Abstract
One way to recognize hand gestures is to use signal electromyography (EMG). The processed signal can use the time domain, frequency domain, or a mixture of the two domains. Meanwhile, the classification method that is widely used recently is the classification of Artificial Neural Networks (ANN). This paper presents a comparison study between time domains with frequency domain for EMG signals using ANN classification. This comparison aims to find out a better method for controlling the hand robot. The time domain features are root mean square (RMS) of the signal, while the signal’s octave band becomes a feature of the frequency domain. The EMG signals were obtained from the subject with eight fingers gestures. The results of this classification are used to control the robot’s hand. The success of each method in recognizing hand movements was counted. In addition, the response speed of the robot in changing positions is measured. The results showed that features using the frequency domain had a higher percentage of success than another domain. But the speed and memory used then the system using signals in the time domain is better.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
