Surface electromyography pattern recognition methods have been widely applied to decode limb movement intentions for prosthesis control. These methods generally require amputees to provide sufficient myoelectric signals from their residual limb muscles. Previous studies have shown that amputees with high level amputation or neuromuscular disorder usually do not have sufficient residual limb muscles to provide enough myoelectric signals for accurate identification of limb movements. Electroencephalography (EEG), another bioelectric signal associated with limb movements has also been proposed and used for decoding the limb motion intents of humans. With an attempt to improve the performance of EEG-based method in identifying multiple classes of upper limb movement intents, four spectral domain features of EEG were proposed in this study. Motor imagery patterns associated with five different classes of imagined upper limb movements were distinctively decoded based on the four features extracted from 64-channel EEG recordings in four transhumeral amputees. Experimental results show that an average accuracy of 97.81% was achieved across all the subjects and limb movement classes. By applying a sequential channel selection method, an accuracy of around 95.00% was realized with about 20-channels of EEG. Thus, the proposed method might be potential for providing accurate control input for neuroprosthesis.

Motor imagery classification of upper limb movements based on spectral domain features of EEG patterns

EEG Motor Imagery Classification of Hand Movements for a Brain Machine Interface( Biosensors: Data Acquisition, Processing and Control)

This paper proposes to relate a Linear Discriminant Analysis Classification based system with Quality Similarity Clustering process and a Brain Mapping Technique in order to clarify the brain activity differences that could sustain the better classification rates between each of the Motor Imagery (MI - flex right arm, flex left arm, close right hand, close left hand). To achieve this goal the Eletroencephalogram (EEG) entropy was used as principal feature and a Principal Component Analyses (PCA) was also used. EEG signal, from each of the 8-channel transversal set up, was acquired from electrodes Fz, Cz, Pz and Oz to electrodes F3, F4, C3, C4, P3, P4, O1, and O2. Results showed that for each MI there is an specific topographic distribution of the cortex activation. A common point was the minor activation of the motor area. The principal areas were the frontal and the parietal ones. The clustering analysis showed, considering 20% of similarity, that the points which possibly contribute to motor imagery recognition came from those areas. Furthermore, the best results in the classification process were reached to distinguish between left arm and left hand with 89.74% and between arms and hands with 80.77%. Both of these scenes were possible using only the information provided by the frontal electrodes, and this agree with brain mapping. The activation of frontal and parietal lobes reflects the network involved in sensory-motor integration (posterior parietal), decision-making (prefrontal) and preparation of motor response (premotor). Our finding that the frontal electrodes were the most representative may be related to the fact that the premotor cortex is responsible for motor planning and thus, should be the most active area in distinguishing between different motor movements.

Motor imagery recognition and its cerebral mapping

Individuals with high-level amputation or neuromuscular disorder basically lack sufficient residual arm muscles from which adequate myoelectric signals could be obtained for accurate decoding of their limb movement intents for prosthesis control. In this regard, electroencephalogram (EEG) signal associated with their limb movements could be used to provide alternative control input to multiple degrees of freedom prosthesis for such individuals. The feature extraction method and analysis window parameters (window size and window increment) used to characterize the EEG signal patterns plays an important role in determining the accuracy and stability of the entire prosthetics. Therefore, we studied the effect of different analysis windowing parameters on classification accuracy and stability of frequency-domain features using 64-channel EEG recordings obtained from three amputees. Experimental results shows that the motor imagery patterns associated with the five classes of upper limb movement were decoded with an average accuracy of 99.79% when a window length of 100ms and increment of 25ms was utilized. Regardless of the window increment used, the classification accuracy of the decoded limb movements increased steadily with a decrease in the window length, indicating an inverse relationship between accuracy and window length. Thus, the outcome of this study may provide valuable information for the development of accurate and robust control mechanism for multifunctional neuroprosthesis.

Determining the Optimal Window Parameters for Accurate and Reliable Decoding of Multiple Classes of Upper Limb Motor Imagery Tasks

A lot of effort has been made to investigate EEG features that could better represent signal characteristics. The results are usually based on the best mean recognition rates and statistical analysis is done only when different methods are compared. In this work, we propose a new approach that applies multiple rate intercomparisons based on large samples aiming at detecting differences among treatments in order to recognize their importance for the classification rates. Ten frequency band compositions expressed by power spectral density averages were extracted from 8 EEG channels during 4 motor imageries, and spatial feature selections were also considered during the recognition process. Classification rate in large samples can be represented by a normal distribution and, for multiple rate inter-comparisons, the level of significance was corrected based on the Bonferroni Method. The variables were considered to be independents and the test was performed as non paired samples in a very conservative approach. The results showed that there are significant differences among cases of spatial feature selection and thus the considered electrodes are important parameters. On the other hand, considering or not the Delta and Theta bands along with different arrangements for Gamma band resulted in no significant difference.

A Different Statistical Approach Aiming at EEG Parameter Investigation for Brain Machine Interface Use

C EEG channel data are usually used when building systems that aim at distinguishing among right and left hand movements. Few alternatives use multichannel systems when bigger sets of motor imagery are subject to classification and more inputs are required. In this context, this work proposes the use of 8 EEG channels (F,C,P, and O), disposed in a non-conventional set up, to classify up to 4 motor imagery of the upper limbs through a Linear Discriminant Analysis classifier. A spatial feature selection, prior to classification, is applied in order to improve the classification accuracy. For the many channel combinations tested, results suggest that, in addition to the motor areas, other brain areas should be considered. For the proposed system, the best classification accuracy was achieved when distinguishing between left arm and left hand (89.74%) and using only the electrodes in F areas. For the right versus left hand a 71.80% rate was obtained, with electrodes either in P and O areas or in F and P areas. To discriminate between arms and hands, independently of the body side, the best score was 83.33%, for F and P channels, whereas for right and left limbs the best score was 66.02%, with only P channels. The best classification accuracy for the 4 movement problem achieved 50.00%, using

João Pedro de O. P. Galhianne

Papers

EEG Motor Imagery Classification of Upper Limb Movements