Abstract: Systems and methods for detecting oscillations in neural signals are disclosed that provide for high precision and specificity in detecting neural oscillations in time and frequency domains. The disclosed systems and methods identify oscillations according to criteria including 1/f noise, number of cycles, and auto-correlation. The disclosed method detects periodic signals and filters out spurious oscillations associated with harmonic frequencies.

Abstract: The present disclosure discloses an apparatus for a brain computer interface (BCI) including a feature extraction filter trainer for training a feature extraction filter which minimizes an influence of a background brain wave while maximizing a difference between intended brain waves; and a classifier trainer for training a classifier for classifying the intended brain waves by using a feature vector obtained by filtering the intended brain wave at the feature extraction filter. With the apparatus, only the background brain wave is additionally measured, such that previous intended brain wave data can be reused and the brain wave can be classified more quickly and accurately.

Abstract: The present disclosure discloses an apparatus for a brain computer interface (BCI) including a feature extraction filter trainer for training a feature extraction filter which minimizes an influence of a background brain wave while maximizing a difference between intended brain waves; and a classifier trainer for training a classifier for classifying the intended brain waves by using a feature vector obtained by filtering the intended brain wave at the feature extraction filter. With the apparatus, only the background brain wave is additionally measured, such that previous intended brain wave data can be reused and the brain wave can be classified more quickly and accurately.