Journal of Bionic Engineering最新文献

{"title":"Dendritic Learning and Miss Region Detection-Based Deep Network for Multi-scale Medical Segmentation","authors":"Lin Zhong,&nbsp;Zhipeng Liu,&nbsp;Houtian He,&nbsp;Zhenyu Lei,&nbsp;Shangce Gao","doi":"10.1007/s42235-024-00499-2","DOIUrl":"10.1007/s42235-024-00499-2","url":null,"abstract":"<div><p>Automatic identification and segmentation of lesions in medical images has become a focus area for researchers. Segmentation for medical image provides professionals with a clearer and more detailed view by accurately identifying and isolating specific tissues, organs, or lesions from complex medical images, which is crucial for early diagnosis of diseases, treatment planning, and efficacy tracking. This paper introduces a deep network based on dendritic learning and missing region detection (DMNet), a new approach to medical image segmentation. DMNet combines a dendritic neuron model (DNM) with an improved SegNet framework to improve segmentation accuracy, especially in challenging tasks such as breast lesion and COVID-19 CT scan analysis. This work provides a new approach to medical image segmentation and confirms its effectiveness. Experiments have demonstrated that DMNet outperforms classic and latest methods in various performance metrics, proving its effectiveness and stability in medical image segmentation tasks.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 4","pages":"2073 - 2085"},"PeriodicalIF":4.9,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141356890","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":"Research on the Influencing Factors of Peristalsis Amplitude Based on an in Vitro Bionic Rat Stomach Model","authors":"Wentao Liang,&nbsp;Keyong Zhao,&nbsp;Peng Wu,&nbsp;Changyong Li,&nbsp;Xiaodong Chen,&nbsp;Renpan Deng,&nbsp;Zhigang Lei","doi":"10.1007/s42235-024-00566-8","DOIUrl":"10.1007/s42235-024-00566-8","url":null,"abstract":"<div><p>The In Vitro Bionic Digestion Model (IVBDM) are used to simulate the digestion process of food or pharmaceuticals in corresponding digestion tracts for obtaining the digestion data, which are expected to replace in vivo experiments with animals in the early stages of functional food or drug development, and thus have broad applications prospects. However, little is known so far about how the factors including the Young’s modulus of the model, the level, location and direction of the applied load, affect the peristalsis amplitude of the IVBDM. Based on an In Vitro Bionic Rat Stomach Model (IVBRSM), simulation and experimental analysis were conducted to examine the factors effecting the peristalsis amplitude of the IVBRSM. It is shown that Young’s modulus of the model significantly affects the peristalsis amplitude, with lower Young’s modulus resulting in larger amplitude. Load level, location, and direction also influence the peristalsis amplitude. Additionally, IVBRSM size and wall thickness play a role, with larger models requiring higher load levels or lower Young’s modulus for the same peristalsis amplitude. Simulation data correlate well with experimental results. These findings contribute to the understanding of the peristalsis state of IVBRSM under different conditions and can guide the design and fabrication of such in vitro bionic digestion models.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 5","pages":"2379 - 2394"},"PeriodicalIF":4.9,"publicationDate":"2024-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141369520","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 Hierarchical Control Scheme for Active Power-assist Lower-limb Exoskeletons","authors":"Jing Deng,&nbsp;Wenzheng Jiang,&nbsp;Haibo Gao,&nbsp;Yapeng Shi,&nbsp;Mantian Li","doi":"10.1007/s42235-024-00561-z","DOIUrl":"10.1007/s42235-024-00561-z","url":null,"abstract":"<div><p>Effectively controlling active power-assist lower-limb exoskeletons in a human-in-the-loop manner poses a substantial challenge, demanding an approach that ensures wearer autonomy while seamlessly adapting to diverse wearer needs. This paper introduces a novel hierarchical control scheme comprising five integral components: intention recognition layer, dynamics feedforward layer, force distribution layer, feedback compensation layer, as well as sensors and actuators. The intention recognition layer predicts the wearer’s movement and enables wearer-dominant movement through integrated force and position sensors. The force distribution layer effectively resolves the statically indeterminate problem in the context of double-foot support, showcasing flexible control modes. The dynamics feedforward layer mitigates the effect of the exoskeleton itself on movement. Meanwhile, the feedback compensation layer provides reliable closed-loop control. This approach mitigates abrupt changes in joint torques during frequent transitions between swing and stance phases by decomposed dynamics. Validating this innovative hierarchical control scheme on a hydraulic exoskeleton platform through a series of experiments, the results demonstrate its capability to deliver assistance in various modes such as stepping, squatting, and jumping while adapting seamlessly to different terrains.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 5","pages":"2184 - 2198"},"PeriodicalIF":4.9,"publicationDate":"2024-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141370698","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":"Boosted Spider Wasp Optimizer for High-dimensional Feature Selection","authors":"Elfadil A. Mohamed,&nbsp;Malik Sh. Braik,&nbsp;Mohammed Azmi Al-Betar,&nbsp;Mohammed A. Awadallah","doi":"10.1007/s42235-024-00558-8","DOIUrl":"10.1007/s42235-024-00558-8","url":null,"abstract":"<div><p>With the increasing dimensionality of the data, High-dimensional Feature Selection (HFS) becomes an increasingly difficult task. It is not simple to find the best subset of features due to the breadth of the search space and the intricacy of the interactions between features. Many of the Feature Selection (FS) approaches now in use for these problems perform significantly less well when faced with such intricate situations involving high-dimensional search spaces. It is demonstrated that meta-heuristic algorithms can provide sub-optimal results in an acceptable amount of time. This paper presents a new binary Boosted version of the Spider Wasp Optimizer (BSWO) called Binary Boosted SWO (BBSWO), which combines a number of successful and promising strategies, in order to deal with HFS. The shortcomings of the original BSWO, including early convergence, settling into local optimums, limited exploration and exploitation, and lack of population diversity, were addressed by the proposal of this new variant of SWO. The concept of chaos optimization is introduced in BSWO, where initialization is consistently produced by utilizing the properties of sine chaos mapping. A new convergence parameter was then incorporated into BSWO to achieve a promising balance between exploration and exploitation. Multiple exploration mechanisms were then applied in conjunction with several exploitation strategies to effectively enrich the search process of BSWO within the search space. Finally, quantum-based optimization was added to enhance the diversity of the search agents in BSWO. The proposed BBSWO not only offers the most suitable subset of features located, but it also lessens the data’s redundancy structure. BBSWO was evaluated using the k-Nearest Neighbor (k-NN) classifier on 23 HFS problems from the biomedical domain taken from the UCI repository. The results were compared with those of traditional BSWO and other well-known meta-heuristics-based FS. The findings indicate that, in comparison to other competing techniques, the proposed BBSWO can, on average, identify the least significant subsets of features with efficient classification accuracy of the k-NN classifier.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 5","pages":"2424 - 2459"},"PeriodicalIF":4.9,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141381952","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":"Improving PID Controller Performance in Nonlinear Oscillatory Automatic Generation Control Systems Using a Multi-objective Marine Predator Algorithm with Enhanced Diversity","authors":"Yang Yang,&nbsp;Yuchao Gao,&nbsp;Jinran Wu,&nbsp;Zhe Ding,&nbsp;Shangrui Zhao","doi":"10.1007/s42235-024-00548-w","DOIUrl":"10.1007/s42235-024-00548-w","url":null,"abstract":"<div><p>Power systems are pivotal in providing sustainable energy across various sectors. However, optimizing their performance to meet modern demands remains a significant challenge. This paper introduces an innovative strategy to improve the optimization of PID controllers within nonlinear oscillatory Automatic Generation Control (AGC) systems, essential for the stability of power systems. Our approach aims to reduce the integrated time squared error, the integrated time absolute error, and the rate of change in deviation, facilitating faster convergence, diminished overshoot, and decreased oscillations. By incorporating the spiral model from the Whale Optimization Algorithm (WOA) into the Multi-Objective Marine Predator Algorithm (MOMPA), our method effectively broadens the diversity of solution sets and finely tunes the balance between exploration and exploitation strategies. Furthermore, the QQSMOMPA framework integrates quasi-oppositional learning and Q-learning to overcome local optima, thereby generating optimal Pareto solutions. When applied to nonlinear AGC systems featuring governor dead zones, the PID controllers optimized by QQSMOMPA not only achieve 14<span>(%)</span> reduction in the frequency settling time but also exhibit robustness against uncertainties in load disturbance inputs.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 5","pages":"2497 - 2514"},"PeriodicalIF":4.9,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s42235-024-00548-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141377435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Development of a Bio-inspired Tailless FWMAV with High-Frequency Flapping Wings Trajectory Tracking Control","authors":"Qingcheng Guo,&nbsp;Chaofeng Wu,&nbsp;Yichen Zhang,&nbsp;Feng Cui,&nbsp;Wu Liu,&nbsp;Xiaosheng Wu,&nbsp;Junguo Lu","doi":"10.1007/s42235-024-00554-y","DOIUrl":"10.1007/s42235-024-00554-y","url":null,"abstract":"<div><p>The development of a tailless Flapping Wing Micro Aerial Vehicle (FWMAV) inspired by the hummingbird is presented in this work. By implementing mechanical simplifications, it is possible to use planar machining technology for manufacturing of the FWMAV’s body, greatly reducing assembly errors. Traditionally, studies on flapping wing aircraft are limited to open-loop wing kinematics control. In this work, an instantaneous closed-loop wing trajectory tracking control system is introduced to minimize wings’ trajectory tracking errors. The control system is based on Field-Oriented Control (FOC) with a loop shaping compensation technique near the flapping frequency. Through frequency analysis, the loop shaping compensator ensures the satisfactory bandwidth and performance for the closed-loop flapping system. To implement the proposed controller, a compact autopilot board integrated with FOC hardware is designed, weighing only 2.5 g. By utilizing precise wing trajectory tracking control, the hummingbird-inspired FWMAV demonstrates superior ability to resist external disturbances and exhibits reduced attitude tracking errors during hovering flight compared to the open-loop wing motion.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 5","pages":"2145 - 2166"},"PeriodicalIF":4.9,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141378811","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":"Single Solution Optimization Mechanism of Teaching-Learning-Based Optimization with Weighted Probability Exploration for Parameter Estimation of Photovoltaic Models","authors":"Jinge Shi,&nbsp;Yi Chen,&nbsp;Zhennao Cai,&nbsp;Ali Asghar Heidari,&nbsp;Huiling Chen","doi":"10.1007/s42235-024-00553-z","DOIUrl":"10.1007/s42235-024-00553-z","url":null,"abstract":"<div><p>This article presents a novel optimization approach called RSWTLBO for accurately identifying unknown parameters in photovoltaic (PV) models. The objective is to address challenges related to the detection and maintenance of PV systems and the improvement of conversion efficiency. RSWTLBO combines adaptive parameter <i>w</i>, Single Solution Optimization Mechanism (SSOM), and Weight Probability Exploration Strategy (WPES) to enhance the optimization ability of TLBO. The algorithm achieves a balance between exploitation and exploration throughout the iteration process. The SSOM allows for local exploration around a single solution, improving solution quality and eliminating inferior solutions. The WPES enables comprehensive exploration of the solution space, avoiding the problem of getting trapped in local optima. The algorithm is evaluated by comparing it with 10 other competitive algorithms on various PV models. The results demonstrate that RSWTLBO consistently achieves the lowest Root Mean Square Errors on single diode models, double diode models, and PV module models. It also exhibits robust performance under varying irradiation and temperature conditions. The study concludes that RSWTLBO is a practical and effective algorithm for identifying unknown parameters in PV models.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 5","pages":"2619 - 2645"},"PeriodicalIF":4.9,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141257035","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":"Fast and Accurate Pupil Localization in Natural Scenes","authors":"Zhuohao Guo,&nbsp;Manjia Su,&nbsp;Yihui Li,&nbsp;Tianyu Liu,&nbsp;Yisheng Guan,&nbsp;Haifei Zhu","doi":"10.1007/s42235-024-00550-2","DOIUrl":"10.1007/s42235-024-00550-2","url":null,"abstract":"<div><p>The interferences, such as the background, eyebrows, eyelashes, eyeglass frames, illumination variations, and specular lens reflection pose challenges for pupil localization in natural scenes. In this paper, we propose a novel method comprising improved YOLOv8 and Illumination Adaptive Algorithm (IAA), for fast and accurate pupil localization in natural scenes. We introduced deformable convolution into the backbone of YOLOv8 to enable the model to extract the eye regions more accurately, thus avoiding the interference of background outside the eye on subsequent pupil localization. The IAA can reduce the interference of illumination variations and lens reflection by adjusting automatically the grayscale of the image according to the exposure. Experimental results verified that the improved YOLOv8 exhibited an eye detection accuracy (IOU<span>(ge)</span>0.5) of 90.2%, while the IAA leads to a 9.15% improvement on 5-pixels error ratio <span>({varvec{e}}_{5})</span> with processing times in the tens of microseconds on GPU. Experimental results on the benchmark database CelebA show that the proposed method for pupil localization achieves an accuracy of 83.05% on <span>({varvec{e}}_{5})</span> and achieves real-time performance of 210 FPS on GPU, outperforming other advanced methods.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 5","pages":"2646 - 2657"},"PeriodicalIF":4.9,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s42235-024-00550-2.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141257095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Efficiency Enhancement in Hammer Mills through Biomimetic Pigeon Wing Sieve Design","authors":"Jindong Wang,&nbsp;Zhanyang Wu,&nbsp;Yi Chen,&nbsp;Yuhong Xie,&nbsp;Zhongrong Zhou","doi":"10.1007/s42235-024-00551-1","DOIUrl":"10.1007/s42235-024-00551-1","url":null,"abstract":"<div><p>Hammer mill is widely used in the feed processing industry. During its operation, the material is thrown against the inner wall of the sieve after being broken by the hammer. Limited by the annular structure sieve, the grinded material tends to produce a “air- material circulation layer” on the inner wall of the sieve, leading to problems such as low grinding efficiency and high grinding energy consumption. Considering the disruptive characteristics of the special profile structure of a pigeon’s wing on the airflow field, we extract the geometric characteristics of the coupling element and optimize the related structural parameters. Based on the principles of bionics, a new wing sieve is then designed, and its efficient grinding mechanism is studied. Compared to the commercial sieve, the experimental results indicate the bio-inspired sieve can significantly improve the material productivity and grinding quality.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 5","pages":"2366 - 2378"},"PeriodicalIF":4.9,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141257181","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":"Multi-strategy Hybrid Coati Optimizer: A Case Study of Prediction of Average Daily Electricity Consumption in China","authors":"Gang Hu,&nbsp;Sa Wang,&nbsp;Essam H. Houssein","doi":"10.1007/s42235-024-00549-9","DOIUrl":"10.1007/s42235-024-00549-9","url":null,"abstract":"<div><p>The power sector is an important factor in ensuring the development of the national economy. Scientific simulation and prediction of power consumption help achieve the balance between power generation and power consumption. In this paper, a Multi-strategy Hybrid Coati Optimizer (MCOA) is used to optimize the parameters of the three-parameter combinatorial optimization model TDGM(1,1,<i>r</i>,<i>ξ</i>,<i>Csz</i>) to realize the simulation and prediction of China’s daily electricity consumption. Firstly, a novel MCOA is proposed in this paper, by making the following improvements to the Coati Optimization Algorithm (COA): (i) Introduce improved circle chaotic mapping strategy. (ii) Fusing Aquila Optimizer, to enhance MCOA's exploration capabilities. (iii) Adopt an adaptive optimal neighborhood jitter learning strategy. Effectively improve MCOA escape from local optimal solutions. (iv) Incorporating Differential Evolution to enhance the diversity of the population. Secondly, the superiority of the MCOA algorithm is verified by comparing it with the newly proposed algorithm, the improved optimization algorithm, and the hybrid algorithm on the CEC2019 and CEC2020 test sets. Finally, in this paper, MCOA is used to optimize the parameters of TDGM(1,1,<i>r</i>,<i>ξ</i>,<i>Csz</i>), and this model is applied to forecast the daily electricity consumption in China and compared with the predictions of 14 models, including seven intelligent algorithm-optimized TDGM(1,1,<i>r</i>,<i>ξ</i>,<i>Csz</i>), and seven forecasting models. The experimental results show that the error of the proposed method is minimized, which verifies the validity of the proposed method.</p></div>","PeriodicalId":614,"journal":{"name":"Journal of Bionic Engineering","volume":"21 5","pages":"2540 - 2568"},"PeriodicalIF":4.9,"publicationDate":"2024-05-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141193078","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}