Figure 4.

Average classification errors as a function of number of feature numbers for three feature selection methods. SFS, feature selection using sequential forward selection; SI, feature selection using the separability indices of each feature; PCA, principal component analysis. LDA classifiers were trained and tested with data from seven wrist positions to recognize four motion classes. Shaded error bars represent SE. (A) Extrinsics: non-amputees, (B) intrinsics: non-amputees, (C) extrinsics and intrinsics: non-amputees, (D) extrinsics: amputees, (E) intrinsics: amputees, and (F) extrinsics and intrinsics: amputees.