Power Aware Hessian Multi-set Canonical Correlations Based Algorithm for Wireless Eeg Sensor Networks

The miniaturized Electroencephalography (EEG) modules monitors the EEG signals over a smaller area, however, thus modules suffer from poor spatial coverage. The wireless EEG sensor network (WESN) provides an improved spatial coverage with multiple EEG modules, which communicated through a shorter distances. Further, the miniaturized EEG modules tend to create a high energy cost in wireless communication. This paper aims to remove the eye blink artifacts from the WESN EEG channels. The exploitation of correlation among the signals from various EEG modules is taken into consideration for resolving the problem of artifact removal in stringent bandwidth constraints. In this paper, Hessian multi-set canonical correlations based algorithm is used that computes optimal linear combination of the EEG signal between the local EEG channels and other modules. This correlation makes the EEG signal to be correlated at a maximum rate. The use of Hessian multi-set canonical correlations to remove the eye blink artifacts in a distributed realization reduces the transmission cost in the network. The proposed method has been validated against the real and synthetic EEG datasets, collected from the WESN shortest distance communication. The removal of redundant data from the wireless nodes, the algorithm attains an improved performance to remove the eye blink artifact with reduced power consumption in the wireless networks.