No abstract

No abstract

Abstract-An approach to recognize the familiarity of a listener with music using both the electroencephalogram (EEG) signals and the music signal is proposed in this paper. Eight participants listened to melodies produced by piano sounds as simple natural stimuli. We classified the familiarity of each participant using cross-correlation values between EEG and the envelope of the music signal as features of the support vector machine (SVM) or neural network used. Here, we report that the maximum classification accuracy was 100% obtained by the SVM. These results suggest that the familiarity of music can be classified by cross-correlation values. The proposed approach can be used to recognize high-level brain states such as familiarity, preference, and emotion.

No abstract

The present paper proposes a novel kernel adaptive filtering algorithm, where each Gaussian kernel is parameterized by a center vector and a symmetric positive definite (SPD) precision matrix, which is regarded as a generalization of scalar width parameter. In fact, different from conventional kernel adaptive systems, the proposed filter is structured as a superposition of non-isotropic Gaussian kernels, whose non-isotropy makes the filter more flexible. The adaptation algorithm will search for optimal parameters in a wider parameter space. This generalization brings the need of special treatment of parameters that have a geometric structure. In fact, the main contribution of this paper is to establish update rules for precision matrices on the Lie group of SPD matrices in order to ensure their symmetry and positive-definiteness. The parameters of this filter are adapted on the basis of a leastsquares criterion to minimize the filtering error, together with an ℓ 1-type regularization criterion to avoid overfitting and to prevent the increase of dimensionality of the dictionary. Experimental results confirm the validity of the proposed method.