Abstract-For patients with Type 1 Diabetes Mellitus, hypoglycemia is a very common but dangerous complication which can lead to unconsciousness, coma and even death. The variety of hypoglycemia symptoms is originated from the inadequate supply of glucose to the brain. In this study, we explored the connection between hypoglycemia episodes and the electrical activity of neurons within the brain or EEG signals. By analyzing EEG signals from a clinical study of five children with T1DM, associated with hypoglycemia at night, we found that under hypoglycemia conditions, some EEG parameters changed significantly. Based on these results, we proposed a method of detecting hypoglycemic episodes using EEG signals, including a feed-forward multi-layer neural network algorithm for classifying. The classification results are 72% sensitivity and 55% specificity when using the signals from 2 electrodes C3 and O2. We also used signals from different channels to see the contribution of each to performance of classifying. The results of the study show the potentiality of our method and will be improved and developed in the near future.