Band Correlation Histogram to Improve Classification of Acute Encephalopathy in Infants


EEG-AESD-CH.jpg
[Abstract]
In this study, we propose a method to determine whether the early onset of acute encephalopathy causes severe sequela by using electroencephalogram (EEG) waves. Even though sequela can severely damage the brains of infants, no prevalent method can automatically diagnose acute encephalopathy in infants. We address this problem by designing a discriminative feature that delivers impressive classification performance. Based on knowledge of the diagnosis, our method randomly selects pairs of waves over a short period and computes a correlation histogram from a distribution of their correlation coefficients. The results of experiments showed that the correlation histogram is significantly superior to a prevalent method in terms of the classification of a dataset of patients with acute encephalopathy.
[Publication]
[Publication (Japanese) ]



otama1.png