Pattern Recognition of Composite Motions based on EMG Signal via Machine Learning

Abstract

In the past few years, physical therapy plays a crucial role during rehabilitation. Numerous efforts are made to demonstrate the effectiveness of medical/ clinical and human-machine interface (HMI) applications. One of the most common control methods is using electromyography (EMG) signals generated by muscle contractions to implement the prosthetic human body parts. This paper presents an EMG signal classification system based on the EMG signal. The data is collected from biceps and triceps muscles for six different motions, i.e., bowing, clapping, handshaking, hugging, jumping, and running using a Myo armband with eight electromyography sensors. The Root Mean Square, Difference Absolute Standard Deviation Value, and Principle Component Analysis are used to extract the raw signal data and enhance classification accuracy. The machine learning method is applied, i.e., Support Vector Machine and K-Nearest Neighbors are used for classification; the results show that the K-Nearest Neighbors method achieves a higher accuracy percentage than the SVM. Making high training accuracy for different physical actions helps implement human prosthetic parts to help the people who suffer from an amputee.

Fault Detection and Fault Tolerant Control for Anti-lock Braking Systems )ABS) Speed Sensors by Using Neural Networks

“…The algorithms of NN are typically much faster than those of conventional iterative CF techniques. Additionally, the solution does not require an initial guess, and there is an ability to implement the designed network model with special-purpose hardware and, in this way, take advantage of the full ability of NN, including high processing speed [17][18][19][20].…”

“…This suggested approach is implemented using the principle of fast processing Curve Fitting (CF) executed by Neural Networks (NNs). NNs have been employed in various fields due to, in part, a new powerful algorithm development that affects their ability to process information rapidly and leads to faster response [17][18][19][20]. NNs provide a perfect tool with high accuracy and fast response solution for nonlinear CF problems [15].…”

Textual Dataset Classification Using Supervised Machine Learning Techniques

“…Then, the training phase of KNN saves the training set feature vectors with their related class labels. In the testing phase, the algorithm determines the K value, which can be estimated by trial and error and find out the optimal K value like 2,3 or 5, or it can be identified based on the dataset by using the following equation [14,15,16]:…”