EOG signal Modeling using Double Exponential Smoothing for Robot Arm Control System

This paper present a novel way of modeling EOG signal to use in a robot arm control system, two procedures implemented, offline procedure to measure and modeling EOG for building a pattern reference model ,and online procedure used to Control the robot arm. By comparing online measured EOG and the EOG pattern in reference model suitable manipulation instruction generated by the micro controller. The double exponential smoothing method used for building the pattern reference model, the accuracy of the reference model tested with main squire error (MSE) and main absolute error (MAPE) measures. Auto correlation analysis applied to study the existing pattern and linearity of EOG signal with eye movements. EOG signal measurement for this research classified in to five kinds: EOG horizontal (left and right) Vertical (up and down), and blinking. The EOG signal models of this research saved and used as a reference model file to classify the eye movements. a measurement and robot arm control system constructed by using arduino olimix 328, olimix sensor shield, and robot arm driving circuit, arduino C used as a programming environment, Minitab software used to build the model and correlation analysis ,Brain Bay software used to control and signal processing.

Abstract licence: CC BY-NC-ND

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.