Comparison Experiment of Artificial Intelligence Models Based on EEG Wave Continuity

In this study, we conducted comparative experiments on continuous data for BCI research using various comparison models depending on the data composition. The goal was to compare the classification performance of artificial intelligence models on data that considered continuity, a characteristic of time series data, and data that did not. To summarize the research results in BCI research using EEG signals, action and thought classification achieved a high-performance score of 0.8728 in LSTM as data continuity decreased. Additionally, DNN showed maximum performance with a score of 0.9178 when continuity was not considered. Moreover, it was observed that the data without considering continuity performed well in task classification. Therefore, BCI research focusing on behavior and accident classification based on EEG signals is expected to achieve excellent performance by showing various data characteristics through shuffling rather than considering data continuity.