Fuzzy ensemble system for SSVEP stimulation frequency detection using the MLR and MsetCCA

Boosting the Evoked Response of Brain to Enhance the Reference Signals of CCA Method

“…In the proposed method, the average accuracy obtained in subject-independent mode using a 0.5-seconds time window was equal to 97.5%, and using a 0.6-seconds time window was equal to 100% which is less than the subject-dependent mode but still is much higher compared to CCA and the MsetCCA methods. In addition, the proposed method was compared with MLR methods and the ensemble of MLR and MsetCCA methods introduced in [26], which show a significant improvement in the accuracy of SSVEP stimulation frequency detection in the proposed method.…”

“…In the study [25], the authors combined the experimental mode analysis method and the decision tree classifier and were able to improve the accuracy of the detection over a wide frequency range. Ziafati and Maleki ensembled MLR and MsetCCA methods using their fuzzy ensemble system and achieved excellent results [26].…”

Data Analytics in Steady-State Visual Evoked Potential-Based Brain–Computer Interface: A Review

“…Jiao et al [18] further presented a three-layer model based on MsetCCA, named multilayer correlation maximization (MCM) which adopts superiorities of both CCA and MsetCCA to avoid extracting the background noise as common features. Ziafati et al [75] proposed a fuzzy ensemble system which encompasses the benefits of all the subsystems, i.e. multivariate linear regression (MLR) and MsetCCA.…”

“…system [75] The advantages and disadvantages of the MLR and MsetCCA are investigated using expert knowledge, and the rules are developed for their strategic combination to improve the overall performance.…”