人体行为识别研究

人体行为识别是计算机视觉、模式识别等领域的重要研究方向,在智能家居、智能视频监控、虚拟现实等应用领域有着极大的应用价值。笔者对人体行为识别的国内外研究现状及目前存在的主要问题进行介绍,并对人体行为识别的主要步骤,以及各阶段已有的关键技术和方法进行了概述。最后简要说明了人体行为识别领域近年较新的研究进展和未来可能的发展趋势。

Influence of parental education on the intelligence quotient profiles and socially adaptive behavior of school-age children with autism spectrum disorder in eastern China

Intelligence quotient(IQ)and adaptive behavior are the influencing factors of autism spectrum disorder(ASD)in children entering mainstream schools.This study explored the association between parental education level,IQ,and adaptive behavior in ASD groups.A total of 257 school-age ASD children were enrolled in our study from January 2017 to June 2021.Their parents completed a standard demographic form,including age at autism diagnosis,gender,school placement,and parents’educational background.The Chinese version of the Wechsler Intelligence Scale for Children,Fourth Edition(WISC-IV)was completed by a certified assessor for each enrolled child.Parents were interviewed on adaptive behavior using the Chinese version of the Adaptive Behavior Assessment System,Second Edition(ABAS-II).The average IQ of school-age ASD children was 76.88(standard deviation(SD)=22.62)and boys had higher IQ levels than girls.The IQ was positively correlated with age.The General Adaptive Composite(GAC)score was 82.47(SD=15.86)and adaptive behavior did not increase with age.ASD children who attended mainstream schools had better adaptive behavior profiles than other children.The mother’s education level showed a significant correlation with the IQ and adaptive behavior of autistic children,while the father’s education level did not.Consequently,better training and support for parents may help autistic children enter mainstream schools,with adaptive training being the most urgently required skill for parents.

Pigeon-Inspired Circular Formation Control for Multi-UAV System with Limited Target Information

The problem of cooperative circular formation with limited target information for multiple Unmanned Aerial Vehicle(UAV)system is addressed in this paper.A pigeon-inspired circular formation control method is proposed to form the desired circular distribution in a plane based on the intelligent pigeon behavior during hovering.To reach the goal of prescribed radius and angular distribution,the controller is designed consisting of a circular movement part and a formation distribution part.Therein,the circular movement part is designed to make each UAV rotate around the speci-ed circle at the same angular speed only using the relative position between the UAV and the target.The formation distribution part could adjust the angular distance between each UAV and its neighbors with the jointly connected network to reduce communication cost.To smooth the speed variation,nonlinear PID-type method is delivered throughout the evolution of the system.The convergence analysis of the proposed control protocol is presented using Lyapunov theory and graph tools.The e®ectiveness of the proposed control strategies is demonstrated through numerical simulations.

一种基于类内类间协同的用电数据聚类选择

为应对大数据环境下用户用电的最佳聚类数的选择问题,提出一种用户用电行为的聚类优选策略;针对用户用电的行为复杂性和特征选择的有效性,通过一种基于信息量的方法对用户用电进行聚类。首先,引入评价指标,提出一种合理的聚类优选方法。然后,针对用户用电特征选择,提出基于互信息的特征优选算法。在传统聚类算法中,聚类数是随机给定的,其值选取不合理会使聚类陷入局部最优,基于此,根据“类内相似度最大化,类间相似度最小化”原理,提出距离评价函数并将其作为评判最佳聚类数的标准,采用多种方法进行综合分析得到最优聚类数。最后,用具体的用电数据对用户进行计算机仿真,验证了聚类优选策略的合理性。以自适应分布式聚类算法作为对比算法,进一步验证了所提算法的有效性。