In many Eastern and Western countries,falling birth rates have led to the gradual aging of society.Older adults are often left alone at home or live in a long-term care center,which results in them being susceptible t...In many Eastern and Western countries,falling birth rates have led to the gradual aging of society.Older adults are often left alone at home or live in a long-term care center,which results in them being susceptible to unsafe events(such as falls)that can have disastrous consequences.However,automatically detecting falls fromvideo data is challenging,and automatic fall detection methods usually require large volumes of training data,which can be difficult to acquire.To address this problem,video kinematic data can be used as training data,thereby avoiding the requirement of creating a large fall data set.This study integrated an improved particle swarm optimization method into a double interactively recurrent fuzzy cerebellar model articulation controller model to develop a costeffective and accurate fall detection system.First,it obtained an optical flow(OF)trajectory diagram from image sequences by using the OF method,and it solved problems related to focal length and object offset by employing the discrete Fourier transform(DFT)algorithm.Second,this study developed the D-IRFCMAC model,which combines spatial and temporal(recurrent)information.Third,it designed an IPSO(Improved Particle Swarm Optimization)algorithm that effectively strengthens the exploratory capabilities of the proposed D-IRFCMAC(Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller)model in the global search space.The proposed approach outperforms existing state-of-the-art methods in terms of action recognition accuracy on the UR-Fall,UP-Fall,and PRECIS HAR data sets.The UCF11 dataset had an average accuracy of 93.13%,whereas the UCF101 dataset had an average accuracy of 92.19%.The UR-Fall dataset had an accuracy of 100%,the UP-Fall dataset had an accuracy of 99.25%,and the PRECIS HAR dataset had an accuracy of 99.07%.展开更多
为了解决设备相关颜色空间CMYK与设备无关颜色空间之间的相互转换问题,利用小脑模型神经网络(cerebellar model articulation controller,CMAC)高度非线性拟合能力,研究CMYK颜色空间与CIE L*a*b*之间的转换关系,研究结果显示该方法具有...为了解决设备相关颜色空间CMYK与设备无关颜色空间之间的相互转换问题,利用小脑模型神经网络(cerebellar model articulation controller,CMAC)高度非线性拟合能力,研究CMYK颜色空间与CIE L*a*b*之间的转换关系,研究结果显示该方法具有结构简单,易于软件和硬件的实现,将IT8.7/3标准色靶文件中104个专业色块值作为检验样本,检验样本的平均色差为1.6,完全适用于两种不同颜色空间之间的转换过程.展开更多
CMAC(Cerebellar Model Articulation Controller)和PD(Proportional Derivative)复合控制算法有时因输出不平滑会引起加载电机抖动而影响控制效果.通过对该输出不平滑问题进行分析,提出了一种新的提高输出平滑性的改进CMAC复合控制算法...CMAC(Cerebellar Model Articulation Controller)和PD(Proportional Derivative)复合控制算法有时因输出不平滑会引起加载电机抖动而影响控制效果.通过对该输出不平滑问题进行分析,提出了一种新的提高输出平滑性的改进CMAC复合控制算法,该方法通过新的权值更新公式,在权值更新时直接达到减小误差和提高输出平滑性的目的.仿真和实验结果表明:改进后的算法能够有效提高输出平滑性,降低了21%的稳态误差,且保证在加载时有良好的稳定性和抗干扰能力.展开更多
为了提高双层被动隔振系统隔离低频结构噪声的效果,采用混合隔振思想,将小脑模型神经网络(cerebellar model articulation controller,CMAC)理论与PID控制算法相结合,设计了双层混合隔振系统CMAC与PID复合控制器,仿真分析了双层混合隔...为了提高双层被动隔振系统隔离低频结构噪声的效果,采用混合隔振思想,将小脑模型神经网络(cerebellar model articulation controller,CMAC)理论与PID控制算法相结合,设计了双层混合隔振系统CMAC与PID复合控制器,仿真分析了双层混合隔振系统在不同低频正弦激励信号下的加速度和加速度功率谱。仿真结果表明,采用CMAC与PID复合控制的双层混合隔振系统的隔振效果要优于被动双层隔振系统的隔振效果。展开更多
A principal component analysis-cerebellar model articulation controller (PCA-CMAC) model is proposed for machine performance degradation assessment.PCA is used to feature selection,which eliminates the redundant inf...A principal component analysis-cerebellar model articulation controller (PCA-CMAC) model is proposed for machine performance degradation assessment.PCA is used to feature selection,which eliminates the redundant information among the features from the sensor signals and reduces the dimension of the input to CMAC.CMAC is used to assess degradation states quantitatively based on its local generalization ability.The implementation of the model is presented and the model is applied in a drilling machine to assess the states of the cutting tool. The results show that the model can assess the wear states quantitatively based on the normal state of the cutting tool.The influence of the quantization parameter g and the generalization parameter r in the CMAC model on the assessment results is analyzed.If g is larger,the generalization ability is better,but the difference of degradation states is not obvious.If r is smaller,the different states are distinct,but memory requirements for storing the weights are larger.The principle for selecting two parameters is that the memory storing the weights should be small while the degradation states should be easily distinguished.展开更多
基金supported by the National Science and Technology Council under grants NSTC 112-2221-E-320-002the Buddhist Tzu Chi Medical Foundation in Taiwan under Grant TCMMP 112-02-02.
文摘In many Eastern and Western countries,falling birth rates have led to the gradual aging of society.Older adults are often left alone at home or live in a long-term care center,which results in them being susceptible to unsafe events(such as falls)that can have disastrous consequences.However,automatically detecting falls fromvideo data is challenging,and automatic fall detection methods usually require large volumes of training data,which can be difficult to acquire.To address this problem,video kinematic data can be used as training data,thereby avoiding the requirement of creating a large fall data set.This study integrated an improved particle swarm optimization method into a double interactively recurrent fuzzy cerebellar model articulation controller model to develop a costeffective and accurate fall detection system.First,it obtained an optical flow(OF)trajectory diagram from image sequences by using the OF method,and it solved problems related to focal length and object offset by employing the discrete Fourier transform(DFT)algorithm.Second,this study developed the D-IRFCMAC model,which combines spatial and temporal(recurrent)information.Third,it designed an IPSO(Improved Particle Swarm Optimization)algorithm that effectively strengthens the exploratory capabilities of the proposed D-IRFCMAC(Double-Interactively Recurrent Fuzzy Cerebellar Model Articulation Controller)model in the global search space.The proposed approach outperforms existing state-of-the-art methods in terms of action recognition accuracy on the UR-Fall,UP-Fall,and PRECIS HAR data sets.The UCF11 dataset had an average accuracy of 93.13%,whereas the UCF101 dataset had an average accuracy of 92.19%.The UR-Fall dataset had an accuracy of 100%,the UP-Fall dataset had an accuracy of 99.25%,and the PRECIS HAR dataset had an accuracy of 99.07%.
文摘为了解决设备相关颜色空间CMYK与设备无关颜色空间之间的相互转换问题,利用小脑模型神经网络(cerebellar model articulation controller,CMAC)高度非线性拟合能力,研究CMYK颜色空间与CIE L*a*b*之间的转换关系,研究结果显示该方法具有结构简单,易于软件和硬件的实现,将IT8.7/3标准色靶文件中104个专业色块值作为检验样本,检验样本的平均色差为1.6,完全适用于两种不同颜色空间之间的转换过程.
文摘CMAC(Cerebellar Model Articulation Controller)和PD(Proportional Derivative)复合控制算法有时因输出不平滑会引起加载电机抖动而影响控制效果.通过对该输出不平滑问题进行分析,提出了一种新的提高输出平滑性的改进CMAC复合控制算法,该方法通过新的权值更新公式,在权值更新时直接达到减小误差和提高输出平滑性的目的.仿真和实验结果表明:改进后的算法能够有效提高输出平滑性,降低了21%的稳态误差,且保证在加载时有良好的稳定性和抗干扰能力.
文摘为了提高双层被动隔振系统隔离低频结构噪声的效果,采用混合隔振思想,将小脑模型神经网络(cerebellar model articulation controller,CMAC)理论与PID控制算法相结合,设计了双层混合隔振系统CMAC与PID复合控制器,仿真分析了双层混合隔振系统在不同低频正弦激励信号下的加速度和加速度功率谱。仿真结果表明,采用CMAC与PID复合控制的双层混合隔振系统的隔振效果要优于被动双层隔振系统的隔振效果。
基金The National Natural Science Foundation of China(No.60443007,50390063).
文摘A principal component analysis-cerebellar model articulation controller (PCA-CMAC) model is proposed for machine performance degradation assessment.PCA is used to feature selection,which eliminates the redundant information among the features from the sensor signals and reduces the dimension of the input to CMAC.CMAC is used to assess degradation states quantitatively based on its local generalization ability.The implementation of the model is presented and the model is applied in a drilling machine to assess the states of the cutting tool. The results show that the model can assess the wear states quantitatively based on the normal state of the cutting tool.The influence of the quantization parameter g and the generalization parameter r in the CMAC model on the assessment results is analyzed.If g is larger,the generalization ability is better,but the difference of degradation states is not obvious.If r is smaller,the different states are distinct,but memory requirements for storing the weights are larger.The principle for selecting two parameters is that the memory storing the weights should be small while the degradation states should be easily distinguished.