Optimal Shape Factor and Fictitious Radius in the MQ-RBF:Solving Ill-Posed Laplacian Problems

To solve the Laplacian problems,we adopt a meshless method with the multiquadric radial basis function(MQRBF)as a basis whose center is distributed inside a circle with a fictitious radius.A maximal projection technique is developed to identify the optimal shape factor and fictitious radius by minimizing a merit function.A sample function is interpolated by theMQ-RBF to provide a trial coefficient vector to compute the merit function.We can quickly determine the optimal values of the parameters within a preferred rage using the golden section search algorithm.The novel method provides the optimal values of parameters and,hence,an optimal MQ-RBF;the performance of the method is validated in numerical examples.Moreover,nonharmonic problems are transformed to the Poisson equation endowed with a homogeneous boundary condition;this can overcome the problem of these problems being ill-posed.The optimal MQ-RBF is extremely accurate.We further propose a novel optimal polynomial method to solve the nonharmonic problems,which achieves high precision up to an order of 10^(−11).

A Multi-Baseline PolInSAR Forest Height Inversion Method Taking into Account the Model Ill-posed Problem

Affected by the insufficient information of single baseline observation data,the three-stage method assumes the Ground-to-Volume Ratio(GVR)to be zero so as to invert the vegetation height.However,this assumption introduces much biases into the parameter estimates which greatly limits the accuracy of the vegetation height inversion.Multi-baseline observation can provide redundant information and is helpful for the inversion of GVR.Nevertheless,the similar model parameter values in a multi-baseline model often lead to ill-posed problems and reduce the inversion accuracy of conventional algorithm.To this end,we propose a new step-by-step inversion method applied to the multi-baseline observations.Firstly,an adjustment inversion model is constructed by using multi-baseline volume scattering dominant polarization data,and the regularized estimates of model parameters are obtained by regularization method.Then,the reliable estimates of GVR are determined by the MSE(mean square error)analysis of each regularized parameter estimation.Secondly,the estimated GVR is used to extracts the pure volume coherence,and then the vegetation height parameter is inverted from the pure volume coherence by least squares estimation.The experimental results show that the new method can improve the vegetation height inversion result effectively.The inversion accuracy is improved by 26%with respect to the three-stage method and the conventional solution of multi-baseline.All of these have demonstrated the feasibility and effectiveness of the new method.

基于改进YOLO-Pose轻量模型的多人姿态估计

YOLO-Pose作为人体姿态估计算法模型,在精度和速度上有着不错的表现,但其在复杂和有遮挡的场景下存在误检率较大的问题,并且模型的复杂度仍然有优化的空间.针对这几个问题,通过选取Slim-neck模块和Res2Net模块,重新设计其特征融合层,减少其计算量和参数量,提高特征提取能力,在提升精度的同时,使模型轻量化;引入EIoU损失函数,加快边框检测的收敛速度,并提高定位的准确性.在压缩的OC_Human数据集上进行测试,改进后的模型与YOLO-Pose相比,P值、mAP@0.5和mAP@.5:95分别提高了10.6,3.1和2.9个百分点.此外,参数量和计算量也分别减少了16.7%和19.3%,在精度和轻量化方面均有所提升,为其应用在资源有限的边缘计算设备提供了可能性.

基于改进YOLOv8-pose的分心驾驶检测与识别

针对现有的分心驾驶检测算法存在检测率低、检测速率慢等问题,本文构建了一种基于改进YOLOv8-pose的分心驾驶检测识别模型YOLOv8-EFM。首先,通过使用EfficientViT更换YOLOv8-pose的主干网络,结合CNN和VIT之间的互补性,提升了检测的准确率;其次,使用FasterBlock模块替换C2f中的Bottleneck模块,增加了检测速率并减小模型参数;最后在SPPF后加入了轻量级的MLCA注意力模块,在模型大小和准确性之间取得了良好的平衡。实验结果表明,本文所构建的YOLOv8-EFM模型,mAP50可以达到98.9%,模型大小只有9.7 M,该方法不仅可以识别出具体分心行为,还可以检测上半身的人体骨架,可以有效应用在驾驶员分心驾驶的检测场景中。

基于改进YOLOv8n-Pose的轨道作业人员跨轨安全动作识别

针对轨道作业人员跨轨安全动作监督方法存在效率低、漏检率高等问题,引入改进的人体姿态估计算法YOLOv8n-Pose对跨轨安全动作进行识别和监督。对YOLOv8n-Pose算法改进方法为在网络中添加注意力机制并轻量化网络结构,并改进网络的bbox损失函数和关键点损失函数,以提高网络的识别精度和速度。使用高斯滤波和ColorJitter算法对自制数据集增强。在训练前使用遗传算法对训练超参数进行自适应调整,在训练时使用迁移学习和知识蒸馏方法,提高网络训练速度、识别精度和泛化能力。将训练好的模型对轨道现场作业人员图像进行检测,可成功识别出作业人员姿态并根据关键点位置信息识别安全动作,人体关键点识别精确度为94.3%,推理速度为238.1 fps,验证模型改进研究取得了有益效果,提高了模型识别精度、识别速度和鲁棒性。

基于Yolopose的挖掘机检测与工作状态识别

针对光缆、高压油气管道等地下基础设施周边容易受到挖掘机的野蛮入侵问题.本文提出了一种结合Yolopose和多层感知机的挖掘机检测与工作状态判别方法.首先,设计了基于Yolopose的挖掘机6点姿势的提取网络Yolopose-ex;其次,利用Yolopose-ex模型提取视频中挖掘机工作姿态的变化信息,构建了挖掘机的工作状态特征向量(MSV);最后,利用深度学习算法多层感知机(multilayer perceptron,MLP)分析了视频中的挖掘机的工作状态.实验结果表明,所提出的方法克服了复杂背景难以识别的问题,对挖掘机工作状态识别准确率达到了96.6%,具有较高的推理速度和泛化能力.

基于改进YOLOv8-Pose的码垛快速识别与抓取点检测

针对码垛场景中在仓库内对米袋和面袋的识别与抓取点检测的任务,提出了一种基于改进的YOLOv8-Pose的轻量化快速检测算法模型。其基于YOLOv8-Pose,使用若干个ShuffleNetv2模块取代原Darknet主干网络,降低模型大小;添加SimAM注意力机制,提升目标特征提取能力。通过对比实验表明,该模型在不牺牲准确性的前提下可提升模型的识别速度。模型在自制数据集中的平均精度达到了93.7%,检测速度达到了62 fps,优于常见模型。证明该模型能够实现复杂场景下的抓取点识别,且该轻量化模型能够适用于嵌入式硬件,降低设备成本。

基于Yolov7_Pose的轻量化人体姿态估计网络

人体姿态估计在计算机视觉、人机交互与运动分析等领域广泛应用。当前人体姿态估计算法往往通过构建复杂的网络来提高精度,但这带来了模型体量和计算量增大,以及检测速度变慢等问题。因此,文中提出一种基于Yolov7_Pose的轻量化人体姿态估计网络。首先,采用轻量化CARAFE模块替换原网络中的上采样模块,完成上采样工作;接着,在特征融合部分引入轻量化Slim-neck模块,以降低模型的计算量和复杂度;最后,提出了RFB-NAM模块,将其添加到主干网络中,用以获取多个不同尺度的特征信息,扩大感受野,提高特征提取能力。实验结果表明,改进后网络模型的GFLOPs和模型大小分别降低了约18.1%、22%,检测速度提升37.93%,并在低光环境、小目标、密集人群和俯视角度下表现出了较好的性能。

基于MediaPipe Pose的人体动作识别方法研究

针对已有人体动作识别方法存在识别效率低、检测速度慢等问题,提出了基于MediaPipe Pose算法的人体动作识别方法。具体内容:将摄像头实时采集数据输入到检测网络以获取人体33个关键点的坐标信息,然后通过关键点的空间位置组合来确定人体动作类别;采用COCO数据集格式标定动作类别,并且对动作标签进行onehot编码,训练人体动作识别模型;利用单目RGB摄像头对8类动作进行实验验证。结果表明,基于MediaPipe Pose算法的人体动作识别方法其帧率达到30帧/s,识别精确率为96.67%,能够实时、准确地识别人体动作。

Association of preschool children behavior and emotional problems with the parenting behavior of both parents

BACKGROUND Parental behaviors are key in shaping children’s psychological and behavioral development,crucial for early identification and prevention of mental health issues,reducing psychological trauma in childhood.AIM To investigate the relationship between parenting behaviors and behavioral and emotional issues in preschool children.METHODS From October 2017 to May 2018,7 kindergartens in Ma’anshan City were selected to conduct a parent self-filled questionnaire-Health Development Survey of Preschool Children.Children’s Strength and Difficulties Questionnaire(Parent Version)was applied to measures the children’s behavioral and emotional performance.Parenting behavior was evaluated using the Parental Behavior Inventory.Binomial logistic regression model was used to analyze the association between the detection rate of preschool children’s behavior and emotional problems and their parenting behaviors.RESULTS High level of parental support/participation was negatively correlated with conduct problems,abnormal hyperactivity,abnormal total difficulty scores and abnormal prosocial behavior problems.High level of maternal support/participation was negatively correlated with abnormal emotional symptoms and abnormal peer interaction in children.High level of parental hostility/coercion was positively correlated with abnormal emotional symptoms,abnormal conduct problems,abnormal hyperactivity,abnormal peer interaction,and abnormal total difficulty scores in children(all P<0.05).Moreover,paternal parenting behaviors had similarly effects on behavior and emotional problems of preschool children compared with maternal parenting behaviors(all P>0.05),after calculating ratio of odds ratio values.CONCLUSION Our study found that parenting behaviors are associated with behavioral and emotional issues in preschool children.Overall,the more supportive or involved the parents are,the fewer behavioral and emotional problems the children experience;conversely,the more hostile or controlling the parents are,the more behavioral and emotional problems the children face.Moreover,the impact of fathers’parenting behaviors on preschool children’s behavior and emotions is no less significant than that of mothers’parenting behaviors.

基于YOLO-Pose的城市街景小目标行人姿态估计算法

现有的姿态估计算法在城市街景中对小目标行人的检测效果不佳。针对该问题,提出一种基于YOLO-Pose的小目标行人姿态估计算法YOLO-Pose-CBAM。通过引入CBAM注意力机制模块,在不增加过多计算量的前提下,增强网络聚焦小目标行人区域的能力,提升算法对小目标行人的敏感度,同时在主干网络中使用4个不同尺寸的检测头,丰富算法对图片中不同大小行人的检测手段;在骨干网络和颈部之间架设2条跨层级联通道,提升浅层网络与深层网络之间的特征融合能力,进一步增强信息交流,降低小目标行人漏检率;引入SIoU重新定义边界框回归的定位损失函数,加快训练的收敛速度,提高检测精度;采用k-means++算法代替k-means算法对数据集中标注的锚框进行聚类,避免聚类中心初始化时导致的局部最优解问题,从而选择出更适合检测小目标行人的锚框。对比实验结果表明,在小目标行人Wider Keypoints数据集上,所提算法相较于YOLO-Pose和YOLOv7-Pose在平均精度上分别提升了4.6和6.5个百分比。

基于改进YOLOv8n-pose和三维点云分析的蒙古马体尺自动测量方法

[目的/意义]准确高效地获取马匹体尺信息是马产业现代化进程中的关键环节。传统的人工测量方法耗时长、工作量大,且会对马匹造成一定应激反应。因此,实现准确且高效的体尺参数自动测量对于制定蒙古马早期育种计划至关重要。[方法]选择Azure Kinect深度相机获取蒙古马双侧RGB-D数据,以YOLOv8n-pose为基础,通过在C2f模块中引入可变形卷积(Deformable Convolution v2, DCNv2),同时添加洗牌注意力机制(Shuffle Attention, SA)模块和优化损失函数(SCYLLA-IoU Loss, SIoU)的方法,利用余弦退火法动态调整学习率,提出一种名为DSS-YOLO (DCNv2-SA-SIoU-YOLO)的模型用于蒙古马体尺关键点的检测。其次,将RGB图中的二维关键点坐标与深度图中对应深度值相结合,得到关键点三维坐标,并实现蒙古马点云信息的转换。利用直通滤波、随机抽样一致性(Random Sample Consensus, RANSAC)、统计离群值滤波、主成分分析法(Principal Component Analysis, PCA)完成点云处理与分析。最终根据关键点坐标自动计算体高、体斜长、臀高、胸围和臀围5项体尺参数。[结果和讨论] DSS-YOLO的平均关键点检测精度为92.5%;d_(DSS)为7.2个像素;参数量和运算量分别仅为3.48 M和9.1 G。体尺参数自动测量结果与人工测量值相比,各项体尺参数的整体平均绝对误差为3.77 cm;平均相对误差为2.29%。[结论]研究结果可为蒙古马运动性能相关遗传参数的确定提供技术支撑。

Enhancing Critical Path Problem in Neutrosophic Environment Using Python

In the real world,one of the most common problems in project management is the unpredictability of resources and timelines.An efficient way to resolve uncertainty problems and overcome such obstacles is through an extended fuzzy approach,often known as neutrosophic logic.Our rigorous proposed model has led to the creation of an advanced technique for computing the triangular single-valued neutrosophic number.This innovative approach evaluates the inherent uncertainty in project durations of the planning phase,which enhances the potential significance of the decision-making process in the project.Our proposed method,for the first time in the neutrosophic set literature,not only solves existing problems but also introduces a new set of problems not yet explored in previous research.A comparative study using Python programming was conducted to examine the effectiveness of responsive and adaptive planning,as well as their differences from other existing models such as the classical critical path problem and the fuzzy critical path problem.The study highlights the use of neutrosophic logic in handling complex projects by illustrating an innovative dynamic programming framework that is robust and flexible,according to the derived results,and sets the stage for future discussions on its scalability and application across different industries.

Lightweight Multi-Resolution Network for Human Pose Estimation

Human pose estimation aims to localize the body joints from image or video data.With the development of deeplearning,pose estimation has become a hot research topic in the field of computer vision.In recent years,humanpose estimation has achieved great success in multiple fields such as animation and sports.However,to obtainaccurate positioning results,existing methods may suffer from large model sizes,a high number of parameters,and increased complexity,leading to high computing costs.In this paper,we propose a new lightweight featureencoder to construct a high-resolution network that reduces the number of parameters and lowers the computingcost.We also introduced a semantic enhancement module that improves global feature extraction and networkperformance by combining channel and spatial dimensions.Furthermore,we propose a dense connected spatialpyramid pooling module to compensate for the decrease in image resolution and information loss in the network.Finally,ourmethod effectively reduces the number of parameters and complexitywhile ensuring high performance.Extensive experiments show that our method achieves a competitive performance while dramatically reducing thenumber of parameters,and operational complexity.Specifically,our method can obtain 89.9%AP score on MPIIVAL,while the number of parameters and the complexity of operations were reduced by 41%and 36%,respectively.

Movement Function Assessment Based on Human Pose Estimation from Multi-View

Human pose estimation is a basic and critical task in the field of computer vision that involves determining the position(or spatial coordinates)of the joints of the human body in a given image or video.It is widely used in motion analysis,medical evaluation,and behavior monitoring.In this paper,the authors propose a method for multi-view human pose estimation.Two image sensors were placed orthogonally with respect to each other to capture the pose of the subject as they moved,and this yielded accurate and comprehensive results of three-dimensional(3D)motion reconstruction that helped capture their multi-directional poses.Following this,we propose a method based on 3D pose estimation to assess the similarity of the features of motion of patients with motor dysfunction by comparing differences between their range of motion and that of normal subjects.We converted these differences into Fugl–Meyer assessment(FMA)scores in order to quantify them.Finally,we implemented the proposed method in the Unity framework,and built a Virtual Reality platform that provides users with human–computer interaction to make the task more enjoyable for them and ensure their active participation in the assessment process.The goal is to provide a suitable means of assessing movement disorders without requiring the immediate supervision of a physician.

A Comparative Study of Metaheuristic Optimization Algorithms for Solving Real-World Engineering Design Problems

Real-world engineering design problems with complex objective functions under some constraints are relatively difficult problems to solve.Such design problems are widely experienced in many engineering fields,such as industry,automotive,construction,machinery,and interdisciplinary research.However,there are established optimization techniques that have shown effectiveness in addressing these types of issues.This research paper gives a comparative study of the implementation of seventeen new metaheuristic methods in order to optimize twelve distinct engineering design issues.The algorithms used in the study are listed as:transient search optimization(TSO),equilibrium optimizer(EO),grey wolf optimizer(GWO),moth-flame optimization(MFO),whale optimization algorithm(WOA),slimemould algorithm(SMA),harris hawks optimization(HHO),chimp optimization algorithm(COA),coot optimization algorithm(COOT),multi-verse optimization(MVO),arithmetic optimization algorithm(AOA),aquila optimizer(AO),sine cosine algorithm(SCA),smell agent optimization(SAO),and seagull optimization algorithm(SOA),pelican optimization algorithm(POA),and coati optimization algorithm(CA).As far as we know,there is no comparative analysis of recent and popular methods against the concrete conditions of real-world engineering problems.Hence,a remarkable research guideline is presented in the study for researchersworking in the fields of engineering and artificial intelligence,especiallywhen applying the optimization methods that have emerged recently.Future research can rely on this work for a literature search on comparisons of metaheuristic optimization methods in real-world problems under similar conditions.

An Effective Meshless Approach for Inverse Cauchy Problems in 2D and 3D Electroelastic Piezoelectric Structures

In the past decade,notable progress has been achieved in the development of the generalized finite difference method(GFDM).The underlying principle of GFDM involves dividing the domain into multiple sub-domains.Within each sub-domain,explicit formulas for the necessary partial derivatives of the partial differential equations(PDEs)can be obtained through the application of Taylor series expansion and moving-least square approximation methods.Consequently,the method generates a sparse coefficient matrix,exhibiting a banded structure,making it highly advantageous for large-scale engineering computations.In this study,we present the application of the GFDM to numerically solve inverse Cauchy problems in two-and three-dimensional piezoelectric structures.Through our preliminary numerical experiments,we demonstrate that the proposed GFDMapproach shows great promise for accurately simulating coupled electroelastic equations in inverse problems,even with 3%errors added to the input data.

Investigation of Inside-Out Tracking Methods for Six Degrees of Freedom Pose Estimation of a Smartphone in Augmented Reality

Six degrees of freedom(6DoF)input interfaces are essential formanipulating virtual objects through translation or rotation in three-dimensional(3D)space.A traditional outside-in tracking controller requires the installation of expensive hardware in advance.While inside-out tracking controllers have been proposed,they often suffer from limitations such as interaction limited to the tracking range of the sensor(e.g.,a sensor on the head-mounted display(HMD))or the need for pose value modification to function as an input interface(e.g.,a sensor on the controller).This study investigates 6DoF pose estimation methods without restricting the tracking range,using a smartphone as a controller in augmented reality(AR)environments.Our approach involves proposing methods for estimating the initial pose of the controller and correcting the pose using an inside-out tracking approach.In addition,seven pose estimation algorithms were presented as candidates depending on the tracking range of the device sensor,the tracking method(e.g.,marker recognition,visual-inertial odometry(VIO)),and whether modification of the initial pose is necessary.Through two experiments(discrete and continuous data),the performance of the algorithms was evaluated.The results demonstrate enhanced final pose accuracy achieved by correcting the initial pose.Furthermore,the importance of selecting the tracking algorithm based on the tracking range of the devices and the actual input value of the 3D interaction was emphasized.

Abnormal Action Recognition with Lightweight Pose Estimation Network in Electric Power Training Scene

Electric power training is essential for ensuring the safety and reliability of the system.In this study,we introduce a novel Abnormal Action Recognition(AAR)system that utilizes a Lightweight Pose Estimation Network(LPEN)to efficiently and effectively detect abnormal fall-down and trespass incidents in electric power training scenarios.The LPEN network,comprising three stages—MobileNet,Initial Stage,and Refinement Stage—is employed to swiftly extract image features,detect human key points,and refine them for accurate analysis.Subsequently,a Pose-aware Action Analysis Module(PAAM)captures the positional coordinates of human skeletal points in each frame.Finally,an Abnormal Action Inference Module(AAIM)evaluates whether abnormal fall-down or unauthorized trespass behavior is occurring.For fall-down recognition,three criteria—falling speed,main angles of skeletal points,and the person’s bounding box—are considered.To identify unauthorized trespass,emphasis is placed on the position of the ankles.Extensive experiments validate the effectiveness and efficiency of the proposed system in ensuring the safety and reliability of electric power training.

Efficient Inverse Analysis for Solving a Coupled Conduction,Convection and Radiation Problem Involving Non⁃gray Participating Media

The presence of non-gray radiative properties in a reheating furnace’s medium that absorbs,emits,and involves non-gray creates more complex radiative heat transfer problems.Furthermore,it adds difficulty to solving the coupled conduction,convection,and radiation problem,leading to suboptimal efficiency that fails to meet real-time control demands.To overcome this difficulty,comparable gray radiative properties of non-gray media are proposed and estimated by solving an inverse problem.However,the required iteration numbers by using a least-squares method are too many and resulted in a very low inverse efficiency.It is necessary to present an efficient method for the equivalence.The Levenberg-Marquardt algorithm is utilized to solve the inverse problem of coupled heat transfer,and the gray-equivalent radiative characteristics are successfully recovered.It is our intention that the issue of low inverse efficiency,which has been observed when the least-squares method is employed,will be resolved.To enhance the performance of the Levenberg-Marquardt algorithm,a modification is implemented for determining the damping factor.Detailed investigations are also conducted to evaluate its accuracy,stability of convergence,efficiency,and robustness of the algorithm.Subsequently,a comparison is made between the results achieved using each method.