Dynamic Mechanism Research Articles

A prior-knowledge-guided dynamic attention mechanism to predict nocturnal hypoglycemic events in type 1 diabetes

Nocturnal hypoglycemia is a critical problem faced by diabetic patients. Failure to intervene in time can be dangerous for patients. The existing early warning methods struggle to extract crucial information comprehensively from complex multi-source heterogeneous data. In this paper, a deep learning framework with an innovative dynamic attention mechanism is proposed to predict nocturnal hypoglycemic events for type 1 diabetes patients. Features related to nocturnal hypoglycemia are extracted from multi-scale and multi-dimensional data, which enables comprehensive information extraction from diverse sources. Then, we propose a prior-knowledge-guided attention mechanism to enhance the network's learning capability and interpretability. The method was evaluated on a public available clinical dataset, which successfully warned 94.91% of nocturnal hypoglycemic events with an F1-score of 96.35%. By integrating our proposed framework into the nocturnal hypoglycemia early warning model, issues related to feature redundancy and incompleteness were mitigated. Comparative analysis demonstrates that our method outperforms existing approaches, offering superior accuracy and practicality in real-world scenarios.

The role of relatedness, age and origin in shaping social networks for two bison (Bison bison bison) herds in north-central Montana

Species with fission-fusion social organization, where groups break apart and merge over time, show variable subgroup stability. Plains bison (Bison bison bison Linnaeus, 1758), a keystone species in North American grasslands, exhibit fission-fusion dynamics. However, it is unclear whether subgroups are stable over time nor whether they are composed of related individuals. We used fine-scale behavioral observations and movement data from GPS ear tags to construct social networks for two plains bison herds over multiple years at American Prairie in north-central Montana. These herds are semi-free roaming and graze year-round in 32.4 and 111.6 km2 fenced pastures. While the bison in our study did exhibit fission-fusion behavior, we did not observe stable subgroups in time-aggregated social networks constructed over single growing seasons (eigenvector modularity ranged from -0.008 to 0.027). We used Mantel tests to assess the relationships between association strength and relatedness, age, and place of origin. We found that only first-order relatives were more likely to associate, and shared age and place of origin had no significant impact. The observed lack of stable subgroups challenges prevailing assumptions and highlights the need for future research into the mechanisms of fission-fusion dynamics in plains bison and other managed social species.

Spall: accurate and robust unveiling cellular landscapes from spatially resolved transcriptomics data using a decomposition network

Recent developments in spatially resolved transcriptomics (SRT) enable the characterization of spatial structures for different tissues. Many decomposition methods have been proposed to depict the cellular distribution within tissues. However, existing computational methods struggle to balance spatial continuity in cell distribution with the preservation of cell-specific characteristics. To address this, we propose Spall, a novel decomposition network that integrates scRNA-seq data with SRT data to accurately infer cell type proportions. Spall introduced the GATv2 module, featuring a flexible dynamic attention mechanism to capture relationships between spots. This improves the identification of cellular distribution patterns in spatial analysis. Additionally, Spall incorporates skip connections to address the loss of cell-specific information, thereby enhancing the prediction capability for rare cell types. Experimental results show that Spall outperforms the state-of-the-art methods in reconstructing cell distribution patterns on multiple datasets. Notably, Spall reveals tumor heterogeneity in human pancreatic ductal adenocarcinoma samples and delineates complex tissue structures, such as the laminar organization of the mouse cerebral cortex and the mouse cerebellum. These findings highlight the ability of Spall to provide reliable low-dimensional embeddings for downstream analyses, offering new opportunities for deciphering tissue structures.

Information or normative impacts? Influencing factors and dynamic mechanisms of fertility intentions among first-time married young adults based on the TPB-SIT model

ABSTRACT The data from the Seventh Population Census (7th Population Census) indicate that China is currently confronted with significant demographic challenges, particularly those arising from low fertility rates. Due to the complexity of factors affecting fertility decisions, which are typically characterized under the concept of “perceived behavioral control,” it is challenging to investigate the multifaceted factors that influence fertility decisions. To conduct a broad analysis of the factors that shape fertility decisions among young adults in their first marriage, a TPB-SIT model is constructed from a policy-oriented perspective, which integrates the Theory of Planned Behavior (TPB) with the Socioeconomic Influences Theory (SIT). By focusing on targeted policy tools, the effectiveness and specificity of policy-oriented measures were examined quantitatively. The analysis of the TPB-SIT model using CFPS data underscores the regulatory function of policy tools and the significance of traditional values. Based on these findings, targeted suggestions are proposed to effectively enhance fertility rates.

The global effect of aortic coarctation on carotid and renal pulsatile hemodynamics.

Coarctation of the aorta (CoA) is a congenital disease characterized by the narrowing of the aorta, typically the descending portion after the left subclavian artery. If left untreated, by the time individuals reach 50 years of age, the mortality rate can reach 90%. Previous studies have highlighted the adverse effects of CoA on local hemodynamics. However, no study has investigated the global hemodynamic effects of CoA in end-organ (brain and kidney) damage. Clinical studies have shown that coarctation acts as a reflection site, potentially damaging the hemodynamics of the brain and kidneys. Our goal in this study is to investigate the underlying mechanisms of these altered wave dynamics and their impacts on the pulsatile hemodynamics of end-organs. In this study, we use a physiologically accurate in-vitro experimental setup that simulates the hemodynamics of systemic circulation. Experiments are conducted across various cardiac outputs, heart rates, and coarctation degrees using aortas across a wide range of aortic stiffnesses. Our principal finding is that CoA increases cerebral blood flow and harmful pulsatile energy transmission to the brain. Conversely, both renal blood flow and pulsatile energy transmission to the kidneys are reduced in CoA at every level of aortic stiffness.

An all integer-based spiking neural network with dynamic threshold adaptation

Spiking Neural Networks (SNNs) are typically regards as the third generation of neural networks due to their inherent event-driven computing capabilities and remarkable energy efficiency. However, training an SNN that possesses fast inference speed and comparable accuracy to modern artificial neural networks (ANNs) remains a considerable challenge. In this article, a sophisticated SNN modeling algorithm incorporating a novel dynamic threshold adaptation mechanism is proposed. It aims to eliminate the spiking synchronization error commonly occurred in many traditional ANN2SNN conversion works. Additionally, all variables in the proposed SNNs, including the membrane potential, threshold and synaptic weights, are quantized to integers, making them highly compatible with hardware implementation. Experimental results indicate that the proposed spiking LeNet and VGG-Net achieve accuracies exceeding 99.45% and 93.15% on the MNIST and CIFAR-10 datasets, respectively, with only 4 and 8 time steps required for simulating one sample. Due to this all integer-based quantization process, the required computational operations are significantly reduced, potentially providing a substantial energy efficiency advantage for numerous edge computing applications.

A Robust Salp Swarm Algorithm for Photovoltaic Maximum Power Point Tracking Under Partial Shading Conditions

Currently, numerous intelligent maximum power point tracking (MPPT) algorithms are capable of tackling the global optimization challenge of multi-peak photovoltaic output power under partial shading conditions, yet they often face issues such as slow convergence, low tracking precision, and substantial power fluctuations. To address these challenges, this paper introduces a hybrid algorithm that integrates an improved salp swarm algorithm (SSA) with the perturb and observe (P&O) method. Initially, the SSA is augmented with a dynamic spiral evolution mechanism and a Lévy flight strategy, expanding the search space and bolstering global search capabilities, which in turn enhances the tracking precision. Subsequently, the application of a Gaussian operator for distribution calculations allows for the adaptive adjustment of step sizes in each iteration, quickening convergence and diminishing power oscillations. Finally, the integration with P&O facilitates a meticulous search with a small step size, ensuring swift convergence and further mitigating post-convergence power oscillations. Both the simulations and the experimental results indicate that the proposed algorithm outperforms particle swarm optimization (PSO) and grey wolf optimization (GWO) in terms of convergence velocity, tracking precision, and the reduction in iteration power oscillation magnitude.

Dental Loop Chatbot: A Prototype Large Language Model Framework for Dentistry

The Dental Loop Chatbot was developed as a real-time, evidence-based guidance system for dental practitioners using a fine-tuned large language model (LLM) and Retrieval-Augmented Generation (RAG). This paper outlines the development and preliminary evaluation of the chatbot as a scalable clinical decision-support tool designed for resource-limited settings. The system’s architecture incorporates Quantized Low-Rank Adaptation (QLoRA) for efficient fine-tuning, while dynamic retrieval mechanisms ensure contextually accurate and relevant responses. This prototype lays the groundwork for future triaging and diagnostic support systems tailored specifically to the field of dentistry.

Historical Evolution, Logical Deconstruction and Future Trends in Marine Ecological Compensation Policies in China

The marine ecological compensation policy has become an important tool for China to protect the ocean and promote the construction of ecological civilization. However, problems such as a fragmented policy system structure and inefficient implementation still plague the sustainable development of marine ecological compensation policy. In the context of the high-quality development of the marine economy in the future, it is necessary to evaluate the current status of the construction of China’s marine ecological compensation policy system and explore the plans to improve the marine ecological compensation policy in depth. This paper takes the marine ecological compensation policies issued from 1982 to 2023 as the analysis sample, uses semantic network analysis to analyze the evolution of China’s marine ecological compensation policy and divides the evolution into four stages based on the focuses of the policies in different periods. This paper uses a policy element model to analyze the scope, direction and dynamic mechanism of the change in the marine ecological compensation policy. The study found that the policy elements at the abstract level remained stable for a long time, and the policy elements at the procedural level and operational level are heterogeneous at different stages; China’s marine ecological compensation has gradually developed in the direction of improved quality, land and sea coordination, full-process supervision and integrated management, and is affected by the macro-environment, institutional demand and supply and cost–benefit coordination and balance. The marine ecological compensation policies should start with the top-level design of the supplementary system, improve the supporting tools and coordinate multiple synergies to promote the improvement of the marine ecological compensation policy system.

Dynamic event-triggered data-driven iterative learning consensus control for nonlinear MASs with unknown disturbance

This work tackles the consensus problem for nonlinear nonaffine multi-agent systems (MASs) with unknown disturbances using a data-driven iterative learning control (DDILC) scheme. The unknown model of the agent is first converted through dynamic linearisation into a equivalent data model, comprising a linear combination of an unknown dynamic parameter and an uncertain term. An adaptive algorithm is then formulated to estimate the unknown dynamic parameters accurately. The total uncertainty, which arises from the parameter estimation error and the uncertain term, is estimated by the extended state observer. The estimations are used by the controller to compensate for total uncertainty. Further, considering the resource limitations of communication and the constraints of the actual control input, a constrained iterative learning controller with a dynamic event-triggered mechanism is developed, which guarantees control performance and reduces the number of communications in MASs. It is proven that the tracking error asymptotically approaches a small bound around zero under the proposed DDILC framework. The simulation results confirm the effectiveness of the theoretical research.

Research on Interprovincial Embodied Carbon Transfer Network in China and Its Endogenous Dynamic Evolutionary Mechanism

This paper uses the multi-regional input–output model to measure China’s interprovincial embodied carbon transfer and constructs an interprovincial network; then, the temporal exponential random graph model is applied to analyze the spatial correlation characteristics and endogenous evolutionary mechanism of the network. The results show that interprovincial embodied carbon transfer relationships are increasingly close in China, but the weak symmetric accessibility between the eastern and central regions leads to less reciprocity in the embodied carbon network, and carbon emission inequality still exists. Based on the identification of networks, it is shown that the global network structures are stable, with obvious small-world characteristics and a core–periphery structure. And a structure-dependent effect and time-dependent effect also exist in the formation and evolution of the interprovincial embodied carbon transfer network in China. The popularity, multi-connectivity, and path-dependent effects among the provinces are significant, but the imperfection of interprovincial communication and the cooperation mechanism leads to the failure to form stable structures of ternary closed loops. Interprovincial embodied carbon transfer relationships tend to occur between provinces, with large differences in energy consumption structures, while geographical distance can hinder the formation of embodied carbon transfer relationships. Consequently, considering the spatial network correlation and its endogenous dynamic evolutionary mechanism, it is important to implement policies to guide coordinated carbon reduction among the provinces and to improve the fairness in embodied carbon transferring, in order to promote the fine governance of all links in the transferring process of embodied carbon.

BRA-YOLOv7: improvements on large leaf disease object detection using FasterNet and dual-level routing attention in YOLOv7

Tea leaf diseases are significant causes of reduced quality and yield in tea production. In the Yunnan region, where the climate is suitable for tea cultivation, tea leaf diseases are small, scattered, and vary in scale, making their detection challenging due to complex backgrounds and issues such as occlusion, overlap, and lighting variations. Existing object detection models often struggle to achieve high accuracy in detecting tea leaf diseases. To address these challenges, this paper proposes a tea leaf disease detection model, BRA-YOLOv7, which combines a dual-level routing dynamic sparse attention mechanism for fast identification of tea leaf diseases in complex scenarios. BRA-YOLOv7 incorporates PConv and FasterNet as replacements for the original network structure of YOLOv7, reducing the number of floating-point operations and improving efficiency. In the Neck layer, a dual-level routing dynamic sparse attention mechanism is introduced to enable flexible computation allocation and content awareness, enhancing the model’s ability to capture global information about tea leaf diseases. Finally, the loss function is replaced with MPDIoU to enhance target localization accuracy and reduce false detection cases. Experiments and analysis were conducted on a collected dataset using the Faster R-CNN, YOLOv6, and YOLOv7 models, with Mean Average Precision (mAP), Floating-point Operations (FLOPs), and Frames Per Second (FPS) as evaluation metrics for accuracy and efficiency. The experimental results show that the improved algorithm achieved a 4.8% improvement in recognition accuracy, a 5.3% improvement in recall rate, a 5% improvement in balance score, and a 2.6% improvement in mAP compared to the traditional YOLOv7 algorithm. Furthermore, in external validation, the floating-point operation count decreased by 1.4G, FPS improved by 5.52%, and mAP increased by 2.4%. In conclusion, the improved YOLOv7 model demonstrates remarkable results in terms of parameter quantity, floating-point operation count, model size, and convergence time. It provides efficient lossless identification while balancing recognition accuracy, real-time performance, and model robustness. This has significant implications for adopting targeted preventive measures against tea leaf diseases in the future.

Thermal-Dependent Dynamic Compressive Behavior and Damage Mechanism of Granite

Thermal-Dependent Dynamic Compressive Behavior and Damage Mechanism of Granite

Crowd-CapsNet: capsule network based adaptive crowdsourcing task recommendation

Purpose The crowdsourcing software development platforms organize geographically distributed developers to complete various developing tasks, bringing convenience and efficiency to users. However, with the increasing number of both developers and tasks, it becomes more and more challenging to match tasks and suitable developers, especially for imbalanced data. The purpose of this paper is to propose an accurate and diverse recommendation model for crowdsourcing tasks. Design/methodology/approach A revised circle loss function is applied to achieve a certain adaptive ability, which is critical for imbalanced data, it guarantees diversity by maximizing the target label score and leveraging mathematical approximation to automatically balance the weights. Besides, the authors leverage the capsule network to obtain the semantic feature of tasks’ descriptions, modify the dynamic routing mechanism to better learn users’ preferences and improve the recommendation accuracy. Findings The comprehensive experiments conducted on real crowdsourcing platform data demonstrate that the proposed Crowd-CapsNet model can achieve high recommendation accuracy with a certain diversity. It improves around 1% accuracy with only 37% training time of the LSFA approach. Originality/value This paper proposes Crowd-CapsNet, an adaptive crowdsourcing task recommendation model. A relatively general feature pre-processing method describes crowd-sourcing tasks and the modified capsule network further obtains the semantic features to improve the recommendation accuracy and diversity.

A new dynamic shift mechanism based on cyclic group theory for continuous attractor neural networks

A new dynamic shift mechanism based on cyclic group theory for continuous attractor neural networks

ASFormer: Attentive Semantic Feature Fusion Transformer for Pixel -level Defect Detection

Abstract Surface defect detection is pivotal for ensuring product quality in various industries. These defects typically manifest as low background contrast, substantial variations in shape, and a scarcity of balanced training samples. Traditional defect detection methods often encounter limitations in terms of low detection accuracy and insufficient detection granularity. This study introduces an innovative attentive semantic feature fusion transformer network (ASFormer) tailored for pixel-level defect detection tasks to overcome these challenges. Initially, the transformer architecture is employed to extract the multiscale features of defects. Subsequently, a multiscale semantic fusion module is integrated, complemented by a dynamic upsampling mechanism, to mitigate the loss of detailed information during feature fusion. Moreover, a scale-aware dual-attention module is developed, which effectively captures the intricacies of the fused features across both channel and spatial dimensions, ensuring pixel-level detection precision. Additionally, a contextual boundary loss function is proposed to augment the ability of the network to discern defect boundaries, different categories and defect scales. Experimental validation on the NEU-Seg and Crack500 surface defect datasets demonstrated that the proposed ASFormer achieved state-of-the-art performance, with mIoU scores of 85.24% and 78.20%, respectively.

Intrinsic disordered nature and prediction of secondary structures of pinoresinol lariciresinol reductases 2 in Flax (Linum usitatissimum)

Flax (Linum usitatissimum) contains a wide range of essential nutrients, such as proteins, polyunsaturated fatty acids (PUFAs), phenolic compounds, fibers, flavonoids, and lignans. The production of lignans in flax is mainly caused by pinoresinol-lariciresinol reductases (PLRs). Amongst these, PLR2s play a pivotal function by contributing to the further reduction of lariciresinol to secoisolariciresinol in the biosynthesis of lignans. However, the in-silico analysis of PLR2 gene family interlinking the intrinsic disordered nature and secondary structures that could support this hypothesis is still missing in Flax. Herein, we present the first study of Intrinsic disorder proteins (IDPs) in flax to gain an understanding of their biological functions. This study was conducted from June to August 2024 at the Department of Biochemistry, Lovely Professional University, Phagwara, Punjab, India. The flax genome assembly from Phytozome was used to retrieve 30 PLR2 genes which encode for 30 PLR2 proteins. Further, we used PONDR database to identify the intrinsic disordered nature of the proteins while GOR database was used to predict the secondary structures. For identifying the amino acid composition, Protparam database was used. The results of PONDR database revealed that all the proteins are somewhat disordered whereas amino acid composition marked the presence of disorder-promoting residues in almost all the proteins. Secondary structure predictions by GOR revealed the presence of coils, helices and strands. To relate the structural functional relationship, it is of the utmost importance to have an in-depth knowledge of the balance between intrinsic disorder and secondary structure as this will provide key insights into the dynamic functionality and regulatory mechanisms that are the foundation of complex biological processes.

Separation and Dynamic Binding Mechanism of 3D Model Animation by Integrating Improved Genetic Algorithm and WebAR

With the development of the economy, the demand for 3D model animation in fields such as games, film and television, and education is constantly increasing. At present, many 3D model animations are built based on genetic algorithm. However, due to the slow convergence speed and poor local search ability of genetic algorithm, this model still has many shortcomings. Therefore, a cellular automaton is used to optimize the genetic algorithm, and a cellular genetic algorithm is proposed. It is integrated with WebAR technology, which has the characteristics of lightweight and low cost, aiming to improve the separation and dynamic binding mechanism of 3D model animation. Experimental analysis showed that when the number of chromosome genes was 90, the vertex gene value of the research algorithm was the highest, ranging from 281 to 501, and the convergence was the highest. The file size of the model dataset based on the research method was reduced by 50% compared with before. The FPDT based on the animation separation and dynamic binding mechanism was decreased by 15.2 s on average. To sum up, it can be seen that the designed 3D model animation is more detailed and the animation dynamic is also the best. This research method can significantly improve the separation and dynamic binding mechanism of 3D model animation. This research will improve the integration of genetic algorithm and WebAR technology, which can not only effectively deal with complex 3D models and animations, but also has broad application prospects.

Pothole detection‐you only look once: Deformable convolution based road pothole detection

AbstractThe detection of road potholes plays a crucial role in ensuring passenger comfort and the structural safety of vehicles. To address the challenges of pothole detection in complex road environments, this paper proposes a model focusing on shape features (pothole detection you only look once, PD‐YOLO). The model aims to overcome the limitations of multi‐scale feature learning caused by the use of fixed convolutional kernels in the baseline model, by constructing a feature extraction module that better adapts to variations in the shape of potholes. Subsequently, a cross‐stage partial network was designed using a one‐time aggregation method, simplifying the model while enabling the network to fuse information between feature maps at different stages. Additionally, a dynamic sparse attention mechanism is introduced to select relevant features, reducing redundancy and suppressing background noise. Experiments conducted on the VOC2007 and GRDDC2020_Pothole datasets reveal that compared to the baseline model YOLOv8, PD‐YOLO achieves improvements of 3.9% and 2.8% in mean average precision, with a frame rate of approximately 290 frames per second, effectively meeting the accuracy and real‐time requirements for pothole detection. The code and dataset for this paper are located at: https://github.com/woyijiankou/PD‐YOLO.

Patents of Systems and Methods Using Non-Ionizing Radiation for Measuring Rearfoot Deformations: A Review

Individuals’ lifestyles are affected by valgus and varus deformities in the rearfoot, causing pain in the joints and plantar surface due to the misalignment between the tibial and calcaneus. In orthopedics, medical professionals measure this misalignment by using X-ray systems and goniometers. The X-ray emits ionizing radiation that can cause damage through cumulative exposure over a lifetime, whereas the goniometer will produce measurement errors. This patent review conducted a technological search of systems and methods across various databases using inclusion and exclusion criteria. These thirty-five obtained patents provide valuable information about mechanical, electronic, and mechatronic technologies and non-ionizing radiation to evaluate valgus and varus deformities. The patents are classified into stationary mechanisms, stationary electronic devices, dynamic mechanisms, dynamic electronic devices, stationary mechatronic devices, and dynamic mechatronic devices. They are further categorized based on their measurement methods as either visual or automatic. Additionally, the patents are grouped by usage mode into sitting, standing, and walking. This patent review aims to provide medical professionals with little-known techniques for measuring and evaluating the rearfoot alignment.