Search Results (4,049)

Traditional ECG detection devices are limited in their development due to the constraints of power consumption and differences in data sources. Currently, spiking neural networks (SNNs) have quickly attracted widespread attention owing to their low power consumption enabled by the event-driven nature and efficient learning capability inspired by the biological brain. This paper proposes a low-power SNN processor that supports on-chip learning. By implementing an efficient on-chip learning algorithm through hardware, adopting a two-layer dynamic neural network architecture, and utilizing an asynchronous communication interface for data transmission, the processor achieves excellent inference and learning performance while maintaining outstanding power efficiency. The proposed design was implemented and verified on Xilinx xc7z045ffg900. On the MIT-BIH database for ECG applications, it achieved an accuracy of 91.4%, with an inference power consumption of 62 mW and 215.53 $\mathsf{\mu }\mathrm{J}$ per classification. The designed processor is well-suited for ECG applications that demand low power consumption and environmental adaptability. Full article

Current research on disaster-adaptive resilience predominantly focuses on urban systems, with insufficient attention paid to the unique scale of traditional settlements and their formation mechanisms and pathways to systemic realization remain significantly understudied. There is also a lack of multi-dimensional coupling analysis and innovative methods tailored to the specific contexts of rural areas. To address this, this study innovatively introduces ant colony bionic intelligence, drawing on its characteristics of swarm intelligence, positive feedback, path optimization, and dynamic adaptation to reframe emergency decision-making logic in human societies. An evaluation model for disaster-adaptive resilience is constructed based on these four dimensions as the criterion layer. The weights of dimensions and indicators are determined using a combined AHP–entropy weight method, enabling a comprehensive assessment of settlement resilience. Taking Fenghuang Ancient Town as an empirical case, the research utilizes methods such as field surveys, questionnaire surveys, and GIS data analysis. The results indicate that (1) the overall resilience evaluation score of Fenghuang Ancient Town is 3.408 (based on a 5-point scale); (2) the path optimization dimension contributes the most to the overall resilience, with road redundancy design (C21) being the core driving factor; within the positive feedback mechanism dimension, soil and water conservation projects (C15) provide the fundamental guarantee for village safety; (3) based on these findings, hierarchical planning strategies encompassing infrastructure reinforcement, community capacity enhancement, and ecological risk management are proposed. This study verifies the applicability of the evaluation model based on ant colony bionic intelligence in assessing the disaster resilience of traditional settlements, revealing a new paradigm of “bio-intelligence-driven” resilience planning. It successfully translates ant colony behavioral principles into actionable planning and design guidelines and governance tools, providing a replicable method for resilience evaluation and enhancement for traditional settlements in ecological barrier areas such as the Qinling Mountains. Full article

Phenylalanine ammonia-lyase (PAL) is the core branch-point enzyme connecting plant primary aromatic amino acid metabolism to the phenylpropanoid pathway, which determines carbon flux redistribution between growth and defense and is essential for plant adaptation to various environments. Extensive research has clarified PAL’s conserved homotetrameric structure, MIO cofactor-dependent catalytic mechanism, and its roles in plant growth, development, and stress responses. However, there is a lack of comprehensive review studies focusing on PAL-mediated carbon metabolic flux redistribution, specifically covering its structural and evolutionary foundations, the links between this flux regulation and plant growth/development, its multi-layered regulatory network, and its roles in stress adaptation, limiting a comprehensive understanding of its evolutionary and functional diversity. This review systematically covers four core aspects: first, the molecular foundation, encompassing PAL’s structural features and catalytic specificity governed by the MIO cofactor; second, evolutionary diversity spanning from algae to angiosperms, with emphasis on unique regulatory mechanisms and evolutionary significance across lineages; third, the multi-layered regulatory network, integrating transcriptional control, post-translational modifications, epigenetic regulation, and functional crosstalk with phytohormones; and fourth, functional dynamics, which elaborate PAL’s roles in organ development, including root lignification, stem mechanical strength, leaf photoprotection, flower and fruit quality formation, and lifecycle-wide dynamic expression, as well as its mediated stress adaptations and regulatory networks under combined stresses. These insights provide a theoretical basis for targeted manipulation of PAL to optimize crop carbon allocation, thus improving growth performance, enhance stress resilience, and promote sustainable agriculture. Full article

Elucidating shrub ecohydrological adaptation is critical for optimizing vegetation-restoration strategies in arid regions and maintaining regional ecological stability. This study examined typical desert shrubs at the northern edge of the Mu Us Sand Land. During the growth peak season (July–September), we measured understory-soil δ¹⁸O, soil water content (SWC), leaf δ¹³C_p, stem δ¹⁸O, and gas-exchange rates, and evaluated shrub drought resistance and water-use efficiency using Mantel tests and principal component analysis (PCA). Based on the VPDB standard, the δ13Cp values of leaves ranked as follows: Caragana microphylla (−27.21‰) > Salix psammophila (−27.80‰) > Artemisia ordosica (−28.48‰). The results indicate that leaf δ¹³C_p and water δ¹⁸O are effective indicators of shrub water-use efficiency, reflecting Cᵢ/Cₐ dynamics and water-transport pathways, respectively. The three shrubs exhibit distinct water-use strategies: Caragana microphylla follows a conservative strategy that relies on deep-water sources and tight stomatal regulation; Salix psammophila shows an opportunistic strategy, responding to precipitation pulses and drawing from multiple soil layers; Artemisia ordosica displays a vulnerable, shallow-water-dependent strategy with high drought susceptibility. SWC was the primary driver of higher Long Water Use Efficiency (WUE), whereas Mean Air Temperature (MMAT) and Mean Relative Humidity (MMRH) exerted short-term regulation by modulating the vapor-pressure deficit (VPD). We conclude that desert-shrub water-use strategies form a complementary functional portfolio at the community scale. Vegetation restoration should prioritize high-WUE conservative species, complement them with opportunistic species, and use vulnerable species cautiously to optimize community water-use efficiency and ecosystem stability. Full article

Underwater optical docking is essential for enabling autonomous underwater vehicles (AUVs) to maintain long-duration operations through standardized energy replenishment and data exchange. However, existing optical docking guidance still faces challenges including discontinuous guidance space, fluctuating beacon visibility, and limited real-time feasibility on resource-constrained AUV platforms. This study proposes a three-layer underwater optical guidance framework designed to enhance both stability and deployment feasibility. First, a multi-dimensional beacon configuration is developed to provide stage-based optical guidance, supported by a spatial simulation tool that evaluates beacon placement and effective detection regions. Second, an adaptive spatiotemporal guidance algorithm is introduced, integrating Kalman-based prediction and correction mechanisms to maintain consistent beacon tracking under dynamic underwater conditions. Third, a lightweight optical beacon detection model is implemented to reduce computational cost while preserving sufficient detection accuracy for real-time onboard processing. Pool and lake experiments demonstrate that the proposed framework achieves continuous optical guidance over a range of 0–35 m, significantly improving guidance stability and perception continuity compared with conventional approaches. Full article

In response to the challenges in unmanned aerial vehicle (UAV)-based poppy plant detection, such as dense small targets, occlusions, and complex backgrounds, an improved YOLOv8-based detection algorithm with multi-module collaborative optimization is proposed. First, the lightweight Efficient Channel Attention (ECA) mechanism was integrated into the YOLOv8 backbone network to construct a composite feature extraction module with enhanced representational capacity. Subsequently, a Bidirectional Feature Pyramid Network (BiFPN) was introduced into the neck network to establish adaptive cross-scale feature fusion through learnable weighting parameters. Furthermore, the Wise Intersection over Union (WIoU) loss function was adopted to enhance the accuracy of bounding box regression. Finally, a dedicated 160 × 160 pixels detection head was added to leverage the high-resolution features from shallow layers, thereby enhancing the detection capability for small targets. Under five-fold cross-validation, the proposed model achieved mAP@0.5 and mAP@0.5:0.95 of 0.989 ± 0.003 and 0.850 ± 0.013, respectively, with average increases of 1.3 and 3.2 percentage points over YOLOv8. Statistical analysis confirmed that these performance gains were significant, demonstrating the effectiveness of the proposed method as a reliable solution for poppy plant detection. Full article

This paper proposes an innovative methodological framework for integrating Cultural Ecosystem Services (CES) into landscape planning, with the aim of enhancing the conservation and adaptive management of rural historical landscapes. Grounded in the principles of the European Landscape Convention and the recent Nature Restoration Law, the study advocates for a shift from prescriptive and sectoral approaches toward performance-based and ecosystem-oriented models. The research focuses on the Marche Region (Italy), where the historical landscape shaped by the mezzadria (sharecropping) system provides a representative case for testing the proposed methodology. Six spatial layers have been selected as ecosystem-based indicators to identify new potential landscape CES’ hotspots as agricultural landscape high-value areas, and to redefine protection and management strategies. The analysis integrates historical, ecological, and cultural dimensions to construct a spatially explicit value matrix, supporting the definition of differentiated management zones. Results reveal the persistence of high landscape and ecosystem values in mid- and upper-hill areas, contrasted by the progressive loss of structural and functional diversity in lowland and peri-urban contexts. The findings highlight the need for more adaptive and flexible planning models, capable of incorporating nature-based actions, climate-smart agriculture, and performance-oriented evaluation criteria. The proposed approach demonstrates potential for replicability and policy integration, providing a decision-support framework to align landscape planning with rural development strategies and climate adaptation objectives. Despite limitations related to data availability and model simplification, the methodology contributes to the ongoing paradigm shift toward dynamic, evidence-based, and transdisciplinary landscape governance across Mediterranean regions. Full article

Amid global efforts toward carbon neutrality, carbon emission accounting in the construction sector has become essential for sustainable design. Public buildings, with complex energy systems and high operational loads, are major carbon emitters. However, early design stages often provide only low-dimensional parameters—such as floor area, number of floors, and location—limiting conventional regression methods. This study develops a lightweight prediction framework using a multilayer perceptron (MLP) neural network. Feature engineering constructs composite indicators—layers per unit area (LPA) and height-to-area ratio (HAR)—to quantify spatial compactness and vertical density. A three-layer MLP with Swish activation, adaptive L2 regularization, and Dropout reduces overfitting and improves generalization. Tests show the model achieves a mean absolute error of 4160 tCO₂ and R² of 0.966, reducing prediction error by 54.7% compared to linear regression. For high-rise buildings (>15 floors), error remains below 8.1%. SHAP analysis highlights floor area as the dominant factor (51.2%), while HAR and LPA jointly improve accuracy by 5.8%. A Python-based tool is developed for rapid emission estimation during design. Using 150 samples and 10-fold cross-validation, this work demonstrates the potential of deep learning in low-dimensional carbon prediction, offering a practical reference for early-stage green building design, though generalizability requires further validation with larger datasets. Full article

This paper addresses the flexible job-shop scheduling problem with multiple time factors—namely, transportation time and setup time—as well as job priorities (referred to as FJSP-JPC-TST). An optimization model is established with the objective of minimizing the completion time. Considering the characteristics of the FJSP-JPC-TST, we propose an improved whale optimization algorithm that incorporates multiple strategies. First, a two-layer encoding mechanism based on operations and machines is introduced. To prevent illegal solutions, a priority-based encoding repair mechanism is designed, along with an active scheduling decoding method that fully considers multiple time factors and job priorities. Subsequently, a multi-level sub-population optimization strategy, an adaptive inertia weight, and a cross-population differential evolution strategy are implemented to enhance the optimization efficiency of the algorithm. Finally, extensive simulation experiments demonstrate that the proposed algorithm offers significant advantages and exhibits high reliability in effectively solving such scheduling problems. Full article

With the exponential growth of digital music, efficiently identifying key music relationship nodes in large-scale music knowledge graphs is crucial for enhancing music recommendation, emotion analysis, and genre classification. To address this challenge, we propose MUSIGAIN, a GATv2-based adaptive framework that combines graph robustness metrics with advanced graph neural network mechanisms for multi-relationship mining in heterogeneous music knowledge graphs. MUSIGAIN tackles three fundamental challenges: the prohibitive computational complexity of exact graph-robustness calculations, the limitations of traditional centrality measures in capturing semantic heterogeneity, and the over-smoothing problem in deep graph neural networks. The framework introduces three key innovations: (1) a layer-wise dynamic skipping mechanism that adaptively controls propagation depth based on third-order embedding stability, reducing computation by 30–40% while preventing over-smoothing; (2) the DiGRAF adaptive activation function that enables node-specific nonlinear transformations to capture semantic heterogeneity across different entity types; and (3) ranking-based optimization supervised by graph robustness metrics, focusing on relative importance ordering rather than absolute value prediction. Experimental results on four real-world music knowledge graphs (POP-MKG, ROCK-MKG, JAZZ-MKG, CLASSICAL-MKG) demonstrate that MUSIGAIN consistently outperforms existing methods in Top-5% node identification accuracy, achieving up to 96.78% while maintaining linear scalability to graphs with hundreds of thousands of nodes. MUSIGAIN provides an efficient, accurate, and interpretable solution for key node identification in complex heterogeneous graphs. Full article

Additive manufacturing has increasingly become a transformative approach in the design and fabrication of personalized medical devices, offering improved adaptability, reduced production time, and enhanced patient-specific functionality. Within this framework, simulation-driven design plays a critical role in ensuring the structural reliability and performance of orthopedic supports before fabrication. This research study delineates the novel development of a wrist hybrid splint (WHS) which has a simulation-based design and was additively manufactured using fused deposition modeling (FDM). The primary material selected for this purpose was polylactic acid (PLA), recognized for its biocompatibility and structural integrity in medical applications. Prior to the commencement of the actual FDM process, an extensive pre-analysis was imperative, involving the application of nonlinear numerical models aiming at replicating the mechanical response of the WHS in respect to different deposition configurations. The methodology encompassed the evaluation of a sophisticated material model incorporating a damage mechanism which was grounded in experimental data derived from meticulous tensile and three-point bending testing of samples with varying FDM process parameters, namely nozzle diameter, layer thickness, and deposition orientation. The integration of custom subroutines with utility routines was coded with a particular emphasis on maximum stress thresholds to ensure the fidelity and reliability of the simulation outputs on small scale samples in terms of their elasticity and strength. After the formulation and validation of these computational models, a comprehensive simulation of a full-scale, finite element (FE) model of two WHS design variations was conducted, the results of which were aligned with the stringent requirements set forth by the product specifications, ensuring comfortable and safe usage. Based on the results of this study, the final force comparison between the numerical simulation and experimental measurements demonstrated a discrepancy of less than 2%. This high level of agreement highlights the accuracy of the employed methodologies and validates the effectiveness of the WHS simulation and fabrication approach. The research also concludes with a strong affirmation of the material model with a damage mechanism, substantiating its applicability and effectiveness in future manufacturing of the WHS, as well as other orthopedic support devices through an appropriate selection of FDM parameters. Full article

The focus of this paper is on the large-format wooden panel painting Maundy Thursday Altarpiece from Southern Germany. Its wooden support and paint layer were severely damaged due to high climatic fluctuations, above all dryness. The aim of the research project was to develop a low-risk, conservatively acceptable procedure for controlled in situ humidification. In an interdisciplinary approach, a practical monitoring concept on-site was linked to art technology analyses, surface monitoring, hygrothermal simulations, and climate chamber tests. Based on the results, an individual climate corridor for controlled humidification of the case study was developed with the help of an enclosure and implemented in two gradual moistening phases. The combination of conservative support, measurement technology, and digital assessment allowed a controlled approach to a conservation optimum without other active interventions in the original material. The results highlight the need for object-specific strategies and humidity corridors at the interface between conservation, climate adaptation, and sustainability. A deviation from museum standard recommendations (depending on the guidelines 40–60% rH) shows the special challenges of monument preservation. Full article

Technical constraints to be faced in microgrids have become more frequent with high renewable integration. In this context, Thermal Energy Storage (TES) has emerged as a promising solution to enable consumers’ flexibility to contribute to the solution of such operational issues. This paper examines the integration of the novel system ECHO-TES (a Thermal Energy Storage System developed within the European Project ECHO) in microgrids to address technical constraints, utilizing OpenDSS and Python simulations. Building on that, the Efficient Compact Modular Transaction Simulation System (ECHO-TSS) adds a layer of virtual automated transactions, coordinating multiple ECHO-TES assets to simulate not only energy flows and electricity consumption, but also the associated economic interactions. The study explores the critical role of TES in enhancing microgrid efficiency, flexibility, and sustainability, particularly when coupled with renewable energy sources. By analyzing diverse demand scenarios, the research aims to assess its impact on grid stability and management. The paper highlights the importance of advanced modeling tools like OpenDSS in simulating complex microgrid operations, including the dynamic behavior of TES systems. It also investigates demand-side management strategies and the potential of TES to mitigate challenges associated with renewable energy variability. The findings contribute to the development of robust, adaptive microgrid systems and support the global transition towards sustainable energy infrastructure. Full article

To address the challenges of non-stationary signals, noise corruption, and limited interpretability in intelligent fault diagnosis, we propose a Time-Frequency Dual Transformation (TFDT) framework. By embedding a trainable Time-Frequency Convolution (TFConv) layer into a convolutional neural network, TFDT integrates physics-informed time-frequency transforms—STTF, Morlet wavelet, and Chirplet—into the learning process. This allows the model to adaptively extract fault-sensitive features while maintaining physical interpretability. Experimental results on the CWRU dataset show that TFDT outperforms standard CNNs and fixed-transform pipelines in accuracy, convergence speed, and robustness under noisy conditions. Ablation studies confirm the critical role of the TFConv layer, and t-SNE visualizations reveal discriminative and compact feature clusters, supporting the model’s interpretability claims. Full article

To address challenges in agent path planning within complex environments—particularly slow convergence speed, high path redundancy, and insufficient smoothness—this paper proposes KDB-RRT*, a novel algorithm built upon RRT.* This method integrates a bidirectional search strategy with a three-layer optimization framework: ① accelerated node retrieval via KD-tree indexing to reduce computational complexity; ② enhanced exploration efficiency through goal-biased dynamic circle sampling and a bidirectional gravitational field guidance model, coupled with adaptive step size adjustment using a Sigmoid function for directional expansion and obstacle avoidance; and ③ trajectory optimization employing DP algorithm pruning and cubic B-spline smoothing to generate curvature-continuous paths. Additionally, a multi-level collision detection framework integrating Separating Axis Theorem (SAT) pre-judgment, R-tree spatial indexing, and active obstacle avoidance strategies is incorporated, ensuring robust collision resistance. Extensive experiments in complex environments (Z-shaped map, loop-shaped map, and multi-obstacle settings) demonstrate KDB-RRT’s superiority over state-of-the-art methods (Optimized RRT*, RRT*-Connect, and Informed-RRT*), reducing average planning time by up to 97.9%, shortening path length by 5.5–21.4%, and decreasing inflection points by 40–90.5%. Finally, the feasibility of the algorithm’s practical application was further verified based on the ROS platform. The research results provide a new method for efficient path planning of intelligent agents in unstructured environments, and its three-layer optimization framework has important reference value for mobile robot navigation systems. Full article