Skip to main content

Table 5 Comparison of different feature selection and classification methods for the University of Essex BCI data files: maxima Kappa values evaluated with the test patterns

From: Classification of motor imagery tasks for BCI with multiresolution analysis and multiobjective feature selection

Subject

OPT0

SR-LDA

SR-SVC

OPT1

OPT2

OPT3

Kappa index (xe#)

Kappa index (xe# max)

Kappa index (xe# max)

Kappa index (xe# max)

Kappa index (xe# max)

Kappa index (xe# max)

101

0.438

0.450

0.528

0.472

0.489

0.430

102

0.455

0.408

0.541

0.405

0.463

0.447

103

0.279

0.244

0.287

0.329

0.354

0.413

104

0.564

0.696

0.664

0.589

0.614

0.606

105

0.287

0.194

0.170

0.287

0.287

0.287

106

0.321

0.236

0.284

0.338

0.381

0.292

107

0.631

0.547

0.598

0.631

0.665

0.656

108

0.254

0.161

0.155

0.170

0.245

0.237

109

0.388

0.320

0.380

0.346

0.371

0.388

110

0.648

0.505

0.530

0.530

0.673

0.639

  1. Italic values represent the best values provided by any alternative procedure for a given subject