Anomalies Classification System and Method Based on Deep Neural Network Algorithm

摘要

A deep neural network algorithm-based problem behavior classification method according to an embodiment of the present invention comprises the steps of: measuring and classifying the feedback behavior of a test subject with respect to conditional stimulus information predefined in a database in a limited environment; presenting the conditional stimulus to the subject in a stimulus delivery unit; acquiring data on the feedback behavioral response of the test subject to the conditional stimulus from the stimulus measuring unit; and classifying the problem behavior among the feedback behavioral responses by using a deep neural network algorithm for the human body data for the feedback behavioral response.