国家自然科学基金(61603003); 安徽省科技重大专项(18030901021); 安徽省领军人才队伍项目; 安徽省高校优秀拔尖人才培育资助项目(gxbjZD26)资助.
1.Anqing Normal University;2.Tongling University
the National Nature Science Foundation of China (Nos. 61603003); the Science and Technology Major Project of Anhui Province (18030901021); the Leading Talent Team Project of Anhui Province; the Anhui Provincial Department of Education outstanding top-notch talent-funded projects (No. gxbjZD26) in China.
传统的意图识别方法所用传感器数量及种类较多, 特征向量维数偏高, 统计特征对短时样本具有不稳定性. 本文将关节角表示的几何特征与加速度、角速度表示的物理特征有机融合并应用于智能下肢假肢的运动意图识别. 首先, 利用惯性测量单元于健侧大腿、小腿处采集的摆动相前期短时时序数据解算膝关节角, 以获取大腿、小腿绕关节轴的转动特性. 其次, 对物理特征提取均值、方差以反映短时数据的平均水平及离散程度, 对几何特征提取最值斜率以反映短时数据的局部变化率并弥补统计特征的不稳定性. 最后, 将几何特征与物理特征融合, 采用支持向量机对13种日常行为进行分类. 实验结果表明, 对5类稳态模式: 平地行走、上楼、下楼、上坡和下坡的识别率达到96.9%, 对8类转换模式的识别率达到97.1%, 对13 种模式的识别率为94.3%. 本文仅用健侧两个传感器数据, 通过特征融合构成25维的混合特征, 实现了快速降维, 降低了算法复杂度.
A large number of sensors are used in the method of traditional intention recognition. The feature space composed of data has high dimension, the statistical features are unstable for short-term samples. In this paper, the geometric features represented by the joint angles and the physical features represented by the acceleration and angular velocity are organically integrated, and they are used in the motion intention recognition of the intelligent lower limb prosthesis. Firstly, the knee joint angle is calculated by using the short time series data collected from the healthy thigh and calf in the early swing phase by the inertial measurement unit. Obtaining the rotation characteristics of the thigh and calf around the joint axis. Secondly, the mean value and variance of physical features are extracted to reflect the mean level and dispersion degree of short-term data, and the slopes of the maximum and minimum of geometric features is extracted to reflect the local change rate of short-term data and make up for the instability of statistical features. Finally, the geometric features and physical features are fused, and the support vector machine is used to classify 13 daily behaviors. The experimental results show that the recognition rate of 5 kinds of steady states: walking, stair ascent, stair descent, ramp ascent and ramp descent reaches 96.9%. The recognition rate of 8 kinds of transitional states reaches 97.1%. And the recognition rate of 13 kinds of states reaches 94.3%. In this paper, only the data of two sensors on the healthy side to form a 25-dimensional hybrid feature by feature fusion, which achieves rapid dimensionality reduction and reduces the algorithm complexity.