Pattern Recognition of EMG Signals by Machine Learning for the Control of a Manipulator Robot

Electromyographic signals analysis to assess the response of a proprioceptive neuromuscular facilitation pattern execution

Proprioceptive Neuromuscular Facilitation is a rehabilitation technique that consists of the stimulation of a healthy muscle in one extremity of the body to produce an activation effect of a damaged muscle in another extremity, laterally or contralaterally. The use of the analysis of the electromyographic response during the process allows us to describe and evaluate if the damaged muscle produces an activation. This paper presents the progress of the results of a clinical protocol where PNF is explored in healthy subjects, manipulating the upper limb, and recording the electromyographic response of the lower limbs in three different muscles in both inferior limbs. Four activation patterns (movement sequence) with three different stages with different intensities of resistance are considered. Lateral plane video recording analysis is performed to extract the trajectory of the manipulated limb and correlate this information with electromyography signals. The electromyography signals are analyzed in their temporal response by integrating the rectified and smoothed signal according to the beginning and end of the trajectory of the manipulated superior limb. Additionally, the spectrogram analysis of the signals is performed. The partial results of the protocol allow us to establish that the response in the most distal muscles to the manipulated upper limb has been non-significant for the subjects, compared to the response of the proximal muscles, where a relationship with activation and trajectory of the arm is observed. particularly in the process with greater resistance. The observed changes in signal frequency across the spectrogram correspond to low-frequency changes in the 15 to 20Hz band.Clinical Relevance- This work presents a strategy to assess the rehabilitation process based on proprioceptive neuromuscular facilitation by analyzing the time and time-frequency response of the electromyographic signal.

A Review of EMG-, FMG-, and EIT-Based Biosensors and Relevant Human–Machine Interactivities and Biomedical Applications

Wearables developed for human body signal detection receive increasing attention in the current decade. Compared to implantable sensors, wearables are more focused on body motion detection, which can support human–machine interaction (HMI) and biomedical applications. In wearables, electromyography (EMG)-, force myography (FMG)-, and electrical impedance tomography (EIT)-based body information monitoring technologies are broadly presented. In the literature, all of them have been adopted for many similar application scenarios, which easily confuses researchers when they start to explore the area. Hence, in this article, we review the three technologies in detail, from basics including working principles, device architectures, interpretation algorithms, application examples, merits and drawbacks, to state-of-the-art works, challenges remaining to be solved and the outlook of the field. We believe the content in this paper could help readers create a whole image of designing and applying the three technologies in relevant scenarios.

Intelligent Sensors for Human Motion Analysis

Currently, the analysis of human motion is one of the most interesting and active research topics in computer science, especially in computer vision [...].