Portable brain-computer interface based on novel convolutional neural network

• Published in: Computers in biology and medicine 2019-04, Vol.107, p.248-256
• Main Authors: Zhang, Yu, Zhang, Xiong, Sun, Han, Fan, Zhaowen, Zhong, Xuefei
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Analog to digital conversion; Analog to digital converters; Artificial neural networks; Biomedical signal processing; Bluetooth; Brain; Brain research; Brain-computer interface; Classification; Computer applications; Convolutional neural network; Design; Digital computers; Dry electrode; EEG; Electrodes; Electroencephalography; Embedded systems; Experiments; Fourier transforms; Frequencies; Gels; Headphones; Human-computer interface; Image classification; Implants; Medical research; Mental task performance; Methods; Motor imagery; Neural networks; Outerwear; Personal computers; Portable equipment; Principal components analysis; R&D; Research & development; Research methodology; Signal processing; Skin; Skin preparations; Statistical analysis; Statistical methods; Temporal resolution; Test procedures; Wavelet transforms
• ISSN: 0010-4825; 1879-0534
• DOI: 10.1016/j.compbiomed.2019.02.023

Electroencephalography (EEG) is a powerful, noninvasive tool that provides a high temporal resolution to directly reflect brain activities. Conventional electrodes require skin preparation and the use of conductive gels, while subjects must wear uncomfortable EEG hats. These procedures usually create a challenge for subjects. In the present study, we propose a portable EEG signal acquisition system. This study consists of two main parts: 1) A novel, portable dry-electrode and wireless brain–computer interface is designed. The EEG signal acquisition board is based on 24 bit, analog-to-digital converters chip and wireless microprocessor unit. The wireless portable brain computer interface device acquires an EEG signal comfortably, and the EEG signals are transmitted to a personal computer via Bluetooth. 2) A convolutional neural network (CNN) classification algorithm is implemented to classify the motor imagery (MI) experiment using novel feature 3-dimension input. The time dimension was reshaped to represent the first and second dimension, and the frequency band was used as the third dimension. Specifically, frequency domain representations of EEG signals obtained via wavelet package decomposition (WPD) are obtained to train CNN. The classification performance in terms of the value of kappa is 0.564 for the proposed method. The t-test results show that the performance improvement of CNN over other selected state-of-the-art methods is statistically significant. Our results show that the proposed design is reliable in measuring EEG signals, and the 3D CNN provides better classification performance than other method for MI experiments. •The purpose of this study was to design a portable EEG BCI with 24 bit, ADC chip and wireless microprocessor unit.•The experiment suggests that this system has the potential to provide very stable EEG signals.•A novel classifier based on the 3D CNN for MI-BCI is proposed.•Our study suggests that the proposed portable EEG and classifier can be potentially used for developing improved MI-BCI.