. For the cantilever beam problem, the optimal solution achieved by the CAED is 13.3925, with a standard deviation of merely 0.0098. For the three-bar truss problem, the optimal solution is 259.805047, and the standard deviation is an extremely small 1.11 × 10^-7. These results are much better than those achieved by the traditional ED algorithm and the other comparative algorithms. Overall, through the coordinated implementation of multiple optimization strategies, the CAED algorithm exhibits high precision, strong robustness, and rapid convergence when searching in complex solution spaces. As such, it offers an efficient approach for solving various engineering optimization problems.</p>","PeriodicalId":8907,"journal":{"name":"Biomimetics","volume":"10 5","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-05-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12109219/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144148908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}