基于有监督Kohonen神经网络的步态识别

表面肌电信号随着时间的变化而改变,这将影响运动模式的分类精度.传统人体下肢假肢运动模式的识别算法不能保证在整个肌电控制时间内达到对运动模式的有效识别.为了解决这些问题,本文提取步态初期200ms的信号的特征值,将无监督和有监督的Kohonen神经网络算法应用到大腿截肢者残肢侧的步态识别中,并与传统BP神经网络进行了对比.结果表明,有监督的Kohonen神经网络算法将五种路况下步态的平均识别率提高到88.4%,优于无监督的Kohonen神经网络算法和BP神经网络.     

基于隐马尔可夫模型的动力型下肢假肢步态预识别

为使动力型假肢膝关节协调配合人体的运动,关键是对人体行走步态进行有效预识别.本文利用安装在假肢接受腔上的加速度传感器和安装在足底的压力传感器采集人体的运动信息,根据人体运动的规律性和重复性特点,通过将隐马尔可夫模型引入到所获得的运动信息中来分析并预识别人体的运动步态.实验表明,基于隐马尔可夫模型的动力型下肢假肢的步态预识别方法是有效并且准确的.     

针对上肢高位截肢者的肌电假肢设计

给出了一种基于人体表面肌电信号控制的上肢假肢系统,服务于基于靶向肌肉神经移植术的高位截肢者.通过解析人体肌电信号包含的动作意图控制假肢的运动.系统包括假肢的机械结构、控制系统的硬件和算法.假肢的机械结构包括肘关节、腕关节和手部.控制系统的硬件包括主控板、驱动板和肌电采集模块.模式识别算法采用基于贝叶斯原理的线性分类器,通过在线实时训练,得到需要的线性分类器参数.根据得到的分类器模型,对采集到的肌电信号进行在线实时识别,并根据识别的结果实时控制相应假肢关节的运动.系统样机在健康受试者身上进行了测试,效果良好.     

基于sEMG的行走步态非均匀特性及其对识别的影响

人体生理特性和运动特性是影响步态识别的重要因素。利用实验采集的下肢表面肌电信号,首先对肌电信号进行小波消噪及特征提取,然后构造支持向量机分类器进行分类与识别,并针对步态周期数据的非均匀性（非等时性）特性进行了详细讨论。结果表明,即使在匀速行走条件下,人体步态周期仍然存在一定的非均匀特性,且这一特点会影响步态识别的准确性。这对于进一步研究步态稳定性和步态识别率等具有一定的参考价值。     

基于上臂关节角度和肌电信号的二自由度假肢控制方法

肌电信号的采集易受到空气湿度和皮肤表面汗液等多种随机因素的干扰,使采集到的肌电信号极不稳定.为了应对此问题,市售的肌电假肢普遍采用基于开关量的控制方法,但是开关量对多自由度假肢的控制依赖于顺序动作切换,这使得假肢的实际使用过程比较繁琐.利用肢体运动学信息的假肢控制方法常见于下肢假肢,这是因为上肢的运动受抓取物体的形状和位置等因素变化,其肢体运动的规律性较差.本文提出一种利用上臂关节角度和肌电信号的控制方法,利用人体在抓握时肩关节的运动模式区分使用者对不同形状物体的抓握,并将此方法应用在二自由度假肢的控制中.通过与开关量控制的假肢在日常物品抓握实验中的对比,表明本文所提出方法在稳定性和使用效率方面都优于开关量控制的方式.     

一种面向下肢假肢的运动意图识别方法及验证

对截肢者下肢运动意图的准确识别是提高下肢假肢人机交互性能，降低假肢使用者运动能耗的关键。基于健康受试者在不同运动模式的下肢表面肌电信号(sEMG)和由六自由度惯性测量单元(IMU)采集到的角速度信号、加速度信号等运动学信号设计了一种面向下肢假肢的运动意图识别方法，并通过髋截肢者的健侧肌电和两侧下肢的运动学数据对上述方法进行可行性和有效性验证。结果表明，该方法能在健康受试者的多源传感信息中选出最适于分类的最小特征子集，并在精细K最近邻(KNN)分类器中实现对站、平地走、上下楼梯、上下斜坡这6种不同运动意图高达99.2%的识别准确率；同时在髋截肢者这一类高位截肢患者的多源传感信息中依然能筛选出最小特征子集并实现高达99.8%的识别精度。实验结果说明了所提出方法的有效性和普遍适用性。     

GA-BP神经网络在下肢运动步态识别中的应用研究

为了提高下肢表面肌电信号步态识别的准确性,提出了一种基于遗传算法（GA）优化的BP神经网络分类器设计方法。首先,对采集的下肢表面肌电信号进行小波滤波及特征值提取,其次,构造基于GA优化的BP神经网络分类器,然后,以提取的表面肌电信号特征作为输入对分类器进行训练,最后利用训练好的分类器进行测试。实验结果表明,基于GA优化的BP神经网络分类器能成功识别下肢正常行走的五个步态,平均识别率达到98%以上,效果明显优于BP神经网络分类器的识别效果。     

下肢截肢者行走意图识别方法研究进展

直立行走是人类独立生活和正常参与社会活动的基本功能之一.人因遭受工伤、交通事故、战争、自然灾害（地震等）、疾病（糖尿病、癌症等）、先天出生缺陷等意外和不幸造成下肢截肢，从而部分或全部丧失行走能力，严重影响正常生活和参与社会活动.下肢假肢是下肢截肢者恢复行走功能的唯一手段，其技术发展吸引了众多研究者的关注.为使下肢假肢使用者能像正常腿一样或接近的步态行走，关键是实现截肢者行走意图的自动精确识别.本文首先探索了行走意图识别的内涵；然后从信号源的角度分析了不同截肢者行走意图识别方法的特点，尤其是神经功能重建作为补充的肌电信号（Electromyography，EMG）源的方法，并简述其研究进展，提出了一种融合生物力学信号和生物电信号的截肢者行走意图识别方法；最后对下肢截肢者行走意图识别方法发展趋势进行了总结和展望.     

基于改进模板匹配的智能下肢假肢运动意图实时识别

传统下肢假肢运动意图识别常使用多模态传感器采集残肢侧时频域特征,在短时意图识别中,具有一定的复杂性和滞后性,且时频域特征不稳定难以达到实时意图识别的目的.鉴于此,提出基于改进模板匹配技术的智能下肢假肢运动意图实时识别的方法.在重新定义单侧下肢截肢者的运动模式后,仅采用惯性传感器采集健肢侧位于摆动相的数据,基于改进的模板匹配,通过滑动窗口创建完备的模板库,使得每类运动模式在库中有充足的原子模式,对下肢假肢的运动意图进行实时识别.实验结果表明,所提出方法在5种稳态模式(平地行走、上下楼、上下坡)的识别率为99.50%,在引入8种转换模式后的识别率为97.03%,可以大大提高下肢假肢实时识别性能,助力单侧下肢截肢者更自然地行走.     

基于肌电信号的行走步态周期识别方法与实验系统的设计

通过下肢表面肌电信号的人体行走步态周期识别方法设计了实验系统;针对表面肌电信号的微弱性、交变性、低频性等特点,提出了识别肌肉动作起始时刻的峰—谷线性插值分段积分算法,并将该算法与阈值法相结合,提取足跟着地前肌肉动作起始时刻,从而达到划分步态周期的目的;该方法仅需单通道信号作为信息源,不同被测者可以选用不同的肌电信号;有效回避了肌电信号传感器零点漂移现象;文中分别对5位被测者行走时的7个下肢肌电信号进行采集,以VisualC++为工具,基于用户界面设计了步态周期的识别系统,其系统识别结果验证了该方法具有广泛性、可靠性、准确性和实用性。     

基于足底压力与支持向量机的步态相位识别研究

随着两足机器人、人工假肢技术以及为行走困难病人康复设计的康复训练机器人的发展,在线的步态相位识别方法越来越重要。本文提出的基于足底压力与支持向量机(SVM)的步态相位识别算法主要由五部分组成,即数据采集、数据预处理、特征提取、训练分类器和分类识别。实验表明：该方法能够对运动中的步态相位进行准确的判断。     

Multi-channel Fusion Based Adaptive Gait Trajectory Generation Using Wearable Sensors

This paper presents a method to regenerate lower limb joint angle trajectories during gait cycle by judging human intention using wearable sensor system. Myoelectric signals from user are used to detect the intention of gait initiation and gait phases. Multi-channel redundant fusion technique is implemented to obtain a robust stride time and gait phase calculation algorithm. Joint trajectories corresponding to particular gait events and phases are regenerated using a Radial basis neural network. The network is trained with joint angle data measured by Inertial Measurement Unit (IMU) from users with varying anthropomorphic features. Generated trajectory is adaptive to anthropomorphic as well as gait velocity variation. Contribution of this paper is in development of a wearable sensor system, multi-channel redundant fusion to calculate stride time and an adaptive gait trajectory generation algorithm. The proposed method of trajectory generation is used to regenerate lower limb joint motion in sagittal plane for wearable robotic devices like prosthesis and active lower limb exoskeleton.     

惯性动捕数据驱动下的智能下肢假肢运动意图识别方法

为了解决传统意图识别方法使用多模态传感器信号所带来的复杂性以及识别转换模式一般具有滞后性等问题, 本文提出了基于惯性传感器的智能下肢假肢的运动意图实时识别方法.从模式识别的角度看, 在对象空间到模式空间的转换中, 对运动模式尤其是运动转换模式进行了重定义; 在模式采集中, 采用在患侧的运动模式进行转换之前, 采集绑定在健侧的传感器于摆动相前期所产生的时序运动数据, 选择均值、方差等特征统计量和支持向量机分类器对其进行特征选择提取与特征分类的策略, 实现对残疾人运动意图准确、实时地识别.实验结果表明, 本文所提出的方法可以识别出单肢截肢患者在不同地形下的运动意图, 包括平地行走、上楼、下楼、上坡、下坡5种稳态模式, 识别率可达到97.52 %, 并且加入在5种模式之间相互转换的转换模式之后, 识别率可达到95.12 %.本文方法可以极大提高智能下肢假肢的控制性能, 实现智能假肢能根据人的运动意图在多种运动模式之间进行自然、无缝的状态切换.     

Neural computing for walking gait pattern identification based on multi-sensor data fusion of lower limb muscles

The use of neural computing for gait analysis widely known as computational intelligent gait analysis is addressed recently. This research work reports multilayer feed-forward neural networks for walking gait pattern identification using multi-sensor data fusion; electromyography (EMG) signals and soft tissue deformation analysis using successive frames of video sequence extracted from lower limb muscles according to each gait phase within the considered gait cycle. Neural computing framework for walking gait pattern identification consists of system hardware and intelligent system software. System hardware comprises a wireless surface EMG sensor unit and two video cameras for measuring the neuromuscular activity of lower limb muscles, and a custom-developed artificial neural network for classifying the gait patterns of subjects during walking. The system uses root mean square and soft tissue deformation parameter as the input features. Multilayer feed-forward back propagation neural networks (FFBPNNs) with different network training functions were designed, and their classification results were compared. The intelligent gait analysis system validation has been carried out for a group of healthy and injured subjects. The results demonstrated that the overall accuracy of 98 % prediction is achieved for gait patterns classification established by multi-sensor data fusion of lower limb muscles using FFBPNN with Levenberg–Marquardt training function resulting better performance over FFBPNN with other training functions.

     

基于足底压力和关节运动信息的步态检测系统设计

作为老年人高发疾病,脑卒中有着较高的几率造成患者行动障碍。及时检测、获取偏瘫患者行走时步态信息,是治疗师为患者制定康复计划的重要环节。目前,较新的步态检测系统大多采用三维分析,三维步态分析系统体积较大、成本高、操作不便,在患者主动康复训练中存在较大的局限。针对现今步态检测系统的局限,设计了一种结合无线传输技术,检测患者关节运动角度及足底压力的运动信息检测系统。系统采用薄膜压力传感器、惯性传感器分别采集足底压力及关节运动信息,实现了对患者的8路足底压力信息及下肢关节运动角度信息的快速、有效采集。实验表明,系统可以有效采集关节运动角度及足底压力信息,在未来的康复训练中有着很好的应用前景。     

Advanced multimodal visualisation of clinical gait and fluoroscopy analyses in the assessment of total knee replacement

Traditional gait and fluoroscopy analysis of human movement are largely utilised but are still limited in registration, integration, synchronisation and visualisation capabilities. The present work exploits the features of a recently developed software tool based on multimodal display (Data Manager developed within the EU-funded project 'Multimod') in an exemplary clinical case. Standard lower limb gait analysis, comprising segment position, ground reaction force and EMG data collection, and three-dimensional fluoroscopy analysis at the replaced joint were performed in a total knee replacement patient while ascending stairs. Clinical information such as X-rays and standard scores were also available. Data Manager was able to import all this variety of data and to structure these in an original hierarchical tree. Bone and prosthesis component models were registered to corresponding marker position data for effective three-dimensional animations. These were also synchronised with corresponding standard video sequences. Animations, video, time-histories of collected and also processed data were shown in various combinations, according to specific interests of the bioengineering and medical professionals expected to observe and to interpret this large amount of data. This software tool demonstrated to be a valuable means to enhance representation and interpretation of measurements coming from human motion analysis. In a single software, a thorough and effective clinical and biomechanical analysis of human motion was performed.     

下肢康复机器人的自适应人机交互控制策略

针对康复机器人运动过程中的人机交互性问题,提出一种下肢康复机器人自适应人机交互控制策略.提取伸屈运动中下肢表面肌电信号（Surface electromyography,sEMG）和足底压力特征,分别用于表征下肢运动意图和人机交互力（Interaction force,IF）信息,建立基于sEMG-IF的人机交互信息融合模型,实现下肢康复机器人运动轨迹的在线规划;考虑主动康复运动过程中的人机交互作用,建立具有时变动态特性的人机系统动力学模型,设计间接模糊自适应控制器对期望轨迹进行跟踪控制,实现下肢康复机器人自适应人机交互控制.通过对5名被试者进行下肢康复机器人运动控制实验研究,验证所提方法的可行性和有效性.     

Electromyography-based control of active above-knee prostheses

This paper presents a new electromyography (EMG)-based control approach for above-knee (AK) prostheses, which enables the user to control the prosthesis motion directly with his or her muscle activating neural signals. Furthermore, the unique ‘active-reactive’ control structure mimics the actuation mechanism of a human biological joint, and thus provides the user an experience similar to that of a biological lower limb in the control process. In the proposed control approach, surface EMG is utilized to provide a non-intrusive interface to the user's central nervous system, through which the muscle-activating signals can be obtained. With the EMG signals as inputs, an ‘active-reactive’ control algorithm is developed based on the analysis on a simplified musculoskeletal structure of human biological joint. This control algorithm incorporates an ‘active’ component, which reflects the user's active effort to actuate the joint, and a ‘reactive’ component, which models the reaction of the joint to the motion as a result of the controllable impedance displayed on the joint. With this unique structure, the controller enables the active control of the joint motion, while at the same time achieves a natural interaction with the environment through the modulation of the joint impedance. The effectiveness of the proposed control approach was demonstrated through a set of free swing experiments, in which the user was able to control the prosthesis to follow arbitrary motion commands, and a set of level walking experiments, in which the user achieved natural walking gait similar to the typical walking gait of healthy subjects.