Biomimetics最新文献

Small object detection, as an important research topic in computer vision, has been widely applied in aerial visual tasks such as remote sensing and UAV imagery. However, due to challenges such as small object size, large-scale variations, and complex backgrounds, existing detection models often struggle to capture fine-grained semantics and high-resolution texture information in aerial scenes, leading to limited performance. To address these issues, this paper proposes an efficient aerial small object detection model, EABI-DETR (Efficient Attention and Bi-level Integration DETR), based on the RT-DETR framework. The proposed model introduces systematic enhancements from three aspects: (1) A lightweight backbone network, C2f-EMA, is developed by integrating the C2f structure with an efficient multi-scale attention (EMA) mechanism. This design jointly models channel semantics and spatial details with minimal computational overhead, thereby strengthening the perception of small objects. (2) A P2-BiFPN bi-directional multi-scale fusion module is further designed to incorporate shallow high-resolution features. Through top-down and bottom-up feature interactions, this module enhances cross-scale information flow and effectively preserves the fine details and textures of small objects. (3) To improve localization robustness, a Focaler-MPDIoU loss function is introduced to better handle hard samples during regression optimization. Experiments conducted on the VisDrone2019 dataset demonstrate that EABI-DETR achieves 53.4% mAP@0.5 and 34.1% mAP@0.5:0.95, outperforming RT-DETR by 6.2% and 5.1%, respectively, while maintaining high inference efficiency. These results confirm the effectiveness of integrating lightweight attention mechanisms and shallow feature fusion for aerial small object detection, offering a new paradigm for efficient UAV-based visual perception.

Animal welfare education requires pedagogical models that bridge conceptual knowledge with practice. This study presents GamifyWELL, a biomimetic, gamified learning environment for students, farmers, and veterinary technicians. Grounded in ecological principles of adaptation, diversification, and niche specialization, the design emulates how living systems evolve through feedback and cooperation. These principles were translated into an instructional model that integrates a core pathway (Pre-Test, Levels 1-4, Post-Test) with optional enrichment tasks and a role-specific Reward Marketplace. Question formats are constant across levels (MCQ, image-based, video-based) while cognitive difficulty increases, culminating in Positive Welfare scenarios. We describe the learning design structure and report preliminary implementation observations using a mixed-methods evaluation plan (pre/post knowledge assessments and engagement indicators). Results from early deployment indicate strong usability and engagement, with high voluntary uptake of enrichment tasks and positive learner feedback on role-tailored rewards; full empirical testing is in progress. Findings support the feasibility and pedagogical promise of biomimetic gamification to enhance knowledge, motivation, and intended practice in animal welfare education. GamifyWELL offers a replicable framework for nature-inspired instructional design that can be extended to allied sustainability domains.

The Arctic Puffin Optimization (APO) algorithm, proposed in 2024, is a swarm intelligence optimization. Similar to other swarm intelligence optimization algorithms, it suffers from issues such as slow convergence in the early stage, being easy to fall into local optima, and insufficient balance between exploration and exploitation. To address these limitations, an improved APO (IAPO) algorithm incorporating multiple strategies is proposed. Firstly, a mirror opposition-based learning mechanism is introduced to expand the search scope, improving the efficiency of searching for the optimal solution, which enhances the algorithm's convergence accuracy and optimization speed. Secondly, a dynamic differential evolution strategy with adaptive parameters is integrated to improve the algorithm's ability to escape local optima and achieve precise optimization. Comparative experimental results between IAPO and eight other optimization algorithms on 20 benchmark functions, as well as CEC2019 and CEC2022 test functions, show that IAPO achieves higher accuracy, faster convergence, and superior robustness, securing first-place average rankings of 1.35, 1.30, 1.25, and 1.08 on the 20 benchmark functions, CEC 2019, 10- and 20-dimensional CEC 2022 test sets, respectively. Finally, simulation experiments were conducted on three engineering optimization design problems. IAPO achieved optimal values of 5.2559 × 10^-1, 1.09 × 10³, and 1.49 × 10⁴ for these engineering problems, ranking first in all cases. This further validates the effectiveness and practicality of the IAPO algorithm.

Among the gynecological cancers, ovarian cancer is the most fatal. Despite advancements in modern medicine, the survival rate is abysmally low among ovarian cancer patients. Ovarian cancer poses several unique challenges, like late diagnosis due to the initial vagueness of the symptoms and lack of effective screening protocols. Recently, biomaterials have been explored and utilized extensively for the diagnosis, treatment, and screening of ovarian malignancies. Biomaterials can help bypass the obstacles of traditional chemotherapy and enhance imaging capabilities. They are also indispensable for next-generation biosensors and tumor organoids. Biomaterials inspired by biomimetic strategies that replicate the structural, chemical, and functional properties of natural biological systems have proven to have better functionalities. While numerous review articles have examined biomaterials in oncology, there is a lack of reviews dedicated specifically to their applications in ovarian cancer. This review aims to address this critical gap by providing the first comprehensive overview of the current biomaterial research on ovarian cancer and highlighting key challenges, opportunities, and future directions in this evolving interdisciplinary field.

Online parameter tuning significantly enhances the performance of optimization algorithms by dynamically adjusting mutation and crossover rates. However, current approaches often suffer from high computational costs and limited adaptability to complex and dynamic fitness landscapes, particularly when machine learning methods are employed. This work proposes a quantized shallow neural network (SNN) as an efficient learning-based component for dynamically adjusting the mutation and crossover rates of a genetic algorithm (GA). By leveraging runtime-generated data and applying quantization techniques like Quantization-aware Training (QaT) and Post-training Quantization (PtQ), the proposed approach reduces computational overhead while maintaining competitive performance. Experimental evaluation on 15 continuous benchmark functions demonstrates that the quantized SNN achieves high-quality solutions while significantly reducing execution time compared to alternative shallow learning methods. This study highlights the potential of quantized SNNs to balance efficiency and performance, broadening the applicability of shallow learning in optimization.

In this study, we used the hydrophobic-polar (HP) two-dimensional square and three-dimensional cubic lattice models for the problem of protein structure prediction (PSP). This kind of lattice reduces computational time and calculations, the conformational space from 9n to 3n-2 for the 2D square lattice and 5n-2 for the 3D cubic lattice. Even within this context, it remains challenging for genetic algorithms or other metaheuristics to identify the optimal solutions. The contributions of the paper consist of: (1) implementation of a high-performing novel genetic algorithm (GA); instead of considering only the self-avoiding walk (SAW) conformations approached in other work, we decided to allow any conformation to appear in the population at all stages of the proposed all conformations biomimetic genetic algorithm (ACGA). This increases the probability of achieving good conformations (self avoiding walk ones), with the lowest energy. In addition to classical crossover and mutation operators, (2) we introduced specific translation operators for these two operations. We have proposed and implemented an HP Protein Visualizer tool which offers interpretability, a hybrid approach in that the visualizer gives some insight to the algorithm, that analyse and optimise protein structures HP model. The program resulted based on performed research, provides a molecular modeling tool for studying protein folding using technologies such as Node.js, Express and p5js for 3D rendering, and includes optimization algorithms to simulate protein folding.

With the expansion of unmanned aerial vehicles (UAVs) into complex three-dimensional (3D) terrains for reconnaissance, rescue, and related missions, traditional path planning methods struggle to meet multi-constraint and multi-objective requirements. Existing swarm intelligence algorithms, limited by the "no free lunch" theorem, also face challenges when the standard Information Acquisition Optimizer (IAO) is applied to such tasks, including low exploration efficiency in high-dimensional search spaces, rapid loss of population diversity, and improper boundary handling. To address these issues, this study proposes a Multi-Strategy Enhanced Information Acquisition Optimizer (MEIAO). First, a Levy Flight-based information collection strategy is introduced to leverage its combination of short-range local searches and long-distance jumps, thereby broadening global exploration. Second, an adaptive differential evolution operator is designed to dynamically balance exploration and exploitation via a variable mutation factor, while crossover and greedy selection mechanisms help maintain population diversity. Third, a globally guided boundary handling strategy adjusts out-of-bound dimensions to feasible regions, preventing the generation of low-quality paths. Performance was evaluated on the CEC2017 (dim = 30/50/100) and CEC2022 (dim = 10/20) benchmark suites by comparing MEIAO with eight algorithms, including VPPSO and IAO. Based on the mean, standard deviation, Friedman mean rank, and Wilcoxon rank-sum tests, MEIAO demonstrated superior performance in local exploitation of unimodal functions, global exploration of multimodal functions, and complex adaptation on composite functions while exhibiting stronger robustness. Finally, MEIAO was applied to 3D mountainous UAV path planning, where a cost model considering path length, altitude standard deviation, and turning smoothness was established. The experimental results show that MEIAO achieved an average path cost of 253.9190, a 25.7% reduction compared to IAO (341.9324), with the lowest standard deviation (60.6960) among all algorithms. The generated paths were smoother, collision-free, and achieved faster convergence, offering an efficient and reliable solution for UAV operations in complex environments.

The Secretary Bird Optimization Algorithm (SBOA) is a novel swarm-based meta-heuristic that formulates an optimization model by mimicking the secretary bird's hunting and predator-evasion behaviors, and thus possesses appreciable application potential. Nevertheless, it suffers from an unbalanced exploration-exploitation ratio, difficulty in maintaining population diversity, and a tendency to be trapped in local optima. To eliminate these drawbacks, this paper proposes an SBOA variant (MESBOA) that integrates a multi-population management strategy with an experience-trend guidance strategy. The proposed method is compared with eight advanced basic/enhanced algorithms of different categories on both the CEC2017 and CEC2022 test suites. Experimental results demonstrate that MESBOA delivers faster convergence, more stable robustness and higher accuracy, achieving mean rankings of 2.500 (CEC2022 10-D), 2.333 (CEC2022 20-D), 1.828 (CEC2017 50-D) and 1.931 (CEC2017 100-D). Moreover, engineering constrained optimization problems further verify its applicability to real-world optimization tasks.

Population aging and rising rehabilitation demands highlight the need for advanced assistive devices to improve mobility in individuals with motor impairments. Existing back-support lifting nursing beds often lack adequate human-machine adaptability, safety, and emotional consideration. This study presents a human-centered, data-driven optimization pipeline that integrates behavior-emotion dual recognition, simulation verification, and parameter optimization with user demand mining, biomechanical simulation, and sustainable practices. The design utilizes GreenAI, focusing on low-power algorithms and eco-friendly materials, ensuring energy-efficient AI models and reducing the environmental footprint. A dual-channel data fusion method was developed, combining movement parameters from sit-to-lie transitions with emotional needs extracted from e-commerce reviews using the Term Frequency-Inverse Document Frequency (TF-IDF) and Latent Dirichlet Allocation (LDA) models. The fuzzy Kano model prioritized design objectives, identifying multi-position adjustment, joint protection, armrest optimization, and interaction comfort as key targets. An AnyBody-based human-device model quantified muscle (erector spinae, rectus abdominis, trapezius) and hip joint loads during posture changes. Simulations verified the design's ability to improve load distribution, reduce joint stress, and enhance comfort. The optimized nursing bed demonstrated improved adaptability across user profiles while maintaining functional reliability. This framework offers a scalable paradigm for intelligent rehabilitation equipment design, with potential extension toward AI-driven adaptive control and clinical validation. This sustainable methodology ensures that the device not only meets rehabilitation goals but also contributes to a more environmentally responsible healthcare solution, aligning with global sustainability efforts.

The Crested Porcupine Optimizer (CPO), as a newly emerging swarm intelligence algorithm, demonstrates advantages in balancing global exploration and local exploitation but still suffers from limitations in convergence speed and local exploitation precision. To address these issues, this paper proposes an enhanced variant, the Butterfly Search and Triangular Walk Crested Porcupine Optimizer (BTCPO). The method achieves a dynamic balance between exploration and exploitation by combining triangular walk to boost local exploitation and butterfly search to increase global variety. Experimental results on 23 classical benchmark functions and the CEC2021 test suite show that BTCPO outperforms CPO as well as seven state-of-the-art algorithms (DBO, HBA, BKA, HHO, GWO, GOOSE, and SSA). Specifically, BTCPO achieves the best performance on more than 80% of CEC2021 functions, with convergence speed improved by approximately 25% compared to CPO. Furthermore, BTCPO exhibits higher efficiency and usefulness in engineering design problems such as trusses, welded beams, and cantilever beams. These findings demonstrate the theoretical and practical advantages of BTCPO, making it a workable approach to solving difficult optimization problems.