基于改进小脑模型的sEMG下肢关节力矩预测

关节力矩预测在康复医学、临床医学和运动训练等领域有着重要作用,对力矩连续、实时地预测可以使人机交互设备更好地反馈、复刻人体运动意图。为了给患者提供一个安全、主动、舒适的康复训练环境,提升人机交互设备的柔顺性,提出了一种改进型递归小脑模型神经网络模型关节力矩预测方法。该方法采用肌肉协同分析对采集的相关肌肉的表面肌电信号(sEMG)进行降维,将降维后的sEMG特征向量与关节角速度、关节角度作为输入信号,并在小脑模型神经网络中加入递归单元和模糊逻辑规则,以小波函数作为隶属度函数,对非疲劳、过渡疲劳及疲劳这3种状态下的踝关节背屈跖屈运动的动态力矩进行连续预测。力矩预测值与实际值之间的平均皮尔逊相关系数和平均标准均方根误差分别为0.933 5和0.159 8,实验结果验证了该方法对下肢关节力矩连续预测的准确性和有效性。     

肌电模糊熵特征的加权核FDA跌倒识别

针对跌倒常常对老年人的健康构成严重危害的问题.本文设计了一种基于肌电信号的跌倒检测方法,首先提取腓肠肌和股外侧肌的sEMG的模糊熵特征作为特征向量,然后,针对日常活动动作类(Activities of Daily Life,ADL)的数目远多于跌倒类导致的数据集不平衡的问题,提出了加权核Fisher线性判别方法,采用相应的平衡参数来调节样本核矩阵,最终,将跌倒与行走、蹲下和坐下辨识出来.实验结果表明,该方法跌倒平均识别率96.7%,ADL平均识别率99.4%,识别结果优于其它分类方法.     

Deep Learning for EMG-based Human-Machine Interaction: A Review

Electromyography (EMG) has already been broadly used in human-machine interaction (HMI) applications. Determining how to decode the information inside EMG signals robustly and accurately is a key problem for which we urgently need a solution. Recently, many EMG pattern recognition tasks have been addressed using deep learning methods. In this paper, we analyze recent papers and present a literature review describing the role that deep learning plays in EMG-based HMI. An overview of typical network structures and processing schemes will be provided. Recent progress in typical tasks such as movement classification, joint angle prediction, and force/torque estimation will be introduced. New issues, including multimodal sensing, inter-subject/inter-session, and robustness toward disturbances will be discussed. We attempt to provide a comprehensive analysis of current research by discussing the advantages, challenges, and opportunities brought by deep learning. We hope that deep learning can aid in eliminating factors that hinder the development of EMG-based HMI systems. Furthermore, possible future directions will be presented to pave the way for future research.      

小波变换在肌电信号预处理中的应用

传统检测方法处理肌电信号时，个体差异比较大，针对这一不足，首先应用小波消噪理论对肌电信号进行预处理，将信号进行小波分解与重构，消除了肌电信号实际测量中不可测噪声的干扰，然后分析重构得到的信号的功率谱比值和对应肢体动作变化之间的关系。这种方法很适合处理非特定人的肌电信号。实验表明这种方法与单一使用功率谱比值法的方法相比，动作模式识别率得到了提高。同时，采用虚拟仪器技术提高仪器的测量精度，降低成本。     

肱二头肌离心和向心收缩的肌电信号特征

采用线性分析指标平均振幅、平均功率频率和非线性分析指标Lempel-Ziv复杂度、确定性线段百分比，分别对在5、10和15 kg 3种负荷水平下肱二头肌离心和向心收缩运动诱发肌肉疲劳过程中表面肌电信号的变化进行了分析.结果发现，表面肌电信号的线性和非线性指标的均值在离心和向心2种收缩类型间均存在显著差异（P<0.05），平均振幅和确定性线段百分比的均值在3种负荷水平间存在显著差异（P<0.05），而平均功率频率和 Lempel-Ziv复杂度的均值在3种负荷水平间无显著差异.线性和非线性指标的斜率在3种负荷水平间均存在显著差异（P<0.05），但在离心和向心2种收缩类型间仅有平均振幅存在显著差异（P<0.001）.实验结果为在疲劳过程中表面肌电信号的疲劳相关性指标的变化具有非疲劳特异性的观点提供了新的实验证据.     

Facial EMG as an index of affective response to nicotine.

Negative affect reduction has been postulated to be a key feature of cigarette smoking. In the present study, facial electromyography (EMG), heart rate (HR), and skin conductance response (SCR) were used to evaluate the affective significance of acute nicotine administration and overnight withdrawal. Smokers (N = 115) attended four 90-min laboratory assessment sessions scheduled approximately 3 days apart. The sessions provided a complete crossing of 2 prelaboratory deprivation conditions (12-hr deprived vs. nondeprived) with 2 drug conditions (nicotine vs. placebo nasal spray). During each session, smokers viewed affective slides while facial EMG, HR, and SCR were recorded. Results indicated that for women, nicotine nasal spray resulted in lower corrugator EMG activity during both smoking-deprived and nondeprived sessions, compared with placebo. However, nondeprived women also showed an increase in zygomaticus EMG when given nicotine compared with placebo spray, whereas smoking-deprived women demonstrated a decrease in the zygomaticus response to nicotine compared with placebo. With men, nicotine also appeared to lower corrugator during deprivation, but not nondeprivation, compared with placebo spray, though the contrast only approached significance. With zygomaticus EMG, nicotine spray decreased men's zygomaticus responding during nondeprivation but not during deprivation, compared with placebo spray. The HR results reflected the stimulatory properties of the drug rather than nicotine's affective properties, whereas SCR was unresponsive to our experimental manipulations. The corrugator EMG results support negative reinforcement models of smoking that postulate that acute nicotine use reduces withdrawal-driven negative affect. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Towards a systematic approach to real-time sonification design for surface electromyography

Surface electromyography (sEMG) is a technique for measuring the electrical activity of muscles and is often used as a biofeedback tool. However, challenges associated with the typically visual display of sEMG data have motivated researchers to find non-visual ways of displaying sEMG data, and parameter-mapping sonification has been explored in order to present sEMG data acoustically. Parameter-mapping sonification is a technique that involves mapping values in a data set to acoustic properties of sound. Sonification of EMG data has shown potential for identifying musculoskeletal disease and improving athletic and exercise performance. However, many sonification designs to date have not been systematically evaluated and there have been few quantitative approaches to objective comparisons of sonification paradigms. In this study, we performed a quantitative comparison of different sonification designs in order to test our hypothesis that different sonification designs may be better suited to different tasks. Thirty-six participants (ages 18–31, 14 male) who volunteered to listen to the sEMG sonifications created for this study were asked to identify two different features of the data: muscle activation time and muscle exertion level. Their responses were analyzed in order to determine the effect of sonification design on listener performance. Results indicated that having the sonifications spatialized resulted in the best performance for both tasks. However, different sonification designs resulted in the best performance for the muscle activation time estimation task (Pitch and Loudness mapped redundantly) and the muscle exertion level estimation task (Pitch, Loudness, and Attack mapped redundantly). Further, for the time estimation task, the use of the Attack mapping appeared to reliably inhibit performance. These findings strongly suggest that sonification designs for sEMG need to be designed differently based on the task the user is performing.     

Physiological and subjective responses to breathing resistance of N95 filtering facepiece respirators in still-sitting and walking

The objective of this study was to assess the impact of breathing resistance on physiological and subjective responses to N95 filtering facepiece respirators (N95 FFRs) during still-sitting and walking. Fifteen subjects sat for 5 min and walked for 5 min while wearing 2 different models of N95 FFRs, 1 model of which was equipped with exhalation valves (N95 FFR/EV). The subjects were monitored by a modified monitoring garment for respiratory signals (RSP) and surface electromyography (sEMG). Subjects also were asked to complete subjective ratings of overall breathing resistance. The results of the physiological measurements in this study have shown that compared with no respirator, wearing N95 FFR had a direct effect on increasing respiratory amplitude, muscle activity and fatigue of abdominal, and fatigue of scalene; The use of N95 FFR/EV conferred limited physiological benefit over N95 FFR in walking; Compared with sitting still, walking significantly decreased respiratory amplitude, but increased respiratory rate, the muscle activity of sternomastoid, scalene, diaphragm and abdominal, the fatigue of scalene and intercostal. The subjective survey showed that wearing respirators and walking had a direct effect on improving the subjective overall breathing resistance. Significantly low to moderate correlation coefficients were shown between physiological values (respiratory amplitude, the muscle activity of diaphragm, the muscle activity and fatigue of scalene and abdominal), and the subjective breathing resistance. This is the first reported study that combines RSP, sEMG and subjective overall breathing resistance to evaluate breathing resistance on the use of N95 FFR in sitting still and walking. The physiological responses to breathing resistance of wearing a N95 FFR for 5 min in still-sitting and walking are relatively small and should generally be well tolerated by healthy persons.Relevance to industryThis paper's findings can be readily employed by respirator manufactures and administrations for evaluating the respiratory muscle function (activity, fatigue) and breathing parameters of wearing N95 FFRs. Observations of present study are in support of issuing new regulations to raise the limit for breathing resistance over short periods at low-moderate exertion tasks. Thus, the manufacturers could easily fulfill the requirements for collection efficiency by adding more filter media while still meeting the requirements for air resistance.     

Mind at ease puts a smile on the face: Psychophysiological evidence that processing facilitation elicits positive affect.

The affect system, in its position to monitor organismic–environmental transactions, may be sensitive to the internal dynamics of information processing. Hence, the authors predicted that facilitation of stimulus processing should elicit a brief, mild, positive affective response. In 2 studies, participants watched a series of neutral pictures while the processing ease was unobtrusively manipulated. Affective reactions were assessed with facial electromyography (EMG). In both studies, easy-to-process pictures elicited higher activity over the region of zygomaticus major, indicating positive affect. The EMG data were paralleled by self-reports of positive responses to the facilitated stimuli. The findings suggest a close link between processing dynamics and affect and may help understand several preference phenomena, including the mere-exposure effect. The findings also highlight a potential source of affective biases in social judgments. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

基于小波变换和盲信号分离的多通道肌电信号处理方法

 为了消除多通道表面肌电信号(SEMG)采集时形成的混叠现象,提出一种新的SEMG处理方法.该方法将小波变换和独立分量分析(ICA)结合,利用小波变换的去噪作用,滤除混合在原始SEMG中的部分噪声后作为ICA的输入信号,采用Infomax算法对输入信号实施盲分离,并引入相关系数验证ICA分量与源信号的一致性.实验结果表明,该方法用于多通道SEMG的盲分离是很有效的.