An FPGA-Based Brain Computer Interfacing Using Compressive Sensing and Machine Learning

Electrocorticography (ECoG) is a type of electrophysiological monitoring useful for recording the activity from the cerebral cortex. It has emerged as a promising recording technique in brain-computer interfaces (BCI). Compression of these signals is essential for saving power and bandwidth in the novel application scenarios of Health-based IoT and Body Area Networks. However, this task is particularly challenging since, ECoG signals are not compressible either in time domain or in frequency domain. To that end, Block Sparse Bayesian Learning (BSBL) techniques were suggested for the reconstruction of compressed EEG and ECG signals, which is however, computationally demanding. Furthermore, given the heterogeneity in modern computing systems, careful design partitioning is required to most effectively evaluate the particular resources available on the deployed architecture. In this paper, we propose to utilise a combination of compressive sensing and neural network for the compression and reconstruction of ECoG signals, respectively. For the choice of the neural network, a multi-layer perceptron regressor with a stochastic gradient descent solver is developed. For a sample system, we show that the network has a compression ratio of 50%, and reconstruction accuracy of 89.85% after training with a practical, medium-sized dataset. In general, the results show that the most efficient system implementation is a heterogeneous architecture combining a CPU and a fieldprogrammable gate array (FPGA).