Feature extraction is meant to get representation and information that embedded in the signals, this is necessary to minimize complexity of implementation and reduce the cost of information processing. Recently, there are many methods for features extraction. This research is comparing five feature extractions from eight channels electromyography (EMG) signals that obtained from Myo Armband located on forearm muscles in order to get significant differences when hand do some movements. The time series features extraction that evaluated are Mean Absolute Value (MAV), Variance (VAR), Willison Amplitude (WAMP), Waveform Length (WL), and Zero Crossing (ZC). The variety of hand movement are fist, rest, half-fist, gun-point, and mid-finger fold. Moreover, the result shows that the rank of evaluated features extraction always showhs same results in four experiment, MAV is always giving the best performance WL. From this finding, MAV and WL are two recommendation for time series features extraction. This rank of time series features extraction gives worthiness when process information in future development research.

This paper proposes the control system for 3-D locomotion of a humanoid biped robot based on a biological approach. The muscular system in the human body and the neural oscillator for generating locomotion signals are adapted in this paper. We extend the neuro-locomotion system for modeling a multiple neuron system, where motoric neurons represent the muscular system and sensoric neurons represent the sensor system inside the human body. The output signals from coupled neurons representing the angle joint level are controlled by gain neurons that represent the energy burst for driving the joint in each motor. The direction and the length of step in robot locomotion can be adjusted by command neurons. In order to form the locomotion pattern, we apply multiobjective evolutionary computation to solve the multiobjective problem when optimizing synapse weights between the motoric neurons. We use recurrent neural network (RNN) for the stabilization system required for supporting locomotion. RNN generates a dynamic weight synapse value between the sensoric neuron and the motoric neuron. The effectiveness of our system is demonstrated in open dynamic engine computer simulation and in a real robot application that has 12 degrees of freedom (DoFs) in legs and four DoFs in hands.

Application of Artificial Neural Networks in Modeling Direction Wheelchairs Using Neurosky Mindset Mobile (EEG) Device

This paper proposes a research about the humanoid robot system stability to the basic movements in playing football (walking, running, and kicking a ball). The system controls the stability of the robot body angle in order to remain in an ideal position, using the hand as a function of the feedback that has been controlled the actuator separately with leg function on the robot. The hand has a function as robot body tilt actuator controller and the foot has a function as gait motion control system that controls the robot to walk. This system has deficiency to disorders the high impulse, resulting in added angular velocity control system functions, which can reduce the foot force moment generated when stopping suddenly and unexpectedly ran. System control used PID control while in motion pattern and kinematic control system using Fuzzy algorithm. We applied the combination between the control and speed control angle pose at EROS (EEPIS Robosoccer).

This paper discusses about adaptive trajectory control applied in motion pattern trajectory of humanoid robot movement. The aim of this research is to increase the stabilization of robot during walking and running. In this research, the control system produced the next step of the trajectory based on the current condition and analyzed the center of gravity point from the body of the robot. According to this, robot posed the foot step depend on the location of center of gravity point and stop the swing of its foot when the foot has reached the ground. In order to reduce the vibration effect arised by the swing of robot steps, this system is supported by vibration control. Robot is also supported by hand reaction learning system based on recurrent neural network. The trajectory pattern of robot movement has 2 trajectory equations: ankle trajectory formed by circle function in Cartesian coordinate space and pelvis trajectory formed by the third order polynomial equation. Both of them are influenced by inclination of the body of robot. We used the inverted pendulum approach combined with dynamic step trajectory. By using this system, robot can walk in the different surface and uneven surface. This system is applied on humanoid robot EROS (EEPIS Robot Soccer).