P300 signal detection method based on LSTM network

Abstract

The invention discloses a P300 signal detection method based on an LSTM network. The method comprises the following steps: step one, an experiment is carried out by using a P300 character speller andEEG signals are extracted to form a training set and a testing set; step two, preprocessing is carried out on the collected data and the processed data are used as an input data set of a model; step three, an LSTM layer is designed as a spatio-temporal filter of the EEG data set, an all-connection layer is added after a least time step of the LSTM layer, a Softmax layer is added to convert a network output value into a probability form, and then the network is trained and a model parameter is determined, wherein the Softmax layer is a generalized form of the logic function; and step four, a model evaluation index and a testing set character recognition rate are calculate to verify the performance of the model. The method has the following characteristics: no manual feature extraction is needed; the recognition performance is good; the generalization ability is high; and the good information conversion rate is realized. The P300 signal detection method is a good P300 classification algorithm.

Description

technical field [0001] The invention relates to the technical field of EEG signal detection, in particular to a P300 signal detection method based on an LSTM network. Background technique [0002] Brain-computer interface (BCI for short) is a direct connection path created between the human brain or animal brain and external devices. The word "brain" refers to the brain or nervous system of an organic life form, not just the abstract "mind". "Machine" means any processing or computing device, which may take the form of a simple circuit to a silicon chip. Research on brain-computer interfaces has been going on for more than 30 years. Since the mid-1990s there has been a remarkable increase in such knowledge gained from experiments. At present, as a new type of human-computer interaction, brain-computer interface is gradually becoming a hot topic in brain science research, and has great application prospects in rehabilitation engineering, high-risk operations, and psycholog...

AI Technical Summary

Problems solved by technology

However, the accuracy and information conversion rate of convolutional neural network (CNN) to identify P300 need to be further improved, while the structure of circular convolutional neural network (RCNN) is slightly complicated, and there are too many parameters, and the learning speed is slow.

Images