结合经验模态分解能量矩占比和方差贡献率法的步态信号特征向量提取
摘要
步态即人体走路时的姿态,是一种复杂而有规律的运动过程。步态包含了许多运动信息,通过采集和分析步态信息得到的步态参数在康复治疗中可以发挥重要作用。为了对步态信息进行准确分类,文中分析了步态信号的特性,提出了基于经验模态分解(EMD)能量矩占比、方差贡献率法与BP神经网络理论相结合的正常人与患者步态信号的特征向量提取和步态分类的分析方法。首先将步态信号进行经验模态分解,得到所需要内禀模态函数分量(IMF),通过离散采样点求出包含主要步态特征信息的各阶IMF分量的能量矩占比与方差贡献率作为特征向量,并以此作为BP神经网络的输入,通过BP神经网络分类器对步态进行分类。经实验分析该方法能较好地识别出步态类型。
引文
[1]许林海,韩丽雅.功能强化训练结合肌电生物反馈对急性脑卒中患者上肢功能的影响[J].中国康复,2015(3):185-188.
[2]孟殿怀,励建安.功能性电刺激辅助步行设备的应用进展[J].中国康复医学杂志,2012,27(10):973-976.
[3]李光耀.基于角速度传感器的人体下肢运动识别[D].天津:河北工业大学,2013.
[4]KAUR S,SANDHU E R K.A survey on enhanced human identification using gait recognition based on neural network and support vector machine[J].International journal of application or innovation in engineering&management(IJAIEM),2013,2(6):72-78.
[5]刘荣,黄璐,李少伟,等.基于步态加速度的步态分析研究[J].传感器学报,2009,22(6):893-896.
[6]DEJNABADI H,JOLLES B M,AMINIAN K.A new approach to accurate measurement of uniaxial joint angles based on a combination of accelerometers and gyroscopes[J].Biomedical engineering,2005,52(8):1478-1484.
[7]YAN L,YUE E L,JIAN H.Gait recognition based on MEMS accelerometer[C]//Proceedings of the 10th IEEE International Conference on Signal Processing Signal,2010:1679-1681.
[8]BUSSMANN J B J,VELTINK P H,KOELMA F,et al.Ambulatory mobility-related activities:the initial phase of the development monitor[J].Eur j phys rehabil med,1995,5(1):2-7.
[9]SAREMI K,MAREHBIAN J,YAN X,et a1.Reliability and validity of bilateral thigh and foot accelerometry measures of walking in healthy and hemiparetic subjects[J].Neurorehabilitation and neural repair,2006,20(2):297-305.
[10]章婉霞.步态监测系统的嵌入式软件设计与实现[D].大连:大连理工大学,2013.
[11]AMES B L,REBECCA B M,BRENDAN J B.The use of a single inertial sensor to identify stride,step,and stance durations of running gait[J].Journal of science and medicine in sport,2010,13:270-273.
[12]HUANG N E,SHEN Z,LONG S R,et a1.The empirical mode decomposition and the Hilbert spectrum for nonlinearand nonstationary time serie analysis[J].Proc.R.Soc.Lond.A,1998,45(4):903-995.
[13]李天云,赵妍,季小慧.HHT方法在电力系统故障信号分析中的应用[J].电工技术学报,2005,20(6):87-91.
[14]于徳介,程军圣,杨宇.机械故障诊断的Hilberthuang变换方法[M].北京:科学出版社,2006.
[15]陈忠,郑时雄.基于经验模式分解(EMD)的齿轮箱齿轮故障诊断技术研究[J].振动工程学报,2003,16(2):229-231.
[16]LOH C H.Application of the empirical mode decomposition-Hilbert spectrum method to identify near-fault ground-motion characteristics and structural responses[J].Bulletin of theseism gical society of America,2001(91):1339-1357.
[17]程军圣.基于Hilbert-Huang变换的旋转机械故障诊断方法研究[D].长沙:湖南大学,2005.
[18]庄育锋,胡晓瑾,翟宇.基于BP神经网络的微量药品动态称重系统非线性补偿[J].仪器仪表学报,2014,35(8):1914-1920.
[19]王同旭,马鸿雁,聂沐晗.电梯用永磁同步电机BP神经网络PID调速控制方法的研究[J].电工技术学报,2015,30(1):43-47.
[20]程军圣,罗颂荣,杨斌,等.LMD能量矩和变量预测模型模式识别在轴承故障智能诊断中的应用[J].振动工程学报,2013,26(5):751-757.
[21]姚刚,赵建军,姚跃亭,等.基于改进EMD方法的系统误差分离方法研究[J].振动与冲击,2014,33(14):176-180.
[22]LEE J A,CHO S H,LEE Y J,et a1.Portable activity monitoring system for temporal parameters of gait cycles[J].Journal of medical systems,2010,34(5):959-966.
[23]黄金兰.步态分析及在功能性电刺激中的应用[D].福州:福州大学,2016.
[2]孟殿怀,励建安.功能性电刺激辅助步行设备的应用进展[J].中国康复医学杂志,2012,27(10):973-976.
[3]李光耀.基于角速度传感器的人体下肢运动识别[D].天津:河北工业大学,2013.
[4]KAUR S,SANDHU E R K.A survey on enhanced human identification using gait recognition based on neural network and support vector machine[J].International journal of application or innovation in engineering&management(IJAIEM),2013,2(6):72-78.
[5]刘荣,黄璐,李少伟,等.基于步态加速度的步态分析研究[J].传感器学报,2009,22(6):893-896.
[6]DEJNABADI H,JOLLES B M,AMINIAN K.A new approach to accurate measurement of uniaxial joint angles based on a combination of accelerometers and gyroscopes[J].Biomedical engineering,2005,52(8):1478-1484.
[7]YAN L,YUE E L,JIAN H.Gait recognition based on MEMS accelerometer[C]//Proceedings of the 10th IEEE International Conference on Signal Processing Signal,2010:1679-1681.
[8]BUSSMANN J B J,VELTINK P H,KOELMA F,et al.Ambulatory mobility-related activities:the initial phase of the development monitor[J].Eur j phys rehabil med,1995,5(1):2-7.
[9]SAREMI K,MAREHBIAN J,YAN X,et a1.Reliability and validity of bilateral thigh and foot accelerometry measures of walking in healthy and hemiparetic subjects[J].Neurorehabilitation and neural repair,2006,20(2):297-305.
[10]章婉霞.步态监测系统的嵌入式软件设计与实现[D].大连:大连理工大学,2013.
[11]AMES B L,REBECCA B M,BRENDAN J B.The use of a single inertial sensor to identify stride,step,and stance durations of running gait[J].Journal of science and medicine in sport,2010,13:270-273.
[12]HUANG N E,SHEN Z,LONG S R,et a1.The empirical mode decomposition and the Hilbert spectrum for nonlinearand nonstationary time serie analysis[J].Proc.R.Soc.Lond.A,1998,45(4):903-995.
[13]李天云,赵妍,季小慧.HHT方法在电力系统故障信号分析中的应用[J].电工技术学报,2005,20(6):87-91.
[14]于徳介,程军圣,杨宇.机械故障诊断的Hilberthuang变换方法[M].北京:科学出版社,2006.
[15]陈忠,郑时雄.基于经验模式分解(EMD)的齿轮箱齿轮故障诊断技术研究[J].振动工程学报,2003,16(2):229-231.
[16]LOH C H.Application of the empirical mode decomposition-Hilbert spectrum method to identify near-fault ground-motion characteristics and structural responses[J].Bulletin of theseism gical society of America,2001(91):1339-1357.
[17]程军圣.基于Hilbert-Huang变换的旋转机械故障诊断方法研究[D].长沙:湖南大学,2005.
[18]庄育锋,胡晓瑾,翟宇.基于BP神经网络的微量药品动态称重系统非线性补偿[J].仪器仪表学报,2014,35(8):1914-1920.
[19]王同旭,马鸿雁,聂沐晗.电梯用永磁同步电机BP神经网络PID调速控制方法的研究[J].电工技术学报,2015,30(1):43-47.
[20]程军圣,罗颂荣,杨斌,等.LMD能量矩和变量预测模型模式识别在轴承故障智能诊断中的应用[J].振动工程学报,2013,26(5):751-757.
[21]姚刚,赵建军,姚跃亭,等.基于改进EMD方法的系统误差分离方法研究[J].振动与冲击,2014,33(14):176-180.
[22]LEE J A,CHO S H,LEE Y J,et a1.Portable activity monitoring system for temporal parameters of gait cycles[J].Journal of medical systems,2010,34(5):959-966.
[23]黄金兰.步态分析及在功能性电刺激中的应用[D].福州:福州大学,2016.