Journal of Bionic Engineering最新文献

{"title":"Global–Local Hybrid Modulation Network for Retinal Vessel and Coronary Angiograph Segmentation","authors":"Pengfei Cai,&nbsp;Biyuan Li,&nbsp;Jinying Ma,&nbsp;Xiao Tian,&nbsp;Jun Yan","doi":"10.1007/s42235-025-00727-3","DOIUrl":"10.1007/s42235-025-00727-3","url":null,"abstract":"<div><p>The segmentation of retinal vessels and coronary angiographs is essential for diagnosing conditions such as glaucoma, diabetes, hypertension, and coronary artery disease. However, retinal vessels and coronary angiographs are characterized by low contrast and complex structures, posing challenges for vessel segmentation. Moreover, CNN-based approaches are limited in capturing long-range pixel relationships due to their focus on local feature extraction, while ViT-based approaches struggle to capture fine local details, impacting tasks like vessel segmentation that require precise boundary detection. To address these issues, in this paper, we propose a Global–Local Hybrid Modulation Network (GLHM-Net), a dual-encoder architecture that combines the strengths of CNNs and ViTs for vessel segmentation. First, the Hybrid Non-Local Transformer Block (HNLTB) is proposed to efficiently consolidate long-range spatial dependencies into a compact feature representation, providing a global perspective while significantly reducing computational overhead. Second, the Collaborative Attention Fusion Block (CAFB) is proposed to more effectively integrate local and global vessel features at the same hierarchical level during the encoding phase. Finally, the proposed Feature Cross-Modulation Block (FCMB) better complements the local and global features in the decoding stage, effectively enhancing feature learning and minimizing information loss. The experiments conducted on the DRIVE, CHASEDB1, DCA1, and XCAD datasets, achieving AUC values of 0.9811, 0.9864, 0.9915, and 0.9919, F1 scores of 0.8288, 0.8202, 0.8040, and 0.8150, and IOU values of 0.7076, 0.6952, 0.6723, and 0.6878, respectively, demonstrate the strong performance of our proposed network for vessel segmentation.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"2050 - 2074"},"PeriodicalIF":5.8,"publicationDate":"2025-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimized Decision-Making Framework for Detecting Important Factors Influencing Students’ Innovative Capabilities","authors":"Chengwen Wu,&nbsp;Li Quan,&nbsp;Xiaoqin Zhang,&nbsp;Huiling Chen","doi":"10.1007/s42235-025-00703-x","DOIUrl":"10.1007/s42235-025-00703-x","url":null,"abstract":"<div><p>Developing innovative capabilities in university students is essential for individual career success and broader societal advancement. This study introduces a predictive Feature Selection (FS) model named bWRBA-SVM-FS, which combines an enhanced Bat Algorithm (BA) and Support Vector Machine (SVM). To enhance the optimization capability of BA, water follow search and random follow search are introduced to optimize the efficiency and accuracy of the feature subset search. Experimental validation conducted on the IEEE CEC 2017 benchmark functions and the talented innovative capacity dataset demonstrates the efficacy of the proposed method relative to peer and prominent machine learning models. The experimental results reveal that the predictive accuracy of the bWRBA-SVM-FS model is 97.503%, with a sensitivity of 98.391%. Our findings indicate significant predictors of innovation capacity, including project application goals, educational background, and interdisciplinary thinking abilities. The bWRBA-SVM-FS model offers effective strategies for talent selection in higher education, fostering the development of future research leaders.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"2075 - 2114"},"PeriodicalIF":5.8,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Flea Beetle-Inspired Combustion-Powered Jumping Robot","authors":"Zonghui Sun,&nbsp;Tianhao Zhang,&nbsp;Le Zong,&nbsp;Pingping Yang,&nbsp;Wenjie Li,&nbsp;Zhengzhong Huang,&nbsp;Guoteng Zhang,&nbsp;Siqin Ge","doi":"10.1007/s42235-025-00726-4","DOIUrl":"10.1007/s42235-025-00726-4","url":null,"abstract":"<div><p>Bio-inspired jumping robots have emerged as a promising solution for traversing complex terrains inaccessible to conventional locomotion systems. Drawing upon the exceptional jumping kinematics observed in insects, researchers have developed multiple robotic prototypes mimicking biological propulsion mechanisms. However, the principal technological barrier resides in actuator systems, where current energy storage technologies suffer from inadequate energy density, fundamentally limiting takeoff velocity and jumping height. To overcome these limitations, we present a novel combustion-explosive propulsion system exhibiting high mass-specific energy release and rapid acceleration characteristics. By integrating this propulsion mechanism with a unique jumping leg structure, experimental validation through prototype testing demonstrated vertical leaps reaching 20 cm (1.67 times body length) under laboratory conditions, accompanied by comprehensive thermodynamic modeling using ABAQUS simulations that validated the effectiveness of this actuation system. The integrated design approach combines bionic structural design with combustible fuel formulations to offer new possibilities for the development of highly flexible robotic systems capable of negotiating obstacles in disaster response scenarios.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"1622 - 1636"},"PeriodicalIF":5.8,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a Magnetically-Actuated Capsule Robot for Biopsy Sampling Using SMA","authors":"Hao Zhang,&nbsp;Keding Luo,&nbsp;Feihao Wang,&nbsp;Shishi Li,&nbsp;Xianghe Meng,&nbsp;Hui Xie","doi":"10.1007/s42235-025-00734-4","DOIUrl":"10.1007/s42235-025-00734-4","url":null,"abstract":"<div><p>Capsule Robots (CRs) with active locomotion improve on the inefficiency of passive locomotion in capsule endoscopes, showing great potential for clinical use. However, despite the development of various CR types, efficient locomotion and functional integration remain challenges due to space limitations and increasing demands. Additionally, many CRs are overly complex, so simplifying their structure while maintaining functionality is essential. This paper presents a novel magnetically actuated CR with two internal permanent magnets for oscillating locomotion and anchoring, along with a Shape Memory Alloy (SMA)-driven actuator for biopsy sampling. Compared to existing CRs, this design simplifies the structure while ensuring biopsy functionality and leaving space for a micro-CCD. The robot’s dynamics are modeled to guide its structural design and locomotion strategy. SMA characteristics are also examined to optimize the biopsy module’s parameters, improving efficiency and success rates. The CR undergoes experiments to assess safety, locomotion performance, and functionality, with results showing stable steering, and advantages in driving height, speed, and accuracy. Finally, the CR’s biopsy capabilities are validated in a gastric model and ex vivo stomach. This work offers a novel solution for gastrointestinal disease diagnosis and treatment, enhancing the application of CRs in biomedical engineering.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"1609 - 1621"},"PeriodicalIF":5.8,"publicationDate":"2025-07-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Three-Dimensional-Printed Polycaprolactone/Nanohydroxyapatite-Nanoclay Scaffold for Bone Tissue Engineering Applications","authors":"Saba Nazari,&nbsp;Seyed Ali Poursamar,&nbsp;Mitra Naeimi,&nbsp;Mohammad Rafienia,&nbsp;Majid Monajjemi","doi":"10.1007/s42235-025-00704-w","DOIUrl":"10.1007/s42235-025-00704-w","url":null,"abstract":"<div><p>The field of bone tissue engineering has experienced an increase in prevalence due to the inherent challenge of the natural regeneration of significant bone deformities. This investigation focused on the preparation of Three-Dimensional (3D)-printed Polycaprolactone (PCL) scaffolds with varying proportions of Nanohydroxyapatite (NHA) and Nanoclay (NC), and their physiochemical and biological properties were assessed. The mechanical properties of PCL are satisfactory; however, its hydrophobic nature and long-term degradation hinder its use in scaffold fabrication. NHA and NC have been employed to improve the hydrophilic characteristics, mechanical strength, adhesive properties, biocompatibility, biodegradability, and osteoconductive behavior of PCL. The morphology results demonstrated 3D-printed structures with interconnected rectangular macropores and proper nanoparticle distribution. The sample containing 70 wt% NC showed the highest porosity (65.98 ± 2.54%), leading to an increased degradation rate. The compressive strength ranged from 10.65 ± 1.90 to 84.93 ± 9.93 MPa, which is directly proportional to the compressive strength of cancellous bone (2–12 MPa). The wettability, water uptake, and biodegradability of PCL scaffolds considerably improved as the amount of NC increased. The results of the cellular assays exhibited increased proliferation, viability, and adhesion of MG-63 cells due to the addition of NHA and NC to the scaffolds. Finally, according to the in vitro results, it can be concluded that 3D-printed samples with higher amounts of NC can be regarded as a suitable scaffold for expediting the regeneration process of bone defects.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"1863 - 1880"},"PeriodicalIF":5.8,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and Application of a Bionic Origami Mechanism Based on Adjustable Bistability","authors":"Daiwei Yu,&nbsp;Shenlong Wang,&nbsp;Yongge Li","doi":"10.1007/s42235-025-00731-7","DOIUrl":"10.1007/s42235-025-00731-7","url":null,"abstract":"<div><p>The unique arrangement of panels and folds in origami structures provides distinct mechanical properties, such as the ability to achieve multiple stable states, reconfigure shapes, and adjust performance. However, combining movement and control functions into a simple yet efficient origami-based system remains a challenge. This study introduces a practical and efficient bistable origami mechanism, realized through lightweight and tailored designs in two bio-inspired applications. The mechanism is constructed from two thin materials: a PET sheet with precisely cut flexible hinges and a pre-tensioned elastic band. Its mechanical behavior is studied using nonlinear spring models. These components can be rearranged to create new bistable structures, enabling the integration of movement and partial control features. Inspired by natural systems, the mechanism is applied to two examples: a passive origami gripper that can quickly and precisely grasp moving objects in less than 100 ms, and an active magnetic-driven fish tail capable of high-speed swimming in multiple modes, reaching a maximum straight-line speed of 3.35 body lengths per second and a turning speed of 2.3 radians per second. This bistable origami mechanism highlights its potential for flexible design and high performance, offering useful insights for developing origami-based robotic systems.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"1717 - 1730"},"PeriodicalIF":5.8,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Modified Cubic-Honeycomb-Plate Structure: A Novel Bone Regeneration Scaffold with Enhanced Mechanical Stiffness Achieved Through High Printing Fidelity","authors":"Rigoberto Lopez Reyes,&nbsp;Min-Soo Ghim,&nbsp;Eun Chae Kim,&nbsp;Nae-Un Kang,&nbsp;Dongwoo Sohn,&nbsp;Young-Sam Cho","doi":"10.1007/s42235-025-00733-5","DOIUrl":"10.1007/s42235-025-00733-5","url":null,"abstract":"<div><p>Achieving exact printing fidelity in polymer-based bone regeneration scaffolds through additive manufacturing, particularly those of dispensing-type, remains a significant challenge. During fabrication, scaffolds often deviate from the intended design geometry, which can negatively affect their performance. Additionally, achieving mechanical properties similar to natural bone in scaffolds remains challenging. Therefore, this study introduces the Hybrid Modified Cubic-Honeycomb Plate (hybrid MCHP) structure to improve printing fidelity and mechanical properties over previous bone regeneration scaffolds through innovative geometry design. This hybrid MCHP scaffold was inspired by cubic honeycomb and plate-lattice structures due to their excellent mechanical performance and well-optimized geometry, which ensure optimal printability. The effective elastic stiffness of the proposed structure and control group was predicted using a numerical Asymptotic Expansion Homogenization (AEH) model. Bone regeneration scaffolds were fabricated using Polycaprolactone (PCL) and a 3D printer with a Precision Extrusion Deposition (PED) system. Printing fidelity in manufactured scaffolds was then evaluated, resulting in a printing fidelity of 97.93 ± 1.1% for the hybrid MCHP-structure scaffold (compared to 82.31 ± 3.6% and 92.00 ± 2.5% in the case of Kagome-structure and modified honeycomb (MHC)-structure scaffolds, which are the control groups). Mechanical testing of the hybrid MCHP-structure scaffold using a Universal Testing Machine (UTM) depicted similarity with 91.1% of the numerical estimated effective elastic stiffness (compared to 82.8% and 79.0% in the case of Kagome-structure and MHC-structure scaffolds, which serve as the control groups). The biological potential of the scaffolds was evaluated through in vitro studies using MC3T3-E1 pre-osteoblasts. The CCK-8 assay showed significantly enhanced cell viability and proliferation on the hybrid MCHP scaffold at all time points (days 1, 7, and 14), consistently outperforming the Kagome and MHC scaffolds. Additionally, immunofluorescence staining analysis revealed abundant focal adhesions and uniform nuclear distribution, highlighting the superior cytocompatibility and effective support for cellular activity of the hybrid MCHP scaffold.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"1881 - 1909"},"PeriodicalIF":5.8,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Bioinspired Discrete Two-Stage Surrogate-Assisted Algorithm for Large-Scale Traveling Salesman Problem","authors":"Ai-Qing Tian,&nbsp;Hong-Xia Lv,&nbsp;Xiao-Yang Wang,&nbsp;Jeng-Shyang Pan,&nbsp;Václav Snášel","doi":"10.1007/s42235-025-00724-6","DOIUrl":"10.1007/s42235-025-00724-6","url":null,"abstract":"<div><p>The Traveling Salesman Problem (TSP) is a well-known NP-Hard problem, particularly challenging for conventional solving methods due to the curse of dimensionality in high-dimensional instances. This paper proposes a novel Double-stage Surrogate-assisted Pigeon-inspired Optimization algorithm (DOSA-PIO) to address this issue. DOSA-PIO integrates the ordering points to identify the clustering structure method for data clustering and employs a local surrogate model to assist the evolution of the Pigeon-inspired Optimization (PIO) algorithm. This combination enhances the algorithm’s ability to explore the solution space and converge to optimal solutions more effectively. Additionally, two novel approaches are introduced to extend the generalizability of continuous algorithms for solving discrete problems, enabling the adaptation of continuous optimization techniques to the discrete nature of TSP. Extensive experiments using benchmark functions and high-dimensional TSP instances demonstrate that DOSA-PIO significantly outperforms comparative algorithms in various dimensions (10D, 20D, 30D, 50D, and 100D). The proposed algorithm provides superior solutions compared to traditional methods, highlighting its potential for solving high-dimensional TSPs. By leveraging advanced data clustering techniques and surrogate-assisted optimization, DOSA-PIO offers an effective solution for high-dimensional TSP instances, with experimental results confirming its superior performance and potential for practical applications in complex optimization problems.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"1926 - 1939"},"PeriodicalIF":5.8,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891412","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Black-Winged Kite Algorithm with Deep Learning for Autism Detection of Privacy Preserved Data","authors":"Kalyani Nagarajan,&nbsp;Sasikumar Rajagopalan","doi":"10.1007/s42235-025-00722-8","DOIUrl":"10.1007/s42235-025-00722-8","url":null,"abstract":"<div><p>Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition that causes multiple challenges in behavioral and communication activities. In the medical field, the data related to ASD, the security measures are integrated in this research responsibly and effectively to develop the Mobile Neuron Attention Stage-by-Stage Network (MNASNet) model, which is the integration of both Mobile Network (MobileNet) and Neuron Attention Stage-by-Stage. The steps followed to detect ASD with privacy-preserved data are data normalization, data augmentation, and K-Anonymization. The clinical data of individuals are taken initially and preprocessed using the Z-score Normalization. Then, data augmentation is performed using the oversampling technique. Subsequently, K-Anonymization is effectuated by utilizing the Black-winged Kite Algorithm to ensure the privacy of medical data, where the best fitness solution is based on data utility and privacy. Finally, after improving the data privacy, the developed approach MNASNet is implemented for ASD detection, which achieves highly accurate results compared to traditional methods to detect autism behavior. Hence, the final results illustrate that the proposed MNASNet achieves an accuracy of 92.9%, TPR of 95.9%, and TNR of 90.9% at the k-samples of 8.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"1985 - 2011"},"PeriodicalIF":5.8,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Study on Microscopic Interfacial Mechanical Properties of the Gecko's Foot Adhesion Mechanism","authors":"Yilin Su,&nbsp;Xuyan Hou,&nbsp;Kaiwei Li,&nbsp;Zhe Wang,&nbsp;Lei Ren,&nbsp;Luquan Ren","doi":"10.1007/s42235-025-00725-5","DOIUrl":"10.1007/s42235-025-00725-5","url":null,"abstract":"<div><p>The gecko's feet possess unique microstructures that enable strong adhesive forces when interacting with various surfaces. Understanding the interfacial forces generated by these microstructures is crucial for deciphering their adhesion mechanism. This study developed a contact mechanics model based on van der Waals forces and frictional self-locking effects, incorporating both the spatular pad and spatular shaft of the gecko’s foot microstructures. Building on this foundation, a discrete element simulation model was established using the bonding method to replicate the contact between the gecko's spatula and different surfaces. The dynamic adhesion and detaching processes under normal and tangential external forces were simulated, allowing for the analysis of variation curves of normal and tangential adhesion forces at different detaching angles. This provided insights into the directional adhesion mechanics of the gecko's spatula. Furthermore, a force measurement system was constructed using a multi-degree-of-freedom nano-manipulator and an atomic force microscope within a scanning electron microscope. This system was used to experimentally test the adhesion characteristics of the gecko’s foot microstructures, validating the accuracy of the proposed adhesion mechanics model.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"22 4","pages":"1776 - 1787"},"PeriodicalIF":5.8,"publicationDate":"2025-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144891380","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}