基于表面肌电信号的肘关节运动角度的提取

随着人口老龄化问题的越来越严重,医疗护理机器人的开发,今后将会有大量的需求,基于表面肌电信号的医疗护理机器人的开发将是其中的一个热点.本文提出了基于Bayesian正则化的多层感知器人工神经网络方法来提取人体肘关节运动角度,解决了普通神经网络对于表面肌电信号这一复杂亚高斯随机信号泛化能力不强的缺点,有助于将表面肌电信号的研究推向医疗护理机器人研发的实际应用阶段.

The Degree Extraction of Elbow Joint Based on EMG Signals

With the ageing population of our society, the desire of the medical robot will be more and more. The development of the medical robot based on the electromyogram (EMG) will be a pop direction. We use the MLPs based on the Bayesian Regulation to abstract the degree of the elbow joint of the subject, and reduce the disadvantage of the normal MLPs which is without the enough ability of extension towards this complicated Sub-Gaussian random signals. Our research will be helpful to develop the EMG signals into the actual application of the medical robot.