Multi-Class Motor Imagery Classification

Saeed Seyedtabaii | Mohammad Jyannasab

---

URL :   http://research.shahed.ac.ir/WSR/WebPages/Report/PaperView.aspx?PaperID=158634
Date :  2021/06/10
Publish in :    بيستمين کنفرانس ملي دانشجويي مهندسي برق ايران

Link :  http:// latter is added
Keywords :Motor Imagery Classification, SVM, LSTM, CSP

Abstract :

---

The Motor Imagery (MI) classification task is a high dimension multivariate and complicated subject. In this respect, the original signals are analyzed and minimal unique features of the classes are extracted to facilitate accurate classification of the actions performed. The fusion of common spatial pattern, Fisher discrimination ratio, and filter bank alongside the SVM and CNN-LSTM are incorporated to provide accurate clustering. As a result and after extensive simulations, it is shown that the CSP+ FDR + CNN-LSTM setup more accurately differentiates the classes.

http:// latter is added