لخّصلي

Conclusion The ANN architecture has been successfully developed for the identification of EMG signals.The reported classification accuracy is good.This research shows an EMG signal analysis technique for applying the correct method during any biomedical research, clinical diagnosis, applications of end-users and hardware usage.In order to classify the EMG signals, classification methods such as Support Vector Machine, K-NN, fine-tree was also used.Neural Network is a useful tool for classifying EMG signals in two different groups, such as healthy, patient signals.These EMG signals produced by muscles in the human body are mostly used for medical field diagnostics.The accuracy could be slightly increased by applying convolutional neural network.

Conclusion
The ANN architecture has been successfully developed for the identification of EMG signals.The
reported classification accuracy is good.This research shows an EMG signal analysis technique for applying the correct method
during any biomedical research, clinical diagnosis, applications of end-users and hardware usage.In order to classify the EMG signals, classification methods such as Support Vector Machine, K-NN,
fine-tree was also used.Neural
Network is a useful tool for classifying EMG signals in two different groups, such as healthy, patient
signals.These EMG signals produced by muscles in the human body are mostly used for medical field
diagnostics.The
accuracy could be slightly increased by applying convolutional neural network.