SYSTEM FOR CLASSIFICATING MENTAL WORKLOAD USING EEG AND METHOD THEREOF

摘要

The present technology discloses a brain cognitive load classification system and method. According to a specific example of the present technology, each multi-level feature of each layer is derived through a predetermined number of convolutions on input data of a three-dimensional image including spectrum and spatial information of an input EEG signal, and the derived multi-level Based on the parameters optimized through features and learning, each weight of each multi-level feature is derived, the logit of each multi-level feature is derived by the product of the derived weight and the multi-level feature, and the logit of each derived multi-level feature The classification loss function is applied to calculate the angular loss of each multi-level feature, and each multi-level feature with the calculated angular loss is completely combined to classify the brain cognitive load for the input EEG signal into one of a number of classifiers. Accordingly, it is possible to improve the classification accuracy of the cognitive load of the brain, and by determining the optimized weight by learning the weight based on the EEG signal, it is possible to increase the learning speed, thereby improving the performance of the system.