Classification Of Motor Imagery And BCI Experiment System Based On VC++

The EEG-based brain-computer interface(BCI) is a novel technology, which provides a wholly new communication and control channel for sending messages and instructions from brain to external computers or other electronic devices, instead of the normal output pathways of peripheral nerves and muscles. Quick and correct classification of these event-related EEG pattern can be used to help patients with severe paralysis to move a cursor or to replace impaired motor function and provide a new communication channel to environment.Brain-computer interface technology is an interdisciplinary technology integrating neurology, signal collection, signal processing, pattern recognition and more other relevant techniques. A typical BCI system consists of several parts, such as signal acquisition, feature extraction, classification algorithm, command output and so on. Feature extraction and classification algorithm are most-important. Left and right hand movement imagery can modify neural activity in the primary sensor motor areas in a very similar way as observable with a real executed movement, leading to special changes of EEG components such as event-related desynchronization/synchronization(ERD/ERS).In this paper, the classification of mental activities based on the energy of mu rhythm was proposed. The EEG signals were recorded during imagination of left or right hand movement. The energy of mu rhythm(2th order moment) and its dynamic properties with respect to time were analyzed. Since the computation of 2th order moment is very simple and can also be estimated in on-line way, the new method has the practicability in the application of brain-computer interface technique.In this paper, we focus on the discrimination of left-hand and right-hand motor imagery event-related EEG pattern. It is two-class classification task. We introduce Perceptron algorithm, LDA algorithm, Mahalanobis distance-based discriminant algorithm in pattern recognition. We will extract the energy of mu rhythm of two channels(C3, C4) as feature vector, and classify the event-related EEG pattern during left and right hand motor imagery with the those algorithm. According to the analysis and experiment results, the correct rate of classification can achieve 87.86%.Microsoft provide customer with Visual C++ as a strong system development tool. Visual C++ is well known as its opening interface, object-oriented programming design and Active X controls. It is most developer's favorite. We apply VC++ on brain-computer interface study to establish BCI experiment system. In this system, we can realize the analysis and classification of original EEG signal, just like dynamic view, basic rhythm extraction, frequency analysis, power analysis, correlation analysis, energy on-line analysis and so on. According to ERD/ERS, we use the result of classification to control the movement of cursor of device.