An Optimized Quadratic Support Vector Machine for EEG Based Brain Computer Interface

The Brain Computer Interface (BCI) has a great impact on mankind. Many researchers have been trying to employ different classifiers figure out the human brain's thoughts accurately. In order overcome poor performance of single classifier, some used combined classifier. Others delete redundant information in channels before applying classifier as they thought it might reduce accuracy BCI helps clinicians learn more about brain problems and disabilities such stroke use recovery. main objective this paper is propose an optimized High-Performance Support Vector Machines (SVM) based (HPSVM-BCI) using SelectKBest (SKB). proposed HPSVM-BCI, SKB algorithm select features competition III Dataset IVa subjects. Then, classify prepared data from previous phase, SVM with Quadratic kernel (QSVM) were second phase. As well enhancing mean dataset, HPSVM-BCI reduces computational cost time. A major research improve classification dataset. Furthermore, decreased feature count translates fewer electrodes, factor that risk brain. Comparative studies conducted recent models same results obtained study show highest average accuracy, 99.24% for each subject 40 only.