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

• Published in: Journal of neuroscience methods Vol. 338; p. 108686
• Main Authors: Ziafati, Amir, Maleki, Ali
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 15.05.2020
• Subjects: Brain-computer interface (BCI); Fuzzy ensemble; MLR; MsetCCA; Steady-state visual evoked potentials (SSVEP); Brain-computer interface (BCI); MLR; Fuzzy ensemble; Steady-state visual evoked potentials (SSVEP); MsetCCA
• ISSN: 0165-0270; 1872-678X; 1872-678X
• DOI: 10.1016/j.jneumeth.2020.108686

•MLR and MsetCCA are the most powerful methods to detect SSVEP stimulation frequency.•Using a fuzzy ensemble system yields better results than both MLR and MsetCCA methods.•The results obtained from the proposed system show 100 % accuracy in 2 s signals. BCI systems based on steady-state visual evoked potentials (SSVEP) have formed an immense contribution to practical applications, due to their high recognition accuracy and ease of use. The MLR method has a better frequency recognition accuracy for short-term windows, and the MsetCCA method works more accurately in long-term windows. The proposed fuzzy ensemble system can analyze the relevant SSVEP signals of each subject from 0.5 to 4 s windows with 0.5 s incremental steps. It is capable of taking decisions to improve the accuracy of SSVEP stimulation frequency recognition using the MLR and MsetCCA methods. Our fuzzy system provides high-accuracy results for the stimulation frequency recognition in signals with the length of 1 s and more. Specifically, the average accuracy of 2 s windows has improved to 100 percent. The recognition accuracy of the presented system is always better than both MLR and MsetCCA methods. One of the capabilities of fuzzy systems is that they can use human information and knowledge to build engineering systems. The fuzzy ensemble system can utilize various methods or classifiers simultaneously. The new system has proposed to combine multiple methods using the fuzzy ensemble, which encompasses the benefits of all the subsystems.