Sparse Representation-Based Classification (SRC): A Novel Method to Improve the Performance of Convolutional Neural Networks in Detecting P300 Signals

Introduction: brain-computer interface (bci) offers a non-muscle way between the human brain and the outside world to make a better life for disabled people. in bci applications p300 signal has an effective role; therefore, distinguishing p300 and non-p300 components in eeg signal (i.e. p300 detection) becomes a vital problem in bci applications. recently, convolutional neural networks (cnns) have had a significant application in detection of p300 signals in the field of bcis. the p300 signal has low signal to noise ratio (snr). on the other hand, the cnn detection rate is so sensitive to snr; therefore, cnn detection rate drops dramatically when it is faces with p300 data. in this study, a novel structure is proposed to improve the performance of cnn in p300 signal detection by means of improving its performance against low snr signals. methods: in the proposed structure, sparse representation-based classification (src) was used as the first substructure. this block is responsible for prediction of the expected p300 signal among artifacts and noise. the second substructure performed p300 classification with adadelta algorithm. thanks to such snr improvement scheme; the proposed structure is able to increase the rate of accuracy in the field of p300 signal detection. results: to evaluate the performance of the proposed structure, we applied it on epfl dataset for p300 detection, and then the achieved results were compared with those obtained from the basic cnn structure. the comparisons revealed the superiority of the proposed structure against its alternative, so that its true positive rate (tpr) was promoted about 19.66%. such improvements for false detections and accuracy parameters were 1.93% and 10.46%, respectively, which show the effectiveness of applying the proposed structure in detecting p300 signals. conclusion: the better accuracy of the proposed algorithm compared to basic cnn, in parallel with its more robustness, showed that the sparse representation-based classification (src) had a considerable potential to be used as an improving idea in cnn-based p300 detection.