STN: a new tensor network method to identify stimulus category from brain activity pattern
This work addresses the challenge of decoding stimulus categories from brain activity patterns, which is important for neurocomputing and brain-computer interfaces, but it appears incremental as it builds on existing tensor decomposition methods.
The authors tackled neural decoding by proposing a stimulus constrained tensor brain model (STN) that incorporates tensor decomposition and stimulus category constraints to better extract multi-dimensional spatio-temporal information from brain networks, achieving accuracy improvements of 11.06% and 18.46% over other methods on MEG and fMRI datasets.
Neural decoding is still a challenge and hot topic in neurocomputing science. Recently, many studies have shown that brain network patterns containing rich spatial and temporal structure information, which represents the activation information of brain under external stimuli. %Therefore, the research of decoding stimuli from brain network received extensive more attention. The traditional method extracts brain network features directly from the common machine learning method, then puts these features into the classifier, and realizes to decode external stimuli. However, this method cannot effectively extract the multi-dimensional structural information, which is hidden in the brain network. The tensor researchers show that the tensor decomposition model can fully mine unique spatio-temporal structure characteristics in multi-dimensional structure data. This research proposed a stimulus constrained tensor brain model(STN)which involves the tensor decomposition idea and stimulus category constraint information. The model was verified on the real neuroimaging data sets (MEG and fMRI). The experimental results show that the STN model achieves more than 11.06% and 18.46% on accuracy matrix compared with others methods on two modal data sets. These results imply the superiority of extracting discriminative characteristics about STN model, especially for decoding object stimuli with semantic information.