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.

In the past few years, physical therapy plays a very important role during rehabilitation. Numerous efforts have been made to demonstrate the effectiveness of medical/clinical and human-machine interface (HMI) applications. The prevalent control methods are using electromyography (EMG) signals generated by muscle contractions to implement the prosthetic human body parts. This paper aims to provide and summarize ideas about recent researches in the field of Pattern Recognition (PR) based on EMG signals to save time and efforts for the readers working in this field. The first step starts by demonstrating a general overview of the various techniques to collect the database by taking into consideration the factors that affect the accuracy of the collected data. Hence, different types of filters are presented to process the signals and reduce the noise of the raw EMG signals. This research clarifies the features extraction methods using time-domain (TD), frequency domain (FD), and time-frequency domain (TFD) and which of these methods will be suitable to use for EMG signals. Finally, a group of studies is reviewed based on three classification methods i.e. artificial neural network (ANN), machine learning (ML), and deep learning (DL). Depending on these methods, the accuracy range can be specified for each classifier, also the factors which affect the accuracy percentage. Therefore, the researchers can avoid these issues that reduce accuracy.

The recent revolution in the biomedical field carried out the researchers to work on the prosthetic technique because it reflects the amputee's need. Therefore, the electromyography (EMG) signals generated by muscle contractions are used to implement the prosthetic human body parts. This paper presents a pattern recognition system based on two EMG data; the first EMG data represents the general body movements collected from biceps and triceps muscles for six different motions, i.e., bowing, clapping, handshaking, hugging, jumping, and running. The Root Mean Square, Difference Absolute Standard Deviation Value, and Principal Component Analysis extract the raw signal data features and enhance classification accuracy. The machine learning method is applied, i.e., Support Vector Machine (SVM) and K-Nearest Neighbours (KNN) are used for data classification; the results show high accuracy reached 94.8% and 98.9%, respectively. Whereas, the second EMG data is selected to be more specific in hand movements, i.e., cylindrical, spherical, palmar, lateral, hook, and tip motions, because these significant motions are the first step implementing any prosthetic hand. Consequently, the mean, Standard Deviation Value, and Principal Component Analysis extract the raw signal feature. Meanwhile, the same algorithm used in the first data classification is also used to classify the second data because it shows high accuracy and good performance. SVM algorithm is used to classify the data and achieved high training accuracy, reaching 89%. The high training accuracy for different hand movements is considered an essential step toward implementing human prosthetic parts to help the people who suffer from an amputee.

The revolution in prosthetic hands allows the evolution of a new generation of prostheses that increase artificial intelligence to control an adept hand. A suitable gripping and grasping action for different shapes of the objects is currently a challenging task of prosthetic hand design. The most artificial hands are based on electromyography signals. A novel approach has been proposed in this work using deep learning classification method for assorting items into seven gripping patterns based on EMG and image recognition. Hence, this approach conducting two scenarios; The first scenario is recording the EMG signals for five healthy participants for the basic hand movement (cylindrical, tip, spherical, lateral, palmar, and hook). Then three time-domain (standard deviation, mean absolute value, and the principal component analysis) are used to extract the EMG signal features. After that, the SVM is used to find the proper classes and achieve an accuracy that reaches 89%. The second scenario is collecting the 723 RGB images for 24 items and sorting them into seven classes, i.e., cylindrical, tip, spherical, lateral, palmar, hook, and full hand. The GoogLeNet algorithm is used for training based on 144 layers; these layers include the convolutional layers, ReLU activation layers, max-pooling layers, drop-out layers, and a softmax layer. The GoogLeNet achieves high training accuracy reaches 99%. Finally, the system is tested, and the experiments showed that the proposed visual hand based on the myoelectric control method (Vision-EMG) could significantly give recognition accuracy reaches 95%.