Wavelet Multi-level Multi-scale Neural Network for EEG Classification

Electroencephalogram (EEG) plays a crucial role in Brain-computer interface (BCI) research by recording brain electrical activity, allowing direct communication with external devices without relying on muscles or peripheral nerves. EEG signals are non-invasive and low-cost, which are commonly used in BCIs. Although existing work has achieved success in many BCI paradigms, there is still a significant challenge: how to automatically extract spectral features from raw EEG signals. To address this, we propose a novel wavelet multi-level multi-scale neural network for EEG-based BCIs, called wavelet-MMNN. Our model uses wavelet decomposition with multi-scale convolutional kernels to automatically extract abundant spectral features from the raw EEG signals. The cross-subject experiments and cross-session experiments are conducted on SSVEP Benchmark dataset, and the results indicate that the proposed model is superior to the state-of-the-art models.