An ergonomics study of thumb movements on smartphone touch screen

This study investigated the relationships between thumb muscle activity and thumb operating tasks on a smartphone touch screen with one-hand posture. Six muscles in the right thumb and forearm were targeted in this study, namely adductor pollicis, flexor pollicis brevis, abductor pollicis brevis (APB), abductor pollicis longus, first dorsal interosseous (FDI) and extensor digitorum. The performance measures showed that the thumb developed fatigue rapidly when tapping on smaller buttons (diameter: 9 mm compared with 3 mm), and moved more slowly in flexion–extension than in adduction–abduction orientation. Meanwhile, the electromyography and perceived exertion values of FDI significantly increased in small button and flexion–extension tasks, while those of APB were greater in the adduction–abduction task. This study reveals that muscle effort among thumb muscles on a touch screen smartphone varies according to the task, and suggests that the use of small touch buttons should be minimised for better thumb performance.     

Feature extraction of the first difference of EMG time series for EMG pattern recognition

This paper demonstrates the utility of a differencing technique to transform surface EMG signals measured during both static and dynamic contractions such that they become more stationary. The technique was evaluated by three stationarity tests consisting of the variation of two statistical properties, i.e., mean and standard deviation, and the reverse arrangements test. As a result of the proposed technique, the first difference of EMG time series became more stationary compared to the original measured signal. Based on this finding, the performance of time-domain features extracted from raw and transformed EMG was investigated via an EMG classification problem (i.e., eight dynamic motions and four EMG channels) on data from 18 subjects. The results show that the classification accuracies of all features extracted from the transformed signals were higher than features extracted from the original signals for six different classifiers including quadratic discriminant analysis. On average, the proposed differencing technique improved classification accuracies by 2–8%.     

改进AR模型特征提取及分类

目前,表面肌电信号（sEMG）是手势动作识别研究的重要信号源.本文以肌电信号为对象,从非平稳与非线性的角度出发,采用ICA独立成分分析和经验模式分解的方法,消除表面肌电信号中的工频干扰,对处理后的信号建立AR模型.将模型系数作为信号的特征,对6种手势动作进行模式识别.实验表明,该方法获得的特征具有较好的分类效果.     

Application of electromagnetic-assisted stamping (EMAS) technique in incremental sheet metal forming

The application of high velocity electromagnetic-assisted stamping (EMAS) technique in incremental sheet metal forming has been proposed. EMAS whose principle is based on Lorenz force is a hybrid forming process that uses both quasi-static conventional stamping technique and electromagnetic forming actuators built into sharp corners and other difficult-to-form contours to form metals. The recent push to use more artificial intelligent (AI) aluminum alloys in automobile and aircraft industries as a result of increasing demand for fuel efficient cars and aircrafts, large size vehicle panels, improved formability limit of materials and weight reduction have placed EMAS as one of the best high velocity forming technique.It is believed that the end result of this vision will lead to more cost effective land and aerospace vehicles.     

Fault tolerant approach for biosignal-based robot control

This paper proposes a fault tolerant framework for biosignal-based robot control with multiple sensor electrodes. In this approach, to cope with sensor faults, a reliable joint torque estimation model is selected from a group of estimation models based on sensor failure classifiers. The correlation among the electromyography (EMG) signal streams is used as input feature vectors for fault detection. To validate our proposed method, we artificially disconnect an EMG electrode or detach one side of an EMG probe from the skin surface during elbow-joint torque estimation experiments with five participants. When one EMG sensor electrode experiences one of the problems, the experimental results show that the joint torque can be estimated with significantly fewer errors using our proposed approach than a joint torque estimation method without sensor fault detection or than a method with a conventional sensor fault detection algorithm. Furthermore, we controlled a mannequin-arm-attached one-DOF exoskeleton based on the estimated torque profiles by generating movements with the estimated torque derived from the selected model.     

基于肌电信号容错分类的手部动作识别

针对肌电交互系统中因电极断开、损坏及数据传输中断等故障造成的数据错误/丢失问题,提出一种基于高斯混合模型的肌电信号容错分类方法,通过对肌电信号特征样本中错误/丢失数据边缘化或条件均值归错实现非完整数据样本分类.应用所提出的方法识别5种手部动作,实验结果表明,该方法的动作识别精度要高于传统的零归错与均值归错方法.最后,融合容错分类机制开发了肌电假手平台,在线实验验证了提出的方法可以有效提高肌电交互系统的鲁棒性.     

基于小波变换与神经网络的表面肌电信号的情感识别

情感识别是情感计算的一个关键问题。针对表面肌电图(EMG)的非平稳性,采用小波变换方法对表面肌电信号进行分析,提取小波系数最大值和最小值构造特征矢量,分别输入用L-M算法改进的BP神经网络分类器和最近邻法分类器进行情感识别。实验表明,提取EMG的小波系数对joy、anger、sadness、pleasure四种情感进行识别,BP神经网络分类器识别效果优于最近邻法分类器。说明小波变换的方法对EMG进行分析是可行且有效的,并有很大的应用前景。     

盲信号处理技术在双通道前臂肌电信号识别中的应用

根据肌电信号产生机理,本文对双通道前臂肌电信号建立单输入多输出FIR系统模型 ,由于模型输入未知且不可测,采用了盲信号处理方法对模型参数进行辨识．通过提取模型 冲激响应作为信号特征,能够对握拳、展拳、前臂内旋和前臂外旋四类前臂动作进行识别． 实验表明,该方法仅需建立较低阶数的模型即可达到较好的分类目的,性能要优于传统的AR 模型方法．     

基于小波变换的肌电信号识别方法研究

针对肌电信号的非平稳特性,采用小波变换方法对表面肌电信号进行分析,提取小波系数最大值构造特征矢量输入神经网络分类器进行模式识别,经过训练能够成功地从掌长肌和肱桡肌采集的两道表面肌电信号中识别展拳、握拳、前臂内旋、前臂外旋四种运动模式。实验表明,基于小波变换的神经网络分类方法所需的数据短、运算快,对于肌电假肢的控制具有良好的应用前景。     

Physiological and cognitive responses when riding an electrically assisted bicycle versus a classical bicycle

The present study compared the physiological responses and the subsequent cognitive performance when riding an electrically assisted (EB) versus a classical (CB) bicycle. Oxygen uptake, heart rate and leg extensor muscles electromyographic (EMG) activity were recorded in 10 subjects during a 30-min intermittent cycling exercise performed with EB versus CB. Cognitive performance was evaluated by a mail sorting test, performed at rest and after each cycling session. Averaged oxygen uptake and heat rate were significantly (P < 0.05) lower during EB cycling than during CB cycling. The EMG activities of the vastus lateralis, rectus femoris and gastrocnemius medialis muscles were significantly (P < 0.001) greater during CB cycling than during EB cycling. The time to complete the mail sorting test was significantly (P < 0.05) shorter after EB cycling than after CB cycling. Because EB cycling reduced muscle strains and physiological stress, it might offer benefits for those using bicycles in their work, such as postal workers and police officers. STATEMENT OF RELEVANCE: This study compared physiological and cognitive responses when riding an electrically assisted versus a classical bicycle. The results showed that the electrically assisted bicycle led to reduced muscle strains and physiological stress and, therefore, might offer benefits for those using bicycles in their work, such as postal workers and police officers.