| Popis: |
Increasing availability of multiple responses and requirement of thorough analysis demand efficient modeling to derive a feasible support system which can make the analysis less-onerous, time-consuming, error-prone. Further, it is an indispensable provision to develop compact health monitoring devices, utility, and reliability of which rely on efficiency of program embedded that can manage the jobs without intervention of clinicians. In this article, a feature-level fusion framework is addressed using discriminant correlation analysis to effectively classify electroencephalogram (EEG) templates. Experiment on EEG data set shows that proposed method is efficacious and promising in terms of accuracy in comparison to the state-of-the-art methods. |
