Performance Enhancement of P300 Detection by Multiscale-CNN

Abstract

P300-based spelling system is one of the most popular brain-computer interface applications. Its success largely depends on performance, including the information transmission rate (ITR) and detection rate (i.e., accuracy). To achieve good performance, we proposed a multi-scale convolutional neural network (MS-CNN) model, which consists of seven layers. First, an upfront dataset was used to train the MS-CNN, aiming to obtain a subject-unspecific model (universal model) for P300 detection. Second, this universal model was adapted by a portion of data derived from a subject to update the model to obtain a subject-specific model by incorporating a transfer learning technique. We applied the proposed model in the BCI Controlled Robot Contest at the 2019 World Robot Conference, and our performance was the best among the teams in the contest. In the contest, ten healthy young subjects were randomly assigned by the contest committee to assess the model. Our model achieved the best P300 detection performance (higher accuracy with less repetition time). The ITR for the subject-unspecific case was 13.49 bits/min while the ITR for the subject-specific case was 12.13 bits/min when the repetitions were fewer than six. It is believed that our method may pave a promising path for taking a further step toward efficient implementation of P300-based spelling system.

ST-CapsNet: Linking Spatial and Temporal Attention With Capsule Network for P300 Detection Improvement

“…We found that all three spatial attention maps share two common channels (Cz and CPz), and the enhanced electrodes were located roughly in the central and parietal lobes of the brain, indicating that the attention module was able to capture the spatial features of P300. Furthermore, the learned spatial attention maps generally accords with those of previous studies [15], [23], [24].…”

“…However, it has a low symbol recognition rate in the first 5 or even 10 repetitions, leading to a low information transfer rate (ITR). To further increase the symbol recognition rate in the first 5 repetitions, Wang et al [24], who have crowned champions of the P300based BCI competition in the 2019 World Robot Conference, proposed Multiscale-CNN to enhance the performance of P300 detection. Three temporal kernels at different scales were applied on its temporal convolution layer to obtain discriminative time features.…”

Personalized Brain–Computer Interface and Its Applications

“…Erdogan et al analyzed the response of specific users to the spelling paradigm and determined the most appropriate P300 detection band for them [ 93 ]. In recent years, Wang et al used a multi-scale convolutional neural network (MS-CNN) to train a general decoding model and then adjusted the general model by using part of the data of specific subjects through transfer learning to obtain a customized decoding model [ 94 ]. In addition, Li et al proposed a TrAdaBoost algorithm based on cross-validation and an adaptive threshold (CV-T-TAB).…”

Brain Network Reorganization During Visual Search Task Revealed by a Network Analysis of Fixation-Related Potential

“…Through averaging the EEG signal time-locked to fixations on target object, a relatively late component in FRP associated with P300 potential was observed [14], [15], which is typically related to cognitive functions such as attention and object identification. Considering the ability of P300 in discriminating target stimulus and distractors [16], it can be inferred that the fixation-related P300 could provide discriminative information in terms of FRP classification. For example, Brouwer et al achieved satisfactory single-trial FRP classification accuracy and revealed the reliable discrimination of a P300-liked FRP component [11].…”