A 1D CNN for high accuracy classification and transfer learning in motor imagery EEG-based brain-computer interface

Objective. Brain-computer interface (BCI) aims to establish communication paths between the brain processes and external devices. Different methods have been used to extract human intentions from electroencephalography (EEG) recordings. Those based on motor imagery (MI) seem to have a great potential for future applications. These approaches rely on the extraction of EEG distinctive patterns during imagined movements. Techniques able to extract patterns from raw signals represent an important target for BCI as they do not need labor-intensive data pre-processing. Approach. We propose a new approach based on a 10-layer one-dimensional convolution neural network (1D-CNN) to classify five brain states (four MI classes plus a 'baseline' class) using a data augmentation algorithm and a limited number of EEG channels. In addition, we present a transfer learning method used to extract critical features from the EEG group dataset and then to customize the model to the single individual by training its late layers with only 12-min individual-related data. Main results. The model tested with the 'EEG Motor Movement/Imagery Dataset' outperforms the current state-of-the-art models by achieving a 99.38% = 80%. The 2-year MPR (MPR730) was 61.9%, and 49.6% of patients had an MPR730 >= 80%. Both the persistence proportion and MPR730 were higher in females than in males, whereas MPRdiscon was higher in males. The persistence proportion and MPR730 were highest in the 70-79 years age group, whereas MPRdiscon improved with increasing age. The MPRdiscon and MPR730 were higher in the mixed-fracture and vertebral-fracture groups, respectively. The persistence proportion, MPRdiscon, and MPR730 were higher in patients with polypharmacy than in those without. Conclusion In Japan, persistence and the 2-year MPR were inadequate in increasing fracture control efficacy despite a high adherence rate during the treatment period. To bridge the care gap following osteoporosis pharmacotherapy, improvements are required for males, the elderly, and those without polypharmacy.