Abstract
This paper presents a new embedded architecture for home devices control system directed through motor imagery actions captured by EEG headset. The proposed system is validated by an offline approach which consists on using available public data-set. These recording are always accompanied with noise and useless information related to the equipment, eyes blinking and many others resources of artifacts. For this reason, a complex EEG signal processing is required; starting by filtering EEG to keep the frequency of interest which is located on mu-rhytm and beta-rhytm bands in our case; followed by the extraction of useful feature to minimize the size of EEG data and enhance the probability of classifying each trial correctly. A prototype of our proposed embedded system has been implemented on Stratix IV FPGA Board. The prototype operates at 200 MHz and performs real-time classification with an execution delay of 0.5 second per trial and an accuracy average of 72%.