FB Dictionary Based SSBL-EM and Its Application for Multi-Class SSVEP Classification Using Eight-Channel EEG Signals

Abstract

Many applications of signal processing require efficient reconstruction and economical processing of a signal. A classical approach for efficient reconstruction and economical processing of signal is compression. In recent studies, compressed sensing (CS) is an emerging field for compression and reconstruction. Moreover, CS is well-known for energy-efficient signal compression. However, most CS algorithms do not provide efficient reconstruction of physiological signals, such as electroencephalogram (EEG) and electrocardiogram (ECG). Efficient reconstruction is not possible due to non-stationary and non-sparsity characteristics of these signals. On the other hand, processing of these multichannel physiological signals is also time-consuming since the processing time is directly proportional to the number of channels. Hence, we have proposed a Fourier–Bessel (FB) dictionary-based spatiotemporal sparse Bayesian learning (SSBL) algorithm with expectation–maximization (EM) method for efficient reconstruction of multichannel physiological signals. This proposed method is based on the existing SSBL-EM method in which the authors used discrete cosine transform (DCT) dictionary for efficient reconstruction. In our work, we have used FB dictionary instead of DCT dictionary as the Bessel functions have non-stationary characteristic and provide good compression for signals such as EEG. The proposed method has been tested on two different databases for steady-state visual evoked potential (SSVEP)-based brain–computer interface (BCI) classification using multichannel EEG signals and provides 100% classification accuracy with 50% compression and 2-s time duration using the first database. Classification has been performed using L1-regularized multiway canonical correlation analysis (L1-RMCCA) method. The performance of the proposed method has been compared with the DCT-dictionary-based SSBL-EM method. The classification accuracy result makes this proposed method more beneficial for uninterrupted wireless telemonitoring of multichannel EEG signals.