Read Aloud the Text Content

This audio was created by Woord's Text to Speech service by content creators from all around the world.

Text Content or SSML code:

The main contributions of the present study can be summarized as follows: 1.We propose to utilize the local spatio-temporal features and the global temporal features extracted by a 3D convolutional neural network (3D-CNN) and a recurrent neural network (RNN) respectively to enhance the EEG-based brain activity analysis. 2.We develop an ensemble system employing the fuzzy integral to combine both 3D-CNN and RNN classifiers. 3.The deep reinforcement learning technique is applied to optimize the fuzzy measures of each integrated classifier in the fuzzy integral, rather than heuristically assigning the fuzzy measures. We evaluate the proposed approach on a public EEG-based movement intention dataset in the context of cross-subject and multiclass scenario analysis. 4. According to the results, the proposed ensemble model can automatically find the optimal fuzzy measures for classifiers and enhances the EEG-based recognition of human intentions.#