Research Article

Comparative Study on Interaction of Form and Motion Processing Streams by Applying Two Different Classifiers in Mechanism for Recognition of Biological Movement

Figure 6

Confusion matrices ELM classifying KTH dataset attained by adapted active basis model as combination of form and motion pathways. Confusion matrices of the proposed approach have been presented which is obtained from human action movements of KTH dataset [39]. There are three different kernels which have been used in classifying using ELM algorithm [33ā€“38] in the decision making and categorization of the biological movement. From left to right, RBF kernel-ELM, wavelet kernel ELM, and sigmoid-ELM confusion matrices have been depicted where sigmoid kernel-ELM has better results in classification of biological movement. The accuracy of categorizations is ELM-Wav = 91.5%, ELM-RBF = 92.7%, and ELM-Sig = 96.5%.
723213.fig.006a
(a)
723213.fig.006b
(b)
723213.fig.006c
(c)