Japanese Janken Recognition by Support VectorMachine Based on Electromyogram - 2016 PROJECT TITLE: Japanese Janken Recognition by Support VectorMachine Based on Electromyogram - 2016 ABSTRACT: Recent years, biosignal is receiving attention as a tool of human interface. Above all, electromyogram (EMG) has already applied to many researches. In this study, we have a tendency to propose a method which will discriminate hand motions. We tend to measured an electromyogram of wrist by using eight dry kind sensors. We have a tendency to focused on four motions, like "Rock-Scissors-Paper" and "Neutral". "Neutral" may be a state that doesn't do anything. Within the proposed methodology, we have a tendency to apply quick Fourier transformation (FFT) to measured EMG knowledge, and then remove hum noise. Next, we have a tendency to combine values of sensors based mostly on a Gaussian perform. In this Gaussian function, variance and mean are zero.a pair of and 0, respectively. After that, we have a tendency to apply normalization by linear transformation to the values. Subsequently, we have a tendency to resize the values into range from -one to one. Finally, support vector machine (SVM) conducts learning and discrimination. We tend to conducted experiments in three subjects. Discrimination accuracy of the proposed methodology for 3 subjects was ninety six.nine%, ninety five.threep.c, ninety two.twopercent, respectively. Therefore, we have a tendency to think that the Gaussian perform is sturdy to distinction of sensor position as a result of this function combines each adjacent channels. In the previous technique, the discrimination accuracy rate was 77.onep.c. Therefore, the proposed method is best in accuracy than the previous method. In future work, we tend to will conduct an experiment that discriminates Japanese Janken of a topic who isn't learned. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest New Sparse-Promoting Prior for the Estimation of aRadar Scene with Weak and Strong Targets - 2016 Investigating Ultraharmonic Modeling from Ultrasound Echo Signal with SISO Volterra Filter - 2016