Decoding the Long Term Memory (LTM) using weighted thresholding unio‎n subspaces based classification on Magnetoencephalogram (MEG)

In this paper Long Term Memory (LTM) process during leftward and rightward orientation recalling have been analyzed using Magnetoencephalogram (MEG) signals. This paper presents a novel criterion for decision making using unio‎n subspace based classifier. The proposed method involves the Eigenvalues from Singular Value Decomposition (SVD) of each subspace not only to select basis for each subspace but also to weight the decision making criterion to discriminate two classes. The proposed method has provided orientation detection from recalling signal with 6.75 percent increase in classification accuracy compared to better results on this data.